Authors:Yingbo Ma, Suraj Kolla, Zhenhong Hu, Dhruv Kaliraman, Victoria Nolan, Ziyuan Guan, Yuanfang Ren, Brooke Armfield, Tezcan Ozrazgat-Baslanti, Jeremy A. Balch, Tyler J. Loftus, Parisa Rashidi, Azra Bihorac, Benjamin Shickel

View PDF HTML (experimental)

Abstract:Modern electronic health records (EHRs) hold immense promise in tracking personalized patient health trajectories through sequential deep learning, owing to their extensive breadth, scale, and temporal granularity. Nonetheless, how to effectively leverage multiple modalities from EHRs poses significant challenges, given its complex characteristics such as high dimensionality, multimodality, sparsity, varied recording frequencies, and temporal irregularities. To this end, this paper introduces a novel multimodal contrastive learning framework, specifically focusing on medical time series and clinical notes. To tackle the challenge of sparsity and irregular time intervals in medical time series, the framework integrates temporal cross-attention transformers with a dynamic embedding and tokenization scheme for learning multimodal feature representations. To harness the interconnected relationships between medical time series and clinical notes, the framework equips a global contrastive loss, aligning a patient's multimodal feature representations with the corresponding discharge summaries. Since discharge summaries uniquely pertain to individual patients and represent a holistic view of the patient's hospital stay, machine learning models are led to learn discriminative multimodal features via global contrasting. Extensive experiments with a real-world EHR dataset demonstrated that our framework outperformed state-of-the-art approaches on the exemplar task of predicting the occurrence of nine postoperative complications for more than 120,000 major inpatient surgeries using multimodal data from UF health system split among three hospitals (UF Health Gainesville, UF Health Jacksonville, and UF Health Jacksonville-North).

Submission history

From: Yingbo Ma [view email]
[v1] Wed, 10 Apr 2024 04:19:59 UTC (452 KB)

相關(guān)知識(shí)

我國個(gè)人電子健康檔案隱私保護(hù)現(xiàn)狀調(diào)查與分析——基于普通公眾的視角
Psychological health
馬連韜 MA Liantao
Can language learning support your mental health? ? GO Blog
Law of the People's Republic of China on Basic Medical and Health Care and the Promotion of Health
Mental health services deployed across China in fight against epidemic
Psychosocial Support for Adolescent and Young Adult Patients with Cancer
Xinhua Headlines: Mental health services deployed across China in fight against epidemic
2020 Application Guide for Chinese Language Program
Improved Health & Well

網(wǎng)址: Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision http://m.u1s5d6.cn/newsview1221276.html