Modeling Patient Care Trajectories with Transformer Hawkes Processes

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pandey, Saumya, Chandola, Varun
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