临床预测模型的困境与机遇

doi:10.3969/j.issn.1673-5765.2024.05.001

摘要/Abstract

摘要： 临床预测模型可基于从群体获得的效应证据去预测个体的结局或风险，是链接循证医学和精准医学的强有力工具。随着数据测量、存储、互联互通及分析技术的不断进步，临床预测模型的应用前景将越来越明朗，但与此同时，也面临着诸多问题和挑战。本文对临床预测模型的基础概念、应用场景以及现在面临的困境和发展机遇做一个梳理。

关键词: 临床预测模型; 大数据; 机器学习

Abstract: Clinical prediction models can predict individual outcomes or risks based on effect evidence obtained from the population, serving as a powerful tool linking evidence-based medicine and precision medicine. With the continuous advancement of data measurement, storage, interoperability, and analytical techniques, the application prospect for clinical prediction models is becoming increasingly clear. However, it also faces many problems and challenges. This paper aims to provide an overview of the fundamental concepts, application scenarios, current dilemmas, and development opportunities of clinical prediction models.

Key words: Clinical prediction model; Big data; Machine learning

中图分类号:

谷鸿秋. 临床预测模型的困境与机遇[J]. 中国卒中杂志, 2024, 19(5): 481-487.

GU Hongqiu. Challenges and Opportunities in Clinical Prediction Models[J]. Chinese Journal of Stroke, 2024, 19(5): 481-487.

参考文献

[1] LAUPACIS A，SEKAR N，STIELL I G. Clinical prediction rules. A review and suggested modifications of methodological standards[J]. JAMA，1997，277（6）：488-494.
[2] INGUI B J，ROGERS M A. Searching for clinical prediction rules in MEDLINE[J]. J Am Med Inf Assoc，2001，8（4）：391-397.
[3] TOLL D B，JANSSEN K J M，VERGOUWE Y，et al. Validation，updating and impact of clinical prediction rules：a review[J]. J Clin Epidemiol，2008，61（11）：1085-1094.
[4] ADAMS S T，LEVESON S H. Clinical prediction rules[J/OL]. BMJ，2012，344：d8312[2024-04-20]. https://doi.org/10.1136/bmj.d8312.
[5] MOONS K G M，KENGNE A P，GROBBEE D E，et al. Risk prediction models：Ⅱ. External validation，model updating，and impact assessment[J]. Heart，2012，98（9）：691-698.
[6] MOONS K G M，KENGNE A P，WOODWARD M，et al. Risk prediction models：Ⅰ. Development，internal validation，and assessing the incremental value of a new（bio）marker[J]. Heart，2012，98（9）：683-690.
[7] PENCINA M J，D’AGOSTINO R B，Sr. Evaluating discrimination of risk prediction models：the C statistic[J]. JAMA，2015，314（10）：1063-1064.
[8] BONNETT L J，SNELL K I E，COLLINS G S，et al. Guide to presenting clinical prediction models for use in clinical settings[J/OL]. BMJ，2019，365：l737[2024-04-20]. https://doi.org/10.1136/bmj.l737.
[9] D’AGOSTINO R B，Sr，VASAN R S，PENCINA M J，et al. General cardiovascular risk profile for use in primary care：the Framingham heart study[J]. Circulation，2008，117（6）：743-753.
[10] SCHNABEL R B，SULLIVAN L M，LEVY D，et al. Development of a risk score for atrial fibrillation（Framingham heart study）：a community-based cohort study[J]. Lancet，2009，373（9665）：739-745.
[11] SCHNABEL R B，RIENSTRA M，SULLIVAN L M，et al. Risk assessment for incident heart failure in individuals with atrial fibrillation[J]. Eur J Heart Fail，2013，15（8）：843-849.
[12] WILSON P W，D’AGOSTINO R B，LEVY D，et al. Prediction of coronary heart disease using risk factor categories[J]. Circulation，1998，97（18）：1837-1847.
[13] BRUNINX A，SCHEENSTRA B，DEKKER A，et al. Using clinical prediction models to personalise lifestyle interventions for cardiovascular disease prevention：a systematic literature review[J/OL]. Prev Med Rep，2022，25：101672[2024-04-20]. https://doi.org/10.1016/j.pmedr.2021.101672.
[14] WELLS P S，ANDERSON D R，BORMANIS J，et al. Value of assessment of pretest probability of deep-vein thrombosis in clinical management[J]. Lancet，1997，350（9094）：1795-1798.
[15] WELLS P S，HIRSH J，ANDERSON D R，et al. Accuracy of clinical assessment of deep-vein thrombosis[J]. Lancet，1995，345（8961）：1326-1330.
[16] WELLS P S，ANDERSON D R，RODGER M，et al. Evaluation of D-dimer in the diagnosis of suspected deep-vein thrombosis[J]. New Engl J Med，2003，349（13）：1227-1235.
[17] WELLS P S，ANDERSON D R，RODGER M，et al. Excluding pulmonary embolism at the bedside without diagnostic imaging：management of patients with suspected pulmonary embolism presenting to the emergency department by using a simple clinical model and D-dimer[J]. Ann Intern Med，2001，135（2）：98-107.
[18] LIP G Y H，NIEUWLAAT R，PISTERS R，et al. Refining clinical risk stratification for predicting stroke and thromboembolism in atrial fibrillation using a novel risk factor-based approach：the euro heart survey on atrial fibrillation[J]. Chest，2010，137（2）：263-272.
[19] JOHNSTON S C，ROTHWELL P M，NGUYEN-HUYNH M N，et al. Validation and refinement of scores to predict very early stroke risk after transient ischaemic attack[J]. Lancet，2007，369（9558）：283-292.
[20] WANG Y J，WANG Y L，ZHAO X Q，et al. Clopidogrel with aspirin in acute minor stroke or transient ischemic attack[J]. New Engl J Med，2013，369（1）：11-19.
[21] POWERS W J，RABINSTEIN A A，ACKERSON T，et al. Guidelines for the early management of patients with acute ischemic stroke：2019 update to the 2018 guidelines for the early management of acute ischemic stroke：a guideline for healthcare professionals from the American Heart Association/American
Stroke Association[J/OL]. Stroke，2019，50（12）：e344-e418[2024-04-20]. https://doi.org/10.1161/STR.0000000000000211.
[22] LIU L P，CHEN W Q，ZHOU H Y，et al. Chinese Stroke Association guidelines for clinical management of cerebrovascular disorders：executive summary and 2019 update of clinical management of ischaemic cerebrovascular diseases[J]. Stroke Vasc Neurol，2020，5（2）：159-176.
[23] EMA. PROCOVA™ handbook for the target trial statistician[Z/OL]. [2024-04-20]. https://assets-global.website-files.com/63e2be5ef66a6915fab72f78/656fd06d6f50e4b4448aa70b_Unlearn_PROCOVA-Handbook.pdf.
[24] ELZE M C，GREGSON J，BABER U，et al. Comparison of propensity score methods and covariate adjustment：evaluation in 4 cardiovascular studies[J]. J Am Coll Cardiol，2017，69（3）：345-357.
[25] MCGORRIAN C，YUSUF S，ISLAM S，et al. Estimating modifiable coronary heart disease risk in multiple regions of the world：the INTERHEART modifiable risk score[J]. Eur Heart J，2011，32（5）：581-589.
[26] TADROUS M，GAGNE J J，STÜRMER T，et al. Disease risk score as a confounder summary method：systematic review and recommendations[J]. Pharmacoepidemiol Drug Saf，2013，22（2）：122-129.
[27] DAHABREH I J，KAZI D S. Toward personalizing care：assessing heterogeneity of treatment effects in randomized trials[J]. JAMA，2023，329（13）：1063-1065.
[28] GOLIGHER E C，LAWLER P R，JENSEN T P，et al. Heterogeneous treatment effects of therapeutic-dose heparin in patients hospitalized for COVID-19[J]. JAMA，2023，329（13）：1066-1077.
[29] SLIEKER R C，VAN DER HEIJDEN A A W A，SIDDIQUI M K，et al. Performance of prediction models for nephropathy in people with type 2 diabetes：systematic review and external validation study[J/OL]. BMJ，2021，374：n2134[2024-04-20]. https://doi.org/10.1136/bmj.n2134.
[30] FREEMAN K，DINNES J，CHUCHU N，et al. Algorithm based smartphone apps to assess risk of skin cancer in adults：systematic review of diagnostic accuracy studies[J/OL]. BMJ，2020，368：m127[2024-04-20]. https://doi.org/10.1136/bmj.m127.
[31] DAMEN J A A G，HOOFT L，SCHUIT E，et al. Prediction models for cardiovascular disease risk in the general population：systematic review[J/OL]. BMJ，2016，353：i2416[2024-04-20]. https://doi.org/10.1136/bmj.i2416.
[32] BELLOU V，BELBASIS L，KONSTANTINIDIS A K，et al. Prognostic models for outcome prediction in patients with chronic obstructive pulmonary disease：systematic review and critical appraisal[J/OL]. BMJ，2019，367：l5358[2024-04-20]. https://doi.org/10.1136/bmj.l5358.
[33] WYNANTS L，VAN CALSTER B，COLLINS G S，et al. Prediction models for diagnosis and prognosis of COVID-19 infection：systematic review and critical appraisal[J/OL]. BMJ，2020，369：m1328[2024-04-20]. https://doi.org/10.1136/bmj.m1328.
[34] SIONTIS G C M，TZOULAKI I，CASTALDI P J，et al. External validation of new risk prediction models is infrequent and reveals worse prognostic discrimination[J]. J Clin Epidemiol，2015，68（1）：25-34.
[35] VOLLMER S，MATEEN B A，BOHNER G，et al. Machine learning and artificial intelligence research for patient benefit：20 critical questions on transparency，replicability，ethics，and effectiveness[J/OL]. BMJ，2020，368：l6927[2024-04-20]. https://doi.org/10.1136/bmj.l6927.
[36] WOLFF R F，MOONS K G M，RILEY R D，et al. PROBAST：a tool to assess the risk of bias and applicability of prediction model studies[J]. Ann Intern Med，2019，170（1）：51-58.
[37] COLLINS G S，REITSMA J B，ALTMAN D G，et al. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis（TRIPOD）：the TRIPOD statement[J]. Ann Intern Med，2015，162（1）：55-63.
[38] COLLINS G S，MOONS K G M，DHIMAN P，et al. TRIPOD+AI statement：updated guidance for reporting clinical prediction models that use regression or machine learning methods[J/OL]. BMJ，2024，385：e078378[2024-04-20]. https://doi.org/10.1136/bmj-2023-078378.
[39] JENKINS D A，MARTIN G P，SPERRIN M，et al. Continual updating and monitoring of clinical prediction models：time for dynamic prediction systems?[J/OL]. Diagn Progn Res，2021，5（1）：1[2024-04-20]. https://doi.org/10.1186/s41512-020-00090-3.