Back

Statistical challenges of investigating a disease with a complex diagnosis

Malato, J. T.; Graca, L.; Nacul, L. T.; Lacerda, E. M.; Sepulveda, N.

2021-03-20 epidemiology
10.1101/2021.03.19.21253905 medRxiv
Show abstract

Given the absence of a disease-specific biomarker, there are more than 20 symptoms-based case definitions of myalgic encephalomyelitis/chronic fatigue syndrome. As a consequence, the diagnosis for a given patient could vary from one case definition to another. In this context, we analyse data from a biobank dedicated to this disease in order to study the agreement between different case definitions, the similarity between symptoms profile among all participants including healthy controls and patients with multiple sclerosis. We also investigate the impact of patients misclassification on a hypothetical association analysis using data simulation.

Matching journals

The top 14 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.