Sparse ProtoPatient: Interactive Multi-Prototype Explanations for Clinical Diagnosis Prediction

Fallon, Conor; Kostić, Bogdan; van Aken, Betty; Papaioannou, Jens-Michalis; Figueroa, Alexei; Bressem, Keno; Löser, Alexander

doi:10.24963/ijcai.2026/963

Sparse ProtoPatient: Interactive Multi-Prototype Explanations for Clinical Diagnosis Prediction

Conor Fallon, Bogdan Kostić, Betty van Aken, Jens-Michalis Papaioannou, Alexei Figueroa, Keno Bressem, Alexander Löser

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Demo Track. Pages 8389-8392.

https://doi.org/10.24963/ijcai.2026/963

Keywords

AI: Humans and AI
AI: Multidisciplinary Topics and Applications
AI: AI Ethics, Trust, Fairnes
AI: Natural Language Processing

Abstract

We present the Sparse ProtoPatient Demo, a publicly available interactive system for interpretable ICD-10 diagnosis prediction from clinical admission notes.

The system is designed for clinicians in training, researchers, and educators exploring prototype-based diagnostic reasoning.

The demo links predictions to learned prototypical patient representations and token-level evidence, allowing users to input custom text or select preset cases, inspect predicted ICD-10 codes, visualize label-wise saliency, retrieve supporting prototype notes, and compare alternative prototype cohorts.

The demo provides a reproducible platform for interactive inspection of prototype-based clinical reasoning, enabling complementary opinion exploration, model auditing, and teaching of interpretable diagnosis prediction.

The deployed model is trained on the publicly released CodiEsp corpus (1000 clinical notes, 955 ICD-10 labels) using a sparse multi-prototype architecture with five prototypes per label.

We use the official machine-translated English CodiEsp-MT release to support English-language interaction.

It achieves a macro-AUROC of 0.92 on a held-out test set and supports real-time interaction (300ms per query).

The system is fully containerized for public research and educational use.

Conor Fallon, Bogdan Kostić, Betty van Aken, Jens-Michalis Papaioannou, Alexei Figueroa, Keno Bressem, and Alexander Löser. 2026. Sparse ProtoPatient: Interactive Multi-Prototype Explanations for Clinical Diagnosis Prediction. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8389–8392. https://doi.org/10.24963/ijcai.2026/963

@inproceedings{ijcai2026p963,
  title     = {Sparse ProtoPatient: Interactive Multi-Prototype Explanations for Clinical Diagnosis Prediction},
  author    = {Fallon, Conor and Kostić, Bogdan and van Aken, Betty and Papaioannou, Jens-Michalis and Figueroa, Alexei and Bressem, Keno and Löser, Alexander},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {8389--8392},
  year      = {2026},
  month     = {8},
  note      = {Demo Track},
  doi       = {10.24963/ijcai.2026/963},
  url       = {https://doi.org/10.24963/ijcai.2026/963},
}

TY  - CPAPER
TI  - Sparse ProtoPatient: Interactive Multi-Prototype Explanations for Clinical Diagnosis Prediction
AU  - Fallon, Conor
AU  - Kostić, Bogdan
AU  - van Aken, Betty
AU  - Papaioannou, Jens-Michalis
AU  - Figueroa, Alexei
AU  - Bressem, Keno
AU  - Löser, Alexander
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 8389
EP  - 8392
DO  - 10.24963/ijcai.2026/963
UR  - https://doi.org/10.24963/ijcai.2026/963
ER  -