Simultaneous Measurement Imputation and Outcome Prediction for Achilles Tendon Rupture Rehabilitation

TL;DR

This paper introduces an end-to-end probabilistic framework that simultaneously imputes missing treatment data and predicts Achilles Tendon Rupture rehabilitation outcomes, addressing data gaps and complex relations.

Contribution

It presents a novel integrated model that outperforms traditional two-stage methods in predicting ATR rehabilitation outcomes from incomplete clinical data.

Findings

Model outperforms baselines in accuracy

Effectively handles missing data in clinical datasets

Demonstrates superiority over traditional separate methods

Abstract

Achilles Tendon Rupture (ATR) is one of the typical soft tissue injuries. Rehabilitation after such a musculoskeletal injury remains a prolonged process with a very variable outcome. Accurately predicting rehabilitation outcome is crucial for treatment decision support. However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes. In this work, we design an end-to-end probabilistic framework to impute missing data entries and predict rehabilitation outcomes simultaneously. We evaluate our model on a real-life ATR clinical cohort, comparing with various baselines. The proposed method demonstrates its clear superiority over traditional methods which typically perform imputation and prediction in two separate stages.