|
|
|
| Health literacy prediction models based on machine learning methods: a scoping review |
| PAN Xiang, TONG Yingge, LI Yixuan, NI Ke, CHENG Wenqian, XIN Mengyu, HU Yuying
|
| School of Nursing, Hangzhou Normal University, Hangzhou, Zhejiang 311121, China |
|
|
|
|
Abstract Objective To conduct a scoping review on the types, construction methods and predictive performance of health literacy prediction models based on machine learning methods, so as to provide the reference for the improvement and application of such models. Methods Publications on health literacy prediction models conducted using machine learning methods were retrieved from CNKI, Wanfang Data, VIP, PubMed and Web of Science from inception to May 1, 2024. The quality of literature was assessed using the Prediction Model Risk of Bias ASsessment Tool. Basic characteristics, modeling methods, data sources, missing value handling, predictors and predictive performance were reviewed. Results A total of 524 publications were retrieved, and 22 publications between 2007 and 2024 were finally enrolled. Totally 48 health literacy prediction models were involved, and 25 had a high risk of bias (52.08%), with major issues focusing on missing value handling, predictor selection and model evaluation methods. Modeling methods included regression models, tree-based machine learning methods, support vector machines and neural network models. Predictors primarily encompassed factors at four aspects: individual, interpersonal, organizational and society/policy aspects, with age, educational level, economic status, health status and internet use appearing frequently. Internal validation was conducted in 14 publications, and external validation was conducted in 4 publications. Forty-two models reported the areas under the receiver operating characteristic curve, which ranged from 0.52 to 0.983, indicating good discrimination. Conclusion Health literacy prediction models based on machine learning methods perform well, but have deficiencies in risk of bias, data processing and validation.
|
|
Received: 27 June 2024
Revised: 01 November 2024
Published: 13 February 2025
|
|
|
|
|
|
[1] 中华人民共和国国家卫生健康委员会.2023年全国居民健康素养水平提高到29.70%[EB/OL].[2024-11-01].http://www.nhc.gov.cn/xcs/s3582/202404/287e15ca9fd148b5ab9debce59f58c6d.shtml.
[2] 闫晓彤,徐越,姚丁铭,等.2016—2021年浙江省农村居民健康素养分析[J].预防医学,2022,34(10):1053-1058.
YAN X T,XU Y,YAO D M,et al.Health literacy among rural residents in Zhejiang Province from 2016 to 2021[J].China Prev Med J,2022,34(10):1053-1058.(in Chinese)
[3] LUO W,NGUYEN T,NICHOLS M,et al.Is demography destiny? Application of machine learning techniques to accurately predict population health outcomes from a minimal demographic dataset[J/OL].PLoS One,2015,10(5)[2024-11-01].https://doi.org/10.1371/journal.pone.0125602.
[4] FLAXMAN A D,VOS T.Machine learning in population health:Opportunities and threats[J/OL].PLoS Med,2018,15(11)[2024-11-01].https://doi.org/10.1371/journal.pmed.1002702.
[5] TRICCO A C,LILLIE E,ZARIN W,et al.PRISMA extension for scoping reviews(PRISMA-ScR):checklist and explanation[J].Ann Intern Med,2018,169(7):467-473.
[6] 陈茹,王胜锋,周家琛,等.预测模型研究的偏倚风险和适用性评估工具解读[J].中华流行病学杂志,2020,41(5):776-781.
CHEN R,WANG S F,ZHOU J C,et al.Introduction of the Prediction model Risk Of Bias ASsessment Tool:a tool to assess risk of bias and applicability of prediction model studies[J].Chin J Epidemiol,2020,41(5):776-781.(in Chinese)
[7] ZHOU R S,YIN W H,LI W J,et al.Prediction model for infectious disease health literacy based on synthetic minority oversampling technique algorithm[J/OL].Comput Math Methods Med,2022[2024-11-01].https://doi.org/10.1155/2022/8498159.
[8] İNCEOĞLU F,DENIZ S,YAGIN F H.Prediction of effective sociodemographic variables in modeling health literacy:a machine learning approach[J/OL].Int J Med Inform,2023[2024-11-01].https://doi.org/10.1016/j.ijmedinf.2023.105167.
[9] XIE T,ZHANG N,MAO Y,et al.How to predict the electronic health literacy of Chinese primary and secondary school students?:establishment of a model and web nomograms[J/OL].BMC Public Health,2022,22[2024-11-01].https://doi.org/10.1186/s12889-022-13421-4.
[10] HONG Y,ZHANG X D,CHEN J X.XGBoost-based prediction modelling and analysis for health literacy assessment[J].Int J Model Identif Control,2021,39(3):229-235.
[11] 季娜,贾宝琪,崔莲花.基于logistic回归及决策树模型的大学生健康素养影响因素分析[J].预防医学论坛,2023,29(12):881-886.
JI N,JIA B Q,CUI L H.Analysis on influencing factors of college students' health literacy based on logistic regression and decision tree model[J].Prev Med Trib,2023,29(12):881-886.(in Chinese)
[12] 李现文,李春玉,KIM M Y,等.决策树与Logistic回归在高血压患者健康素养预测中的应用[J].护士进修杂志,2012,27(13):1157-1159.
LI X W,LI C Y,KIM M Y,et al.Application of decision tree and logistic regression on the health literacy prediction of hypertension patients[J].J Nurses Train,2012,27(13):1157-1159.(in Chinese)
[13] 林丰,林彩红,叶少英,等.基于逐步Logistic回归和神经网络模型的健康素养预测及对比研究[J].中国健康教育,2018,34(8):699-702.
LIN F,LIN C H,YE S Y,et al.Comparison on health literacy prediction between stepwise logistic regression and neural network model[J].Chin J Health Educ,2018,34(8):699-702.(in Chinese)
[14] 王可,赵华硕,张虹,等.基于SMOTE算法与机器学习的老年人健康素养预测研究[J].中国校医,2019,33(9):641-643.
WANG K,ZHAO H S,ZHANG H,et al.Prediction of health literacy of the elderly based on SMOTE algorithm and machine learning[J].Chin J School Doctor,2019,33(9):641-643.(in Chinese)
[15] HOU W H,KUO K N,CHEN M J,et al.Simple scoring algorithm to identify community-dwelling older adults with limited health literacy:a cross-sectional study in Taiwan[J/OL].BMJ Open,2021,11[2024-11-01].https://doi.org/10.1136/bmjopen-2020-045411.
[16] ZHANG Q H,YIN J Y,WANG Y J,et al.A nomogram for predicting the infectious disease-specific health literacy of older adults in China.[J].Asian Nurs Res,2024,18(2):106-113.
[17] VAN DER HEIDE I,UITERS E,SØRENSEN K,et al.Health literacy in Europe:the development and validation of health literacy prediction models[J].Eur J Public Health,2016,26(6):906-911.
[18] LUBIMIR K T.Developing a predictive model for measuring health literacy in Hawaii's adult populations[D].Hawaii:University of Hawaii,2017.
[19] MARTIN L T,RUDER T,ESCARCE J J,et al.Developing predictive models of health literacy[J].J Gen Intern Med,2009,24(11):1211-1216.
[20] MILLER M J,DEGENHOLTZ H B,GAZMARMARIAN J A,et al.Identifying elderly at greatest risk of inadequate health literacy:a predictive model for population-health decision makers[J].Res Social Adm Pharm,2007,3(1):70-85.
[21] LAURSEN K R,SEED P T,PROTHEROE J,et al.Developing a method to derive indicative health literacy from routine socio-demographic data[J].J Healthc Commun,2015,1(1):1-9.
[22] HANCHATE A D,ASH A S,GAZMARARIAN J A,et al.The Demographic Assessment for Health Literacy(DAHL):a new tool for estimating associations between health literacy and outcomes in national surveys[J].J Gen Intern Med,2008,23(10):1561-1566.
[23] 陈思婷,马艺菲,卓琳,等.苏北某市居民传染病健康素养水平与影响因素分析[J].现代预防医学,2020,47(23):4307-4311.
CHEN S T,MA Y F,ZHUO L,et al.The level of infectious disease health literacy and its influencing factors among residents in a city in northern Jiangsu province[J].Mod Prev Med,2020,47(23):4307-4311.(in Chinese)
[24] LURIE N,MARTIN L T,RUDER T,et al.Estimating and mapping health literacy in the State of Missouri[M].Santa Monica:RAND Corporation,2010.
[25] CAMPBELL P,LEWIS M,CHEN Y,et al.Can patients with low health literacy be identified from routine primary care health records? A cross-sectional and prospective analysis[J].BMC Fam Pract,2019,20(1):1-11.
[26] ROWLANDS G,WHITNEY D,MOON G.Developing and applying geographical synthetic estimates of health literacy in GP clinical systems[J/OL].Int J Environ Res Public Health,2018,15(8)[2024-11-01].https://doi.org/10.3390/ijerph15081709.
[27] LEUNG A Y M,YU E Y T,LUK J K H,et al.Rapid Estimate of Inadequate Health Literacy(REIHL):development and validation of a practitioner-friendly health literacy screening tool for older adults[J].Hong Kong Med J,2020,26(5):404-412.
[28] JEPPESEN K M,COYLE J D,MISER W F.Screening questions to predict limited health literacy:a cross-sectional study of patients with diabetes mellitus[J].Ann Fam Med,2009,7(1):24-31.
[29] GOLDSTEIN B A,NAVAR A M,PENCINA M J,et al.Opportunities and challenges in developing risk prediction models with electronic health records data:a systematic review[J].J Am Med Inform Assoc,2017,24(1):198-208. |
|
|
|
