Research advances in application of artificial intelligence techniques in predicting outcomes in patients with chronic disease multimorbidities

Abstract

Abstract:

The chronic disease multimorbidity，defined as an individual's coexistence with at least two chronic diseases，constitutes a growing global challenge with significant impacts on individual health，family status，healthcare systems and even society. Compared to suffering from only one disease，the coexistence of multiple diseases significantly reduces patients' physiological function and quality of life，increases the burden of treatment，increases the number of medications and the risk of adverse drug reactions，and affects patients' prognosis. The artificial intelligence（AI） technologies including survival analysis models，time series analysis and reinforcement learning have powerful data recognition and analysis capabilities，and combined with the current development of big data in healthcare，AI plays an important role in predicting the outcomes of patients with chronic multimorbidities. This study summarizes the progress of the application of AI technology in predicting the outcomes of patients with chronic disease co-morbidities for the reference of prognostic assessment of patients with chronic disease multimorbidities.

Key words: Chronic disease multimorbidities, Disease outcomes, Artificial intelligence, Machine learning, Deep learning

CLC Number:

R181.3⁺7

LI Yubo, YE Lixiang, XU Zhaozhao, ZHANG Shuxiang. Research advances in application of artificial intelligence techniques in predicting outcomes in patients with chronic disease multimorbidities. [J]OCCUPATION AND HEALTH, 2026, 42(4): 566-570.

References 38

[1]	SKOU S T, MAIR F S, FORTIN M, et al. Multimorbidity[J]. Nat Rev Dis Primers, 2022, 8(1):48. DOI PMID
[2]	HO I S, AZCOAGA-LORENZO A, AKBARI A, et al. Variation in the estimated prevalence of multimorbidity:systematic review and meta-analysis of 193 international studies[J]. BMJ Open, 2022, 12(4):e057017. DOI URL
[3]	孙菊, 王静茹, 李浩淼. 健康老龄化:内涵辨析、测量方式与中国趋势[J]. 中国卫生政策研究, 2023, 16(5):47-55.
[4]	KHUNTI K, SATHANAPALLY H, MOUNTAIN P. Multiple long term conditions,multimorbidity,and co-morbidities:we should reconsider the terminology we use[J]. BMJ, 2023,383:2327.
[5]	AUBERT C E, KABETO M, KUMAR N, et al. Multimorbidity and long-term disability and physical functioning decline in middle-aged and older Americans:an observational study[J]. BMC Geriatr, 2022, 22(1):910. DOI
[6]	MAKOVSKI T T, SCHMITZ S, ZEEGERS M P, et al. Multimorbidity and quality of life:Systematic literature review and meta-analysis[J]. Ageing Res Rev, 2019,53:100903.
[7]	NI Y, ZHOU Y, KIVIMÄKI M, et al. Socioeconomic inequalities in physical,psychological,and cognitive multimorbidity in middle-aged and older adults in 33 countries:A cross-sectional study[J]. Lancet Healthy Longev, 2023, 4(11):e618-e628.
[8]	邵瑞太, 宫恩莹, 韩莎莎, 等. 积极应对共病的挑战[J]. 中华医学杂志, 2024, 104(22):2015-2021.
[9]	ALOWAIS S A, ALGHAMDI S S, ALSUHEBANY N, et al. Revolutionizing healthcare:the role of artificial intelligence in clinical practice[J]. BMC Med Educ, 2023, 23(1):689. DOI
[10]	CHOI R Y, COYNER A S, KALPATHY-CRAMER J, et al. Introduction to Machine Learning,Neural Networks,and Deep Learning[J]. Transl Vis Sci Technol, 2020, 9(2):14.
[11]	LIU S, RUSSO C, SUERO MOLINA E, et al. Artificial Intelligence Methods[J]. Adv Exp Med Biol, 2024,1462:21-38.
[12]	田世杰, 张一名. 机器学习算法及其应用综述[J]. 软件, 2023, 44(7):70-75.
[13]	The Official Nvidia Blog. NVIDIA Blog:Supervised Vs.Unsupervised Learning[EB/OL].(2018-08-02)[2025-05-13].https://blogs.nvidia.com/blog/supervised-unsupervised-learning/.
[14]	PANTANOWITZ L, PEARCE T, ABUKHIRAN I, et al. Nongenerative Artificial Intelligence in Medicine:Advancements and Applications in Supervised and Unsupervised Machine Learning[J]. Mod Pathol, 2025, 38(3):100680. DOI URL
[15]	WU S, ROBERTS K, DATTA S, et al. Deep learning in clinical natural language processing:A methodical review[J]. J Am Med Inform Assoc, 2020, 27(3):457-470. DOI URL
[16]	SERGHIOU S, ROUGH K. Deep Learning for Epidemiologists:An Introduction to Neural Networks[J]. Am J Epidemiol, 2023, 192(11):1904-1916. DOI URL
[17]	KRÖNER P T, ENGELS M M, GLICKSBERG B S, et al. Artificial intelligence in gastroenterology:A state-of-the-art review[J]. World J Gastroenterol, 2021, 27(40):6794-6824. DOI URL
[18]	SCHOBER P, VETTER T R. Logistic regression in medical research[J]. Anesth Analg, 2021, 132(2):365-366. DOI PMID
[19]	刘贵浩, 薛允莲, 王晟, 等. 某医院老年住院患者疾病累及系统数及死亡风险评估[J]. 中国医院统计, 2021, 28(2):149-152.
[20]	顾刘金, 陈钢. Cox回归分析及SPSS软件实现[J]. 预防医学, 2024, 36(11):1011-1012.
[21]	PONTIROLI A E, TAGLIABUE E, MADOTTO F, et al. Association of non-cardiac comorbidities and sex with long-term Re-hospitalization for heart failure[J]. Eur J Intern Med, 2025,131:125-132.
[22]	苏小凤. 老年阻塞性睡眠呼吸暂停综合征共病2型糖尿病患者的不良预后风险[D]. 延安: 延安大学, 2022.
[23]	CARROLL K J. On the use and utility of the Weibull model in the analysis of survival data[J]. Control Clin Trials, 2003, 24(6):682-701. PMID
[24]	GASTENS V, CHIOLERO A, ANKER D, et al. Development and validation of a new prognostic index for mortality risk in multimorbid adults[J]. PLoS One, 2022, 17(8):e0271923. DOI URL
[25]	BREIMAN L. Bagging predictors[J]. Machine Learning, 1996,24:123-140.
[26]	FREUND Y. Boosting a weak learning algorithm by majority[J]. Information and Computation, 1995, 121(2):256-285. DOI URL
[27]	SVETNIK V, LIAW A, TONG C, et al. Random forest:a classification and regression tool for compound classification and QSAR modeling[J]. J Chem
	Inf Comput Sci, 2003, 43(6):1947-1958.
[28]	LE LAY J, ALFONSO-LIZARAZO E, AUGUSTO V, et al. Prediction of hospital readmission of multimorbid patients using machine learning models[J]. PLoS One, 2022, 17(12):e0279433. DOI URL
[29]	NATEKIN A, KNOLL A. Gradient boosting machines,a tutorial[J]. Front Neurorobot, 2013,7:21.
[30]	KE G, MENG Q, FINLEY T, et al. LightGBM:A highly efficient gradient boosting decision tree[C]. New York: Curran Associates Inc, 2017.
[31]	陈梦蝶. 数据驱动的慢性疾病风险因素关联分析及再入院预测研究[D]. 成都: 电子科技大学, 2020.
[32]	沈范玲子, 王瑞平. 决策树模型在临床研究数据分析中的应用[J]. 上海医药, 2024, 45(5):14-18.
[33]	LEE E W. Selecting the best prediction model for readmission[J]. J Prev Med Public Health, 2012, 45(4):259-266. DOI PMID
[34]	CHALITSIOS C V, SANTOSO C, NARTEY Y, et al. Trajectories in long-term condition accumulation and mortality in older adults:A group-based trajectory modelling approach using the English Longitudinal Study of Ageing[J]. BMJ Open, 2024, 14(7):e074902. DOI URL
[35]	SHENG J Q, XU D, HU P J, et al. Examining the relationships between patients' multimorbidity trajectories and prognostic outcomes after the initial hip fracture[J]. Sci Rep, 2024, 14(1):28329. DOI
[36]	于石成, 王琦琦, 毛凡, 等. 中断时间序列设计及其分析方法[J]. 中华预防医学杂志, 2019, 53(8):858-864.
[37]	DEVLIN J, CHANG M, LEE K, et al. BERT:Pre-training of deep bidirectional transformers for language understanding:North american chapter of the association for computational linguistics[C]. Minnesota: Association for Computational Linguistics, 2019.
[38]	WAMIL M, HASSAINE A, RAO S, et al. Stratification of diabetes in the context of comorbidities,using representation learning and topological data analysis[J]. Sci Rep, 2023, 13(1):11478. DOI