Validation of a machine learning approach using FIB-4 and APRI scores assessed by the metavir scoring system: A cohort study |
| |
| Authors: | Ahmed Hashem Abubakr Awad Hend Shousha Wafaa Alakel Ahmed Salama Tahany Awad Mahasen Mabrouk |
| |
| Institution: | 1. Endemic Medicine and Hepatology Department, Faculty of Medicine, Cairo University, Cairo, Egypt;2. School of Natural and Computing Sciences, University of Aberdeen, Aberdeen, UK;3. National Hepatology and Tropical Medicine Research Institute, Ministry of Health and Population, Cairo, Egypt;1. Cairo University, Department of Pediatrics, Cairo, Egypt;2. Cairo University, Department Clinical & Chemical Pathology, Cairo, Egypt;3. Cairo University, Endemic Medicine & Hepatology Department, Cairo, Egypt;1. Department of Pathology, Faculty of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia;2. Department of Pathology, Faculty of Medicine, Minia University, Al-Minia, Egypt;3. Department of Pathology, King Faisal Specialist Hospital and Research Centre, Jeddah, Saudi Arabia;1. Institute of Gastrosciences and Liver, Apollo Gleneagles Hospitals, Kolkata, India;2. Department of Clinical Imaging and Interventional Radiology, Apollo Gleneagles Hospitals, Kolkata, India;1. Division of Gastroenterology, American University of Beirut Medical Center, P.O. Box 11-0236/16-B, Beirut, Lebanon;2. Department of Family Medicine, American University of Beirut Medical Center, PO Box: 11-0236, Riad El Sol, 1107 2020 Beirut, Lebanon;3. Department of Pathology & Laboratory Medicine, American University of Beirut Medical Center, PO Box 11-0236, Riad El Solh 11072020, Beirut, Lebanon;1. Department of Gastroenterology, The First Affiliated Hospital of Nanchang University, Nanchang, Jiangxi 330006, China;2. Department of Gastroenterology, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong 518000, China;3. School of Mathematical Sciences, Huazhong University of Science and Technology, Wuhan, Hubei 430074, China;4. Department of Preventive Medicine, Jinggangshan University, Ji''an, Jiangxi 343009, China |
| |
| Abstract: | Background and Study AimThe study aim was to improve and validate the accuracy of the fibrosis-4 (FIB-4) and aspartate aminotransferase-to-platelet ratio index (APRI) scores for use in a potential machine-learning (ML) method that accurately predicts the extent of liver fibrosis.Patients and MethodsThis retrospective multicenter study included 69,106 patients with chronic hepatitis C planned for antiviral therapy from January 2010–December 2014 with liver biopsy results. FIB-4 and APRI scores were calculated and their performance for predicting significant liver fibrosis (F3–F4) assessed against the Metavir scoring system. ML was used for feature selection and reduction to identify the most relevant attributes (CfsSubseteval/best first) for prediction.ResultsIn this study, 57,492 (83.2%) patients were F0–F2, and 11,615 (16.8%) patients were F3–F4. The revalidation of FIB-4 and APRI showed lower accuracy and higher disagreement with the biopsy results, with AUCs of 0.68 and 0.58, respectively. FIB-4 diagnosed fewer (14%) F3–F4 patients, and the high specificity and negative predictive values of FIB-4 and APRI reflected the low prevalence of F3–F4 in the study population. Out of 15 attributes, age (>35 years), AFP (>6.5 ng/ml), and platelet count (<150,000/mm3) were the most relevant risk attributes, and patients with one or more of these risk factors were likely to be F3–F4, with a classification accuracy of ≤ 92% and receiver operating characteristics area of 0.74.ConclusionFIB-4 and APRI scores were not very accurate and missed diagnosing most of the F3–F4 patients. ML implementation improved medical decisions and minimized the required clinical data to three risk factors. |
| |
| Keywords: | Hepatitis C virus Liver fibrosis Metavir FIB4 score APRI score Machine learning Attribute reduction |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
