Guardado en:
Detalles Bibliográficos
Autores principales: Jana, Sudeshna, Sinha, Manjira, Dasgupta, Tirthankar
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2504.05691
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908306599051264
author Jana, Sudeshna
Sinha, Manjira
Dasgupta, Tirthankar
author_facet Jana, Sudeshna
Sinha, Manjira
Dasgupta, Tirthankar
contents Accurate prediction of Length of Stay (LOS) in hospitals is crucial for improving healthcare services, resource management, and cost efficiency. This paper presents StayLTC, a multimodal deep learning framework developed to forecast real-time hospital LOS using Liquid Time-Constant Networks (LTCs). LTCs, with their continuous-time recurrent dynamics, are evaluated against traditional models using structured data from Electronic Health Records (EHRs) and clinical notes. Our evaluation, conducted on the MIMIC-III dataset, demonstrated that LTCs significantly outperform most of the other time series models, offering enhanced accuracy, robustness, and efficiency in resource utilization. Additionally, LTCs demonstrate a comparable performance in LOS prediction compared to time series large language models, while requiring significantly less computational power and memory, underscoring their potential to advance Natural Language Processing (NLP) tasks in healthcare.
format Preprint
id arxiv_https___arxiv_org_abs_2504_05691
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle StayLTC: A Cost-Effective Multimodal Framework for Hospital Length of Stay Forecasting
Jana, Sudeshna
Sinha, Manjira
Dasgupta, Tirthankar
Artificial Intelligence
Accurate prediction of Length of Stay (LOS) in hospitals is crucial for improving healthcare services, resource management, and cost efficiency. This paper presents StayLTC, a multimodal deep learning framework developed to forecast real-time hospital LOS using Liquid Time-Constant Networks (LTCs). LTCs, with their continuous-time recurrent dynamics, are evaluated against traditional models using structured data from Electronic Health Records (EHRs) and clinical notes. Our evaluation, conducted on the MIMIC-III dataset, demonstrated that LTCs significantly outperform most of the other time series models, offering enhanced accuracy, robustness, and efficiency in resource utilization. Additionally, LTCs demonstrate a comparable performance in LOS prediction compared to time series large language models, while requiring significantly less computational power and memory, underscoring their potential to advance Natural Language Processing (NLP) tasks in healthcare.
title StayLTC: A Cost-Effective Multimodal Framework for Hospital Length of Stay Forecasting
topic Artificial Intelligence
url https://arxiv.org/abs/2504.05691