Management of diabetes using artificial intelligence: A Systematic Review

  • سال انتشار: 1402
  • محل انتشار: اولین کنگره بین المللی هوش مصنوعی در علوم پزشکی
  • کد COI اختصاصی: AIMS01_253
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 110
دانلود فایل این مقاله

نویسندگان

Fatemeh Bahador

Ph. D Student in Health Information Management, Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran- Faculty member, Department of Health Information Technology, Ferdows schoo

Azam Sabahi

Assistant Professor of Health Information Management Department of Health Information Technology, Ferdows School of Health and Allied Medical Sciences, Birjand University of Medical Sciences

Samaneh Jalali

BSc in Health Information Technology, Birjand University of Medical Sciences, Birjand, Iran

Fatemeh Ameri

MSc Student of Health Information Technology, Student Research Committee, Department of Medical Records and Health Information Technology,School of Paramedical Sciences, Mashhad University of Medical Sciences, Mashhad, Iran

Meisam Dastani

MSc Student of Health Information Technology, Student Research Committee, Department of Medical Records and Health Information Technology, School of Paramedical Sciences, Mashhad University of Medical Sciences, Mashhad, Iran

چکیده

Background and aims: Diabetes is one of the most common metabolic diseases in Iran and thefifth leading cause of death all over the world. Its spread around the world has created new methodsin biomedical research, including artificial intelligence. The present study was carried out toreview the studies conducted in the area of artificial intelligence and diabetes in Iran.Method: This study was carried out using a systematic review method. Valid domestic databases,including Irandoc, Magiran, Sid and Google Scholar search engine, were reviewed using the keywordsof artificial intelligence and diabetes in Persian both individually and in a combined mannerwithout time limitation until June ۲۰, ۲۰۲۱. A total number of ۷۴۹۵ articles were retrieved,which were screened in different stages (exclusion of duplicates (۱۸۲۴), title and summary ofthe articles (۵۸۸۴) and full text (۳۰) and finally ۲۰ articles that met the criteria desired by theresearchers were carefully reviewed.Results: Among the retrieved articles, ۲۰ articles met the inclusion criteria, of which ۱۶ articlesdealt with methods based on artificial intelligence and ۴ articles dealt with the design of new systemsbased on artificial intelligence. Also, ۱۰ articles examined the role of artificial intelligencein prediction (۵۰%), ۸ articles in diagnosis (۴۰%), and ۲ articles dealt with the control and managementof diabetes (۱۰%). Most of the articles were related to the use of data mining methodssuch as artificial neural network (۱۱ studies), decision tree (۷ studies), Logistic regression (۵studies), support vector machine (۴ studies) and genetic algorithm (۲ studies). Some studies alsoevaluated and compared artificial intelligence methods on application, accuracy and the sensitivityof artificial intelligence in diagnosing and predicting diabetes (۱۰ studies).These methods included the combination of genetic algorithm and Lunberg Marquardt, the combinationof adaptive reference model control and modified Smith forecast, the combination ofintegral sliding mode control and adaptive fuzzy estimator, the combination of fuzzy inferencesystem and firefly algorithm, etc.In most of the studies (۱۱ cases), Matlab and simulation software were used for data analysis,SPSS software was used the most in ۷ studies and R in ۶ studies.Conclusion: A systematic review of articles revealed that the use of data mining methods for diabetesmanagement in Iran has been associated with good progress, but there is a need to designartificial intelligence systems and algorithms and more measures should be taken in the area ofdiabetes control and management.

کلیدواژه ها

Artificial intelligence, Diabetes, Diabetes artificial intelligence, Artificial intelligence techniques, Systematic Review

مقالات مرتبط جدید

اطلاعات 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.