Incidence and mortality rates due to COVID-19 have varied widely in different parts of the world and placed a huge strain on hospital resources. Understanding the underlying reasons behind such variation is crucial to developing population-specific or even individual-specific management strategies. This paper presents a comprehensive analysis of incidence and mortality rates from data collected over a cumulative period of approximately 6.5 months from February to August 2020 across 411 districts of India, totalling over 2 million individuals. We identify the health factors which have both positive as well as negative correlates with high mortality rates, using data obtained from district-wise aggregated COVID-19 incidence and mortality rates and health data obtained from National Family Health Survey (NFHS).
To obtain robust indicators, we apply both machine learning techniques as well as classical statistical methods and show that the same factors are identified by both methods. We also identify positive and negative correlates at multiple population scales by dividing the cohort into sub-cohorts formed from two Indian states which were further segregated by gender.
We show that there is a disparity of risk factors among males and females. While obesity is the highest risk factor for men, anaemia is the highest risk factor for women.
Hence, to better manage the health of a specific group of people, it is important to consider gender-wise heterogeneity in health risk factors which could contribute to differing vulnerabilities