Patient Trajectory Prediction: Integrating Clinical Notes with Transformers
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910843821621248 |
|---|---|
| author | Klioui, Sifal Sellami, Sana Trardi, Youssef |
| author_facet | Klioui, Sifal Sellami, Sana Trardi, Youssef |
| contents | Predicting disease trajectories from electronic health records (EHRs) is a complex task due to major challenges such as data non-stationarity, high granularity of medical codes, and integration of multimodal data. EHRs contain both structured data, such as diagnostic codes, and unstructured data, such as clinical notes, which hold essential information often overlooked. Current models, primarily based on structured data, struggle to capture the complete medical context of patients, resulting in a loss of valuable information. To address this issue, we propose an approach that integrates unstructured clinical notes into transformer-based deep learning models for sequential disease prediction. This integration enriches the representation of patients' medical histories, thereby improving the accuracy of diagnosis predictions. Experiments on MIMIC-IV datasets demonstrate that the proposed approach outperforms traditional models relying solely on structured data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18009 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Patient Trajectory Prediction: Integrating Clinical Notes with Transformers Klioui, Sifal Sellami, Sana Trardi, Youssef Machine Learning Predicting disease trajectories from electronic health records (EHRs) is a complex task due to major challenges such as data non-stationarity, high granularity of medical codes, and integration of multimodal data. EHRs contain both structured data, such as diagnostic codes, and unstructured data, such as clinical notes, which hold essential information often overlooked. Current models, primarily based on structured data, struggle to capture the complete medical context of patients, resulting in a loss of valuable information. To address this issue, we propose an approach that integrates unstructured clinical notes into transformer-based deep learning models for sequential disease prediction. This integration enriches the representation of patients' medical histories, thereby improving the accuracy of diagnosis predictions. Experiments on MIMIC-IV datasets demonstrate that the proposed approach outperforms traditional models relying solely on structured data. |
| title | Patient Trajectory Prediction: Integrating Clinical Notes with Transformers |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.18009 |