MYEPI: RETHINKING AN INDIVIDUAL AS A POPULATION

Saturday, January 9, 2016
Foyer, G/F (Jockey Club School of Public Health and Primary Care Building at Prince of Wales Hospital)

Georgiy Bobashev, Ph.D., RTI International, Center fot Data Science, Durham, NC
Purpose: I introduce a concept of individual epidemiology and illustrate how epidemiological methods could be used to analyze and predict intensive data within an individual.

Method(s): The concept of myEpi has been recently introduced to address the analysis of emerging individual-level data obtained from biological sensors, electronic medical records, web-based and mobile-based applications. Examples include monitoring of drug use (e.g. smoking and drinking alcohol) as well as non-risky behaviors such as sleep, exercise, and food consumption. Traditional epidemiology requires that the results should be applicable to some pre-defined population. It often becomes challenging and even unnecessary to define such a population if the focus is on helping a specific individual. The concept of myEpi considers a single individual as an entire population of events that describe behavior and health-related outcomes. I will show how traditional epidemiological methods, that are usually applied to populations of humans, could be applicable to a single individual and thus used for self-monitoring and forecasting of epidemic outbreaks within an individual. I will illustrate similarity between the features of traditional epidemiology (e.g. infectious diseases) and studies of within-person population of risky behavior events. We applied methods developed in epidemiology of infectious diseases to individual data.

Result(s): Using predictive method adapted from epidemiology we have identified patterns of alcohol use, predicted “epidemics” of drinking and weight changes. The results of the analysis are applicable to a single individual and I will present such individual-level results that include shifts in drinking patterns, estimates of next week drinking, time to HIV, time to stroke, and decisions for better exercise.

Conclusion(s): The concept of myEpi allows one to forecast patient’s outcomes from individual data and resolve the conflict between Evidence-based practice and Ecological fallacy. myEpi provides options for an individual to systematically address one’s diary and sensor data, and this approach can be extended to the analysis of individual electronic medical records. myEpi provides background to within-individual interventions such as n-of-one trials.