Federated Learning on Patient Data for Privacy-Protecting Polycystic Ovary Syndrome Treatment

Lucia Morris, Tori Qiu, Nikhil Raghuraman

Keywords: federated learning, machine learning, FedAvg, FedAvgM, FedProx, FedAdam, polycystic ovary syndrome, data privacy

TL;DR: We demonstrate that a variety of federated learning approaches succeed on a synthetic PCOS patient dataset to identify the most effective treatment option.

Abstract: The field of women’s endocrinology has trailed behind data-driven medical solutions, largely due to concerns over the privacy of patient data. Valuable datapoints about hormone levels or menstrual cycling could expose patients who suffer from comorbidities or terminate a pregnancy, violating their privacy. We explore the application of Federated Learning (FL) to predict the optimal drug for patients with polycystic ovary syndrome (PCOS). PCOS is a serious hormonal disorder impacting millions of women worldwide, yet it’s poorly understood and its research is stunted by a lack of patient data. We demonstrate that a variety of FL approaches succeed on a synthetic PCOS patient dataset. Our proposed FL models are a tool to access massive quantities of diverse data and identify the most effective treatment option while providing PCOS patients with privacy guarantees. Our code is open-sourced at https://github.com/toriqiu/fl-pcos.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/federated-learning-on-patient-data-for/code)