Context

Coronavirus disease (COVID-19) is an infectious disease caused by a newly discovered coronavirus. Most people infected with COVID-19 virus will experience mild to moderate respiratory illness and recover without requiring special treatment. Older people, and those with underlying medical problems like cardiovascular disease, diabetes, chronic respiratory disease, and cancer are more likely to develop serious illness. During the entire course of the pandemic, one of the main problems that healthcare providers have faced is the shortage of medical resources and a proper plan to efficiently distribute them. In these tough times, being able to predict what kind of resource an individual might require at the time of being tested positive or even before that will be of immense help to the authorities as they would be able to procure and arrange for the resources necessary to save the life of that patient.

The main goal of this project is to build a machine learning model that, given a Covid-19 patient's current symptom, status, and medical history, will predict whether the patient is in high risk or not.

content

The dataset was provided by the Mexican government (link). This dataset contains an enormous number of anonymized patient-related information including pre-conditions. The raw dataset consists of 21 unique features and 1,048,576 unique patients. In the Boolean features, 1 means "yes" and 2 means "no". values as 97 and 99 are missing data.

• sex: 1 for female and 2 for male.
• age: of the patient.
• classification: covid test findings. Values 1-3 mean that the patient was diagnosed with covid in different degrees. 4 or higher means that the patient is not a carrier of covid or that the test is inconclusive.
• patient type: type of care the patient received in the unit. 1 for returned home and 2 for hospitalization.
• pneumonia: whether the patient already have air sacs inflammation or not.
• pregnancy: whether the patient is pregnant or not.
• diabetes: whether the patient has diabetes or not.
• copd: Indicates whether the patient has Chronic obstructive pulmonary disease or not.
• asthma: whether the patient has asthma or not.
• inmsupr: whether the patient is immunosuppressed or not.
• hypertension: whether the patient has hypertension or not.
• cardiovascular: whether the patient has heart or blood vessels related disease.
• renal chronic: whether the patient has chronic renal disease or not.
• other disease: whether the patient has other disease or not.
• obesity: whether the patient is obese or not.
• tobacco: whether the patient is a tobacco user.
• usmr: Indicates whether the patient treated medical units of the first, second or third level.
• medical unit: type of institution of the National Health System that provided the care.
• intubed: whether the patient was connected to the ventilator.
• icu: Indicates whether the patient had been admitted to an Intensive Care Unit.
• date died: If the patient died indicate the date of death, and 9999-99-99 otherwise.

IntroductionDiabetes is one of the comorbidities associated with poor prognosis in hospitalized COVID-19 patients. In this nationwide retrospective study, we evaluated the risk of in-hospital death attributed to diabetes.MethodsWe analyzed data from discharge reports of patients hospitalized with COVID-19 in 2020 as submitted to the Polish National Health Fund. Several multivariate logistic regression models were used. In each model, in-hospital death was estimated with explanatory variables. Models were built either on the whole cohorts or cohorts matched with propensity score matching (PSM). The models examined either the main effects of diabetes itself or the interaction of diabetes with other variables.ResultsWe included 174,621 patients with COVID-19 who were hospitalized in the year 2020. Among them, there were 40,168 diabetic patients (DPs), and the proportion of DPs in this group was higher than in the general population (23.0% vs. 9.5%, p

The objective of this study was to compare the effect of diabetes and pathologies potentially related to diabetes on the risk of infection and death from COVID-19 among people from Highly-Developed-Country (HDC), including Italians, and immigrants from the High-Migratory-Pressure-Countries (HMPC). Among the population with diabetes, whose prevalence is known to be higher among immigrants, we compared the effect of body mass index among HDC and HMPC populations. A population-based cohort study was conducted, using population registries and routinely collected surveillance data. The population was stratified into HDC and HMPC, according to the place of birth; moreover, a focus was set on the South Asiatic population. Analyses restricted to the population with type-2 diabetes were performed. We reported incidence (IRR) and mortality rate ratios (MRR) and hazard ratios (HR) with 95% confidence interval (CI) to estimate the effect of diabetes on SARS-CoV-2 infection and COVID-19 mortality. Overall, IRR of infection and MRR from COVID-19 comparing HMPC with HDC group were 0.84 (95% CI 0.82–0.87) and 0.67 (95% CI 0.46–0.99), respectively. The effect of diabetes on the risk of infection and death from COVID-19 was slightly higher in the HMPC population than in the HDC population (HRs for infection: 1.37 95% CI 1.22–1.53 vs. 1.20 95% CI 1.14–1.25; HRs for mortality: 3.96 95% CI 1.82–8.60 vs. 1.71 95% CI 1.50–1.95, respectively). No substantial difference in the strength of the association was observed between obesity or other comorbidities and SARS-CoV-2 infection. Similarly for COVID-19 mortality, HRs for obesity (HRs: 18.92 95% CI 4.48–79.87 vs. 3.91 95% CI 2.69–5.69) were larger in HMPC than in the HDC population, but differences could be due to chance. Among the population with diabetes, the HMPC group showed similar incidence (IRR: 0.99 95% CI: 0.88–1.12) and mortality (MRR: 0.89 95% CI: 0.49–1.61) to that of HDC individuals. The effect of obesity on incidence was similar in both HDC and HMPC populations (HRs: 1.73 95% CI 1.41–2.11 among HDC vs. 1.41 95% CI 0.63–3.17 among HMPC), although the estimates were very imprecise. Despite a higher prevalence of diabetes and a stronger effect of diabetes on COVID-19 mortality in HMPC than in the HDC population, our cohort did not show an overall excess risk of COVID-19 mortality in immigrants.

Rank, number of deaths, percentage of deaths, and age-specific mortality rates for the leading causes of death, by age group and sex, 2000 to most recent year.

Background: Diabetes correlates with poor prognosis in patients with COVID-19, but very few studies have evaluated whether impaired fasting glucose (IFG) is also a risk factor for the poor outcomes of patients with COVID-19. Here we aimed to examine the associations between IFG and diabetes at admission with risks of complications and mortality among patients with COVID-19.Methods: In this multicenter retrospective cohort study, we enrolled 312 hospitalized patients with COVID-19 from 5 hospitals in Wuhan from Jan 1 to Mar 17, 2020. Clinical information, laboratory findings, complications, treatment regimens, and mortality status were collected. The associations between hyperglycemia and diabetes status at admission with primary composite end-point events (including mechanical ventilation, admission to intensive care unit, or death) were analyzed by Cox proportional hazards regression models.Results: The median age of the patients was 57 years (interquartile range 38–66), and 172 (55%) were women. At the time of hospital admission, 84 (27%) had diabetes (and 36 were new-diagnosed), 62 (20%) had IFG, and 166 (53%) had normal fasting glucose (NFG) levels. Compared to patients with NFG, patients with IFG and diabetes developed more primary composite end-point events (9 [5%], 11 [18%], 26 [31%]), including receiving mechanical ventilation (5 [3%], 6 [10%], 21 [25%]), and death (4 [2%], 9 [15%], 20 [24%]). Multivariable Cox regression analyses showed diabetes was associated increased risks of primary composite end-point events (hazard ratio 3.53; 95% confidence interval 1.48–8.40) and mortality (6.25; 1.91–20.45), and IFG was associated with an increased risk of mortality (4.11; 1.15–14.74), after adjusting for age, sex, hospitals and comorbidities.Conclusion: IFG and diabetes at admission were associated with higher risks of adverse outcomes among patients with COVID-19.

Introduction. The analysis looks at mental and physical health data from 2000-2019 from various sources the main one being the World Health Organization (WHO).

Task: Analyze health data to gain insights into current consumers health patterns globally and in Kenya to be utilized to make data driven decisions.

Stakeholders: -Company founders and C-suite teams. -Human Resource and Mental Health Professionals. -Government policy makers.

Analysis Objectives: -What is the trend in global and local consumer mental and physical health? -How can these trends influence public and corporate strategies?

ROCCC of Data: A good data source is ROCCC which stands for Reliable, Original, Comprehensive, Current, and Cited.

-Reliablity — High — The data comes from global population sample data sources.

-Originality — LOW — Third party provider (WHO).

-Comprehensive — HIGH — There are several variables summarized into between 1,700-10,980 observations for a period of over 15 years which was fairly comprehensive.

-Current — MID — Data is 3 years old and may not be as relevant as there is no covid data updated to it.

-Cited — HIGH — Data collected from a reliable third party that comprehensively reports its data collection process publicly.

Overall, the dataset is good quality data however its recommended that an updated analysis be done on the health trends during and post-covid.

Key Insights

-There is a higher average suicide rate in men than women both globally and also in Kenya.

-Kenya has a higher average suicide rate for both genders compared to the global average as at 2019.

-The average probability of death between the age of 30 to 70 from from any of cardiovascular disease, cancer, diabetes or chronic respiratory disease in Kenya has been decreasing since 2008 however an increase has been observed since 2016.

-There has been a significant increase in the prevalence of alcohol and substance use disorder in Kenya, moreover, the prevalence in the country increases as the prevalence of anxiety disorders, eating disorders and schizophrenia increases according to the Kenyan correlation heat map.

-As evident on the correlation heat map the prevalence various mental health issues have an impact on each other.

-The global probability of dying between age 30 and 70 from any of cardiovascular disease, cancer, diabetes or chronic respiratory disease has been falling significantly since the 2000s, however, its only been steadily decreasing in Kenya. Men are also at a higher risk of death from these diseases compared to women both globally and locally in Kenya.

-The probability of dying between age 30 and 70 from any of cardiovascular disease, cancer, diabetes or chronic respiratory disease in Kenya has been observed to be significantly inversely proportional to the prevalence of alcohol, substance use anxiety and eating disorders.

-Suicide rates have been observed to not have a significant direct relationship with any mental health disorders both globally and locally however the most significant correlation is the probability of dying between age 30 and 70 from any of cardiovascular disease, cancer, diabetes or chronic respiratory disease in the global analysis.

-Globally a significant inverse relationship between road traffic death rate and eating disorders has been observed however there is a slightly significant relationship between depressive disorders and road traffic death which should be an indicator for further research.

-In Kenya, its been observed that road traffic deaths are inversely proportional to the probability of dying between age 30 and 70 from any of cardiovascular disease, cancer, diabetes or chronic respiratory disease but directly proportional to eating, anxiety, alcohol and substance use disorders.

-Depressive disorders is the most significant variable that has an impact on suicide rates in Kenya therefore further study can look into the impact of depression on attempted and reported suicide cases and other factors that may influence suicide as it has been on the rise in Kenya.

-Road traffic accidents have a significant impact of the mental health of several Kenyans.

Recommendations.

-There should be more education regarding suicide prevention for NGOs.

-Corporate firms should look into providing observed health insurance and mental health days off in addition to more sick days for the affected.

-The government can implement policies and programs that provide more efficient facilities for the handling of observed health issues.

-Insurance companies can restructure their products around the knowledge that mental health issues in Kenya have a significant direct relationship to each other and also that the prevalence of alcohol and substance use critically impacts the road traffic death rate in Kenya.

-The government should critically look at the increase in the prevalence of alcohol...

Context

In the shadows of the Covid-19 pandemic, there is another global health crisis that has gone largely unnoticed. This is the Noncommunicable Disease (NCD) pandemic.

The WHO website describes NCDs as follows:

Noncommunicable diseases (NCDs), also known as chronic diseases, tend to be of long duration and are the result of a combination of genetic, physiological, environmental and behaviours factors.

The main types of NCDs are cardiovascular diseases (like heart attacks and stroke), cancers, chronic respiratory diseases (such as chronic obstructive pulmonary disease and asthma) and diabetes.

NCDs disproportionately affect people in low- and middle-income countries where more than three quarters of global NCD deaths – 32million – occur.

Key facts:

• Noncommunicable diseases (NCDs) kill 41 million people each year, equivalent to 71% of all deaths globally.
• Each year, 15 million people die from a NCD between the ages of 30 and 69 years; over 85% of these "premature" deaths occur in low- and middle-income > * countries.
• Cardiovascular diseases account for most NCD deaths, or 17.9 million people annually, followed by cancers (9.0 million), respiratory diseases (3.9million), and diabetes (1.6 million).
• These 4 groups of diseases account for over 80% of all premature NCD deaths.
• Tobacco use, physical inactivity, the harmful use of alcohol and unhealthy diets all increase the risk of dying from a NCD.
• Detection, screening and treatment of NCDs, as well as palliative care, are key components of the response to NCDs.

Content

This data repository consists of 3 CSV files: WHO-cause-of-death-by-NCD.csv is the main dataset, which provides the percentage of deaths caused by NCDs out of all causes of death, for each nation globally. Metadata_Country.csv and Metadata_Indicator.csv provide additional metadata which is helpful for interpreting the main CSV.

The data collected spans a period from 2000 to 2016. The main CSV has columns for every year from 1960 to 2019. It is advisable to drop all redundant columns where no data was collected.

Furthermore, it is advisable to merge Metadata_Country.csv with the main CSV as it provides valuable additional information, particularly on the economic situation of each nation.

Acknowledgements

This dataset has been extracted from The World Bank 'Cause of death, by non-communicable diseases (% of total)' Dataset, derived based on the data from WHO's Global Health Estimates. It is freely provided under a Creative Commons Attribution 4.0 International License (CC BY 4.0), with the additional terms as stated on the World Bank website: World Bank Terms of Use for Datasets.

Inspiration

I would be interested to see some good data wrangling (dropping redundant columns), as well as kernels interpreting additional information in 'SpecialNotes' column in Metadata_country.csv

It would also be great to see what different factors influence NCDs: most of all, the geopolitical factors. Would be great to see some choropleth visualisations to get an idea of which regions are most affected by NCDs.

Frequency distribution of socio-demographic and bio-clinical characteristics of COVID-19 patients admitted in the ICU.

Medication use associated with hazard ratio among COVID-19 patients admitted in ICU.

Reducing mortality among COVID-19 cases is a major challenge for most health systems worldwide. Estimating the risk of preexisting comorbidities on COVID-19 mortality may promote the importance of targeting at-risk populations to improve survival through primary and secondary prevention. This study was conducted to explore the contribution of exposure to some chronic diseases on the mortality of COVID-19. This was a case control study. The data were collected from the records of all patients hospitalised at Bafoussam Regional Hospital (BRH) from March 2020 to December 2021. A grid was used to extract data on patient history, case management and outcome of hospitalised patients. We estimated the frequency of each common chronic disease and assessed the association between suffering from all and each chronic disease (Diabetes or/and Hypertension, immunodeficiency condition, obesity, tuberculosis, chronic kidney disease) and fatal outcome of hospitalised patients by estimating crude and adjusted odd ratios and their corresponding 95% confidence intervals (CI) using time to symptom onset and hospital admission up to three days, age range 65 years and above, health professional worker and married status as confounder’s factors. Of 645 included patients, 120(20.23%) deaths were recorded. Among these 645 patients, 262(40.62%) were males, 128(19.84%) aged 65 years and above. The mean length of stay was 11.07. On admission, 204 (31.62%) patients presented at least one chronic disease. The most common chronic disease were hypertension (HBP) 73(11.32%), followed by diabetes + HBP 62 (9.61%), by diabetes 55(8.53%) and Immunodeficiency condition 14(2.17%). Diabetes and Diabetes + HBP were associated with a higher risk of death respectively aOR = 2.71[95%CI = 1.19–6.18] and aOR = 2.07[95% CI = 1.01–4.23] but HBP did not significantly increased the risk of death. These results suggest that health authorities should prioritize these specific group to adopt primary and secondary preventive interventions against SARS-CoV-2 infection.

Laboratory results at initial measurements associated with mortality among COVID-19 patients admitted to ICU at Tygerberg Hospital.

Socio-demographic and clinical characteristics associated with mortality among COVID-19 patients admitted to ICU.

Cox proportional hazards model identifying factors associated with the risk of hazard ratio among COVID-19 patients admitted to the ICU.

Laboratory parameters associated with hazard ratio among COVID-19 patients admitted to ICU.