A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study.
A predictive model for hospitalization and survival to COVID-19 in a retrospective population-based study.
复制标题
DOI：
10.1038/s41598-022-22547-9
复制
发表时间：
2022-10-28
影响因子：
4.6
通讯作者：
中科院分区：
文献类型：
--
作者：
开发工具，根据易于获取的数据，在最少使用诊断测试的情况下对COVID-19患者进行早期分诊，这对于降低高发病率情况下的COVID-19死亡率至关重要。本研究提出了一种机器学习模型，利用从86,867例COVID-19患者电子病历中获得的2个简单人口统计学特征和19个合并症来预测死亡率和住院风险，并提出了一种新的方法（LR-IPIP）来处理数据不平衡问题。该模型对患者最终状态（死亡或出院）的预测准确率较高（90-93%,ROC-AUC = 0.94），而对住院风险的预测准确率为中等（71-73%,ROC-AUC = 0.75）。这些模型最相关的特征是年龄、性别、合并症数量、骨关节炎、肥胖、抑郁和肾衰竭。最后，为了方便临床医生使用，我们开发了一个用户友好的网站（https://alejandrocisterna.shinyapps.io/PROVIA）。
The development of tools that provide early triage of COVID-19 patients with minimal use of diagnostic tests, based on easily accessible data, can be of vital importance in reducing COVID-19 mortality rates during high-incidence scenarios. This work proposes a machine learning model to predict mortality and risk of hospitalization using both 2 simple demographic features and 19 comorbidities obtained from 86,867 electronic medical records of COVID-19 patients, and a new method (LR-IPIP) designed to deal with data imbalance problems. The model was able to predict with high accuracy (90–93%, ROC-AUC = 0.94) the patient's final status (deceased or discharged), while its accuracy was medium (71–73%, ROC-AUC = 0.75) with respect to the risk of hospitalization. The most relevant characteristics for these models were age, sex, number of comorbidities, osteoarthritis, obesity, depression, and renal failure. Finally, to facilitate its use by clinicians, a user-friendly website has been developed (https://alejandrocisterna.shinyapps.io/PROVIA).
登录
查看更多内容
影响因子：
7.4
作者：
Ikemura K;Bellin E;Yagi Y;Billett H;Saada M;Simone K;Stahl L;Szymanski J;Goldstein DY;Reyes Gil M
通讯作者：
Reyes Gil M
影响因子：
3.7
作者：
Nguyen NT;Chinn J;De Ferrante M;Kirby KA;Hohmann SF;Amin A
通讯作者：
Amin A
影响因子：
1.5
作者：
Mannucci E;Silverii GA;Monami M
通讯作者：
Monami M
影响因子：
33.9
作者：
Killerby, Marie E.;Link-Gelles, Ruth;Tate, Jacqueline E.
通讯作者：
Tate, Jacqueline E.
影响因子：
3.7
作者：
Chatterjee A;Wu G;Primakov S;Oberije C;Woodruff H;Kubben P;Henry R;Aries MJH;Beudel M;Noordzij PG;Dormans T;Gritters van den Oever NC;van den Bergh JP;Wyers CE;Simsek S;Douma R;Reidinga AC;de Kruif MD;Guiot J;Frix AN;Louis R;Moutschen M;Lovinfosse P;Lambin P
通讯作者：
Lambin P