TUM School of Medicine and Health, Department of Health and Sport Sciences, Technical University of Munich, Munich, Germany.
Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, United States.
Am J Clin Nutr. 2024 Nov;120(5):1233-1244. doi: 10.1016/j.ajcnut.2024.09.003. Epub 2024 Sep 11.
Predicting individual weight loss (WL) responses to lifestyle interventions is challenging but might help practitioners and clinicians select the most promising approach for each individual.
The primary aim of this study was to develop machine learning (ML) models to predict individual WL responses using only variables known before starting the intervention. In addition, we used ML to identify pre-intervention variables influencing the individual WL response.
We used 12-mo data from the comprehensive assessment of long-term effects of reducing intake of energy (CALERIE) phase 2 study, which aimed to analyze the long-term effects of caloric restriction on human longevity. On the basis of the data from 130 subjects in the intervention group, we developed classification models to predict binary ("Success" and "No/low success") or multiclass ("High success," "Medium success," and "Low/no success") WL outcomes. Additionally, regression models were developed to predict individual weight change (percent). Models were evaluated on the basis of accuracy, sensitivity, specificity (classification models), and root mean squared error (RMSE; regression models).
Best classification models used 20-40 predictors and achieved 89%-97% accuracy, 91%-100% sensitivity, and 56%-86% specificity for binary classification. For multiclass classification, accuracy (69%) and sensitivity (50%) tended to be lower. The best regression performance was obtained with 36 variables with an RMSE of 2.84%. Among the 21 variables predicting individual weight change most consistently, we identified 2 novel predictors, namely orgasm satisfaction and sexual behavior/experience. Other common predictors have previously been associated with WL (16) or are already used in traditional prediction models (3).
The prediction models could be implemented by practitioners and clinicians to support the decision of whether lifestyle interventions are sufficient or more aggressive interventions are needed for a given individual, thereby supporting better, faster, data-driven, and unbiased decisions. The CALERIE phase 2 study was registered at clinicaltrials.gov as NCT00427193.
预测个体对生活方式干预的减肥（WL）反应具有挑战性，但可以帮助从业者和临床医生为每个个体选择最有前途的方法。
本研究的主要目的是开发机器学习（ML）模型，仅使用干预前已知的变量来预测个体 WL 反应。此外，我们还使用 ML 来识别影响个体 WL 反应的干预前变量。
我们使用了来自长期减少能量摄入（CALERIE）研究 2 期的 12 个月数据，该研究旨在分析热量限制对人类寿命的长期影响。基于干预组 130 名受试者的数据，我们开发了分类模型来预测二分类（“成功”和“无/低成功”）或多分类（“高成功”、“中成功”和“低/无成功”）WL 结局。此外，还开发了回归模型来预测个体体重变化（百分比）。基于准确性、敏感性、特异性（分类模型）和均方根误差（RMSE；回归模型）来评估模型。
最佳分类模型使用 20-40 个预测因子，二分类的准确性为 89%-97%，敏感性为 91%-100%，特异性为 56%-86%。对于多分类，准确性（69%）和敏感性（50%）往往较低。最佳回归性能是使用 RMSE 为 2.84%的 36 个变量获得的。在预测个体体重变化最一致的 21 个变量中，我们确定了 2 个新的预测因子，即性满足和性行为/体验。其他常见的预测因子以前与 WL 相关（16）或已经用于传统的预测模型（3）。
从业者和临床医生可以实施这些预测模型，以支持是否对给定个体进行生活方式干预足够或需要更积极的干预的决策，从而支持更好、更快、数据驱动和无偏见的决策。CALERIE 研究 2 期在 clinicaltrials.gov 上注册为 NCT00427193。
