Machine Learning Models Using Hospital Admission Characteristics Do Not Optimally Predict Nosocomial Infection Development in a Global Cirrhosis Cohort.
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Silvey Scott, Choudhury Ashok K, Kamath Patrick S, Xie Qing, Wong Florence, Hayes Peter C, Seto Wai-Kay, Arora Umang, Singhal Garima, Jothimani Dinesh, Asrani Sumeet, Gadano Adrian, Dincer Dinc, Farias Alberto Queiroz, Adebayo Daneille, Velarde-Ruiz Velasco José Antonio, Doyle Adam, Kulkarni Anand V, Debzi Nabil, Shaw Jawaid, Barutcu Sezgin, Desalgn Hailemicheal, Bettinger Dominik, Regis Lah Ponan Claude, Duarte-Rojo Andres, Turan Dilara, Wang Lei, Velazquez Rene Male, Zheng Xin, Aghayaeva Sevda, Karasu Zeki, Demirtas Coskun, Liu Chenghai, Cordova-Gallardo Jacqueline, Xu Bin, Nagral Aabha, Gao Haibing, Elangovan Harendran, Fung James, Rajorya Neil, Wang Xinrui, Katchmann Helena, Praharaj Dibyalochan, Mahadeva Sanjiv, Jiang Yongfang, Zheng Katina, Thanapirom Kessarin, Eapen C E, Dhiman Radha K, Lu Mingqin, Arrese Marco, Su Minghua, Hueso Sarai Gonzalez, Zhu Chuanwu, Aberra Hanna, Fisseha Henok, Tan Hiang Keat, Zhao Caiyan, Zhang Ningping, Taneja Sunil, Aravinthan Aloysious D, Sonavane Amey, Saraya Anoop, Gofton Cameron, MacQuillan Gerry, Pereira Gustavo, Reddy K Rajender, Sarin Shiv K, Cao Zhujun, Topazian Mark, Idilman Ramazan, Torre Aldo, George Jacob, Alvares da Silva Mario, Bush Brian J, Bajaj Jasmohan S, CLEARED Consortium
Аннотация
METHODS: The CLEARED consortium consists of prospectively enrolled cirrhosis inpatients from >120 centers. Using day-of-admission clinical data, 3 ML approaches (random forest [RF], extreme gradient boosting, and neural networks [NNs]) were used to predict NI. Data were split 80:20 for training and testing stratified by the outcome. Models were compared using area under the receiver operating characteristic curve (AUC).
RESULTS: In total, 8,263 patients (55.90 ± 13.34 years; 64.1% men) from 127 centers in 37 countries were included. NI developed in 869 (10.5%), a median of 6 (4-11) days of postadmission. Major NIs were respiratory (29.6%) and urinary tract infection (15.7%), and spontaneous bacterial peritonitis (13.5%). NIs occurred more frequently in patients from low/low-middle income countries and those with severe liver disease, alcohol etiology, and admission infections. NIs were associated with inpatient mortality (31.9% vs 8.1%, P < 0.001) and liver transplantation (4.8% vs 1.9%, P < 0.001). Although the RF model (AUC 0.69) showed good calibration (Brier score 0.09), outperforming extreme gradient boosting, neural network, and LR models (AUC 0.66 for all; LR comparison P = 0.043), no model achieved AUC ≥0.80 for clinical utility. At 10% predicted probability threshold, the RF model demonstrated only 75.4% sensitivity, 52.9% specificity, and 15.9% positive predictive value (PPV).
DISCUSSION: NIs cannot be accurately predicted from day-of-admission data using ML models, even in a large, prospective, global cirrhosis cohort. Every hospitalized patient with cirrhosis should receive protocolized infection control measures.