Predicting missed health care visits during the COVID-19 pandemic using machine learning methods: evidence from 55,500 individuals from 28 European countries.
Predicting missed health care visits during the COVID-19 pandemic using machine learning methods: evidence from 55,500 individuals from 28 European countries.
复制标题
DOI：
10.1186/s12913-023-09473-w
复制
发表时间：
2023-05-25
影响因子：
2.8
通讯作者：
Sudharsanan, Nikkil
中科院分区：
文献类型：
--
作者：
Reuter, Anna;Smolic, Sime;Baernighausen, Till;Sudharsanan, Nikkil
COVID-19大流行等流行病和其他严重的医疗保健中断危及个人错过基本护理。机器学习模型可以预测哪些患者错过护理访问的风险最大，可以帮助卫生管理人员优先考虑最需要的患者。这种办法对于有效地针对紧急状态期间负担过重的保健系统采取干预措施可能特别有用。我们使用了欧洲健康、老龄化和退休调查（SHARE）COVID-19调查（2020年6月至8月和2021年6月至8月）中超过55，500名受访者错过医疗保健访问的数据，以及第1-8波（2004年4月至2020年3月）的纵向数据。我们比较了四种机器学习算法（逐步选择，套索，随机森林和神经网络）的性能，以根据大多数医疗保健提供者可用的常见患者特征预测第一次COVID-19调查期间错过的医疗保健访问。我们通过采用5重交叉验证测试了所选模型对第一次COVID-19调查的预测准确性、灵敏度和特异性，并通过将其应用于第二次COVID-19调查的数据来测试模型的样本外性能。在我们的样本中，15. 5%的受访者报告因COVID-19疫情而错过了任何基本医疗服务。所有四种机器学习方法在预测能力方面表现相似。所有模型的曲线下面积（AUC）约为0.61，优于随机预测。一年后第二波COVID-19疫情的数据也保持了这一表现，男性的AUC为0.59，女性为0.61。当将预测风险为0.135（0.170）或更高的所有男性（女性）分类为有错过护理的风险时，神经网络模型正确识别了59%（58%）的错过护理访问的个人和57%（58%）的没有错过护理访问的个人。由于模型的敏感性和特异性与用于对个体进行分类的风险阈值密切相关，因此可以根据用户的资源限制和目标定位方法来校准模型。COVID-19等大流行病需要快速有效的应对措施，以减少对医疗保健的干扰。基于健康管理人员或保险提供商可用的特征，简单的机器学习算法可以用于有效地定位工作，以减少错过的基本护理。在线版本包含补充材料，可通过10.1186/s12913-023-09473-w获取。
Pandemics such as the COVID-19 pandemic and other severe health care disruptions endanger individuals to miss essential care. Machine learning models that predict which patients are at greatest risk of missing care visits can help health administrators prioritize retentions efforts towards patients with the most need. Such approaches may be especially useful for efficiently targeting interventions for health systems overburdened during states of emergency. We use data on missed health care visits from over 55,500 respondents of the Survey of Health, Ageing and Retirement in Europe (SHARE) COVID-19 surveys (June – August 2020 and June – August 2021) with longitudinal data from waves 1–8 (April 2004 – March 2020). We compare the performance of four machine learning algorithms (stepwise selection, lasso, random forest, and neural networks) to predict missed health care visits during the first COVID-19 survey based on common patient characteristics available to most health care providers. We test the prediction accuracy, sensitivity, and specificity of the selected models for the first COVID-19 survey by employing 5-fold cross-validation, and test the out-of-sample performance of the models by applying them to the data from the second COVID-19 survey. Within our sample, 15.5% of the respondents reported any missed essential health care visit due to the COVID-19 pandemic. All four machine learning methods perform similarly in their predictive power. All models have an area under the curve (AUC) of around 0.61, outperforming random prediction. This performance is sustained for data from the second COVID-19 wave one year later, with an AUC of 0.59 for men and 0.61 for women. When classifying all men (women) with a predicted risk of 0.135 (0.170) or higher as being at risk of missing care, the neural network model correctly identifies 59% (58%) of the individuals with missed care visits, and 57% (58%) of the individuals without missed care visits. As the sensitivity and specificity of the models are strongly related to the risk threshold used to classify individuals, the models can be calibrated depending on users’ resource constraints and targeting approach. Pandemics such as COVID-19 require rapid and efficient responses to reduce disruptions in health care. Based on characteristics available to health administrators or insurance providers, simple machine learning algorithms can be used to efficiently target efforts to reduce missed essential care. The online version contains supplementary material available at 10.1186/s12913-023-09473-w.
登录
查看更多内容
影响因子：
8.3
作者：
Cannata A;Watson SA;Daniel A;Giacca M;Shah AM;McDonagh TA;Scott PA;Bromage DI
通讯作者：
Bromage DI
影响因子：
4.8
作者：
Incze, Eduard;Holborn, Penny;Ware, Andrew
通讯作者：
Ware, Andrew
影响因子：
30.8
作者：
Mansfield, Kathryn E.;Mathur, Rohini;Langan, Sinead M.
通讯作者：
Langan, Sinead M.
监测 COVID-19 大流行对英国心血管疾病服务的间接影响。
DOI：
10.1136/heartjnl-2020-317870
发表时间：
2020-12
期刊：
Heart (British Cardiac Society)
影响因子：
--
作者：
Ball S;Banerjee A;Berry C;Boyle JR;Bray B;Bradlow W;Chaudhry A;Crawley R;Danesh J;Denniston A;Falter F;Figueroa JD;Hall C;Hemingway H;Jefferson E;Johnson T;King G;Lee KK;McKean P;Mason S;Mills NL;Pearson E;Pirmohamed M;Poon MTC;Priedon R;Shah A;Sofat R;Sterne JAC;Strachan FE;Sudlow CLM;Szarka Z;Whiteley W;Wyatt M;CVD-COVID-UK Consortium
通讯作者：
CVD-COVID-UK Consortium
影响因子：
13.8
作者：
Anderson KE;McGinty EE;Presskreischer R;Barry CL
通讯作者：
Barry CL