机器学习在非癌症患者缓和医疗中的应用进展

doi:10.3969/j.issn.1003-9198.2026.09.005

摘要/Abstract

摘要： 缓和医疗是一种积极的全人照护实践,旨在缓解患者、家属及照护者的身心痛苦,改善生命质量。人口老龄化背景下,非癌症慢性疾病患者已成为缓和医疗的主要服务人群。该类患者病程长、病情波动大、终末期难以识别,而传统人工评估模式存在照护介入滞后、资源配置不合理、精准干预不足等问题。机器学习可深度挖掘多源医疗数据,助力缓和医疗智能化转型。本文综述了机器学习在非癌症患者缓和医疗中的应用现状与现存挑战,以期为该领域临床实践与研究提供参考。

关键词: 机器学习, 人工智能, 缓和医疗, 非癌症慢性疾病

Abstract: Palliative care is an active practice of whole-person care, aimed at alleviating the physical and psychological suffering of patients, their families, and caregivers, thereby improving quality of life. Against the backdrop of an aging population, patients with non-cancer chronic diseases have become the primary recipients of palliative care services. These patients typically experience prolonged disease courses, significant fluctuations in condition, and difficulty in identifying the terminal phase. Traditional manual assessment models lead to delayed care interventions, suboptimal resource allocation, and insufficient precision in interventions. Machine learning has the potential to deeply mine multi-source medical data, thereby facilitating the intelligent transformation of palliative care. This review summarizes the current applications and existing challenges of machine learning in palliative care of non-cancer patients, aiming to provide a reference for clinical practice and research in this field.

Key words: machine learning, artificial intelligence, palliative care, non-cancer chronic disease

中图分类号:

R 48

李铭麟, 梁庆静, 曾三龙, 李敏锋, 骆建文. 机器学习在非癌症患者缓和医疗中的应用进展[J]. 实用老年医学, 2026, 40(9): 883-887.

LI Minglin, LIANG Qingjing, ZENG Sanlong, LI Minfeng, LUO Jianwen. Research progress of machine learning in palliative care for non-cancer patients[J]. Practical Geriatrics, 2026, 40(9): 883-887.

参考文献

[1] Chinese Expert Consensus Working Group on the Definition of Palliative Care. Chinese expert consensus on the definitions of palliative care and hospice care (2025)[J]. Chin Med Sci J, 2025, 40(2): 89-99.
[2] CAO K, FENG Q, TIAN W, et al. The prevalence of chronic diseases among older Chinese adults in the past 2 decades: a study based on the Chinese longitudinal healthy longevity survey, 2002—2022[J]. Am J Public Health, 2025, 115(12): 2053-2061.
[3] 张彩婧, 蔡羽琪, 陈子菲, 等. 2000―2021年中国60岁及以上老年人群死亡谱变化特征[J]. 中华疾病控制杂志, 2025, 29(9): 1006-1012, 1053.
[4] ZHANG Y, ZHOU W, ZHANG C, et al. Application of digital technology intervention in palliative care: a scoping review[J]. BMC Palliat Care, 2025, 25(1): 12.
[5] SILVA-FERREIRA M, CRUZ S, LUÍS M S, et al. Mapping study on AI-based technologies in palliative care - a scoping study[J]. BMC Palliat Care, 2025, 24(1): 274.
[6] NIKOLOUDI M, MYSTAKIDOU K. Artificial intelligence in palliative care: a scoping review of current applications, challenges, and future directions[J]. Am J Hosp Palliat Care, 2025: 10499091251358379.
[7] 于世英. 缓和医疗存在的争议[J]. 协和医学杂志, 2024, 15(1): 37-41.
[8] NARVAEZ R A, FERRER M, PECO R A, et al. Artificial intelligence in symptom management and clinical decision support for palliative care[J]. Int J Palliat Nurs, 2025, 31(6): 294-306.
[9] DONG L, HIRAYAMA H, ZHENG X, et al. Using voice recognition and machine learning techniques for detecting patient-reported outcomes from conversational voice in palliative care patients[J]. Jpn J Nurs Sci, 2025, 22(1): e12644.
[10] AMBROSY A P, FONAROW G C, BUTLER J, et al. The global health and economic burden of hospitalizations for heart failure: lessons learned from hospitalized heart failure registries[J]. J Am Coll Cardiol, 2014, 63(12): 1123-1133.
[11] JIANG W, SIDDIQUI S, BARNES S, et al. Readmission risk trajectories for patients with heart failure using a dynamic prediction approach: retrospective study[J]. JMIR Med Inform, 2019, 7(4): e14756.
[12] GEBRESILLASSIE B M, ATTIA J, CAVENAGH D, et al. Predicting end-of-life in older women with heart failure: development and internal validation of clinically actionable prognostic models using routinely collected national data[J]. BMC Geriatr, 2026, 26(1): 221.
[13] VU E, STEINMANN N, SCHRÖDER C, et al. Applications of machine learning in palliative care: a systematic review[J]. Cancers: Basel, 2023, 15(5):1596.
[14] ALABBASI A, ALZAHRANI M, SULTAN F, et al. Artificial intelligence-powered predictive tools to improve end-of-life decision-making: mini-review[J]. BMJ Support Palliat Care, 2026, 16(3): 558-564.
[15] WILSTRUP C, CAVE C. Combining symbolic regression with the Cox proportional hazards model improves prediction of heart failure deaths[J]. BMC Med Inform Decis Mak, 2022, 22(1): 196.
[16] BLANES-SELVA V, DOÑATE-MARTÍNEZ A, LINKLATER G, et al. Complementary frailty and mortality prediction models on older patients as a tool for assessing palliative care needs[J]. Health Informatics J, 2022, 28(2): 14604582221092592.
[17] NEJATIFAR Z, ALIZADEH A, AMERZADEH M, et al. The predictive role of identifying frailty in assessing the need for palliative care in the elderly: the application of machine learning algorithm[J]. J Health Popul Nutr, 2025, 44(1): 133.
[18] BRESSLER T, SONG J, KAMALUMPUNDI V, et al. Leveraging artificial intelligence/machine learning models to identify potential palliative care beneficiaries: a systematic review[J]. J Gerontol Nurs, 2025, 51(1): 7-14.
[19] MARTINEZ V A, BETTS R K, SCRUTH E A, et al. The Kaiser permanente northern California advance alert monitor program: an automated early warning system for adults at risk for in-hospital clinical deterioration[J]. Jt Comm J Qual Patient Saf, 2022, 48(8): 370-375.
[20] CHU T, ZHANG H, XU Y, et al. Predicting the behavioral intentions of hospice and palliative care providers from real-world data using supervised learning: a cross-sectional survey study[J]. Front Public Health, 2022, 10: 927874.
[21] CHO S Y, LAI W S, TSAI J H, et al. Interpretable machine learning approach for optimizing hospice care predictions using health assessment data[J]. BMC Med Inform Decis Mak, 2025, 25(1): 456.
[22] HOFFMAN D I, MOORE S, RUAN M, et al. Natural language processing to assess palliative care processes and health care utilization in seriously ill older adults with severe trauma[J]. J Palliat Med, 2026, 29(4): 495-502.
[23] RIAD K, WEBBER C, BATISTA R, et al. The impact of dementia and language on hospitalizations: a retrospective cohort of long-term care residents[J]. BMC Geriatr, 2020, 20(1): 397.
[24] HOTCHKISS J T, RIDDERMAN E, BUFKIN W. Development of a model and method for hospice quality assessment from natural language processing (NLP) analysis of online caregiver reviews[J]. Palliat Support Care, 2024, 22(1): 19-30.
[25] TAUBERT M, HACKETT R, TAVABIE S. Artificial intelligence and large language models in palliative medicine clinical practice and education[J]. BMJ Support Palliat Care, 2024, 15(1): 61-64.
[26] ROTENSTEIN L, WANG L, ZUPANC S N, et al. Looking beyond mortality prediction: primary care physician views of patients’ palliative care needs predicted by a machine learning tool[J]. Appl Clin Inform, 2024, 15(3): 460-468.
[27] XU T, ROSE G M. Opportunities and barriers to artificial intelligence adoption in palliative/hospice care for underrepresented groups: a technology acceptance model-based review[J]. J Hosp Palliat Nurs, 2025, 27(4): E160-E179.
[28] AHMAD O, MASON S, STANLEY S, et al. Exploring perspectives of health care professionals on AI in palliative care: qualitative interview study[J]. JMIR Hum Factors, 2025, 12: e79514.
[29] HAMER M K, ALASMAR A Y, HUBER K, et al. “Screening” for end of life using artificial intelligence: a qualitative study of palliative care team members’ perspectives on ethical use[J]. J Palliat Med, 2025, 28(11): 1465-1472.
[30] BURRY N, NAKAGAWA S, BLINDERMAN C D. “You are not alone”: the allure and limitations of artificial intelligence in serious illness communication[J]. J Palliat Med, 2024, 27(1): 7-9.
[31] SCHENKER Y, ABDULLAH S, ARNOLD R, et al. Conversational agents in palliative care: potential benefits, risks, and next steps[J]. J Palliat Med, 2024, 27(3): 296-300.
[32] CASCELLA M, LAUDANI A, SCARPATI G, et al. Ethical issues in pain and palliation[J]. Curr Opin Anaesthesiol, 2024, 37(2): 199-204.