# Quantifying Impairment and Disease Severity Using AI Models Trained on Healthy Subjects

arXiv: https://arxiv.org/abs/2311.12781 · HTML: https://mlsanity.com/paper/2311.12781/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 61 references that are in the map.
- First posted on arXiv 21 Nov 2023.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data](https://mlsanity.com/paper/2002.11297/) (2020)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers](https://mlsanity.com/paper/1809.03576/) (2018)
- [Alleviating Over-segmentation Errors by Detecting Action Boundaries](https://mlsanity.com/paper/2007.06866/) (2020)
- [Robust Out-of-distribution Detection for Neural Networks](https://mlsanity.com/paper/2003.09711/) (2020)
- [An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization](https://mlsanity.com/paper/2002.07613/) (2020)
- [One Network to Segment Them All: A General, Lightweight System for Accurate 3D Medical Image Segmentation](https://mlsanity.com/paper/1911.01764/) (2019)
- [Deep Probability Estimation](https://mlsanity.com/paper/2111.10734/) (2021)
- [Remote patient monitoring using artificial intelligence: Current state, applications, and challenges](https://mlsanity.com/paper/2301.10009/) (2023)
- [Detecting hidden signs of diabetes in external eye photographs](https://mlsanity.com/paper/2011.11732/) (2020)

## Built on by (most cited first, 2 of 2)

- [The Potential and Limitations of Vision-Language Models for Human Motion Understanding: A Case Study in Data-Driven Stroke Rehabilitation](https://mlsanity.com/paper/2511.17727/) (2025)
- [Wearable-informed generative digital avatars predict task-conditioned post-stroke locomotion](https://mlsanity.com/paper/2512.14329/) (2025)

## Abstract (arXiv)

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a novel framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.845, 95% CI [0.743,0.908]) and video (ρ = 0.746, 95% C.I [0.594, 0.847]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]).