# Computing patient similarity based on unstructured clinical notes

arXiv: https://arxiv.org/abs/2601.07385 · HTML: https://mlsanity.com/paper/2601.07385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 3 of 3)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Unsupervised extraction, labelling and clustering of segments from clinical notes](https://mlsanity.com/paper/2211.11799/) (2022)

## Abstract (arXiv)

Clinical notes hold rich yet unstructured details about diagnoses, treatments, and outcomes that are vital to precision medicine but hard to exploit at scale. We introduce a method that represents each patient as a matrix built from aggregated embeddings of all their notes, enabling robust patient similarity computation based on their latent low-rank representations. Using clinical notes of 4,267 Czech breast-cancer patients and expert similarity labels from Masaryk Memorial Cancer Institute, we evaluate several matrix-based similarity measures and analyze their strengths and limitations across different similarity facets, such as clinical history, treatment, and adverse events. The results demonstrate the usefulness of the presented method for downstream tasks, such as personalized therapy recommendations or toxicity warnings.