Niakan Kalhori Sharareh Rostam, Najafi Farid, Hasannejadasl Hajar, Heydari Soroush
Department of Health Information Management and Medical Informatics School of Allied Medical Sciences Tehran University of Medical Sciences Tehran Iran; Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Braunschweig Germany.
Research Center for Environmental Determinants of Health (RCEDH) Health Institute Kermanshah University of Medical Sciences Kermanshah Iran; Cardiovascular Research Center Kermanshah University of Medical Sciences Kermanshah Iran.
Int J Med Inform. 2025 Apr;196:105804. doi: 10.1016/j.ijmedinf.2025.105804. Epub 2025 Jan 24.
Obesity, now the fifth leading global cause of death, has seen a dramatic rise in prevalence over the last forty years. It significantly increases the risk of diseases such as type 2 diabetes and cardiovascular disease. Early identification of obesity risk allows for preventative actions against obesity-related factors. Despite the existence of AI-based predictive models, developing a comprehensive obesity screening tool requires extensive cohort data.
A thorough review of 6,351 articles, focusing on AI predictions for obesity in cohort studies, was conducted up to March 2024 across databases including PubMed, Scopus, and Web of Science.
Using the JBI checklist, 10 studies involving 411,580 participants were critically appraised. These cohorts varied in length and size, with half lasting 1-5 years and involving less than 5,000 participants. The data types were categorized into nine groups, with demographic (7 studies) and biomarker data (4 studies) being the most frequently used. Machine learning was predominantly used (95 % of studies), mostly employing supervised learning techniques. Algorithms like random forest (RF) (18 %), linear regression (18 %), and stochastic gradient boosting (GBM) (14 %) were common. Top-performing models were noted for k-means (accuracy of 0.977), artificial neural networks (AUC of 0.99), GBM (specificity of 0.95 and sensitivity of 0.65), RF (RMSE of 0.146), and least absolute shrinkage and selection operator (r-squared of 0.684).
Findings indicate that AI algorithms can predict obesity; however, further research is needed to assess their effectiveness in analyzing obesity-related data and examine most advanced AI methods. This review is a valuable resource for dietitians and researchers engaged in developing predictive models and intelligent clinical decision support systems using AI technology.
肥胖现已成为全球第五大主要死因，在过去四十年中患病率急剧上升。它显著增加了2型糖尿病和心血管疾病等疾病的风险。早期识别肥胖风险有助于针对肥胖相关因素采取预防措施。尽管存在基于人工智能的预测模型，但开发全面的肥胖筛查工具需要大量队列数据。
截至2024年3月，对6351篇文章进行了全面回顾，重点关注队列研究中人工智能对肥胖的预测，涉及的数据库包括PubMed、Scopus和Web of Science。
使用JBI检查表，对涉及411580名参与者的10项研究进行了严格评估。这些队列的长度和规模各不相同，一半持续1至5年，参与者少于5000人。数据类型分为九组，其中人口统计学数据（7项研究）和生物标志物数据（4项研究）使用最为频繁。主要使用机器学习（95%的研究），大多采用监督学习技术。随机森林（RF）（18%）、线性回归（18%）和随机梯度提升（GBM）（14%）等算法较为常见。表现最佳的模型包括k均值（准确率0.977）、人工神经网络（AUC为0.99）、GBM（特异性0.95，敏感性0.65）、RF（RMSE为0.146）以及最小绝对收缩和选择算子（r平方为0.684）。
研究结果表明，人工智能算法可以预测肥胖；然而，需要进一步开展研究以评估其在分析肥胖相关数据方面的有效性，并研究最先进的人工智能方法。本综述为营养师以及从事使用人工智能技术开发预测模型和智能临床决策支持系统的研究人员提供了宝贵资源。
