Tong Yao, Messinger Amanda I, Wilcox Adam B, Mooney Sean D, Davidson Giana H, Suri Pradeep, Luo Gang
Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States.
The Breathing Institute, Department of Pediatrics, University of Colorado School of Medicine, Children's Hospital Colorado, Aurora, CO, United States.
J Med Internet Res. 2021 Apr 16;23(4):e22796. doi: 10.2196/22796.
Asthma affects a large proportion of the population and leads to many hospital encounters involving both hospitalizations and emergency department visits every year. To lower the number of such encounters, many health care systems and health plans deploy predictive models to prospectively identify patients at high risk and offer them care management services for preventive care. However, the previous models do not have sufficient accuracy for serving this purpose well. Embracing the modeling strategy of examining many candidate features, we built a new machine learning model to forecast future asthma hospital encounters of patients with asthma at Intermountain Healthcare, a nonacademic health care system. This model is more accurate than the previously published models. However, it is unclear how well our modeling strategy generalizes to academic health care systems, whose patient composition differs from that of Intermountain Healthcare.
This study aims to evaluate the generalizability of our modeling strategy to the University of Washington Medicine (UWM), an academic health care system.
All adult patients with asthma who visited UWM facilities between 2011 and 2018 served as the patient cohort. We considered 234 candidate features. Through a secondary analysis of 82,888 UWM data instances from 2011 to 2018, we built a machine learning model to forecast asthma hospital encounters of patients with asthma in the subsequent 12 months.
Our UWM model yielded an area under the receiver operating characteristic curve (AUC) of 0.902. When placing the cutoff point for making binary classification at the top 10% (1464/14,644) of patients with asthma with the largest forecasted risk, our UWM model yielded an accuracy of 90.6% (13,268/14,644), a sensitivity of 70.2% (153/218), and a specificity of 90.91% (13,115/14,426).
Our modeling strategy showed excellent generalizability to the UWM, leading to a model with an AUC that is higher than all of the AUCs previously reported in the literature for forecasting asthma hospital encounters. After further optimization, our model could be used to facilitate the efficient and effective allocation of asthma care management resources to improve outcomes.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/resprot.5039.
哮喘影响着很大一部分人口，每年导致大量涉及住院和急诊科就诊的医院接触。为了减少此类接触的数量，许多医疗保健系统和健康计划部署了预测模型，以前瞻性地识别高危患者，并为他们提供预防保健的护理管理服务。然而，以前的模型在很好地实现这一目的方面没有足够的准确性。采用检查许多候选特征的建模策略，我们构建了一个新的机器学习模型，以预测山间医疗保健公司（一个非学术性医疗保健系统）中哮喘患者未来的哮喘医院接触情况。该模型比以前发表的模型更准确。然而，尚不清楚我们的建模策略在学术性医疗保健系统中的泛化程度如何，学术性医疗保健系统的患者构成与山间医疗保健公司不同。
本研究旨在评估我们的建模策略对华盛顿大学医学中心（UWM，一个学术性医疗保健系统）的泛化性。
2011年至2018年间访问UWM设施的所有成年哮喘患者作为患者队列。我们考虑了234个候选特征。通过对2011年至2018年的82888个UWM数据实例进行二次分析，我们构建了一个机器学习模型，以预测哮喘患者在随后12个月内的哮喘医院接触情况。
我们的UWM模型在受试者工作特征曲线（AUC）下的面积为0.902。当将二元分类的截止点设置为预测风险最大的哮喘患者中的前10%（1464/14644）时，我们的UWM模型的准确率为90.6%（13268/14644），敏感性为70.2%（153/218），特异性为90.91%（13115/14426）。
我们的建模策略对UWM显示出极好的泛化性，产生了一个AUC高于文献中先前报道的所有预测哮喘医院接触情况的AUC的模型。经过进一步优化，我们的模型可用于促进哮喘护理管理资源的高效有效分配，以改善结果。
国际注册报告识别码（IRRID）：RR2-10.2196/resprot.5039。
