Artificial intelligence based prediction models for individuals at risk of multiple diabetic complications: A systematic review of the literature

Abstract

Aim: The aim of this review is to examine the effectiveness of artificial intelligence in predicting multimorbid diabetes-related complications.Background: In diabetic patients, several complications are often present, which have a significant impact on the quality of life; therefore, it is crucial to predict the level of risk for diabetes and its complications.Evaluation: International databases PubMed, CINAHL, MEDLINE and Scopus were searched using the terms artificial intelligence, diabetes mellitus and prediction of complications to identify studies on the effectiveness of artificial intelligence for predicting multimorbid diabetes-related complications. The results were organized by outcomes to allow more efficient comparison.Key issues: Based on the inclusion/exclusion criteria, 11 articles were included in the final analysis. The most frequently predicted complications were diabetic neuropathy (n = 7). Authors included from two to a maximum of 14 complications. The most commonly used prediction models were penalized regression, random forest and Naïve Bayes model neural network. Conclusion:The use of artificial intelligence can predict the risks of diabetes complications with greater precision based on available multidimensional datasets and provides an important tool for nurses working in preventive health care.Implications for Nursing Management: Using artificial intelligence contributes to a better quality of care, better autonomy of patients in diabetes management and reduction of complications, costs of medical care and mortality.

Task-Oriented Predictive (Top)-BERT: Novel Approach for Predicting Diabetic Complications Using a Single-Center EHR Data

“…Prior studies have shown to improve model performance with inclusion of numerical features such labs and vitals (body mass index, blood pressure, lipid profiles, etc.) 15,55,56 . BERT inherently processes inputs as tokens, including numerical features.…”

“…However, most of the prior research was focused on predicting risk scores using a limited number of risk factors, often curated from previous literature [8][9][10][11][12][13][14] . Despite many machine learning (ML) and deep learning (DL) models that emerged in recent research, classical ML models dominated these studies-mostly limited to performance comparisons, with only a minority delving into exploring novel risk factors and discovering new knowledge 15,16 .…”

A Scientometric Review of Medical Artificial Intelligence Research: From A Social Science Perspective

“…AI technology indeed helps health care professionals, provides more care for a larger number of patients, makes better clinical decisions, and reduces unnecessary hospitalization and health care costs [18] . Gosak et al [19] investigate the effectiveness of AI within predicting complications associated with multimorbid diabetes mellitus through bibliometric studies. Mihevc et al [20] find that AI can be integrated into the platform to optimize the cost structure of remote monitoring of AH and T2D older adults in primary care.…”

“…Graili et al [24] systematically discuss AI in outcomes research, cover the scope of AI techniques used in outcomes research to expend the knowledge of decision-makers. Gosak et al [19] investigate the effectiveness of AI in predicting complications caused by multimorbid diabetes-related using bibliometrics. Few studies systematically and scientometrically review the overall picture of medical AI.…”