Contreras Miguel, Silva Brandon, Shickel Benjamin, Davidson Andrea, Ozrazgat-Baslanti Tezcan, Ren Yuanfang, Guan Ziyuan, Balch Jeremy, Zhang Jiaqing, Bandyopadhyay Sabyasachi, Loftus Tyler, Khezeli Kia, Lipori Gloria, Sena Jessica, Nerella Subhash, Bihorac Azra, Rashidi Parisa
Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA.
Intelligent Clinical Care Center (IC3), University of Florida, Gainesville, FL, USA.
Nat Commun. 2025 Aug 8;16(1):7315. doi: 10.1038/s41467-025-62121-1.
Intensive care unit (ICU) patients often experience rapid changes in clinical status, requiring timely identification of deterioration to guide life-sustaining interventions. Current artificial intelligence (AI) models for acuity assessment rely on mortality as a proxy and lack direct prediction of clinical instability or treatment needs. Here we present APRICOT-M, a state-space model to predict real-time ICU acuity outcomes and transitions, and the need for life-sustaining therapies within the next four hours. The model integrates vital signs, laboratory results, medications, assessment scores, and patient characteristics, to make predictions, handling sparse, irregular data efficiently. Our model is trained on over 140,000 ICU admissions across 55 hospitals and validated on external and real-time data, outperforming clinical scores in predicting mortality and instability. The model demonstrates clinical relevance, with physicians reporting alerts as actionable and timely in a substantial portion of cases. These results highlight APRICOT-M's potential to support earlier, more informed ICU interventions.
重症监护病房（ICU）的患者临床状况往往变化迅速，需要及时识别病情恶化情况，以指导维持生命的干预措施。当前用于病情严重程度评估的人工智能（AI）模型依赖死亡率作为替代指标，缺乏对临床不稳定或治疗需求的直接预测。在此，我们展示了APRICOT-M，这是一种状态空间模型，用于预测ICU实时病情严重程度结果和病情变化，以及未来四小时内对维持生命治疗的需求。该模型整合了生命体征、实验室检查结果、用药情况、评估分数和患者特征，以进行预测，并能有效处理稀疏、不规则的数据。我们的模型在55家医院的超过14万例ICU入院病例上进行了训练，并在外部和实时数据上进行了验证，在预测死亡率和不稳定方面优于临床评分。该模型具有临床相关性，医生报告称在相当一部分病例中，警报是可操作且及时的。这些结果凸显了APRICOT-M在支持更早、更明智的ICU干预方面的潜力。
