# Evaluation of Predictive Reliability to Foster Trust in Artificial Intelligence. A case study in Multiple Sclerosis

arXiv: https://arxiv.org/abs/2402.17554 · HTML: https://mlsanity.com/paper/2402.17554/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 32 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 14 of 14)

- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Denoising diffusion models for out-of-distribution detection](https://mlsanity.com/paper/2211.07740/) (2022)
- [Secure and Robust Machine Learning for Healthcare: A Survey](https://mlsanity.com/paper/2001.08103/) (2020)
- [FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare](https://mlsanity.com/paper/2309.12325/) (2023)
- [Unsupervised Out-of-Distribution Detection with Diffusion Inpainting](https://mlsanity.com/paper/2302.10326/) (2023)
- [Overparameterized Neural Networks Implement Associative Memory](https://mlsanity.com/paper/1909.12362/) (2019)
- [Aleatoric and Epistemic Uncertainty with Random Forests](https://mlsanity.com/paper/2001.00893/) (2020)
- [An Overview of Privacy in Machine Learning](https://mlsanity.com/paper/2005.08679/) (2020)
- [Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology](https://mlsanity.com/paper/2204.04516/) (2022)
- [Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift](https://mlsanity.com/paper/2207.08977/) (2022)
- [Tutorial: Safe and Reliable Machine Learning](https://mlsanity.com/paper/1904.07204/) (2019)
- [Transferring Fairness under Distribution Shifts via Fair Consistency Regularization](https://mlsanity.com/paper/2206.12796/) (2022)

## Abstract (arXiv)

Applying Artificial Intelligence (AI) and Machine Learning (ML) in critical contexts, such as medicine, requires the implementation of safety measures to reduce risks of harm in case of prediction errors. Spotting ML failures is of paramount importance when ML predictions are used to drive clinical decisions. ML predictive reliability measures the degree of trust of a ML prediction on a new instance, thus allowing decision-makers to accept or reject it based on its reliability. To assess reliability, we propose a method that implements two principles. First, our approach evaluates whether an instance to be classified is coming from the same distribution of the training set. To do this, we leverage Autoencoders (AEs) ability to reconstruct the training set with low error. An instance is considered Out-of-Distribution (OOD) if the AE reconstructs it with a high error. Second, it is evaluated whether the ML classifier has good performances on samples similar to the newly classified instance by using a proxy model. We show that this approach is able to assess reliability both in a simulated scenario and on a model trained to predict disease progression of Multiple Sclerosis patients. We also developed a Python package, named relAI, to embed reliability measures into ML pipelines. We propose a simple approach that can be used in the deployment phase of any ML model to suggest whether to trust predictions or not. Our method holds the promise to provide effective support to clinicians by spotting potential ML failures during deployment.