Abstract MIMIC-III is a large, freely-available database comprising deidentified health-related data associated with over 40,000 patients who stayed in critical care units of the Beth Israel Deaconess Medical Center between 2001 and 2012 [1]. The MIMIC-III Clinical Database is available on PhysioNet (doi: 10.13026/C2XW26). Though deidentified, MIMIC-III contains detailed information regarding the care of real patients, and as such requires credentialing before access. To allow researchers to ascertain whether the database is suitable for their work, we have manually curated a demo subset, which contains information for 100 patients also present in the MIMIC-III Clinical Database. Notably, the demo dataset does not include free-text notes.

Background In recent years there has been a concerted move towards the adoption of digital health record systems in hospitals. Despite this advance, interoperability of digital systems remains an open issue, leading to challenges in data integration. As a result, the potential that hospital data offers in terms of understanding and improving care is yet to be fully realized.

MIMIC-III integrates deidentified, comprehensive clinical data of patients admitted to the Beth Israel Deaconess Medical Center in Boston, Massachusetts, and makes it widely accessible to researchers internationally under a data use agreement. The open nature of the data allows clinical studies to be reproduced and improved in ways that would not otherwise be possible.

The MIMIC-III database was populated with data that had been acquired during routine hospital care, so there was no associated burden on caregivers and no interference with their workflow. For more information on the collection of the data, see the MIMIC-III Clinical Database page.

Methods The demo dataset contains all intensive care unit (ICU) stays for 100 patients. These patients were selected randomly from the subset of patients in the dataset who eventually die. Consequently, all patients will have a date of death (DOD). However, patients do not necessarily die during an individual hospital admission or ICU stay.

This project was approved by the Institutional Review Boards of Beth Israel Deaconess Medical Center (Boston, MA) and the Massachusetts Institute of Technology (Cambridge, MA). Requirement for individual patient consent was waived because the project did not impact clinical care and all protected health information was deidentified.

Data Description MIMIC-III is a relational database consisting of 26 tables. For a detailed description of the database structure, see the MIMIC-III Clinical Database page. The demo shares an identical schema, except all rows in the NOTEEVENTS table have been removed.

The data files are distributed in comma separated value (CSV) format following the RFC 4180 standard. Notably, string fields which contain commas, newlines, and/or double quotes are encapsulated by double quotes ("). Actual double quotes in the data are escaped using an additional double quote. For example, the string she said "the patient was notified at 6pm" would be stored in the CSV as "she said ""the patient was notified at 6pm""". More detail is provided on the RFC 4180 description page: https://tools.ietf.org/html/rfc4180

Usage Notes The MIMIC-III demo provides researchers with an opportunity to review the structure and content of MIMIC-III before deciding whether or not to carry out an analysis on the full dataset.

CSV files can be opened natively using any text editor or spreadsheet program. However, some tables are large, and it may be preferable to navigate the data stored in a relational database. One alternative is to create an SQLite database using the CSV files. SQLite is a lightweight database format which stores all constituent tables in a single file, and SQLite databases interoperate well with a number software tools.

DB Browser for SQLite is a high quality, visual, open source tool to create, design, and edit database files compatible with SQLite. We have found this tool to be useful for navigating SQLite files. Information regarding installation of the software and creation of the database can be found online: https://sqlitebrowser.org/

Release Notes Release notes for the demo follow the release notes for the MIMIC-III database.

Acknowledgements This research and development was supported by grants NIH-R01-EB017205, NIH-R01-EB001659, and NIH-R01-GM104987 from the National Institutes of Health. The authors would also like to thank Philips Healthcare and staff at the Beth Israel Deaconess Medical Center, Boston, for supporting database development, and Ken Pierce for providing ongoing support for the MIMIC research community.

Conflicts of Interest The authors declare no competing financial interests.

References Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Mo...

Florida COVID-19 Case Line data, exported from the Florida Department of Health GIS Layer on date seen in file name. Archived by the University of South Florida Libraries, Digital Heritage and Humanities Collections. Contact: LibraryGIS@usf.edu. Starting on 4/6/2021, the Florida Department of Health (FDOH) changed the way they provide COVID-19 caseline data. Beginning with this date the caseline data is being archived as two separate files, one for 2020 and one for 2021. The 2021 file will only include data from 1/1/2021 onward. In addition, FDOH has added two Object ID fields to their dataset. These caseline data are being preserved as they are provided by the FDOH, with a daily archive captured by the USF Libraries DHHC.Please Cite Our GIS HUB. If you are a researcher or other utilizing our Florida COVID-19 HUB as a tool or accessing and utilizing the data provided herein, please provide an acknowledgement of such in any publication or re-publication. The following citation is suggested: University of South Florida Libraries, Digital Heritage and Humanities Collections. 2021. Florida COVID-19 Hub. Available at https://covid19-usflibrary.hub.arcgis.com/. https://doi.org/10.5038/USF-COVID-19-GISLive FDOH Data Source: https://www.arcgis.com/home/item.html?id=7a0c74a551904761812dc6b8bd620ee1 or Direct Download at: https://open-fdoh.hub.arcgis.com/datasets/7a0c74a551904761812dc6b8bd620ee1_0.

Archives for this data layer begin on 5/11/2020. Archived data was exported directly from the live FDOH layer into the archive by the University of South Florida Libraries - Digital Heritage and Humanities Collection.For data definitions please visit the following box folder: https://usf.box.com/s/vfjwbczkj73ucj19yvwz53at6v6w614hData definition files names include the relative date they were published. The below information was taken from ancillary documents associated with the original layer from the Florida Department of Health. This data table represents all laboratory-confirmed cases of COVID-19 in Florida tabulated from the previous day's totals by the Florida Department of Health. Persons Under Investigation/Surveillance (PUI):Essentially, PUIs are any person who has been or is waiting to be tested. This includes: persons who are considered high-risk for COVID-19 due to recent travel, contact with a known case, exhibiting symptoms of COVID-19 as determined by a healthcare professional, or some combination thereof. PUI’s also include people who meet laboratory testing criteria based on symptoms and exposure, as well as confirmed cases with positive test results. PUIs include any person who is or was being tested, including those with negative and pending results.All PUIs fit into one of three residency types:1. Florida residents tested in Florida2. Non-Florida residents tested in Florida 3. Florida residents tested outside of Florida Florida Residents Tested Elsewhere: The total number of Florida residents with positive COVID-19 test results who were tested outsideof Florida, and were not exposed/infectious in Florida. Non-Florida Residents Tested in Florida: The total number of people with positive COVID-19 test results who were tested, exposed, and/or infectious while in Florida, but are legal residents of another state.Table Guide for Records of Confirmed Positive Cases of COVID-19"County": The Florida county where the individual with COVID-19's case has been processed. "Jurisdiction" of the case:"FL resident" -- a resident of Florida"Non-FL resident" -- someone who resides outside of Florida "Travel_Related": Whether or not the positive case of COVID-19 is designated as related to recent travel by the individual. "No" -- Case designated as not being a risk related to recent travel"Unknown" -- Case designated where a travel-related designation has not yet been made."Yes" -- Case is designated as travel-related for a person who recently traveled overseas or to an area with community"Origin": Where the person likely contracted the virus before arriving / returning to Florida."EDvisit": Whether or not an individual who tested positive for coronavirus visited and was admitted to an Emergency Department related to health conditions surrounding COVID-19."No" -- Individual was not admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Unknown" -- It is unknown whether the individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Yes" -- Individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19“Hospitalized”: Whether or not a patient who receives a positive laboratory confirmed test for COVID-19 receives inpatient care at a hospital at any time during illness. These people may no longer be hospitalized. This information does not indicate that a COVID-19 positive person is currently hospitalized, only that they have been hospitalized for health conditions relating to COVID-19 at some point during their illness. "No" -- Individual was not admitted for inpatient care at a hospital at any time during illness "Unknown" -- It is unknown whether the individual was admitted for inpatient care at a hospital at any time during illness "Yes" -- Individual was admitted for inpatient care at a hospital at some point during the illness "Died": Whether or not the individual who tested positive for COVID-19 died as a result of health complications from the viral infection. "NA" -- Not applicable / resident has not died "Yes" -- Individual died of a health complication resulting from COVID-19 "Contact": Whether the person contracted COVID-19 from contact with current or previously confirmedcases."No" -- Case with no known contact with current or previously confirmed cases"Yes" -- Case with known contact with current or previously confirmed cases"Unknown" -- Case where contact with current or previous confirmedcases is not known or under investigation"Case_": The date the positive laboratory result was received in the Department of Health’s database system and became a “confirmed case.” This is not the date a person contracted the virus, became symptomatic, or was treated. Florida does not create a case or count suspected/probable cases in the case counts without a confirmed-positive lab result. "EventDate": When the individual reported likely first experiencing symptoms related to COVID-19. "ChartDate": Also the date the positive laboratory result for an individual was received in the Department ofHealth’s database system and became a recorded, “confirmed case” of COVID-19 in the state. Data definitions updated by the FDOH on 5/13/2020.

Florida COVID-19 Case Line data, exported from the Florida Department of Health GIS Layer on date seen in file name. Archived by the University of South Florida Libraries, Digital Heritage and Humanities Collections. Contact: LibraryGIS@usf.edu. Starting on 4/6/2021, the Florida Department of Health (FDOH) changed the way they provide COVID-19 caseline data. Beginning with this date the caseline data is being archived as two separate files, one for 2020 and one for 2021. The 2021 file will only include data from 1/1/2021 onward. In addition, FDOH has added two Object ID fields to their dataset. These caseline data are being preserved as they are provided by the FDOH, with a daily archive captured by the USF Libraries DHHC.Please Cite Our GIS HUB. If you are a researcher or other utilizing our Florida COVID-19 HUB as a tool or accessing and utilizing the data provided herein, please provide an acknowledgement of such in any publication or re-publication. The following citation is suggested: University of South Florida Libraries, Digital Heritage and Humanities Collections. 2021. Florida COVID-19 Hub. Available at https://covid19-usflibrary.hub.arcgis.com/. https://doi.org/10.5038/USF-COVID-19-GISLive FDOH Data Source: https://www.arcgis.com/home/item.html?id=7a0c74a551904761812dc6b8bd620ee1 or Direct Download at: https://open-fdoh.hub.arcgis.com/datasets/7a0c74a551904761812dc6b8bd620ee1_0.

Archives for this data layer begin on 5/11/2020. Archived data was exported directly from the live FDOH layer into the archive by the University of South Florida Libraries - Digital Heritage and Humanities Collection.For data definitions please visit the following box folder: https://usf.box.com/s/vfjwbczkj73ucj19yvwz53at6v6w614hData definition files names include the relative date they were published. The below information was taken from ancillary documents associated with the original layer from the Florida Department of Health. This data table represents all laboratory-confirmed cases of COVID-19 in Florida tabulated from the previous day's totals by the Florida Department of Health. Persons Under Investigation/Surveillance (PUI):Essentially, PUIs are any person who has been or is waiting to be tested. This includes: persons who are considered high-risk for COVID-19 due to recent travel, contact with a known case, exhibiting symptoms of COVID-19 as determined by a healthcare professional, or some combination thereof. PUI’s also include people who meet laboratory testing criteria based on symptoms and exposure, as well as confirmed cases with positive test results. PUIs include any person who is or was being tested, including those with negative and pending results.All PUIs fit into one of three residency types:1. Florida residents tested in Florida2. Non-Florida residents tested in Florida 3. Florida residents tested outside of Florida Florida Residents Tested Elsewhere: The total number of Florida residents with positive COVID-19 test results who were tested outsideof Florida, and were not exposed/infectious in Florida. Non-Florida Residents Tested in Florida: The total number of people with positive COVID-19 test results who were tested, exposed, and/or infectious while in Florida, but are legal residents of another state.Table Guide for Records of Confirmed Positive Cases of COVID-19"County": The Florida county where the individual with COVID-19's case has been processed. "Jurisdiction" of the case:"FL resident" -- a resident of Florida"Non-FL resident" -- someone who resides outside of Florida "Travel_Related": Whether or not the positive case of COVID-19 is designated as related to recent travel by the individual. "No" -- Case designated as not being a risk related to recent travel"Unknown" -- Case designated where a travel-related designation has not yet been made."Yes" -- Case is designated as travel-related for a person who recently traveled overseas or to an area with community"Origin": Where the person likely contracted the virus before arriving / returning to Florida."EDvisit": Whether or not an individual who tested positive for coronavirus visited and was admitted to an Emergency Department related to health conditions surrounding COVID-19."No" -- Individual was not admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Unknown" -- It is unknown whether the individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Yes" -- Individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19“Hospitalized”: Whether or not a patient who receives a positive laboratory confirmed test for COVID-19 receives inpatient care at a hospital at any time during illness. These people may no longer be hospitalized. This information does not indicate that a COVID-19 positive person is currently hospitalized, only that they have been hospitalized for health conditions relating to COVID-19 at some point during their illness. "No" -- Individual was not admitted for inpatient care at a hospital at any time during illness "Unknown" -- It is unknown whether the individual was admitted for inpatient care at a hospital at any time during illness "Yes" -- Individual was admitted for inpatient care at a hospital at some point during the illness "Died": Whether or not the individual who tested positive for COVID-19 died as a result of health complications from the viral infection. "NA" -- Not applicable / resident has not died "Yes" -- Individual died of a health complication resulting from COVID-19 "Contact": Whether the person contracted COVID-19 from contact with current or previously confirmedcases."No" -- Case with no known contact with current or previously confirmed cases"Yes" -- Case with known contact with current or previously confirmed cases"Unknown" -- Case where contact with current or previous confirmedcases is not known or under investigation"Case_": The date the positive laboratory result was received in the Department of Health’s database system and became a “confirmed case.” This is not the date a person contracted the virus, became symptomatic, or was treated. Florida does not create a case or count suspected/probable cases in the case counts without a confirmed-positive lab result. "EventDate": When the individual reported likely first experiencing symptoms related to COVID-19. "ChartDate": Also the date the positive laboratory result for an individual was received in the Department ofHealth’s database system and became a recorded, “confirmed case” of COVID-19 in the state. Data definitions updated by the FDOH on 5/13/2020.

Florida COVID-19 Case Line data, exported from the Florida Department of Health GIS Layer on date seen in file name. Archived by the University of South Florida Libraries, Digital Heritage and Humanities Collections. Contact: LibraryGIS@usf.edu. Starting on 4/6/2021, the Florida Department of Health (FDOH) changed the way they provide COVID-19 caseline data. Beginning with this date the caseline data is being archived as two separate files, one for 2020 and one for 2021. The 2021 file will only include data from 1/1/2021 onward. In addition, FDOH has added two Object ID fields to their dataset. These caseline data are being preserved as they are provided by the FDOH, with a daily archive captured by the USF Libraries DHHC.Please Cite Our GIS HUB. If you are a researcher or other utilizing our Florida COVID-19 HUB as a tool or accessing and utilizing the data provided herein, please provide an acknowledgement of such in any publication or re-publication. The following citation is suggested: University of South Florida Libraries, Digital Heritage and Humanities Collections. 2021. Florida COVID-19 Hub. Available at https://covid19-usflibrary.hub.arcgis.com/. https://doi.org/10.5038/USF-COVID-19-GISLive FDOH Data Source: https://www.arcgis.com/home/item.html?id=7a0c74a551904761812dc6b8bd620ee1 or Direct Download at: https://open-fdoh.hub.arcgis.com/datasets/7a0c74a551904761812dc6b8bd620ee1_0.

Archives for this data layer begin on 5/11/2020. Archived data was exported directly from the live FDOH layer into the archive by the University of South Florida Libraries - Digital Heritage and Humanities Collection.For data definitions please visit the following box folder: https://usf.box.com/s/vfjwbczkj73ucj19yvwz53at6v6w614hData definition files names include the relative date they were published. The below information was taken from ancillary documents associated with the original layer from the Florida Department of Health. This data table represents all laboratory-confirmed cases of COVID-19 in Florida tabulated from the previous day's totals by the Florida Department of Health. Persons Under Investigation/Surveillance (PUI):Essentially, PUIs are any person who has been or is waiting to be tested. This includes: persons who are considered high-risk for COVID-19 due to recent travel, contact with a known case, exhibiting symptoms of COVID-19 as determined by a healthcare professional, or some combination thereof. PUI’s also include people who meet laboratory testing criteria based on symptoms and exposure, as well as confirmed cases with positive test results. PUIs include any person who is or was being tested, including those with negative and pending results.All PUIs fit into one of three residency types:1. Florida residents tested in Florida2. Non-Florida residents tested in Florida 3. Florida residents tested outside of Florida Florida Residents Tested Elsewhere: The total number of Florida residents with positive COVID-19 test results who were tested outsideof Florida, and were not exposed/infectious in Florida. Non-Florida Residents Tested in Florida: The total number of people with positive COVID-19 test results who were tested, exposed, and/or infectious while in Florida, but are legal residents of another state.Table Guide for Records of Confirmed Positive Cases of COVID-19"County": The Florida county where the individual with COVID-19's case has been processed. "Jurisdiction" of the case:"FL resident" -- a resident of Florida"Non-FL resident" -- someone who resides outside of Florida "Travel_Related": Whether or not the positive case of COVID-19 is designated as related to recent travel by the individual. "No" -- Case designated as not being a risk related to recent travel"Unknown" -- Case designated where a travel-related designation has not yet been made."Yes" -- Case is designated as travel-related for a person who recently traveled overseas or to an area with community"Origin": Where the person likely contracted the virus before arriving / returning to Florida."EDvisit": Whether or not an individual who tested positive for coronavirus visited and was admitted to an Emergency Department related to health conditions surrounding COVID-19."No" -- Individual was not admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Unknown" -- It is unknown whether the individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Yes" -- Individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19“Hospitalized”: Whether or not a patient who receives a positive laboratory confirmed test for COVID-19 receives inpatient care at a hospital at any time during illness. These people may no longer be hospitalized. This information does not indicate that a COVID-19 positive person is currently hospitalized, only that they have been hospitalized for health conditions relating to COVID-19 at some point during their illness. "No" -- Individual was not admitted for inpatient care at a hospital at any time during illness "Unknown" -- It is unknown whether the individual was admitted for inpatient care at a hospital at any time during illness "Yes" -- Individual was admitted for inpatient care at a hospital at some point during the illness "Died": Whether or not the individual who tested positive for COVID-19 died as a result of health complications from the viral infection. "NA" -- Not applicable / resident has not died "Yes" -- Individual died of a health complication resulting from COVID-19 "Contact": Whether the person contracted COVID-19 from contact with current or previously confirmedcases."No" -- Case with no known contact with current or previously confirmed cases"Yes" -- Case with known contact with current or previously confirmed cases"Unknown" -- Case where contact with current or previous confirmedcases is not known or under investigation"Case_": The date the positive laboratory result was received in the Department of Health’s database system and became a “confirmed case.” This is not the date a person contracted the virus, became symptomatic, or was treated. Florida does not create a case or count suspected/probable cases in the case counts without a confirmed-positive lab result. "EventDate": When the individual reported likely first experiencing symptoms related to COVID-19. "ChartDate": Also the date the positive laboratory result for an individual was received in the Department ofHealth’s database system and became a recorded, “confirmed case” of COVID-19 in the state. Data definitions updated by the FDOH on 5/13/2020.

The National Population Health Survey (NPHS) is designed to collect information related to the health of the Canadian population. The first cycle of data collection began in 1994, and will continue every second year thereafter. The survey will collect not only cross-sectional information, but also data from a panel of individuals at two-year intervals.The target population of the NPHS includes household residents in all provinces, with the principal exclusion of populations on Indian Reserves, Canadian Forces Bases and some remote areas in Quebec and Ontario. Separate surveys were conducted to cover the Yukon, the Northwest Territories and the Institutions (long term residents of hospitals and residential care facilities) and will be presented at a later stage. The NPHS data are stored in four different data sets. Some information was collected from all household members. This information is stored in the General file. From each household, one person, aged 12 years and over, was selected to answer a more in-depth questionnaire related to health. These data are stored on the Health file. Each record on the General file corresponds to a household member. The General file carries the socio-demographic variables as well as health utilization variables. There are 58,439 records and 129 variables in the General file. The Health file contains 17,626 records and 439 variables. The Supplemental file is a subset of the health sample. Certain individuals in the Health sample were asked to answer supplemental questions. This file contains 13,400 records and 1023 variables. A special component of the program is a survey designed for people living in health care institutions, including hospitals, nursing homes, and residential facilities for persons with disabilities. This Institutional file contains data collected in 1995 from 2287 long-term residents of health care institutions in the provinces. Data between the files can be linked using the variable recno. Note: This data is also linked to the National Longitudinal Survey of Children

Context

A novel Coronavirus found its First case in December 2019, and after that, coronavirus cases are increasing with each subsequent day. As we all know, many people have lost their lives in the first wave of COVID-19, and the number of Deaths increased in the 2nd Wave of COVID-19.

COVID-19 is commonly mild and self-limiting, but in a considerable portion of patients the disease is severe and fatal. Determining which patients are at high risk of severe illness or mortality is essential for appropriate clinical decision-making.

Content

The data file contains information on demographics, comorbidities, admission laboratory values, admission medications, admission supplemental oxygen orders, discharge, and mortality. The data were derived from a healthcare surveillance software package (Clinical Looking Glass [CLG]; Streamline Health, Atlanta, Georgia) and review of the primary medical records. The data relate to COVID-19 patients admitted to a single healthcare system, over a specific period of time, and separated into the 1st 3 weeks of the pandemic and the 2nd 3 weeks of the pandemic. Some of the variables included in the dataset are: length of hospital stay (LOS), myocardial infraction (MI), peripheral vascular disease (PVD), congestive heart failure (CHF), cardiovascular disease (CVD), dementia (Dement), Chronic obstructive pulmonary disease (COPD), diabetes mellitus simple (DM simple), diabetes mellitus complicated (DM complicated), oxygen saturation (OsSats), mean arterial pressure, in mmHg (MAP), D-dimer, in mg/ml (Ddimer), platelets, in k per mm3 (Plts), international normalized ratio (INR), blood urea nitrogen, in mg/dL (BUN), alanine aminotransferase, in U/liter (AST), while blood cells, in per mm3 (WBC) and interleukin-6, in pg/ml (IL-6).

Acknowledgements

I would like to Thanks Scientific Reports for the study on Covid-19 patients.

Inspiration

This Dataset can help in predicting the Mortality Risk or Severe Covid-19 Patients in the Early Stages when they just get admitted into the hospital. By early prediction of Severe covid-19 patients it can help overburdened hospitals to arrange the resources like Oxygen cylinders and ICU beds accordingly which can save the life of patient.

The National Population Health Survey (NPHS) is designed to collect information related to the health of the Canadian population. The first cycle of data collection began in 1994, and will continue every second year thereafter. The survey will collect not only cross-sectional information, but also data from a panel of individuals at two-year intervals.The target population of the NPHS includes household residents in all provinces, with the principal exclusion of populations on Indian Reserves, Canadian Forces Bases and some remote areas in Quebec and Ontario. Separate surveys were conducted to cover the Yukon, the Northwest Territories and the Institutions (long term residents of hospitals and residential care facilities) and will be presented at a later stage.. The NPHS data are stored in four different data sets. Some information was collected from all household members. This information is stored in the General file. From each household, one person, aged 12 years and over, was selected to answer a more in-depth questionnaire related to health. These data are stored on the Health file. Each record on the General file corresponds to a household member. The General file carries the socio-demographic variables as well as health utilization variables. There are 58,439 records and 129 variables in the General file. The Health file contains 17,626 records and 439 variables.The Supplemental file is a subset of the health sample. Certain individuals in the Health sample were asked to answer supplemental questions. This file contains 13,400 records and 1023 variables. A special component of the program is a survey designed for people living in health care institutions, including hospitals, nursing homes, and residential facilities for persons with disabilities. This Institutional file contains data collected in 1995 from 2287 long-term residents of health care institutions in the provinces. Data between the files can be linked using the variable recno.

This data is the Saving young lives: Triage and treatment using the pediatric rapid sepsis trigger (PRST) tool study. Data collected for this study occurred from April 2020 to April 2022. Objective(s): This is a pre-post intervention study involving pediatric patients presenting to the study hospitals in seek of medical care for an acute illness. The purpose of this study was to develop a prediction model and to perform clinical validation of a digital triage tool to guide triage and treatment of children at health facilities in LMICs with severe infections/suspected sepsis. The study involved three phases: (I) Baseline Period, (II) Interphase Period, (III) Intervention Period. The study hospitals include 2 sites in Kenya (1 control site, 1 experimental site) and 2 in Uganda (1 control site, 1 experimental site). Data Description: Predictor variables were collected at the time of triage by trained study nurses using a custom-built mobile application. All data entered into the mobile application was stored an encrypted database. Data was uploaded directly from the mobile device to a Research Electronic Data Capture (REDCap) database hosted at the BC Children’s Hospital Research Institute (Vancouver, Canada). Outcomes were obtained from facility records or telephone follow-up at 7-10 days and the data was collected electronically. Time-specific outcomes were tracked using an RFID tagging system with study personnel as backup. Limitations: There is missing data and some variables were not collected at all sites. Ethics Declaration: This study was approved by the Makerere University Higher Degrees research and Ethics Committee (No. 743), the Uganda National Institute of Science and Technology (HS 528ES), and the University of British Columbia / Children & Women’s Health Centre of British Columbia Research Ethics Board (H19-02398 & H20-00484). Associated datasets: Saving young lives: Triage and management of sepsis in children using the point-of care Paediatric Rapid Sepsis Trigger (PRST) tool NOTE for restricted files: If you are not yet a CoLab member, please complete our membership application survey to gain access to restricted files within 2 business days. Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator at sepsiscolab@bcchr.ca or visit our website.

This is a study in adults with chronic heart failure. People with chronic heart failure may need to be hospitalised for their condition. Some people with chronic heart failure may eventually die from their condition. The purpose of the study is to find out whether a medicine called empagliflozin lowers the chances of patients having to go to hospital for heart failure and whether it improves their survival. The study is open to patients with a type of chronic heart failure called chronic heart failure with preserved ejection fraction.

Participants stay in the study until researchers have enough information about how effective empagliflozin is. It is expected that participants who enter at the very beginning of the enrolment period may be in the study for over 3 years, while participants who enter near the end of the enrolment period may be in the study for less than 2 years. The participants are put into 2 groups. It is decided by chance who gets into which group. One group gets empagliflozin tablets every day and the other group gets placebo tablets every day. Placebo tablets look like empagliflozin tablets but contain no medicine.

Participants visit the doctors regularly. During these visits, the doctors collect information about the participant's health. The doctors want to know how many patients had to go to hospital because of heart failure or who died from cardiovascular disease.

Background: One in three hospital acute medical admissions is of an older person with cognitive impairment. Their outcomes are poor and the quality of their care in hospital has been criticised. A specialist unit to care for older people with delirium and dementia (the Medical and Mental Health Unit, MMHU) was developed and then tested in a randomised controlled trial where it delivered significantly higher quality of, and satisfaction with, care, but no significant benefits in terms of health status outcomes at three months. Objective: To examine the cost-effectiveness of the MMHU for older people with delirium and dementia in general hospitals, compared with standard care. Methods: Six hundred participants aged over 65 admitted for acute medical care, identified on admission as cognitively impaired, were randomised to the MMHU or to standard care on acute geriatric or general medical wards. Cost per quality adjusted life year (QALY) gained, at 3-month follow-up, was assessed in trial-based economic evaluation (599/600 participants, intervention: 309). Multiple imputation and complete-case sample analyses were employed to deal with missing QALY data (55%). Results: The total adjusted health and social care costs, including direct costs of the intervention, at 3 months was £7714 and £7862 for MMHU and standard care groups, respectively (difference -£149 (95% confidence interval [CI]: -298, 4)). The difference in QALYs gained was 0.001 (95% CI: -0.006, 0.008). The probability that the intervention was dominant was 58%, and the probability that it was cost-saving with QALY loss was 39%. At £20,000/QALY threshold, the probability of cost-effectiveness was 94%, falling to 59% when cost-saving QALY loss cases were excluded. Conclusions: The MMHU was strongly cost-effective using usual criteria, although considerably less so when the less acceptable situation with QALY loss and cost savings were excluded. Nevertheless, this model of care is worthy of further evaluation.

This publication includes analysis of data for the months January 2024 to March 2024 from the Female Genital Mutilation (FGM) Enhanced Dataset (SCCI 2026) which is a repository for individual level data collected by healthcare providers in England, including acute hospital providers, mental health providers and GP practices. The report includes data on the type of FGM, age at which FGM was undertaken and in which country, the age of the woman or girl at her latest attendance and if she was advised of the health implications and illegalities of FGM and various other analyses. Some data for earlier years are reported.

This is a database (parquet format) containing publicly available multiple cause mortality data from the US (CDC/NCHS) for 2014-2022. Not all variables are included on this export. Please see below for restrictions on the use of these data imposed by NCHS. You can use the arrow package in R to open the file. See here for example analysis; https://github.com/DanWeinberger/pneumococcal_mortality/blob/main/analysis_nongeo.Rmd . For instance, save this file in a folder called "parquet3":

library(arrow)

library(dplyr)

pneumo.deaths.in <- open_dataset("R:/parquet3", format = "parquet") %>% #open the dataset
filter(grepl("J13|A39|J181|A403|B953|G001", all_icd)) %>% #filter to records that have the selected ICD codes
collect() #call the dataset into memory. Note you should do any operations you canbefore calling 'collect()" due to memory issues

The variables included are named: (see full dictionary:https://www.cdc.gov/nchs/nvss/mortality_public_use_data.htm)

year: Calendar year of death

month: Calendar month of death

age_detail_number: number indicating year or part of year; can't be interpreted itself here. see agey variable instead

sex: M/F

place_of_death:

Place of Death and Decedent’s Status
Place of Death and Decedent’s Status
1 ... Hospital, Clinic or Medical Center
- Inpatient
2 ... Hospital, Clinic or Medical Center
- Outpatient or admitted to Emergency Room
3 ... Hospital, Clinic or Medical Center
- Dead on Arrival
4 ... Decedent’s home
5 ... Hospice facility
6 ... Nursing home/long term care
7 ... Other
9 ... Place of death unknown

all_icd: Cause of death coded as ICD10 codes. ICD1-ICD21 pasted into a single string, with separation of codes by an underscore

hisp_recode: 0=Non-Hispanic; 1=Hispanic; 999= Not specified

race_recode: race coding prior to 2018 (reconciled in race_recode_new)

race_recode_alt: race coding after 2018 (reconciled in race_recode_new)

race_recode_new:

1='White'

2= 'Black'

3='Hispanic'

4='American Indian'

5='Asian/Pacific Islanders'

agey:

age in years (or partial years for kids <12months)

https://www.cdc.gov/nchs/data_access/restrictions.htm

Please Read Carefully Before Using NCHS Public Use Survey Data

The National Center for Health Statistics (NCHS), Centers for Disease Control and Prevention (CDC), conducts statistical and epidemiological activities under the authority granted by the Public Health Service Act (42 U.S.C. § 242k). NCHS survey data are protected by Federal confidentiality laws including Section 308(d) Public Health Service Act [42 U.S.C. 242m(d)] and the Confidential Information Protection and Statistical Efficiency Act or CIPSEA [Pub. L. No. 115-435, 132 Stat. 5529 § 302]. These confidentiality laws state the data collected by NCHS may be used only for statistical reporting and analysis. Any effort to determine the identity of individuals and establishments violates the assurances of confidentiality provided by federal law.

Terms and Conditions

NCHS does all it can to assure that the identity of individuals and establishments cannot be disclosed. All direct identifiers, as well as any characteristics that might lead to identification, are omitted from the dataset. Any intentional identification or disclosure of an individual or establishment violates the assurances of confidentiality given to the providers of the information. Therefore, users will:

1. Use the data in this dataset for statistical reporting and analysis only.

1. Make no attempt to learn the identity of any person or establishment included in these data.

1. Not link this dataset with individually identifiable data from other NCHS or non-NCHS datasets.

1. Not engage in any efforts to assess disclosure methodologies applied to protect individuals and establishments or any research on methods of re-identification of individuals and establishments.

By using these data you signify your agreement to comply with the above-stated statutorily based requirements.

Sanctions for Violating NCHS Data Use Agreement

Willfully disclosing any information that could identify a person or establishment in any manner to a person or agency not entitled to receive it, shall be guilty of a class E felony and imprisoned for not more than 5 years, or fined not more than $250,000, or both.

The dataset addresses significant gaps in existing VS datasets by including longitudinal data with up to eight time points per patient, compared to our previously published Vestibular-Schwannoma-MC-RC dataset with fewer time points. This longitudinal aspect enables the assessment of tumour progression and patterns, fulfilling a critical clinical need for continuous routine monitoring of vestibular schwannomas, despite the treatments patients undergo. Additionally, the clinical data provided in this dataset enable more comprehensive analyses by correlating imaging findings with patient demographics and clinical decisions.

While the Vestibular-Schwannoma-MC-RC dataset primarily consists of T2-weighted scans, the Vestibular-Schwannoma-MC-RC-2 dataset focuses on T1 contrast-enhanced scans. This distinction allows researchers to explore different imaging modalities and their impact on tumour detection and progression. Additionally, the dataset includes scans from a different region of the UK compared to the Vestibular-Schwannoma-MC-RC dataset, which enhances the diversity and generalizability of the vestibular schwannoma data. Vestibular-Schwannoma-MC-RC2 dataset does not overlap with our previously published datasets.

Methods

The following subsections provide information about how the data were selected, acquired and prepared for publication.

Subject Inclusion and Exclusion Criteria

The dataset comprises longitudinal MRI scans from patients with unilateral sporadic VS, collected from over 15 medical sites across South East England, United Kingdom. A total of 226 patients were referred to the skull base clinic at King's College Hospital, London, where they underwent initial management between August 2008 and November 2012. Eligible participants were adult patients, aged 18 years or older, with a single unilateral VS. This included patients with prior surgical or radiation treatment but individuals with Neurofibromatosis type 2 (NF2) related schwannomatosis were excluded from the study.

All patients with MRI scans available for at least one time point were included in the study. Scans showing other tumours and those covering non-brain regions (e.g., neck) were excluded. Additionally, images with a slice thickness greater than 3.5 mm were excluded due to reduced sensitivity to small lesions and the impact of partial volume effects, which hinder accurate delineation and volumetric analysis of VS.

Data Acquisition

The data were collected across multiple scans performed during routine clinical surveillance. To ensure reproducibility and transparency, MRI acquisition parameters are provided separately and grouped into the following categories:

• Scanner Details: Manufacturer, Manufacturer Model Name, Device Serial Number, Station Name, Magnetic Field Strength, Imaging Frequency
• Patient & Positioning: Body Part, Patient Position, Procedure Step Description
• Software & Protocol: Software Versions, MR Acquisition Type, Study Description, Series Description, Protocol Name, Scanning Sequence, Sequence Variant, Scan Options, Image Type, Deidentification Method
• Acquisition Timing & Numbering: Series Number, Acquisition Time, Acquisition Number
• Geometry & Image Orientation: Slice Thickness, Spacing Between Slices, Image Orientation Patient - DICOM, In Plane Phase Encoding Direction - DICOM
• Sequence & Scan Parameters: SAR, Echo Time, Repetition Time, Flip Angle, Coil String, Percent Phase FOV, Percent Sampling, Echo Train Length, Phase Encoding Steps, AcquisitionMatrixPE, Recon Matrix PE, Acquisition Duration, Pixel Bandwidth

Demographics and clinical information:

The demographics and clinical data captures essential patient information and relevant standards for data collection. For each MRI time point, the following are recorded:

• Demographics: Ethnicity, sex, and age at the time of imaging.
• Treatment Decisions: The primary management strategies for vestibular schwannoma (VS) are included:
  • Routine surveillance
  • Stereotactic radiosurgery (SRS)
  • Surgery
    The majority of patients are managed with routine surveillance. For those undergoing active treatment (SRS or surgery), the treatment date is also provided.
• Prior Treatments: Information on any previous interventions is documented.
• Symptoms: The patient’s clinical symptoms at each time point are recorded.

This structured clinical information allows longitudinal tracking of patient outcomes and management strategies.

Data Analysis

The final curated dataset includes 190 patients, each with 1–8 longitudinal scans acquired from 2010 onwards, totaling 543 contrast-enhanced T1-weighted (T1CE) scans, 481 T1-weighted scans and 133 T2-weighted scans across 621 time points (mean 3.25 scans per patient, mean monitoring period 4.83 ± 3.08 years). All scan dates were uniformly shifted for privacy, with consistent offsets applied within each patient’s imaging series. Binary VS segmentations are provided for 534 T1CE scans; masks are not included for 9 post-operative scans with no visible residual tumour. Supporting data include demographics (sex, ethnicity, age) and clinical decisions documented at each time point.

After converting the original DICOM files to NIfTI format (.nii.gz), the following steps were applied to deface the patient scans.

The defacing pipeline repository: https://github.com/cai4cai/defacing_pipeline.git

1. Reorientation of MRI Images
   The MRI scans are reoriented to match the MNI152 template orientation using the fslreorient2std tool. This step ensures consistency in spatial alignment across all images.
2. Skull Stripping
   The HD-BET (Hybrid Deep Learning Brain Extraction Tool) is employed for tight skull stripping, effectively extracting the brain from the surrounding non-brain tissue. This deep learning model automates brain extraction from multi-sequence MRI data.
3. Binary Mask Creation
   The skull-stripped image is then converted into a binary brain mask, delineating the brain tissue from the rest of the image.
4. Morphological Dilation of Brain Mask
   A 7 mm dilation is applied to the binary brain mask using morphological operations. This step creates a safety margin to ensure that critical brain features near the boundaries are preserved during defacing.
5. Loose Skull Stripping
   The dilated brain mask is applied to the original MRI image to generate a loosely skull-stripped version. This process removes non-brain tissue while retaining essential brain structures.
6. Affine Registration to Template
   The loosely skull-stripped image undergoes affine registration to a skull-stripped T1-weighted ICBM152 reference template. Mutual information serves as the similarity metric during this registration process.
7. Inverse Transformation of Defacing

Haiti Health Facilities Locations

An Evaluation of Operating Health Facilities in 2019

By Humanitarian Data Exchange [source]

About this dataset

This dataset provides an authoritative list of operating health facilities in Haiti. It includes comprehensive information that can be used to analyze the geographical distribution of medical resources throughout the country. The data includes attributes such as facility name, nature and type; categories of services offered; and their exact geographic coordinates (latitude/longitude). This dataset is compiled by a registry, ensuring it is up-to-date and reliable, making it a valuable resource for organizations seeking to understand healthcare infrastructure in the nation. The data can be employed to study inequalities within countries between rural and urban areas or urban hubs versus peripheral regions. Given that access to quality health care should be equitable regardless of geographic areas, researchers could use this dataset to trace unevenness across Haiti's geography—or within certain districts or cities—so that corresponding resources may then be allocated accordingly within the region. In addition, major restructuring initiatives can use this kind of detailed information for effective decision making capabilities with respect to delivery networks – allowing for critical epidemiological analysis on population coverage, accessibility issues faced by citizens from remote locations etc. This dataset is released under Creative Commons Attribution license with no rights reserved which allows users to share or adapt the material in any medium or format they wish as long as they attribute its original creator adequately

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

Getting Started:

Exploring Data:

Analyzing Data: Now that you know what information is provided in each column within a view; analyzing data becomes easier than ever! For example if a researcher wanted insight into specific healthcare facilities in one area they could filter by “Adm 1 Code” which is administrative area level one code - selecting only those located geographical regions would be quickly displayed in first view allowing quick insights into what kind facilities (private / public; pharmacy/hospital) are actually being utilized by people living within those boundaries without having manually sort through every row then totalling up counts across all rows - saving invaluable time when working with large datasets such as those found on Kaggle today! With this data we can determine how accessible healthcare is per region within selected parameters like sectorial access (public/private) or hospital capacity related studies etcetera – helping us understand patient shift trends across various areas that could prove invaluable during times like COVID-19 pandemic where numerous areas might lack resources due higher influxes coming from other surrounding regions facing similar restrictions due same natural hazards etcetera… Allowing us draw insights depending upon our research goals quickly without having sort manage thousands plus rows line item basis saves time & money over long haul allowing quicker actions if needed be put place intervene locally on regional level depending upon findings

Research Ideas

• Finding hospitals in relation to natural disasters or humanitarian crises using a heatmap representation of the data to visualize health facility locations.
• Mapping rural healthcare facilities to provide residents with access to health services and for the government to monitor usage trends over time.
• Plotting data points on an interactive map of Haiti with lines connecting population centers and medical facilities, providing useful data-driven insight into public transportation networks and health infrastructure covering geographic areas across the country

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Columns

File: haiti-healthsites-hdx-1.csv | Column name | Description | |:---------------------|:-------------------------------------------------------| | **Adm1code*...

Identification of Risk Factors for Heart Disease

Exploring Categorical and Numeric Variables

By IBM Watson AI XPRIZE - Health [source]

About this dataset

The Heart Disease Case Study is an investigation into the factors associated with heart disease and mortality. This dataset, gathered by the Hungarian Institute of Cardiology, University Hospital of Zurich and University Hospital of Basel in Switzerland, contains data on over 300 heart disease patients including age, sex, chest pain type, resting blood pressure, serum cholesterol levels, fasting blood sugar results, resting electrocardiographic readings, maximum heart rate achieved and more. All patient names and social security numbers were removed from the dataset for privacy purposes. The research presented in this dataset was made possible through a generous donation from David W. Aha at ICS UCI.

Analyzing this data can uncover significant insights about heart health such as which underlying factors are associated with higher risk for developing cardiac issues or contributing to premature death; such knowledge can be invaluable for those looking to proactively protect their hearts from illness or premature death. With 14 attributes related to the diagnoses of various types of heart diseases (including angina) and treatments used during exercise ECG reading (such as digitalis), this crucial data set allows us to investigate potential problems before they become serious medical conditions or loss of life. So examine these records closely - it may just save a life!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset contains data from the Swiss Heart Disease Study, which was used to investigate the risk factors associated with the progression or prevention of heart disease. The dataset includes 32 columns corresponding to various attributes such as age, sex, chest pain type, resting blood pressure and serum cholesterol level. It also includes indicators of exercise test results such as maximum heart rate achieved and ST segment depression induced by exercise relative to rest.

In order to use this dataset for accurate prediction and analysis of risk factors for heart disease it is important that you understand all the characteristics of each column provided in this dataset. The following is a list of columns provided in this dataset:

• #3 (age): Age in years
• #4 (sex): Sex (1= Male; 0= Female)
• #9 (cp): Chest Pain Type -- Value 1: typical angina -- Value 2: atypical angina -- Value 3: non-anginal pain -- Value 4: asymptomatic 4.#10 (trestbps) Resting Blood Pressure in mm Hg on admission to hospital 5.#12(chol): Serum Cholesterol Level 6.#16(fbs): Fasting Blood Sugar (>120mg/dl) 7:#19(restecg): Resting Electrocardiographic Results 8:#32(thalach) Maximum Heart Rate Achieved 9:#38 exang Exercise Induced Angina 10:#40 oldpeak ST Depression induced by Exercise relative to rest 11:#41 slope The Slope of Peak exercise ST Segment 12#44 ca Number of Major Vessels Colored by Flourosopy 13#51 thal Thalassemia 14#58 num Diagnosis Of Heart Disease The data can be utilized for exploring the relationship between different variables which could lead us closer towards predicting whether a patient is likely or not likely to develop heart disease. For instance, examining age could give us an indication around likelihood since older people are more prone given their potential history with other conditions like hypertension then proceeding further with other variables that may provide additional evidence or insight into risks associated with developing cardiovascular diseases might include studying cholestrol levels after proper dietary restrictions were imposed or if there were no significant changes taken among other things one can study how regular physical activity affects those variables etc... Additionally it will be important that on your investigation consider 2 datasets namely 'processed_sw

Research Ideas

• Exploring the influence of lifestyle factors (ex. Smoking and exercise habits) on heart disease risk.
• Examining the effect of age, gender, and other demographic characteristics on heart disease risk as well as treatment outcomes.
• Creating predictive models to identify which individuals are at a higher likelihood of developing heart disease based on collected data from this dataset such as Age, Chest Pain Type, ST Depression Induced by Exercise Relative to Rest and Maximum Heart Rate Achieved etc

Acknowledgements

If you use this da...

Background: The optimal time to rescue spinal cord function after spinal cord injury is within 24 hours, especially within 3 to 8 hours, after the injury. Timely and proper pre-hospital first aid, hospital admission, patient assessment, and surgery are essential for the rescue of spinal cord function. A sound and rapid treatment system is the basis for improving the level of injury treatment and recovery of spinal cord function. China currently lacks a systematic and standardized treatment system.Methods/Design: We herein propose our study protocol for a prospective, multicenter, nonrandomized controlled trial. We will recruit 200 patients with acute spinal cord injury undergoing pre-hospital treatment at Beijing Emergency Medical Center and Beijing Red Cross Emergency Rescue Center and receiving in-hospital treatment at Peking University People’s Hospital, Peking University Third Hospital, Beijing Friendship Hospital Affiliated to Capital Medical University, Chaoyang Hospital Affiliated to Capital Medical University, and Chinese PLA General Hospital, China. This study will comprise two parts: (1) establishment of a database of patients with spinal cord injury in the Beijing area; and (2) formulation of the pre-hospital and in-hospital process and establishment of a standardized treatment protocol for acute spinal cord injury. The primary outcome will be the American Spinal Injury Association impairment scale score for spinal nerve function. The secondary outcomes will be spinal X-ray, three-dimensional computed tomography, and magnetic resonance imaging findings and the incidence of complications due to improper pre-hospital and in-hospital treatment of acute spinal cord injury.Discussion: The aims of this study are as follows: (1) We will establish a spine and spinal cord injury treatment database in the Beijing area. (2) We will assess the complete pre-hospital and in-hospital evaluation of spine and spinal cord injury, develop and optimize first aid procedures, and create a pre-hospital and in-hospital standardized training program for the treatment of spine and spinal cord injury. (3) We will build a pre-hospital and in-hospital first aid “green channel” for acute spine and spinal cord injury after completion of the study. (4) We will develop first aid guidelines and establish an evaluation and treatment system for early surgery to save spinal cord function and reduce the degree of disability to the greatest extent as possible. (5) We anticipate that our results will be used in expert consensuses on acute spinal cord injury and that “green channel” patterns will be promoted in hospitals in Beijing and other cities of China to improve the level of first aid treatment of acute spine and spinal cord injury in Chinese cities and reduce the occurrence of secondary injury and severe dysfunction due to improper treatment. This trial will begin in May 2017. Patient recruitment will be finished in August 2019. Analysis of all data and results will be completed in December 2020.Trial registration: ClinicalTrials.gov identifier: NCT03103516.doi: 10.4103/2542-3932.205195How to cite this article: Xue F, Xiong J, Zhang PX, Kou YH, Han S, Wang TB, Zhang DY, Jiang BG (2017) Pre-hospital and in-hospital first aid programs and specifications for spine and spinal cord injury in Beijing, China: study protocol for a prospective, multicenter, nonrandomized controlled trial. Asia Pac J Clin Trials Nerv Syst Dis 2(2):58-65.

Context

http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

Retinal optical coherence tomography (OCT) is an imaging technique used to capture high-resolution cross sections of the retinas of living patients. Approximately 30 million OCT scans are performed each year, and the analysis and interpretation of these images takes up a significant amount of time (Swanson and Fujimoto, 2017).

https://i.imgur.com/fSTeZMd.png" alt="">

Figure 2. Representative Optical Coherence Tomography Images and the Workflow Diagram [Kermany et. al. 2018] http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

(A) (Far left) choroidal neovascularization (CNV) with neovascular membrane (white arrowheads) and associated subretinal fluid (arrows). (Middle left) Diabetic macular edema (DME) with retinal-thickening-associated intraretinal fluid (arrows). (Middle right) Multiple drusen (arrowheads) present in early AMD. (Far right) Normal retina with preserved foveal contour and absence of any retinal fluid/edema.

Content

The dataset is organized into 3 folders (train, test, val) and contains subfolders for each image category (NORMAL,CNV,DME,DRUSEN). There are 84,495 X-Ray images (JPEG) and 4 categories (NORMAL,CNV,DME,DRUSEN).

Images are labeled as (disease)-(randomized patient ID)-(image number by this patient) and split into 4 directories: CNV, DME, DRUSEN, and NORMAL.

Optical coherence tomography (OCT) images (Spectralis OCT, Heidelberg Engineering, Germany) were selected from retrospective cohorts of adult patients from the Shiley Eye Institute of the University of California San Diego, the California Retinal Research Foundation, Medical Center Ophthalmology Associates, the Shanghai First People’s Hospital, and Beijing Tongren Eye Center between July 1, 2013 and March 1, 2017.

Before training, each image went through a tiered grading system consisting of multiple layers of trained graders of increasing exper- tise for verification and correction of image labels. Each image imported into the database started with a label matching the most recent diagnosis of the patient. The first tier of graders consisted of undergraduate and medical students who had taken and passed an OCT interpretation course review. This first tier of graders conducted initial quality control and excluded OCT images containing severe artifacts or significant image resolution reductions. The second tier of graders consisted of four ophthalmologists who independently graded each image that had passed the first tier. The presence or absence of choroidal neovascularization (active or in the form of subretinal fibrosis), macular edema, drusen, and other pathologies visible on the OCT scan were recorded. Finally, a third tier of two senior independent retinal specialists, each with over 20 years of clinical retina experience, verified the true labels for each image. The dataset selection and stratification process is displayed in a CONSORT-style diagram in Figure 2B. To account for human error in grading, a validation subset of 993 scans was graded separately by two ophthalmologist graders, with disagreement in clinical labels arbitrated by a senior retinal specialist.

For additional information: see http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

Acknowledgements

Data: https://data.mendeley.com/datasets/rscbjbr9sj/2

Citation: http://www.cell.com/cell/fulltext/S0092-8674(18)30154-5

https://i.imgur.com/8AUJkin.png" alt="enter image description here">

Inspiration

Automated methods to detect and classify human diseases from medical images.

Florida COVID-19 Case Line data, exported from the Florida Department of Health GIS Layer on date seen in file name. Archived by the University of South Florida Libraries, Digital Heritage and Humanities Collections. Contact: LibraryGIS@usf.edu. Starting on 4/6/2021, the Florida Department of Health (FDOH) changed the way they provide COVID-19 caseline data. Beginning with this date the caseline data is being archived as two separate files, one for 2020 and one for 2021. The 2021 file will only include data from 1/1/2021 onward. In addition, FDOH has added two Object ID fields to their dataset. These caseline data are being preserved as they are provided by the FDOH, with a daily archive captured by the USF Libraries DHHC.Please Cite Our GIS HUB. If you are a researcher or other utilizing our Florida COVID-19 HUB as a tool or accessing and utilizing the data provided herein, please provide an acknowledgement of such in any publication or re-publication. The following citation is suggested: University of South Florida Libraries, Digital Heritage and Humanities Collections. 2021. Florida COVID-19 Hub. Available at https://covid19-usflibrary.hub.arcgis.com/. https://doi.org/10.5038/USF-COVID-19-GISLive FDOH Data Source: https://www.arcgis.com/home/item.html?id=7a0c74a551904761812dc6b8bd620ee1 or Direct Download at: https://open-fdoh.hub.arcgis.com/datasets/7a0c74a551904761812dc6b8bd620ee1_0.

Archives for this data layer begin on 5/11/2020. Archived data was exported directly from the live FDOH layer into the archive by the University of South Florida Libraries - Digital Heritage and Humanities Collection.For data definitions please visit the following box folder: https://usf.box.com/s/vfjwbczkj73ucj19yvwz53at6v6w614hData definition files names include the relative date they were published. The below information was taken from ancillary documents associated with the original layer from the Florida Department of Health. This data table represents all laboratory-confirmed cases of COVID-19 in Florida tabulated from the previous day's totals by the Florida Department of Health. Persons Under Investigation/Surveillance (PUI):Essentially, PUIs are any person who has been or is waiting to be tested. This includes: persons who are considered high-risk for COVID-19 due to recent travel, contact with a known case, exhibiting symptoms of COVID-19 as determined by a healthcare professional, or some combination thereof. PUI’s also include people who meet laboratory testing criteria based on symptoms and exposure, as well as confirmed cases with positive test results. PUIs include any person who is or was being tested, including those with negative and pending results.All PUIs fit into one of three residency types:1. Florida residents tested in Florida2. Non-Florida residents tested in Florida 3. Florida residents tested outside of Florida Florida Residents Tested Elsewhere: The total number of Florida residents with positive COVID-19 test results who were tested outsideof Florida, and were not exposed/infectious in Florida. Non-Florida Residents Tested in Florida: The total number of people with positive COVID-19 test results who were tested, exposed, and/or infectious while in Florida, but are legal residents of another state.Table Guide for Records of Confirmed Positive Cases of COVID-19"County": The Florida county where the individual with COVID-19's case has been processed. "Jurisdiction" of the case:"FL resident" -- a resident of Florida"Non-FL resident" -- someone who resides outside of Florida "Travel_Related": Whether or not the positive case of COVID-19 is designated as related to recent travel by the individual. "No" -- Case designated as not being a risk related to recent travel"Unknown" -- Case designated where a travel-related designation has not yet been made."Yes" -- Case is designated as travel-related for a person who recently traveled overseas or to an area with community"Origin": Where the person likely contracted the virus before arriving / returning to Florida."EDvisit": Whether or not an individual who tested positive for coronavirus visited and was admitted to an Emergency Department related to health conditions surrounding COVID-19."No" -- Individual was not admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Unknown" -- It is unknown whether the individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19"Yes" -- Individual was admitted to an emergency department relating to health conditions surrounding the contraction of COVID-19“Hospitalized”: Whether or not a patient who receives a positive laboratory confirmed test for COVID-19 receives inpatient care at a hospital at any time during illness. These people may no longer be hospitalized. This information does not indicate that a COVID-19 positive person is currently hospitalized, only that they have been hospitalized for health conditions relating to COVID-19 at some point during their illness. "No" -- Individual was not admitted for inpatient care at a hospital at any time during illness "Unknown" -- It is unknown whether the individual was admitted for inpatient care at a hospital at any time during illness "Yes" -- Individual was admitted for inpatient care at a hospital at some point during the illness "Died": Whether or not the individual who tested positive for COVID-19 died as a result of health complications from the viral infection. "NA" -- Not applicable / resident has not died "Yes" -- Individual died of a health complication resulting from COVID-19 "Contact": Whether the person contracted COVID-19 from contact with current or previously confirmedcases."No" -- Case with no known contact with current or previously confirmed cases"Yes" -- Case with known contact with current or previously confirmed cases"Unknown" -- Case where contact with current or previous confirmedcases is not known or under investigation"Case_": The date the positive laboratory result was received in the Department of Health’s database system and became a “confirmed case.” This is not the date a person contracted the virus, became symptomatic, or was treated. Florida does not create a case or count suspected/probable cases in the case counts without a confirmed-positive lab result. "EventDate": When the individual reported likely first experiencing symptoms related to COVID-19. "ChartDate": Also the date the positive laboratory result for an individual was received in the Department ofHealth’s database system and became a recorded, “confirmed case” of COVID-19 in the state. Data definitions updated by the FDOH on 5/13/2020.

Context

• Zahlen stammen aus der amtlichen Statistik „Grunddaten der Krankenhäuser (EVAS-Nr. 23111)
• die Daten sind von 12/2017
• es handelt sich um Durchschnittwerte des Jahres der insgesamt zur Verfügung stehenden Betten; die Anzahl der freien Betten ist i.d.R. geringer
• nicht erfasst sind Krankenhäuser des Straf- und Maßregelvollzuges sowie der Polizei
• die Zuordnung zum Landkreis ist immer bezogen auf den Standort des Hauptsitzes der Krankenhausverwaltung (nicht zwingend Standort des Krankenhauses)
• zu den Intensivbetten gehören auch Schwerkrankenbetten mit Überwachungseinrichtungen

Content

This file contains the ICU bed units from germany based on district. Some districts are estimated based on ROR and inhabitants. Here is a short field description:

Nummer - AGS Key (Amtlicher Gemeindeschlüssel) or for Berlin RS Key Kreisebene - Name of the City or District (Kreis oder Kreisfreie Stadt) Intensivbetten - ICU Units in this disctrict Krankenhauser - Amount of hospitals (only for Nordrhein Westfalen) Betten - In general hospital beds (only for Nordrhein Westfalen) Bundesland - two letter abbreviation for federal state EWZ - Amount of inhabitans, only when it was necessary to break down ICU beds from ROR (Raumordnungsregionen) to Gemeinden Region - Raumordnungsregion Intensivbetten_Region - ICU Units in Raumordnungsregion EWZ Region - Inhabitans in Region

Acknowledgements

Thanks to Statistisches Landesamt Rheinland-Pfalz especially Dr. Christoph Wonke.

Inspiration

How to transport patient from one region to another to save as many lives as possible? What will be the local demand for human resources, ventilators, masks, and other protection equipment? How to distribute medical equipment evenly to the necessary places? Currently it is said that capacity was increased from 28.000 beds to 40.000. Was the capacity increase in the right places? Where to increase capacity?