PATIENT-LED RESEARCH FOR LYME DISEASE
Focused on People Who Matter the Most — Patients
For more than ten years, LymeDisease.org has been conducting patient-led research using patient-generated data. Lyme patients are experts in their illness. Patient-powered research takes the traditional top down expertise driven academic research model and turns it on its head. It is conceived by patients, is run by patients, and addresses issues that matter to patients.
Our patient registry, MyLymeData, is contributing to the knowledge base of Lyme disease by collecting, compiling, and analyzing the data essential to understanding and effectively treating chronic Lyme disease. We have published 7 peer-reviewed big-data studies to date and are in the process of publishing others.
Does Biological Sex Matter in Lyme Disease? The Need for Sex-Disaggregated Data in Persistent Illness
An implicit and inaccurate assumption underlying most medical research is that aside from reproductive matters, men and women do not differ substantially in their physiological and pathological response to disease. Most research was primarily conducted on men until 2015 when the National Institutes of Health (NIH) began requiring that sex be included as a biological variable factored into research designs and reported in both animal and human studies. Consideration of sex is now seen as critical to the interpretation, validation, and generalizability of research findings. However, in the case of Lyme disease, only a handful of papers have meaningfully analyzed differences linked to sex.
Lyme disease is a rapidly growing illness that remains poorly understood within the medical community. Critical questions about when and why patients respond to treatment or stay ill, what kinds of treatments are effective, and even how to properly diagnose the disease remain largely unanswered. We investigate these questions by applying machine learning techniques to a large scale Lyme disease patient registry, MyLymeData, developed by the nonprofit LymeDisease.org. We apply various machine learning methods in order to measure the effect of individual features in predicting participants’ answers to the Global Rating of Change (GROC) survey questions that assess the self-reported degree to which their condition improved, worsened, or remained unchanged following antibiotic treatment. We use basic linear regression, support vector machines, neural networks, entropy-based decision tree models, and k-nearest neighbors approaches. We first analyze the general performance of the model and then identify the most important features for predicting participant answers to GROC. After we identify the “key” features, we separate them from the dataset and demonstrate the effectiveness of these features at identifying GROC. In doing so, we highlight possible directions for future study both mathematically and clinically.