The New York Times is releasing a series of data files with cumulative counts of coronavirus cases in the United States, at the state and county level, over time. We are compiling this time series data from state and local governments and health departments in an attempt to provide a complete record of the ongoing outbreak.

Since late January, The Times has tracked cases of coronavirus in real time as they were identified after testing. Because of the widespread shortage of testing, however, the data is necessarily limited in the picture it presents of the outbreak.

We have used this data to power our maps and reporting tracking the outbreak, and it is now being made available to the public in response to requests from researchers, scientists and government officials who would like access to the data to better understand the outbreak.

The data begins with the first reported coronavirus case in Washington State on Jan. 21, 2020. We will publish regular updates to the data in this repository.

Context

Data is obtained from COVID-19 Tracking project and NYTimes. Sincere thanks to them for making it available to the public.

Coronaviruses are a large family of viruses which may cause illness in animals or humans. In humans, several coronaviruses are known to cause respiratory infections ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). The most recently discovered coronavirus causes coronavirus disease COVID-19 - World Health Organization

The number of new cases are increasing day by day around the world. This dataset has information from 50 US states and the District of Columbia at daily level.

LICENSE:

Please refer here Apache License 2.0 A permissive license whose main conditions require preservation of copyright and license notices. Contributors provide an express grant of patent rights. Licensed works, modifications, and larger works may be distributed under different terms and without source code.

For counties dataset, please refer here

Content

us_states_covid19_daily.csv

This dataset has number of tests conducted in each state at daily level. Column descriptions are

date - date of observation state - US state 2 digit code positive - number of tests with positive results negative - number of tests with negative results pending - number of test with pending results death - number of deaths total - total number of tests

Acknowledgements

Sincere thanks to COVID-19 Tracking project from which the data is obtained.

Sincere thanks to NYTimes for the counties dataset

There is a nice tableau public dashboard on the data. Images for this dataset is obtained from the same. Thank you.

Inspiration

Some of the questions that could be answered are 1. How is the spread over time to various states 2. Change in number of people tested over time

Analysis of ‘COVID-19 in Italy’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/sudalairajkumar/covid19-in-italy on 28 January 2022.

--- Dataset description provided by original source is as follows ---

Context

Coronaviruses are a large family of viruses which may cause illness in animals or humans. In humans, several coronaviruses are known to cause respiratory infections ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). The most recently discovered coronavirus causes coronavirus disease COVID-19 - WHO

People can catch COVID-19 from others who have the virus. This has been spreading rapidly around the world and Italy is one of the most affected country.

On March 8, 2020 - Italy’s prime minister announced a sweeping coronavirus quarantine early Sunday, restricting the movements of about a quarter of the country’s population in a bid to limit contagions at the epicenter of Europe’s outbreak. - TIME

Content

This dataset is from https://github.com/pcm-dpc/COVID-19 collected by Sito del Dipartimento della Protezione Civile - Emergenza Coronavirus: la risposta nazionale

This dataset has two files

• covid19_italy_province.csv - Province level data of COVID-19 cases
• covid_italy_region.csv - Region level data of COVID-19 cases

Acknowledgements

Data is collected by Sito del Dipartimento della Protezione Civile - Emergenza Coronavirus: la risposta nazionale and is uploaded into this github repo.

Dashboard on the data can be seen here. Picture courtesy is from the dashboard.

Inspiration

Insights on * Spread to various regions over time * Try to predict the spread of COVID-19 ahead of time to take preventive measures

--- Original source retains full ownership of the source dataset ---

Context

  Coronaviruses are a large family of viruses which may cause illness in animals or humans. In humans, several coronaviruses are known to cause respiratory infections ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). The most recently discovered coronavirus causes coronavirus disease COVID-19 - World Health Organization
  This visualization addresses the question of how the hospital resources needed for COVID-19 patients have varied across the 5 different US States (New York, California, Louisiana, Washington & Alabama) during the Coronavirus pandemic. 
 The hospital resource taken into consideration are:

a)The total no of beds b)The total no of ICU beds c)The total no of Invasive ventilators.

Content

 Data for this analysis is obtained from Institute for Health Metrics and Evaluation. Sincere thanks to them for making it available to the public. A time period of 6 months ranging from February to August was analysed and plotted to help the reader identify when the hospital resource needed for COVID-19 patients will attain its peak!

Acknowledgements

 Sincere thanks to Institute for Health Metrics and Evaluation (https://covid19.healthdata.org/united-states-of-america) from whom the data is acquired.

Inspiration

Coronavirus disease 2019 (COVID-19) has developed into a global pandemic, affecting every nation and territory in the world. Machine learning-based approaches are useful when trying to understand the complexity behind the spread of the disease and how to contain its spread effectively. The unsupervised learning method could be useful to evaluate the shortcomings of health facilities in areas of increased infection as well as what strategies are necessary to prevent disease spread within or outside of the country. To contribute toward the well-being of society, this paper focusses on the implementation of machine learning techniques for identifying common prevailing public health care facilities and concerns related to COVID-19 as well as attitudes to infection prevention strategies held by people from different countries concerning the current pandemic situation. Regression tree, random forest, cluster analysis and principal component machine learning techniques are used to analyze the global COVID-19 data of 133 countries obtained from the Worldometer website as of April 17, 2020. The analysis revealed that there are four major clusters among the countries. Eight countries having the highest cumulative infected cases and deaths, forming the first cluster. Seven countries, United States, Spain, Italy, France, Germany, United Kingdom, and Iran, play a vital role in explaining the 60% variation of the total variations by us of the first component characterized by all variables except for the rate variables. The remaining countries explain only 20% of the variation of the total variation by use of the second component characterized by only rate variables. Most strikingly, the analysis found that the variable number of tests by the country did not play a vital role in the prediction of the cumulative number of confirmed cases.

This dataset is created for a task of UNCOVER COVID-19 Challenge, Mental health impact and support services.

The search interest of mental health related terms on Google before and after the outbreak of COVID-19 pandemic reveals how public's concern is affected by the pandemic, and its impact to mental health of people around the world. I picked worldwide, Canada, US, Italy, Iran, Japan, South Korea and UK as the population. The dataset also includes data of Canada for the past 4 years, from 2016 to 2019.

The mental health related search terms are "mental health", "depression", "anxiety", "ocd", "obsessive compulsive disorder", "insomnia", "panic attack", "counseling", "psychiatrist".

Search interest is indicated by a number between 0 and 100, where 100 means the most popular point of time(by week), 1 means the least, and 0 no enough data.

All data is collected from Google Trends. I assumed, when searching the terms, users from countries other than English-speaking performed the search in their own language, and they typed the word correctly.

Since the identification of SARS-CoV-2, a large number of genomes have been sequenced with unprecedented speed around the world. This marks a unique opportunity to analyze virus spreading and evolution in a worldwide context. Currently, there is not a useful haplotype description to help to track important and globally scattered mutations. Also, differences in the number of sequenced genomes between countries and/or months make it difficult to identify the emergence of haplotypes in regions where few genomes are sequenced but a large number of cases are reported. We propose an approach based on the normalization by COVID-19 cases of relative frequencies of mutations using all the available data to identify major haplotypes. Furthermore, we can use a similar normalization approach to tracking the temporal and geographic distribution of haplotypes in the world. Using 171,461 genomes, we identify five major haplotypes or operational taxonomic units (OTUs) based on nine high-frequency mutations. OTU_3 characterized by mutations R203K and G204R is currently the most frequent haplotype circulating in four of the six continents analyzed (South America, North America, Europe, Asia, Africa, and Oceania). On the other hand, during almost all months analyzed, OTU_5 characterized by the mutation T85I in nsp2 is the most frequent in North America. Recently (since September), OTU_2 has been established as the most frequent in Europe. OTU_1, the ancestor haplotype, is near to extinction showed by its low number of isolations since May. Also, we analyzed whether age, gender, or patient status is more related to a specific OTU. We did not find OTU’s preference for any age group, gender, or patient status. Finally, we discuss structural and functional hypotheses in the most frequently identified mutations, none of those mutations show a clear effect on the transmissibility or pathogenicity.

OverviewCough audio signal classification has been successfully used to diagnose a variety of respiratory conditions, and there has been significant interest in leveraging Machine Learning (ML) to provide widespread COVID-19 screening. The COUGHVID dataset provides over 20,000 crowdsourced cough recordings representing a wide range of subject ages, genders, geographic locations, and COVID-19 statuses. Furthermore, experienced pulmonologists labeled more than 2,000 recordings to diagnose medical abnormalities present in the coughs, thereby contributing one of the largest expert-labeled cough datasets in existence that can be used for a plethora of cough audio classification tasks. As a result, the COUGHVID dataset contributes a wealth of cough recordings for training ML models to address the world’s most urgent health crises.Private Set and Testing ProtocolResearchers interested in testing their models on the private test dataset should contact us at coughvid@epfl.ch, briefly explaining the type of validation they want to make, and their obtained results obtained through cross-validation with the public data. Then, access to the unlabeled recordings will be provided, and the researchers should send the predictions of their models on these recordings. Finally, the performance metrics of the predictions will be sent to the researchers.

Context

Coronaviruses are a large family of viruses which may cause illness in animals or humans. In humans, several coronaviruses are known to cause respiratory infections ranging from the common cold to more severe diseases such as MERS and SARS. The most recently discovered coronavirus causes COVID-19 - World Health Organization (WHO).

The number of new cases is increasing day by day around the world. This dataset has information for states of India at a daily level.

Content

COVID-19 cases at a daily level is present in COVID_19_INDIA.csv file

Acknowledgements

Thanks to the Indian Ministry of Health & Family Welfare for making the data available to the general public.

Thanks to covid19india.org for making the individual level details and testing details available to the general public.

Analysis of ‘Saudi Arabia Booking.com’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/moayadmagadmi/saudi-arabia-bookingcom on 14 February 2022.

--- Dataset description provided by original source is as follows ---

Context

In this dataset, I implemented web-scrapping (selenium technique) to create a dataset from Booking.com. it is about data of 1025 hotels in Saudi Arabian in specific date 24Apr 2020. As you know travel plans and hotels price may be affected by Coronavirus (COVID-19). for that, I just choose a randomly day just to collect data without considering room price.

Content

This dataset contains the most hotels in the KSA collected from the most common booking website in the world Booking.com. you will get an overview of each hotel, resort, or accommodation by the 21 features that provided in the dataset explained bellow.

Result

By analysising the dataset, we will know the best and the worst cities in Saudi Arabia in hotels services. will know the most common hotels and its reviews as well. That will help when you decide for traveling plan, or to help to enhance the hotels services in the worst cities.

--- Original source retains full ownership of the source dataset ---

The COVID-19 pandemic has brought about massive declines in well-being around the world. This paper seeks to quantify and compare two important components of those losses—increased mortality and higher poverty—using years of human life as a common metric. The paper estimates that almost 20 million life-years were lost to COVID-19 by December 2020. Over the same period and by the most conservative definition, more than 120 million additional years were spent in poverty because of the pandemic. The mortality burden, whether estimated in lives or years of life lost, increases sharply with gross domestic product per capita. By contrast, the poverty burden declines with per capita national income when a constant absolute poverty line is used, or is uncorrelated with national income when a more relative approach is taken to poverty lines. In both cases, the poverty burden of the pandemic, relative to the mortality burden, is much higher for poor countries. The distribution of aggregate welfare losses—combining mortality and poverty and expressed in terms of life-years —depends on the choice of poverty line(s) and the relative weights placed on mortality and poverty. With a constant absolute poverty line and a relatively low welfare weight on mortality, poorer countries are found to bear a greater welfare loss from the pandemic. When poverty lines are set differently for poor, middle-income, and high-income countries and/or a greater welfare weight is placed on mortality, upper-middle-income and rich countries suffer the most.

Several urban landscape planning solutions have been introduced around the world to find a balance between developing urban spaces, maintaining and restoring biodiversity, and enhancing quality of human life. Our global mini-review, combined with analysis of big data collected from Google Trends at global scale, reveals the importance of enjoying day-to-day contact with nature and engaging in such activities as nature observation and identification and gardening for the mental well-being of humans during the COVID-19 pandemic. Home-based activities, such as watching birds from one’s window, identifying species of plants and animals, backyard gardening, and collecting information about nature for citizen science projects, were popular during the first lockdown in spring 2020, when people could not easily venture out of their homes. In our mini-review, we found 37 articles from 28 countries with a total sample of 114,466 people. These papers suggest that home-based engagement with nature was an entertaining and pleasant distraction that helped preserve mental well-being during a challenging time. According to Google Trends, interest in such activities increased during lockdown compared to the previous five years. Millions of people worldwide are chronically or temporarily confined to their homes and neighborhoods because of illness, childcare chores, or elderly care responsibility, which makes it difficult for them to travel far to visit such places as national parks, created through land sparing, where people go to enjoy nature and relieve stress. This article posits that for such people, living in an urban landscape designed to facilitate effortless contact with small natural areas is a more effective way to receive the mental health benefits of contact with nature than visiting a sprawling nature park on rare occasions. Methods 1. Identifying the most common types of activities related to nature observation, gardening, and taxa identification during the first lockdown based on scientific articles and non-scientific press For scientific articles, in March 2023 we searched Scopus and Google Scholar. For countries where Google is restricted, such as China, similar results will be available from other scientific browsers, with the highest number of results from our database being available from Scopus. We used the Google Search browser to search for globally published non-scientific press articles. Some selection criteria were applied during article review. Specifically, we excluded articles that were not about the first lockdown; did not study activities at a local scale (from balcony, window, backyard) but rather in areas far away from home (e.g., visiting forests); studied the mental health effect of observing indoor potted plants and pet animals; or transiently mentioned the topic or keyword without going into any scientific detail. We included all papers that met our criteria, that is, studies that analyzed our chosen topic with experiments or planned observations. We included all research papers, but not letters that made claims without any data. Google Scholar automatically screened the title, abstract, keywords, and the whole text of each article for the keywords we entered. All articles that met our criteria were read and double-checked for keywords and content related to the keywords (e.g., synonyms or if they presented content about the relevant topic without using the specific keywords). We identified, from both types of articles, the major nature-based activities that people engaged in during the first lockdown in the spring of 2020. Keywords used in this study were grouped into six main topics: (1) COVID-19 pandemic; (2) nature-oriented activity focused on nature observation, identification of different taxa, or gardening; (3) mental well-being; (4) activities performed from a balcony, window, or in gardens; (5) entertainment; and (6) citizen science (see Table 1 for all keywords). 2. Increase in global trends in interest in nature observation, gardening, and taxa identification during the first lockdown We used the categorical cluster method, which was combined with big data from Google Trends (downloaded on 1 September 2020) and anomaly detection to identify trend anomalies globally in peoples’ interests. We used this combination of methods to examine whether interest in nature-based activities that were mentioned in scientific and nonscientific press articles increased during the first lockdown. Keywords linked with the main types of nature-oriented activities, as identified from press and scientific articles, and used according to the categorical clustering method were classified into the following six main categories: (1) global interest in bird-watching and bird identification combined with citizen science; (2) global interest in plant identification and gardening combined with citizen science; (3) global interest in butterfly watching, (4) local interest in early-spring (lockdown time), summer, or autumn flowering species that usually can be found in Central European (country: Poland) backyards; (5) global interest in traveling and social activities; and (6) global interest in nature areas and activities typically enjoyed during holidays and thus requiring traveling to land-spared nature reserves. The six categories were divided into 15 subcategories so that we could attach relevant words or phrases belonging to the same cluster and typically related to the activity (according to Google Trends and Google browser’s automatic suggestions; e.g., people who searched for “bird-watching” typically also searched for “binoculars,” “bird feeder,” “bird nest,” and “birdhouse”). The subcategories and keywords used for data collection about trends in society’s interest in the studied topic from Google Trends are as follows.

Bird-watching: “binoculars,” “bird feeder,” “bird nest,” “birdhouse,” “bird-watching”; Bird identification: “bird app,” “bird identification,” “bird identification app,” “bird identifier,” “bird song app”; Bird-watching combined with citizen science: “bird guide,” “bird identification,” “eBird,” “feeding birds,” “iNaturalist”; Citizen science and bird-watching apps: “BirdNET,” “BirdSong ID,” “eBird,” “iNaturalist,” “Merlin Bird ID”; Gardening: “gardening,” “planting,” “seedling,” “seeds,” “soil”; Shopping for gardening: “garden shop,” “plant buy,” “plant ebay,” “plant sell,” “plant shop”; Plant identification apps: “FlowerChecker,” “LeafSnap,” “NatureGate,” “Plantifier,” “PlantSnap”; Citizen science and plant identification: “iNaturalist,” “plant app,” “plant check,” “plant identification app,” “plant identifier”; Flowers that were flowering in gardens during lockdown in Poland: “fiołek” (viola), “koniczyna” (shamrock), “mlecz” (dandelion), “pierwiosnek” (primose), “stokrotka” (daisy). They are typical early-spring flowers growing in the gardens in Central Europe. We had to be more specific in this search because there are no plant species blooming across the world at the same time. These plant species have well-known biology; thus, we could easily interpret these results; Flowers that were not flowering during lockdown in Poland: “chaber” (cornflower), “mak” (poppy), “nawłoć” (goldenrod), “róża” (rose), “rumianek” (chamomile). They are typical mid-summer flowering plants often planted in gardens; Interest in traveling long distances and in social activities that involve many people: “airport,” “bus,” “café,” “driving,” “pub”; Single or mass commuting, and traveling: “bike,” “boat,” “car,” “flight,” “train”; Interest in distant places and activities for visiting natural areas: “forest,” “nature park,” “safari,” “trekking,” “trip”; Places and activities for holidays (typically located far away): “coral reef,” “rainforest,” “safari,” “savanna,” “snorkeling”; Butterfly watching: “butterfly watching,” “butterfly identification,” “butterfly app,” “butterfly net,” “butterfly guide”;

In Google Trends, we set the following filters: global search, dates: July 2016–July 2020; language: English.

Context

Coronaviruses are a large family of viruses which may cause illness in animals or humans. In humans, several coronaviruses are known to cause respiratory infections ranging from the common cold to more severe diseases such as Middle East Respiratory Syndrome (MERS) and Severe Acute Respiratory Syndrome (SARS). The most recently discovered coronavirus causes coronavirus disease COVID-19 - World Health Organization

The number of new cases are increasing day by day around the world. This dataset has information from the states and union territories of India at daily level.

Data comes from Ministry of Health & Family Welfare

Content

COVID-19 cases at daily level is present in covid_19_india.csv file

Population at state level is present in population_india_census2011.csv file

Acknowledgements

Thanks to Indian Ministry of Health & Family Welfare for making the data available to general public.

Thanks to Wikipedia for population information.

Photo Courtesy - https://hgis.uw.edu/virus/

Inspiration

Looking for data based suggestions to stop / delay the spread of virus

The association between the most common post COVID-19 symptoms and losing a friend or a relative in the pandemic.

BackgroundMandatory COVID-19 certification, showing proof of vaccination, negative test, or recent infection to access to public venues, was introduced at different times in the four countries of the UK. We aim to study its effects on the incidence of cases and hospital admissions.MethodsWe performed Negative binomial segmented regression and ARIMA analyses for four countries (England, Northern Ireland, Scotland and Wales), and fitted Difference-in-Differences models to compare the latter three to England, as a negative control group, since it was the last country where COVID-19 certification was introduced. The main outcome was the weekly averaged incidence of COVID-19 cases and hospital admissions.ResultsCOVID-19 certification led to a decrease in the incidence of cases and hospital admissions in Northern Ireland, as well as in Wales during the second half of November. The same was seen for hospital admissions in Wales and Scotland during October. In Wales the incidence rate of cases in October already had a decreasing tendency, as well as in England, hence a particular impact of COVID-19 certification was less obvious. Method assumptions for the Difference-in-Differences analysis did not hold for Scotland. Additional NBSR and ARIMA models suggest similar results, while also accounting for correlation in the latter. The assessment of the effect in England itself leads one to believe that this intervention might not be strong enough for the Omicron variant, which was prevalent at the time of introduction of COVID-19 certification in the country.ConclusionsMandatory COVID-19 certification reduced COVID-19 transmission and hospitalizations when Delta predominated in the UK, but lost efficacy when Omicron became the most common variant.

BackgroundSARS-CoV-2 causes coronavirus disease 2019 (COVID-19), a new coronavirus pneumonia, and containing such an international pandemic catastrophe remains exceedingly difficult. Asthma is a severe chronic inflammatory airway disease that is becoming more common around the world. However, the link between asthma and COVID-19 remains unknown. Through bioinformatics analysis, this study attempted to understand the molecular pathways and discover potential medicines for treating COVID-19 and asthma.MethodsTo investigate the relationship between SARS-CoV-2 and asthma patients, a transcriptome analysis was used to discover shared pathways and molecular signatures in asthma and COVID-19. Here, two RNA-seq data (GSE147507 and GSE74986) from the Gene Expression Omnibus were used to detect differentially expressed genes (DEGs) in asthma and COVID-19 patients to find the shared pathways and the potential drug candidates.ResultsThere were 66 DEGs in all that were classified as common DEGs. Using a protein-protein interaction (PPI) network created using various bioinformatics techniques, five hub genes were found. We found that asthma has some shared links with the progression of COVID-19. Additionally, protein-drug interactions with common DEGs were also identified in the datasets.ConclusionWe investigated possible links between COVID-19 and asthma using bioinformatics databases, which might be useful in treating COVID-19 patients. More studies on populations affected by these diseases are needed to elucidate the molecular mechanism behind their association.

Abstract: Coronavirus disease 2019 (COVID-19) has spread exponentially across the world. The typical manifestations of COVID-19 include fever, dry cough, headache and fatigue. However, atypical presentations of COVID-19 are being increasingly reported. Recently, a number of studies have recognized various mucocutaneous manifestations associated with COVID-19. This study sought to summarize the available literature and provide an overview of the potential orofacial manifestations of COVID-19. An online literature search in the PubMed and Scopus databases was conducted to retrieve the relevant studies published up to July 2020. Original studies published in English that reported orofacial manifestations in patients with laboratory-confirmed COVID-19 were included; this yielded 16 articles involving 25 COVID-19-positive patients. The results showed a marked heterogeneity in COVID-19-associated orofacial manifestations. The most common orofacial manifestations were ulcerative lesions, vesiculobullous/macular lesions, and acute sialadentitis of the parotid gland (parotitis). In four cases, oral manifestations were the first signs of COVID-19. In summary, COVID-19 may cause orofacial manifestations that might be the initial features in several cases. However, the occurrence of orofacial manifestations in COVID-19 seems to be underreported, mainly due to the lack of oral examination of patients with suspected and/or confirmed COVID-19. Oral examination of all suspected and confirmed COVID-19 cases is crucial for better understanding and documenting COVID-19-associated orofacial manifestations.

Given that vaccine-induced adverse effects were mostly based on previous laboratory research and clinical trials, real-world data on the safety of coronavirus disease 2019 (COVID-19) vaccination were lacking. This study reported the adverse events (AEs) among inactivated COVID-19 vaccine recipients. Data were collected from a total of 2,808 hospital employees and their family members in Wuhan, China, with all of them receiving the first dose of inactivated COVID-19 vaccines from two pharmaceutical companies. The first dose was given between 29th April and 13th May 2021. A total of 2,732 vaccinees received the second dose between 27th May and 8th July 2021. The whole process of receiving the vaccine was monitored by clinical pharmacists, and the information on AEs including demographics, occurrence, types, and severity was recorded through an online questionnaire and telephone follow-up. Most of the common AEs were mild and tolerable, and the overall incidence of AEs was lower than the data from the safety profile in clinical trials. Moreover, the incidence of AEs in the first dose (21.30%, 598) was higher than that in the second dose (16.07%, 439). Furthermore, the first injection had more severe AEs (4, 0.14%) than the second injection (2, 0.07%). The AEs involved the skin, muscle, respiratory tract, gastrointestinal tract, cardiovascular system, and other tissues and systems. The most common AE was pain at the injection site (first dose: 10.19%, second dose: 12.55%). All the vaccinees with AEs for both doses recovered fully in the end. It was noted that some AEs might cause blood coagulation disorder and bleeding risk. Therefore, ongoing monitoring of AEs after COVID-19 vaccination is essential in evaluating the benefits and risks of each vaccine.

The Covid-19 pandemic has led to an increase in the awareness of and demand for telemedicine services, resulting in a need for automating the process and relying on machine learning (ML) to reduce the operational load. This research proposes a specialty detection classifier based on a machine learning model to automate the process of detecting the correct specialty for each question and routing it to the correct doctor. The study focuses on handling multiclass and highly imbalanced datasets for Arabic medical questions, comparing some oversampling techniques, developing a Deep Neural Network (DNN) model for specialty detection, and exploring the hidden business areas that rely on specialty detection such as customizing and personalizing the consultation flow for different specialties. The proposed module is deployed in both synchronous and asynchronous medical consultations to provide more real-time classification, minimize the doctor effort in addressing the correct specialty, and give the system more flexibility in customizing the medical consultation flow. The evaluation and assessment are based on accuracy, precision, recall, and F1-score. The experimental results suggest that combining multiple techniques, such as SMOTE and reweighing with keyword identification, is necessary to achieve improved performance in detecting rare classes in imbalanced multiclass datasets. By using these techniques, specialty detection models can more accurately detect rare classes in real-world scenarios where imbalanced data is common.

Aim: Patients with malignancies, experience high rates of psychological distress. Fear of Corona-infection combined with the interruptions in some treatment programs might affect the psychological health of cancer patients. This review study was conducted to investigate the psychological distress among cancer patients during COVID-19 pandemic to offer system-adapted individual solutions.Materials and methods: To identify the psychological distress of cancer patients, a comprehensive search was carried out in PubMed, Web of Science, and Scopus. English language and original articles were included in this study. Articles that addressed any psychological distress among cancer patients during COVID-19 pandemic were included.Results: At first 1,410 articles, were included in the study. After removing duplicate articles and reviewing the title and abstract, 55 articles were selected for the review. The findings of this study revealed COVID-19 greatly affects psychological health of cancer patients. Fear of COVID-19, fear of disease progression, disruption of oncology services, cancer stage, and immunocompromised status were the most common causes of psychological distress in oncology patients which can influence patients' decisions about treatment.Conclusion: The COVID-19 related anxiety is an expected reaction to the current situation. Although psychological distress affects many people, it can confuse cancer patients to the point that they refuse to continue treatment for the fear of infection and worsening of their condition. Since the end of this pandemic is unknown, this action can endanger the health and prognosis of this group of patients, so it seems that using psychological interventions and intensive counseling in the current situation is one of the main priorities for cancer patients.