Modeling Patient Care Trajectories with Transformer Hawkes Processes
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911573608497152 |
|---|---|
| author | Pandey, Saumya Chandola, Varun |
| author_facet | Pandey, Saumya Chandola, Varun |
| contents | Patient healthcare utilization consists of irregularly time-stamped events, such as outpatient visits, inpatient admissions, and emergency encounters, forming individualized care trajectories. Modeling these trajectories is crucial for understanding utilization patterns and predicting future care needs, but is challenging due to temporal irregularity and severe class imbalance. In this work, we build on the Transformer Hawkes Process framework to model patient trajectories in continuous time. By combining Transformer-based history encoding with Hawkes process dynamics, the model captures event dependencies and jointly predicts event type and time-to-event. To address extreme imbalance, we introduce an imbalance-aware training strategy using inverse square-root class weighting. This improves sensitivity to rare but clinically important events without altering the data distribution. Experiments on real-world data demonstrate improved performance and provide clinically meaningful insights for identifying high-risk patient populations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05844 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Modeling Patient Care Trajectories with Transformer Hawkes Processes Pandey, Saumya Chandola, Varun Machine Learning Quantitative Methods I.2.6; J.3 Patient healthcare utilization consists of irregularly time-stamped events, such as outpatient visits, inpatient admissions, and emergency encounters, forming individualized care trajectories. Modeling these trajectories is crucial for understanding utilization patterns and predicting future care needs, but is challenging due to temporal irregularity and severe class imbalance. In this work, we build on the Transformer Hawkes Process framework to model patient trajectories in continuous time. By combining Transformer-based history encoding with Hawkes process dynamics, the model captures event dependencies and jointly predicts event type and time-to-event. To address extreme imbalance, we introduce an imbalance-aware training strategy using inverse square-root class weighting. This improves sensitivity to rare but clinically important events without altering the data distribution. Experiments on real-world data demonstrate improved performance and provide clinically meaningful insights for identifying high-risk patient populations. |
| title | Modeling Patient Care Trajectories with Transformer Hawkes Processes |
| topic | Machine Learning Quantitative Methods I.2.6; J.3 |
| url | https://arxiv.org/abs/2604.05844 |