Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.18246 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908631993155584 |
|---|---|
| author | Yildiz, Yusuf Nenadic, Goran Jani, Meghna Jenkins, David A. |
| author_facet | Yildiz, Yusuf Nenadic, Goran Jani, Meghna Jenkins, David A. |
| contents | Objective: Large language models (LLMs) are attracting increasing interest in healthcare. This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks, with a focus on their ability to process longitudinal electronic health record (EHR) data.
Findings: LLMs show promise in handling multimodal and longitudinal EHR data and can support multi-outcome predictions for diverse health conditions. However, methodological, validation, infrastructural, and regulatory chal- lenges remain. These include inadequate methods for time-to-event modelling, poor calibration of predictions, limited external validation, and bias affecting underrepresented groups. High infrastructure costs and the absence of clear regulatory frameworks further prevent adoption.
Implications: Further work and interdisciplinary collaboration are needed to support equitable and effective integra- tion into the clinical prediction. Developing temporally aware, fair, and explainable models should be a priority focus for transforming clinical prediction workflow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18246 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Will Large Language Models Transform Clinical Prediction? Yildiz, Yusuf Nenadic, Goran Jani, Meghna Jenkins, David A. Computers and Society Computation and Language Objective: Large language models (LLMs) are attracting increasing interest in healthcare. This commentary evaluates the potential of LLMs to improve clinical prediction models (CPMs) for diagnostic and prognostic tasks, with a focus on their ability to process longitudinal electronic health record (EHR) data. Findings: LLMs show promise in handling multimodal and longitudinal EHR data and can support multi-outcome predictions for diverse health conditions. However, methodological, validation, infrastructural, and regulatory chal- lenges remain. These include inadequate methods for time-to-event modelling, poor calibration of predictions, limited external validation, and bias affecting underrepresented groups. High infrastructure costs and the absence of clear regulatory frameworks further prevent adoption. Implications: Further work and interdisciplinary collaboration are needed to support equitable and effective integra- tion into the clinical prediction. Developing temporally aware, fair, and explainable models should be a priority focus for transforming clinical prediction workflow. |
| title | Will Large Language Models Transform Clinical Prediction? |
| topic | Computers and Society Computation and Language |
| url | https://arxiv.org/abs/2505.18246 |