The following dashboards provide data on contagious respiratory viruses, including acute respiratory diseases, COVID-19, influenza (flu), and respiratory syncytial virus (RSV) in Massachusetts. The data presented here can help track trends in respiratory disease and vaccination activity across Massachusetts.

Mass media reports can induce individual behaviour change during a disease outbreak, which has been found to be useful as it reduces the force of infection. We propose a compartmental model by including a new compartment of the intensity of the media reports, which extends existing models by considering a novel media function, which is dependent both on the number of infected individuals and on the intensity of mass media. The existence and stability of the equilibria are analyzed and an optimal control problem of minimizing the total number of cases and total cost is considered, using reduction or enhancement in the media reporting rate as the control. With the help of Pontryagin’s Maximum Principle, we obtain the optimal media reporting intensity. Through parameterization of the model with the 2009 A/H1N1 influenza outbreak data in the 8th Hospital of Xi’an in Shaanxi Province of China, we obtain the basic reproduction number for the formulated model with two particular media functions. The optimal media reporting intensity obtained here indicates that during the early stage of an epidemic we should quickly enhance media reporting intensity, and keep it at a maximum level until it can finally weaken when epidemic cases have decreased significantly. Numerical simulations show that media impact reduces the number of cases during an epidemic, but that the number of cases is further mitigated under the optimal reporting intensity. Sensitivity analysis implies that the outbreak severity is more sensitive to the weight α1 (weight of media effect sensitive to infected individuals) than weight α2 (weight of media effect sensitive to media items).

The Public Health Agency of Canada, in collaboration with Canadian public health and infection prevention and control (IPC) experts and the Funeral Services Association of Canada, has developed this guidance on public health measures for the management of mass fatalities from COVID-19. The guidance is for local and regional planners, community leaders, funeral service workers, medical examiners, and coroners.

Recent studies have provided insights into the pathology and immune response to coronavirus disease 2019 (COVID-19). However thorough interrogation of the interplay between infected cells and the immune system at sites of infection is lacking. We use high parameter imaging mass cytometry targeting the expression of 36 proteins, to investigate at single cell resolution, the cellular composition and spatial architecture of human acute lung injury including SARS-CoV-2. This spatially resolved, single-cell data unravels the disordered structure of the infected and injured lung alongside the distribution of extensive immune infiltration. Neutrophil and macrophage infiltration are hallmarks of bacterial pneumonia and COVID-19, respectively. We provide evidence that SARS-CoV-2 infects predominantly alveolar epithelial cells and induces a localized hyper-inflammatory cell state associated with lung damage. By leveraging the temporal range of COVID-19 severe fatal disease in relation to the time of symptom onset, we observe increased macrophage extravasation, mesenchymal cells, and fibroblasts abundance concomitant with increased proximity between these cell types as the disease progresses, possibly as an attempt to repair the damaged lung tissue. This spatially resolved single-cell data allowed us to develop a biologically interpretable landscape of lung pathology from a structural, immunological and clinical standpoint. This spatial single-cell landscape enabled the pathophysiological characterization of the human lung from its macroscopic presentation to the single-cell, providing an important basis for the understanding of COVID-19, and lung pathology in general.

Comprehensive dataset of 760 Infectious disease physicians in Massachusetts, United States as of June, 2025. Includes verified contact information (email, phone), geocoded addresses, customer ratings, reviews, business categories, and operational details. Perfect for market research, lead generation, competitive analysis, and business intelligence. Download a complimentary sample to evaluate data quality and completeness.

Find local risk levels for Eastern Equine Encephalitis (EEE) and West Nile Virus (WNV) based on seasonal testing from June to October.

Data associated with doi: 10.1016/j.isci.2021.102681 CSV file includes peptides observed by HDX-MS with deuteration extents and HDX-MS summary table. PDF includes kinetic plots indicating deuterium uptake for unbound and RNA-bound peptides.

Clinical Diagnostics Mass Spectrometry Market Outlook

The clinical diagnostics mass spectrometry market size was valued at approximately USD 1.2 billion in 2023 and is projected to reach USD 3.2 billion by 2032, growing at a compound annual growth rate (CAGR) of 11.2%. This significant growth is driven by advancements in mass spectrometry technology, increasing prevalence of chronic diseases, and the need for precise diagnostic tools.

The primary growth factor for this market is the technological advancement in mass spectrometry, which has significantly enhanced its application in clinical diagnostics. Innovations such as the development of high-resolution instruments, enhanced ionization techniques, and improved data analysis software have bolstered the adoption of mass spectrometry in clinical settings. These advancements allow for more accurate, sensitive, and rapid analysis of complex biological samples, which is critical in early disease detection and personalized medicine.

Another contributing factor to market growth is the rising prevalence of chronic diseases such as cancer, cardiovascular diseases, and diabetes. As these conditions often require precise and early diagnosis for effective treatment, the demand for advanced diagnostic tools like mass spectrometry is increasing. This diagnostic technique offers high specificity and sensitivity, which are crucial for identifying biomarkers and understanding disease mechanisms at the molecular level.

Furthermore, the increasing focus on personalized medicine is driving the adoption of mass spectrometry in clinical diagnostics. Personalized medicine requires detailed molecular information about a patient's disease state, which mass spectrometry can provide. This technology enables the identification of specific biomarkers associated with different diseases, thereby aiding in the development of tailored treatment plans that improve patient outcomes.

Regionally, North America is expected to dominate the market due to the high adoption rate of advanced diagnostic technologies and the presence of well-established healthcare infrastructure. However, significant growth is also anticipated in the Asia Pacific region, driven by increasing healthcare expenditure, rising awareness about early disease diagnosis, and growing investments in healthcare infrastructure. Countries such as China and India are expected to be key contributors to this growth.

Product Type Analysis

The clinical diagnostics mass spectrometry market is segmented by product type into instruments, consumables, and software. Instruments form the largest segment due to continuous technological advancements and the high cost associated with these devices. The demand for sophisticated and precise instruments is rising as they offer enhanced performance and reliability in clinical settings. Innovations such as tandem mass spectrometry (MS/MS) and high-resolution mass spectrometry (HRMS) have expanded the capabilities of these instruments, thereby driving market growth.

Consumables, including reagents, kits, and other supplies, represent a significant portion of the market. The recurring need for these products in diagnostic procedures ensures a steady demand. The increase in the number of diagnostic tests conducted globally, owing to the rise in chronic diseases and infectious diseases, is propelling the growth of the consumables segment. Additionally, the development of specialized kits for specific diagnostic applications is further boosting this segment.

Software plays a crucial role in the clinical diagnostics mass spectrometry market by enhancing data analysis and interpretation. The integration of advanced software solutions enables the efficient processing of large data sets, improving the accuracy and speed of diagnostic results. Software advancements, such as machine learning and artificial intelligence, are being increasingly incorporated to provide more detailed insights into complex diagnostic data, thereby enhancing the overall diagnostic process.

The synergy between these product types is vital for the efficient functioning of mass spectrometry in clinical diagnostics. Instruments provide the necessary hardware for analysis, consumables ensure the continuity of operations, and software facilitates data interpretation. Together, they form a comprehensive system that enhances the precision and reliability of clinical diagnostics, driving the overall market growth.

Report Scope

Reported by eight state health departments through an online assessment, March 2016.

United States Number of Patients: Probable: Massachusetts data was reported at 2.000 Person in 15 Jul 2003. This stayed constant from the previous number of 2.000 Person for 07 Jul 2003. United States Number of Patients: Probable: Massachusetts data is updated daily, averaging 2.000 Person from Apr 2003 (Median) to 15 Jul 2003, with 45 observations. The data reached an all-time high of 3.000 Person in 05 May 2003 and a record low of 1.000 Person in 28 Apr 2003. United States Number of Patients: Probable: Massachusetts data remains active status in CEIC and is reported by Centers for Disease Control and Prevention. The data is categorized under High Frequency Database’s Disease Outbreaks – Table US.D001: Centers for Disease Control and Prevention: No of SARS Patients.

Distribution of the household population by Children's body mass index (BMI) according to the Center for Disease Control (CDC) classification system, by sex and age group.

Reporting of Aggregate Case and Death Count data was discontinued May 11, 2023, with the expiration of the COVID-19 public health emergency declaration. Although these data will continue to be publicly available, this dataset will no longer be updated.

This archived public use dataset has 11 data elements reflecting United States COVID-19 community levels for all available counties.

The COVID-19 community levels were developed using a combination of three metrics — new COVID-19 admissions per 100,000 population in the past 7 days, the percent of staffed inpatient beds occupied by COVID-19 patients, and total new COVID-19 cases per 100,000 population in the past 7 days. The COVID-19 community level was determined by the higher of the new admissions and inpatient beds metrics, based on the current level of new cases per 100,000 population in the past 7 days. New COVID-19 admissions and the percent of staffed inpatient beds occupied represent the current potential for strain on the health system. Data on new cases acts as an early warning indicator of potential increases in health system strain in the event of a COVID-19 surge.

Using these data, the COVID-19 community level was classified as low, medium, or high.

COVID-19 Community Levels were used to help communities and individuals make decisions based on their local context and their unique needs. Community vaccination coverage and other local information, like early alerts from surveillance, such as through wastewater or the number of emergency department visits for COVID-19, when available, can also inform decision making for health officials and individuals.

For the most accurate and up-to-date data for any county or state, visit the relevant health department website. COVID Data Tracker may display data that differ from state and local websites. This can be due to differences in how data were collected, how metrics were calculated, or the timing of web updates.

Archived Data Notes:

This dataset was renamed from "United States COVID-19 Community Levels by County as Originally Posted" to "United States COVID-19 Community Levels by County" on March 31, 2022.

March 31, 2022: Column name for county population was changed to “county_population”. No change was made to the data points previous released.

March 31, 2022: New column, “health_service_area_population”, was added to the dataset to denote the total population in the designated Health Service Area based on 2019 Census estimate.

March 31, 2022: FIPS codes for territories American Samoa, Guam, Commonwealth of the Northern Mariana Islands, and United States Virgin Islands were re-formatted to 5-digit numeric for records released on 3/3/2022 to be consistent with other records in the dataset.

March 31, 2022: Changes were made to the text fields in variables “county”, “state”, and “health_service_area” so the formats are consistent across releases.

March 31, 2022: The “%” sign was removed from the text field in column “covid_inpatient_bed_utilization”. No change was made to the data. As indicated in the column description, values in this column represent the percentage of staffed inpatient beds occupied by COVID-19 patients (7-day average).

March 31, 2022: Data values for columns, “county_population”, “health_service_area_number”, and “health_service_area” were backfilled for records released on 2/24/2022. These columns were added since the week of 3/3/2022, thus the values were previously missing for records released the week prior.

April 7, 2022: Updates made to data released on 3/24/2022 for Guam, Commonwealth of the Northern Mariana Islands, and United States Virgin Islands to correct a data mapping error.

April 21, 2022: COVID-19 Community Level (CCL) data released for counties in Nebraska for the week of April 21, 2022 have 3 counties identified in the high category and 37 in the medium category. CDC has been working with state officials to verify the data submitted, as other data systems are not providing alerts for substantial increases in disease transmission or severity in the state.

May 26, 2022: COVID-19 Community Level (CCL) data released for McCracken County, KY for the week of May 5, 2022 have been updated to correct a data processing error. McCracken County, KY should have appeared in the low community level category during the week of May 5, 2022. This correction is reflected in this update.

May 26, 2022: COVID-19 Community Level (CCL) data released for several Florida counties for the week of May 19th, 2022, have been corrected for a data processing error. Of note, Broward, Miami-Dade, Palm Beach Counties should have appeared in the high CCL category, and Osceola County should have appeared in the medium CCL category. These corrections are reflected in this update.

May 26, 2022: COVID-19 Community Level (CCL) data released for Orange County, New York for the week of May 26, 2022 displayed an erroneous case rate of zero and a CCL category of low due to a data source error. This county should have appeared in the medium CCL category.

June 2, 2022: COVID-19 Community Level (CCL) data released for Tolland County, CT for the week of May 26, 2022 have been updated to correct a data processing error. Tolland County, CT should have appeared in the medium community level category during the week of May 26, 2022. This correction is reflected in this update.

June 9, 2022: COVID-19 Community Level (CCL) data released for Tolland County, CT for the week of May 26, 2022 have been updated to correct a misspelling. The medium community level category for Tolland County, CT on the week of May 26, 2022 was misspelled as “meduim” in the data set. This correction is reflected in this update.

June 9, 2022: COVID-19 Community Level (CCL) data released for Mississippi counties for the week of June 9, 2022 should be interpreted with caution due to a reporting cadence change over the Memorial Day holiday that resulted in artificially inflated case rates in the state.

July 7, 2022: COVID-19 Community Level (CCL) data released for Rock County, Minnesota for the week of July 7, 2022 displayed an artificially low case rate and CCL category due to a data source error. This county should have appeared in the high CCL category.

July 14, 2022: COVID-19 Community Level (CCL) data released for Massachusetts counties for the week of July 14, 2022 should be interpreted with caution due to a reporting cadence change that resulted in lower than expected case rates and CCL categories in the state.

July 28, 2022: COVID-19 Community Level (CCL) data released for all Montana counties for the week of July 21, 2022 had case rates of 0 due to a reporting issue. The case rates have been corrected in this update.

July 28, 2022: COVID-19 Community Level (CCL) data released for Alaska for all weeks prior to July 21, 2022 included non-resident cases. The case rates for the time series have been corrected in this update.

July 28, 2022: A laboratory in Nevada reported a backlog of historic COVID-19 cases. As a result, the 7-day case count and rate will be inflated in Clark County, NV for the week of July 28, 2022.

August 4, 2022: COVID-19 Community Level (CCL) data was updated on August 2, 2022 in error during performance testing. Data for the week of July 28, 2022 was changed during this update due to additional case and hospital data as a result of late reporting between July 28, 2022 and August 2, 2022. Since the purpose of this data set is to provide point-in-time views of COVID-19 Community Levels on Thursdays, any changes made to the data set during the August 2, 2022 update have been reverted in this update.

August 4, 2022: COVID-19 Community Level (CCL) data for the week of July 28, 2022 for 8 counties in Utah (Beaver County, Daggett County, Duchesne County, Garfield County, Iron County, Kane County, Uintah County, and Washington County) case data was missing due to data collection issues. CDC and its partners have resolved the issue and the correction is reflected in this update.

August 4, 2022: Due to a reporting cadence change, case rates for all Alabama counties will be lower than expected. As a result, the CCL levels published on August 4, 2022 should be interpreted with caution.

August 11, 2022: COVID-19 Community Level (CCL) data for the week of August 4, 2022 for South Carolina have been updated to correct a data collection error that resulted in incorrect case data. CDC and its partners have resolved the issue and the correction is reflected in this update.

August 18, 2022: COVID-19 Community Level (CCL) data for the week of August 11, 2022 for Connecticut have been updated to correct a data ingestion error that inflated the CT case rates. CDC, in collaboration with CT, has resolved the issue and the correction is reflected in this update.

August 25, 2022: A laboratory in Tennessee reported a backlog of historic COVID-19 cases. As a result, the 7-day case count and rate may be inflated in many counties and the CCLs published on August 25, 2022 should be interpreted with caution.

August 25, 2022: Due to a data source error, the 7-day case rate for St. Louis County, Missouri, is reported as zero in the COVID-19 Community Level data released on August 25, 2022. Therefore, the COVID-19 Community Level for this county should be interpreted with caution.

September 1, 2022: Due to a reporting issue, case rates for all Nebraska counties will include 6 days of data instead of 7 days in the COVID-19 Community Level (CCL) data released on September 1, 2022. Therefore, the CCLs for all Nebraska counties should be interpreted with caution.

September 8, 2022: Due to a data processing error, the case rate for Philadelphia County, Pennsylvania,

We implemented an online survey questionnaire for adult Massachusetts licensed hunters in December 2022-February 2023 using the Qualtrics survey platform (Qualtrics, Provo, UT). The online survey covers a number of topics related to chronic wasting disease (CWD) such as knowledge, risk perception, management acceptability, hunting behavior, channel use, and trust in different sources. Of the 39,676 requests, we received a total of 11,741 responses, corresponding to a response rate of 29.6%.

Morocco MA: Cause of Death: by Non-Communicable Diseases: % of Total data was reported at 79.600 % in 2016. This records an increase from the previous number of 78.800 % for 2015. Morocco MA: Cause of Death: by Non-Communicable Diseases: % of Total data is updated yearly, averaging 77.000 % from Dec 2000 (Median) to 2016, with 4 observations. The data reached an all-time high of 79.600 % in 2016 and a record low of 69.400 % in 2000. Morocco MA: Cause of Death: by Non-Communicable Diseases: % of Total data remains active status in CEIC and is reported by World Bank. The data is categorized under Global Database’s Morocco – Table MA.World Bank.WDI: Health Statistics. Cause of death refers to the share of all deaths for all ages by underlying causes. Non-communicable diseases include cancer, diabetes mellitus, cardiovascular diseases, digestive diseases, skin diseases, musculoskeletal diseases, and congenital anomalies.; ; Derived based on the data from WHO's Global Health Estimates.; Weighted average;

The deposited data were collected from 148 patients and 133 family members accepted into the Undiagnosed Diseases Network (https://undiagnosed.hms.harvard.edu/). The NIH Common Fund Undiagnosed Diseases Network (UDN) seeks to provide diagnoses for individuals with undiagnosed disease. Here, we report and provide the mass spectrometry-based metabolomics (GC-MS) and lipidomics (LC-MS/MS) analyses of blood plasma from 148 patients and 133 family members. We have deposited mass spectrometry-based metabolomics and lipidomics files including instrument files, normalized data processed files to allow for statistical analysis, and metabolomics and lipidomics results for each patient and associated relatives. In addition, as part of the mass spectrometry data made available, we have included mass spectrometry analyses and results from a reference population of individuals with no known metabolic diseases. UDN patients suffer from undiagnosed diseases and thus are typically represented as a sample size of one; therefore, understanding normal variation within a proband's condition needs to be measured against of dataset of normal individuals, which is included here.

Clinical Mass Spectrometry Service Market Outlook

According to our latest research, the global clinical mass spectrometry service market size reached USD 2.86 billion in 2024, reflecting a robust demand across clinical laboratories, hospitals, and research institutes. The market is currently experiencing a strong compound annual growth rate (CAGR) of 10.7% and is anticipated to expand to USD 7.13 billion by 2033. This growth is primarily driven by the increasing adoption of advanced mass spectrometry technologies in clinical diagnostics, the rising prevalence of chronic and infectious diseases, and the growing emphasis on precision medicine and biomarker discovery.

The surge in demand for clinical mass spectrometry services is largely attributed to the technology’s unparalleled sensitivity and specificity in analyzing complex biological samples. As healthcare systems worldwide shift toward personalized medicine, the need for accurate and rapid diagnostic tools has become more pronounced. Mass spectrometry offers clinicians the ability to detect and quantify low-abundance biomarkers, enabling earlier disease detection and more effective monitoring of therapeutic interventions. Furthermore, the growing incidence of metabolic, cardiovascular, and oncological disorders is fueling the requirement for advanced diagnostic solutions, positioning mass spectrometry as a cornerstone technology in modern clinical laboratories.

Another significant growth factor is the continuous evolution of mass spectrometry instrumentation and software solutions. Innovations such as high-resolution mass spectrometers, improved sample preparation techniques, and integrated data analytics platforms have dramatically enhanced throughput, reproducibility, and ease of use. These advancements are making mass spectrometry more accessible to a broader range of clinical settings, including smaller hospitals and outpatient diagnostic centers. Additionally, the integration of mass spectrometry with automation and laboratory information management systems (LIMS) is streamlining workflows, reducing turnaround times, and minimizing human error, which collectively contribute to the market’s upward trajectory.

The expansion of clinical mass spectrometry services is also being bolstered by supportive regulatory frameworks and increased healthcare expenditure, particularly in developed economies. Regulatory agencies such as the FDA and EMA are actively providing guidance on the clinical validation of mass spectrometry-based assays, which is accelerating their adoption in routine diagnostics and therapeutic drug monitoring. Simultaneously, public and private investments in healthcare infrastructure and research are enabling laboratories to upgrade their analytical capabilities. This is especially evident in the context of emerging infectious diseases, where mass spectrometry has played a critical role in pathogen identification and surveillance, further underscoring its clinical value.

From a regional perspective, North America currently dominates the clinical mass spectrometry service market, accounting for over 38% of global revenue in 2024. This leadership is underpinned by a well-established healthcare infrastructure, extensive research activities, and the presence of leading industry players. However, the Asia Pacific region is exhibiting the fastest growth, driven by rapid healthcare modernization, increasing investments in life sciences research, and rising awareness of advanced diagnostic technologies. Europe also remains a significant market, supported by strong government initiatives and a high prevalence of chronic diseases. Collectively, these regional dynamics are shaping a vibrant and competitive global market landscape.

Service Type Analysis

The clinical mass spectrometry service market is segmented by service type into proteomics, metabolomics, lipidomics, drug monitoring, and others, each contributing uniquely to the market’s expansion. Proteomics

The stress-induced susceptibility hypothesis, which predicts chronic stress weakens immune defenses, was proposed to explain increasing infectious disease-related mass mortality and population declines. Previous work characterized wetland salinization as a chronic stressor to larval amphibian populations. Thus, we combined field observations with experimental exposures quantifying epidemiological parameters to test the role of salinity stress in the occurrence of ranavirus-associated mass mortality events. Despite ubiquitous pathogen presence (94%), populations exposed to salt runoff had slightly more frequent ranavirus related mass mortality events, more lethal infections, and 117-times greater pathogen environmental DNA. Experimental exposure to chronic elevated salinity (0.8-1.6 g/L Cl-) reduced tolerance to infection, causing greater mortality at lower doses. We found a strong negative relationship between splenocyte proliferation and corticosterone in ranavirus-infected larvae at a...

United States Number of Patients: Suspect: Massachusetts data was reported at 20.000 Person in 15 Jul 2003. This stayed constant from the previous number of 20.000 Person for 07 Jul 2003. United States Number of Patients: Suspect: Massachusetts data is updated daily, averaging 19.000 Person from Apr 2003 (Median) to 15 Jul 2003, with 45 observations. The data reached an all-time high of 20.000 Person in 15 Jul 2003 and a record low of 11.000 Person in 23 Apr 2003. United States Number of Patients: Suspect: Massachusetts data remains active status in CEIC and is reported by Centers for Disease Control and Prevention. The data is categorized under High Frequency Database’s Disease Outbreaks – Table US.D001: Centers for Disease Control and Prevention: No of SARS Patients.

Morocco MA: Cause of Death: by Communicable Diseases & Maternal, Prenatal & Nutrition Conditions: % of Total data was reported at 14.000 % in 2016. This records a decrease from the previous number of 14.600 % for 2015. Morocco MA: Cause of Death: by Communicable Diseases & Maternal, Prenatal & Nutrition Conditions: % of Total data is updated yearly, averaging 15.950 % from Dec 2000 (Median) to 2016, with 4 observations. The data reached an all-time high of 21.900 % in 2000 and a record low of 14.000 % in 2016. Morocco MA: Cause of Death: by Communicable Diseases & Maternal, Prenatal & Nutrition Conditions: % of Total data remains active status in CEIC and is reported by World Bank. The data is categorized under Global Database’s Morocco – Table MA.World Bank.WDI: Health Statistics. Cause of death refers to the share of all deaths for all ages by underlying causes. Communicable diseases and maternal, prenatal and nutrition conditions include infectious and parasitic diseases, respiratory infections, and nutritional deficiencies such as underweight and stunting.; ; Derived based on the data from WHO's Global Health Estimates.; Weighted average;

Originally, the dataset come from the CDC and is a major part of the Behavioral Risk Factor Surveillance System (BRFSS), which conducts annual telephone surveys to gather data on the health status of U.S. residents. As the CDC describes: "Established in 1984 with 15 states, BRFSS now collects data in all 50 states as well as the District of Columbia and three U.S. territories. BRFSS completes more than 400,000 adult interviews each year, making it the largest continuously conducted health survey system in the world.". The most recent dataset (as of February 15, 2022) includes data from 2020. It consists of 401,958 rows and 279 columns. The vast majority of columns are questions asked to respondents about their health status, such as "Do you have serious difficulty walking or climbing stairs?" or "Have you smoked at least 100 cigarettes in your entire life? [Note: 5 packs = 100 cigarettes]".

To improve the efficiency and relevance of our analysis, we removed certain attributes from the original BRFSS dataset. Many of the 279 original attributes included administrative codes, metadata, or survey-specific variables that do not contribute meaningfully to heart disease prediction—such as respondent IDs, timestamps, state-level identifiers, and detailed lifestyle questions unrelated to cardiovascular health. By focusing on a carefully selected subset of 18 attributes directly linked to medical, behavioral, and demographic factors known to influence heart health, we streamlined the dataset. This not only reduced computational complexity but also improved model interpretability and performance by eliminating noise and irrelevant information. All predicting variables could be divided into 4 broad categories:

1. Demographic factors: sex, age category (14 levels), race, BMI (Body Mass Index)

2. Diseases: weather respondent ever had such diseases as asthma, skin cancer, diabetes, stroke or kidney disease (not including kidney stones, bladder infection or incontinence)

3. Unhealthy habits:

   • Smoking - respondents that smoked at least 100 cigarettes in their entire life (5 packs = 100 cigarettes)
   • Alcohol Drinking - heavy drinkers (adult men having more than 14 drinks per week and adult women having more than 7 drinks per week

4. General Health:

   • Difficulty Walking - weather respondent have serious difficulty walking or climbing stairs
   • Physical Activity - adults who reported doing physical activity or exercise during the past 30 days other than their regular job
   • Sleep Time - respondent’s reported average hours of sleep in a 24-hour period
   • Physical Health - number of days being physically ill or injured (0-30 days)
   • Mental Health - number of days having bad mental health (0-30 days)
   • General Health - respondents declared their health as ’Excellent’, ’Very good’, ’Good’ ,’Fair’ or ’Poor’

Below is a description of the features collected for each patient: