Explanation of COVID-۱۹ Mortality Using Artificial Neural Network Based on Underlying and Laboratory Risk Factors in Ilam, Iran
- سال انتشار: 1401
- محل انتشار: مجله آرشیو رازی، دوره: 77، شماره: 3
- کد COI اختصاصی: JR_ARCHRAZI-77-3_050
- زبان مقاله: انگلیسی
- تعداد مشاهده: 76
نویسندگان
Clinical Research Development Unit, Mostafa Khomeini Hospital, Ilam University of Medical Sciences, Ilam, Iran
Department of Physiology, School of Medicine, Ilam University of Medical Sciences, Ilam, Iran
Department of Pediatrics, School of Medicine, Besat Hospital, Hamadan University of Medical Sciences, Hamadan, Iran
Non-Communicable Diseases Research Center, Ilam University of Medical Sciences, Ilam, Iran
چکیده
The spread of new waves of coronavirus outbreaks, high mortality rates, and time-consuming and numerous challenges in achieving collective safety through vaccination and the need to prioritize the allocation of vaccines to the general population have led to the continued identification of risk factors associated with mortality in patients through innovative strategies and new statistical models. In this study, an artificial neural network (ANN) model was used to predict morbidity in patients with coronavirus disease ۲۰۱۹ (COVID-۱۹). Data of ۲,۲۰۶ patients were extracted from the registry program of Shahid Mostafa Khomeini Hospital in Ilam, Iran, and were randomly analyzed in two training (۱,۵۴۴) and testing (۶۶۲) groups. By fitting different models of a three-layer neural network, ۱۲ variables could explain more than ۷۷% of the mortality variance in COVID-۱۹ patients. These findings could be used to better mortality management, vaccination prioritization, public education, and quarantine, and allocation of intensive care beds to reduce COVID-۱۹ mortality. The results also confirmed the power of a better explanation of ANN models to predict the mortality of patients.کلیدواژه ها
Artificial Neural Networks, covid-۱۹, Multilayer perceptron, Iranاطلاعات بیشتر در مورد COI
COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.
کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.