# Think as a Doctor: An Interpretable AI Approach for ICU Mortality Prediction

arXiv: https://arxiv.org/abs/2510.11745 · HTML: https://mlsanity.com/paper/2510.11745/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Multitask learning and benchmarking with clinical time series data](https://mlsanity.com/paper/1703.07771/) (2017)
- [Neural Prototype Trees for Interpretable Fine-grained Image Recognition](https://mlsanity.com/paper/2012.02046/) (2020)
- [Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1706.05764/) (2017)
- [Interpretable Image Classification with Differentiable Prototypes Assignment](https://mlsanity.com/paper/2112.02902/) (2021)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [Explaining Time Series Predictions with Dynamic Masks](https://mlsanity.com/paper/2106.05303/) (2021)
- [Interpretable and Steerable Sequence Learning via Prototypes](https://mlsanity.com/paper/1907.09728/) (2019)
- [ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context](https://mlsanity.com/paper/1911.12216/) (2019)
- [Concept-level Debugging of Part-Prototype Networks](https://mlsanity.com/paper/2205.15769/) (2022)
- [Interpretable Prototype-based Graph Information Bottleneck](https://mlsanity.com/paper/2310.19906/) (2023)
- [SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction](https://mlsanity.com/paper/2405.09039/) (2024)
- [ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU](https://mlsanity.com/paper/1901.08201/) (2019)
- [ProtoX: Explaining a Reinforcement Learning Agent via Prototyping](https://mlsanity.com/paper/2211.03162/) (2022)
- [Care for the Mind Amid Chronic Diseases: An Interpretable AI Approach Using IoT](https://mlsanity.com/paper/2211.04509/) (2022)
- [Decoding Emotional Trajectories: A Temporal-Semantic Network Approach for Latent Depression Assessment in Social Media](https://mlsanity.com/paper/2305.13127/) (2023)
- [Patient Outcome Predictions Improve Operations at a Large Hospital Network](https://mlsanity.com/paper/2305.15629/) (2023)

## Built on by (most cited first, 1 of 1)

- [TA-RNN-Medical-Hybrid: A Time-Aware and Interpretable Framework for Mortality Risk Prediction](https://mlsanity.com/paper/2603.08278/) (2026)

## Abstract (arXiv)

Intensive Care Unit (ICU) mortality prediction, which estimates a patient's mortality status at discharge using EHRs collected early in an ICU admission, is vital in critical care. For this task, predictive accuracy alone is insufficient; interpretability is equally essential for building clinical trust and meeting regulatory standards, a topic that has attracted significant attention in information system research. Accordingly, an ideal solution should enable intrinsic interpretability and align its reasoning with three key elements of the ICU decision-making practices: clinical course identification, demographic heterogeneity, and prognostication awareness. However, conventional approaches largely focus on demographic heterogeneity, overlooking clinical course identification and prognostication awareness. Recent prototype learning methods address clinical course identification, yet the integration of the other elements into such frameworks remains underexplored. To address these gaps, we propose ProtoDoctor, a novel ICU mortality prediction framework that delivers intrinsic interpretability while integrating all three elements of the ICU decision-making practices into its reasoning process. Methodologically, ProtoDoctor features two key innovations: the Prognostic Clinical Course Identification module and the Demographic Heterogeneity Recognition module. The former enables the identification of clinical courses via prototype learning and achieves prognostication awareness using a novel regularization mechanism. The latter models demographic heterogeneity through cohort-specific prototypes and risk adjustments. Extensive empirical evaluations demonstrate that ProtoDoctor outperforms state-of-the-art baselines in predictive accuracy. Human evaluations further confirm that its interpretations are more clinically meaningful, trustworthy, and applicable in ICU practice.