# Instability in clinical risk stratification models using deep learning

arXiv: https://arxiv.org/abs/2211.10828 · HTML: https://mlsanity.com/paper/2211.10828/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 20 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Randomness In Neural Network Training: Characterizing The Impact of Tooling](https://mlsanity.com/paper/2106.11872/) (2021)
- [Noisy Activation Functions](https://mlsanity.com/paper/1603.00391/) (2016)
- [Nondeterminism and Instability in Neural Network Optimization](https://mlsanity.com/paper/2103.04514/) (2021)
- [A Weighted Correlation Index for Rankings with Ties](https://mlsanity.com/paper/1404.3325/) (2014)
- [Analyzing the Role of Model Uncertainty for Electronic Health Records](https://mlsanity.com/paper/1906.03842/) (2019)
- [On Model Stability as a Function of Random Seed](https://mlsanity.com/paper/1909.10447/) (2019)
- [Horizontal and Vertical Ensemble with Deep Representation for Classification](https://mlsanity.com/paper/1306.2759/) (2013)
- [A new paradigm for accelerating clinical data science at Stanford Medicine](https://mlsanity.com/paper/2003.10534/) (2020)
- [Smooth activations and reproducibility in deep networks](https://mlsanity.com/paper/2010.09931/) (2020)
- [Machine learning for dynamically predicting the onset of renal replacement therapy in chronic kidney disease patients using claims data](https://mlsanity.com/paper/2209.01469/) (2022)

## Built on by (most cited first, 3 of 3)

- [A Closer Look at AUROC and AUPRC under Class Imbalance](https://mlsanity.com/paper/2401.06091/) (2024)
- [Exploring End-to-end Differentiable Neural Charged Particle Tracking -- A Loss Landscape Perspective](https://mlsanity.com/paper/2407.13420/) (2024)
- [Diagnostics for Individual-Level Prediction Instability in Machine Learning for Healthcare](https://mlsanity.com/paper/2603.00192/) (2026)

## Abstract (arXiv)

While it has been well known in the ML community that deep learning models suffer from instability, the consequences for healthcare deployments are under characterised. We study the stability of different model architectures trained on electronic health records, using a set of outpatient prediction tasks as a case study. We show that repeated training runs of the same deep learning model on the same training data can result in significantly different outcomes at a patient level even though global performance metrics remain stable. We propose two stability metrics for measuring the effect of randomness of model training, as well as mitigation strategies for improving model stability.