چکیده
مقدمه
پیش زمینه
روششناسی مرور مطالعات پیشین سیستماتیک
مطالعات مرتبط
روش ها
استراتژی جستجو
معیارهای واجد شرایط بودن
استخراج داده ها
تجزیه و تحلیل خطر سوگیری
نتایج
ارزیابی کیفی
تجزیه و تحلیل خطر سوگیری
بحث
نتیجه گیری
منابع
Abstract
Introduction
Background
Systematic literature review methodologies
Related works
Methods
Search strategy
Eligibility criteria
Data extraction
Risk of bias analyses
Results
Quality assessment
Risk of bias analyses
Discussion
Conclusions
References
چکیده
دیابت شیرین یک بیماری مزمن و شدید است که زمانی رخ می دهد که سطح گلوکز خون از حد مشخصی بالاتر رود. طی سال های گذشته، تکنیک های یادگیری عمیق ماشینی و عمیق برای پیش بینی دیابت و عوارض آن مورد استفاده قرار گرفته است. با این حال، محققان و توسعه دهندگان هنوز با دو چالش اصلی هنگام ساخت مدل های پیش بینی دیابت نوع 2 مواجه هستند. اول، ناهمگونی قابلتوجهی در مطالعات قبلی در مورد تکنیکهای مورد استفاده وجود دارد، که شناسایی بهینه را چالش برانگیز میکند. دوم، عدم شفافیت در مورد ویژگی های به کار رفته در مدل ها وجود دارد که قابلیت تفسیر آنها را کاهش می دهد. این بررسی سیستماتیک با هدف ارائه پاسخ به چالش های فوق انجام شد. این بررسی عمدتاً از متدولوژی PRISMA پیروی می کرد که با روشی که توسط دانشگاه های Keele و Durham پیشنهاد شده غنی شده بود. نود مطالعه وارد شد و نوع مدل، تکنیکهای مکمل، مجموعه دادهها و پارامترهای عملکرد گزارششده استخراج شد. هجده نوع مختلف از مدل ها با الگوریتم های مبتنی بر درخت که عملکرد برتر را نشان می دهند، مقایسه شدند. شبکههای عصبی عمیق علیرغم توانایی آنها در مقابله با دادههای بزرگ و کثیف، کمتر از حد مطلوب بودند. متوازن کردن داده ها و تکنیک های انتخاب ویژگی برای افزایش کارایی مدل مفید بود. مدلهایی که بر روی مجموعه دادههای مرتب آموزش دیده بودند، به مدلهای تقریباً کاملی دست یافتند.
توجه! این متن ترجمه ماشینی بوده و توسط مترجمین ای ترجمه، ترجمه نشده است.
Abstract
Diabetes Mellitus is a severe, chronic disease that occurs when blood glucose levels rise above certain limits. Over the last years, machine and deep learning techniques have been used to predict diabetes and its complications. However, researchers and developers still face two main challenges when building type 2 diabetes predictive models. First, there is considerable heterogeneity in previous studies regarding techniques used, making it challenging to identify the optimal one. Second, there is a lack of transparency about the features used in the models, which reduces their interpretability. This systematic review aimed at providing answers to the above challenges. The review followed the PRISMA methodology primarily, enriched with the one proposed by Keele and Durham Universities. Ninety studies were included, and the type of model, complementary techniques, dataset, and performance parameters reported were extracted. Eighteen different types of models were compared, with tree-based algorithms showing top performances. Deep Neural Networks proved suboptimal, despite their ability to deal with big and dirty data. Balancing data and feature selection techniques proved helpful to increase the model’s efficiency. Models trained on tidy datasets achieved almost perfect models.
Introduction
Diabetes mellitus is a group of metabolic diseases characterized by hyperglycemia resulting from defects in insulin secretion, insulin action, or both [1]. In particular, type 2 diabetes is associated with insulin resistance (insulin action defect), i.e., where cells respond poorly to insulin, affecting their glucose intake [2]. The diagnostic criteria established by the American Diabetes Association are: (1) a level of glycated hemoglobin (HbA1c) greater or equal to 6.5%; (2) basal fasting blood glucose level greater than 126 mg/dL, and; (3) blood glucose level greater or equal to 200 mg/dL 2 h after an oral glucose tolerance test with 75 g of glucose [1].
Diabetes mellitus is a global public health issue. In 2019, the International Diabetes Federation estimated the number of people living with diabetes worldwide at 463 million and the expected growth at 51% by the year 2045. Moreover, it is estimated that there is one undiagnosed person for each diagnosed person with a diabetes diagnosis [2].
The early diagnosis and treatment of type 2 diabetes are among the most relevant actions to prevent further development and complications like diabetic retinopathy [3]. According to the ADDITION-Europe Simulation Model Study, an early diagnosis reduces the absolute and relative risk of suffering cardiovascular events and mortality [4]. A sensitivity analysis on USA data proved a 25% relative reduction in diabetes-related complication rates for a 2-year earlier diagnosis.
Results
Search results and reduction
The initial search generated 1327 records, 925 from PubMed and 402 from Web of Science. Only 130 records were excluded when filtering by publication year (2017–2021). Therefore, further searches were conducted using fine-tuned search strings and options for both databases to narrow down the results. The new search was carried out using the original keywords but restricting the word ‘diabetes’ to be in the title, which generated 517 records from both databases. Fifty-one duplicates were discarded. Therefore, 336 records were selected for further screening.
Further selection was conducted by applying the exclusion criteria to the 336 records above. Thirty-seven records were excluded since the study reported used non-omittable genetic attributes as model inputs, something out of this review’s scope. Thirty-eight records were excluded as they were review papers. All in all, 261 articles that fulfill the criteria were included in the quality assessment.