Combining Unsupervised Learning and Statistical Inference For Multimodal N-of-1 Trials

TL;DR

This paper introduces an unsupervised method combining autoencoders and statistical testing to analyze multimodal N-of-1 trials, enabling automated, large-scale personalized health intervention studies without expert-labeled outcomes.

Contribution

It presents a novel unsupervised framework that models multimodal N-of-1 trials using autoencoders and principal component analysis, bypassing the need for outcome labeling.

Findings

High power in detecting treatment effects in simulation studies

Effective identification of individual treatment effects in real trials

Controlled type I error rates in analysis

Abstract

N-of-1 trials are within-person crossover trials allowing both personalized and population-level inference on the effect of health interventions. Using the full potential of modern technologies, multimodal N-of-1 trials can integrate multimedia data for measuring health outcomes. However, methodology required for automated applications in large multimodal trials is not available yet. Here, we present an unsupervised approach for modeling multimodal N-of-1 trials, bypassing the need for expensive outcome labeling by medical experts. First, an autoencoder is trained on the outcome medical images. Then, the dimensionality of embeddings is reduced by extracting the first principal component, which is finally tested for its association with the treatment. Results from imaging simulation studies show high power in detecting a treatment effect while controlling type I error rates. An application to imaging N-of-1 trials of acne severity identifies individual treatment effects and supports that our methodology can enable large clinical multimodal N-of-1 trials.