Predicting health-related social needs in Medicaid and Medicare populations using machine learning.
Predicting health-related social needs in Medicaid and Medicare populations using machine learning.
复制标题
DOI：
10.1038/s41598-022-08344-4
复制
发表时间：
2022-03-16
影响因子：
4.6
通讯作者：
Bernstam EV
中科院分区：
文献类型：
--
作者：
Holcomb J;Oliveira LC;Highfield L;Hwang KO;Giancardo L;Bernstam EV
提供者目前依靠普遍筛查来确定与健康有关的社会需求（HRSNs）。利用电子病历和社区数据预测HRSNs可以提高效率，减少资源消耗。使用机器学习模型，我们评估了参与负责任健康社区模型的医疗保险和医疗补助受益人的EHR和社区层面健康社会决定因素（SDOH）数据中HRSN状态的预测性能。我们假设医疗补助保险可以预测HRSN状态。所有模型的表现都明显优于基线医疗补助假设。auc范围为0.59 ~ 0.68。“任意HRSNs”结果达到了最佳表现（AUC = 0.68 CI 0.66-0.70），这对筛选优先级最有用。社区SDOH特征的预测性能低于EHR特征。机器学习模型可用于筛选患者的优先级。然而，仅筛查我们当前模型识别的患者会错过许多患者。未来的研究有必要优化HRSNs的预测。
Providers currently rely on universal screening to identify health-related social needs (HRSNs). Predicting HRSNs using EHR and community-level data could be more efficient and less resource intensive. Using machine learning models, we evaluated the predictive performance of HRSN status from EHR and community-level social determinants of health (SDOH) data for Medicare and Medicaid beneficiaries participating in the Accountable Health Communities Model. We hypothesized that Medicaid insurance coverage would predict HRSN status. All models significantly outperformed the baseline Medicaid hypothesis. AUCs ranged from 0.59 to 0.68. The top performance (AUC = 0.68 CI 0.66–0.70) was achieved by the “any HRSNs” outcome, which is the most useful for screening prioritization. Community-level SDOH features had lower predictive performance than EHR features. Machine learning models can be used to prioritize patients for screening. However, screening only patients identified by our current model(s) would miss many patients. Future studies are warranted to optimize prediction of HRSNs.
登录
查看更多内容
影响因子：
5.7
作者：
Berkowitz, Seth A.;Baggett, Travis P.;Edwards, Samuel T.
通讯作者：
Edwards, Samuel T.
影响因子：
13.8
作者：
Cottrell EK;Hendricks M;Dambrun K;Cowburn S;Pantell M;Gold R;Gottlieb LM
通讯作者：
Gottlieb LM
影响因子：
3.6
作者：
Chambers EC;McAuliff KE;Heller CG;Fiori K;Hollingsworth N
通讯作者：
Hollingsworth N
影响因子：
12.7
作者：
Fiori, Kevin P.;Heller, Caroline G.;Racine, Andrew
通讯作者：
Racine, Andrew
影响因子：
9.7
作者：
Cantor, Michael N.;Thorpe, Lorna
通讯作者：
Thorpe, Lorna