Predicting pregnancy using large-scale data from a women's health tracking mobile application

TL;DR

This study demonstrates that mobile health tracking data can effectively predict pregnancy probabilities, with models showing significant stratification and interpretability aligned with fertility research, highlighting broad potential for women's health applications.

Contribution

Developed and evaluated deep learning and logistic regression models for pregnancy prediction using large-scale mobile app data, introducing interpretability techniques aligned with fertility science.

Findings

Women in top 10% predicted probability have 89% chance of pregnancy over 6 cycles

Models significantly stratify pregnancy likelihood across populations

Interpretability techniques reveal trends consistent with fertility research

Abstract

Predicting pregnancy has been a fundamental problem in women's health for more than 50 years. Previous datasets have been collected via carefully curated medical studies, but the recent growth of women's health tracking mobile apps offers potential for reaching a much broader population. However, the feasibility of predicting pregnancy from mobile health tracking data is unclear. Here we develop four models -- a logistic regression model, and 3 LSTM models -- to predict a woman's probability of becoming pregnant using data from a women's health tracking app, Clue by BioWink GmbH. Evaluating our models on a dataset of 79 million logs from 65,276 women with ground truth pregnancy test data, we show that our predicted pregnancy probabilities meaningfully stratify women: women in the top 10% of predicted probabilities have a 89% chance of becoming pregnant over 6 menstrual cycles, as compared to a 27% chance for women in the bottom 10%. We develop a technique for extracting interpretable time trends from our deep learning models, and show these trends are consistent with previous fertility research. Our findings illustrate the potential that women's health tracking data offers for predicting pregnancy on a broader population; we conclude by discussing the steps needed to fulfill this potential.