Recovering Loss to Followup Information Using Denoising Autoencoders

TL;DR

This paper introduces a denoising autoencoder-based model to recover loss to followup data in healthcare studies, effectively handling complex non-linear relations and outperforming existing methods.

Contribution

The paper presents a novel overcomplete denoising autoencoder approach specifically designed for high-volume healthcare data to recover loss to followup information.

Findings

Outperforms state-of-the-art methods by up to 20% in recovery accuracy.

Effective across various simulated and real datasets.

Preserves data utility for final analysis.

Abstract

Loss to followup is a significant issue in healthcare and has serious consequences for a study's validity and cost. Methods available at present for recovering loss to followup information are restricted by their expressive capabilities and struggle to model highly non-linear relations and complex interactions. In this paper we propose a model based on overcomplete denoising autoencoders to recover loss to followup information. Designed to work with high volume data, results on various simulated and real life datasets show our model is appropriate under varying dataset and loss to followup conditions and outperforms the state-of-the-art methods by a wide margin ($\ge 20\%$ in some scenarios) while preserving the dataset utility for final analysis.