SynthA1c: Towards Clinically Interpretable Patient Representations for Diabetes Risk Stratification

TL;DR

This paper introduces SynthA1c, a neural network-based method that uses image-derived phenotypic data to predict Type 2 Diabetes Mellitus risk, achieving high sensitivity and enabling opportunistic screening without additional blood tests.

Contribution

It presents a novel approach to leverage image-derived phenotypes with neural networks to predict diabetes risk, including a new metric for model generalization across populations.

Findings

Achieves up to 87.6% sensitivity in risk prediction.

Uses a novel generalizable metric for out-of-domain performance.

Combines phenotypic and physical exam data for accurate risk stratification.

Abstract

Early diagnosis of Type 2 Diabetes Mellitus (T2DM) is crucial to enable timely therapeutic interventions and lifestyle modifications. As the time available for clinical office visits shortens and medical imaging data become more widely available, patient image data could be used to opportunistically identify patients for additional T2DM diagnostic workup by physicians. We investigated whether image-derived phenotypic data could be leveraged in tabular learning classifier models to predict T2DM risk in an automated fashion to flag high-risk patients without the need for additional blood laboratory measurements. In contrast to traditional binary classifiers, we leverage neural networks and decision tree models to represent patient data as 'SynthA1c' latent variables, which mimic blood hemoglobin A1c empirical lab measurements, that achieve sensitivities as high as 87.6%. To evaluate how SynthA1c models may generalize to other patient populations, we introduce a novel generalizable metric that uses vanilla data augmentation techniques to predict model performance on input out-of-domain covariates. We show that image-derived phenotypes and physical examination data together can accurately predict diabetes risk as a means of opportunistic risk stratification enabled by artificial intelligence and medical imaging. Our code is available at https://github.com/allisonjchae/DMT2RiskAssessment.