Predicting Visit Cost of Obstructive Sleep Apnea using Electronic Healthcare Records with Transformer

TL;DR

This paper introduces a novel two-Transformer model approach to accurately predict the annual healthcare costs for OSA patients by effectively utilizing limited high-quality data and data augmentation techniques.

Contribution

The authors develop a two-Transformer model framework that enhances prediction accuracy by leveraging data augmentation and case enrichment, addressing data scarcity challenges in healthcare cost prediction.

Findings

Prediction $R^{2}$ improved from 88.8% to 97.5% with the two-model approach.

Baseline models' $R^{2}$ increased from 61.6% to 81.9% using data augmentation.

Method effectively utilizes limited high-quality patient data for cost prediction.

Abstract

Background: Obstructive sleep apnea (OSA) is growing increasingly prevalent in many countries as obesity rises. Sufficient, effective treatment of OSA entails high social and financial costs for healthcare. Objective: For treatment purposes, predicting OSA patients' visit expenses for the coming year is crucial. Reliable estimates enable healthcare decision-makers to perform careful fiscal management and budget well for effective distribution of resources to hospitals. The challenges created by scarcity of high-quality patient data are exacerbated by the fact that just a third of those data from OSA patients can be used to train analytics models: only OSA patients with more than 365 days of follow-up are relevant for predicting a year's expenditures. Methods and procedures: The authors propose a method applying two Transformer models, one for augmenting the input via data from shorter visit histories and the other predicting the costs by considering both the material thus enriched and cases with more than a year's follow-up. Results: The two-model solution permits putting the limited body of OSA patient data to productive use. Relative to a single-Transformer solution using only a third of the high-quality patient data, the solution with two models improved the prediction performance's $R^{2}$ from 88.8% to 97.5%. Even using baseline models with the model-augmented data improved the $R^{2}$ considerably, from 61.6% to 81.9%. Conclusion: The proposed method makes prediction with the most of the available high-quality data by carefully exploiting details, which are not directly relevant for answering the question of the next year's likely expenditure.