Predicting prognosis in COVID-19 patients using machine learning and readily available clinical data.
Predicting prognosis in COVID-19 patients using machine learning and readily available clinical data.
复制标题
DOI：
10.1016/j.ijmedinf.2021.104594
复制
发表时间：
2021-11
影响因子：
4.9
通讯作者：
Erlandson KM
中科院分区：
文献类型：
--
作者：
Campbell TW;Wilson MP;Roder H;MaWhinney S;Georgantas RW 3rd;Maguire LK;Roder J;Erlandson KM
用于帮助治疗住院的 COVID-19 患者的预后工具可以通过识别患有较高或较低严重疾病风险的患者来帮助改善结果。研究目的是开发模型，利用入院时现成的信息，根据 COVID-19 住院期间严重后果的风险对患者进行分层。对 229 名因 COVID-19 住院的患者训练了分层集成分类模型，以预测严重后果，包括 ICU 入院、急性呼吸窘迫综合征的发展或插管，使用易于获得的属性，包括基本患者特征、入院时的生命体征以及在就诊时收集的基本实验室结果。每项测试都将患者分为风险逐渐增加的组。另外一个由 330 名患者组成的队列被用于进行盲法独立验证。沙普利值分析评估了哪些属性对模型风险预测贡献最大。使用最终风险组的精确度（阳性预测值）和召回率（敏感性）评估测试表现。所有测试截止值在盲法验证之前均已确定。在开发和验证过程中，最低风险组的测试精度达到接近或高于 0.9。在风险增加的人群中，出现严重后果的患者比例显着增加。虽然属性的重要性因测试和患者而异，但 C 反应蛋白、乳酸脱氢酶和 D-二聚体通常被发现在风险分配中很重要。可以根据入院时常规收集的属性，使用基于机器学习的模型来评估因感染 COVID-19 住院的患者出现严重后果的风险。
Prognostic tools for aiding in the treatment of hospitalized COVID-19 patients could help improve outcome by identifying patients at higher or lower risk of severe disease. The study objective was to develop models to stratify patients by risk of severe outcomes during COVID-19 hospitalization using readily available information at hospital admission. Hierarchical ensemble classification models were trained on a set of 229 patients hospitalized with COVID-19 to predict severe outcomes, including ICU admission, development of acute respiratory distress syndrome, or intubation, using easily attainable attributes including basic patient characteristics, vital signs at admission, and basic lab results collected at time of presentation. Each test stratifies patients into groups of increasing risk. An additional cohort of 330 patients was used for blinded, independent validation. Shapley value analysis evaluated which attributes contributed most to the models’ predictions of risk. Test performance was assessed using precision (positive predictive value) and recall (sensitivity) of the final risk groups. All test cut-offs were fixed prior to blinded validation. In development and validation, the tests achieved precision in the lowest risk groups near or above 0.9. The proportion of patients with severe outcomes significantly increased across increasing risk groups. While the importance of attributes varied by test and patient, C-reactive protein, lactate dehydrogenase, and D-dimer were often found to be important in the assignment of risk. Risk of severe outcomes for patients hospitalized with COVID-19 infection can be assessed using machine learning-based models based on attributes routinely collected at hospital admission.
登录
查看更多内容
影响因子：
14.2
作者：
Cheng, B.;Hu, J.;Deng, A.
通讯作者：
Deng, A.
影响因子：
11.8
作者：
Louie, Janice K.;Acosta, Meileen;Matyas, Bela T.
通讯作者：
Matyas, Bela T.
影响因子：
16.6
作者：
Feng Z;Yu Q;Yao S;Luo L;Zhou W;Mao X;Li J;Duan J;Yan Z;Yang M;Tan H;Ma M;Li T;Yi D;Mi Z;Zhao H;Jiang Y;He Z;Li H;Nie W;Liu Y;Zhao J;Luo M;Liu X;Rong P;Wang W
通讯作者：
Wang W
影响因子：
13.8
作者：
Ioannou GN;Locke E;Green P;Berry K;O'Hare AM;Shah JA;Crothers K;Eastment MC;Dominitz JA;Fan VS
通讯作者：
Fan VS
影响因子：
5.7
作者：
Morais AHA;Passos TS;de Lima Vale SH;da Silva Maia JK;Maciel BLL
通讯作者：
Maciel BLL