A Random Forest a Day Keeps the Doctor Away

Using a unique dataset from a German health check-up provider including detailed individual questionnaire data as well as medical test data, I apply a random forest to predict several health risk factors. I evaluate the prediction performance using various metrics and find decent prediction qualities across all outcomes. By identifying the most relevant predictor variables, I compile concise and validated questionnaire tools to identify individuals’ blood pressure, blood glucose, and cholesterol levels, their risk of a coronary heart disease, whether or not they suffer from plaque or a metabolic syndrome as well as their relative fitness levels. In a second step, I compare the prediction results to physician predictions of the same patient observations. I find that the random forest outperforms the physicians if predictions are based on the same information set. When additionally providing the physicians with the random forest predictions for a particular patient observation, the physicians align with the random forest predictions. Finally, while the random forest considers various psychological scales, the physicians focus on family health history information instead.