Department of Clinical and Preventive Nutrition Sciences, School of Health Professions, Rutgers University, New Brunswick, NJ, USA.
Department of Health Informatics, School of Health Professions, Rutgers University, New Brunswick, NJ, USA.
Ann Med. 2023;55(2):2238182. doi: 10.1080/07853890.2023.2238182.
Approximately 700,000 people in the USA have chronic kidney disease requiring dialysis. Protein-energy wasting (PEW), a condition of advanced catabolism, contributes to three-year survival rates of 50%. PEW occurs at all levels of Body Mass Index (BMI) but is devastating for those people at the extremes. Treatment for PEW depends on an accurate understanding of energy expenditure. Previous research established that current methods of identifying PEW and assessing adequate treatments are imprecise. This includes disease-specific equations for estimated resting energy expenditure (eREE). In this study, we applied machine learning (ML) modelling techniques to a clinical database of dialysis patients. We assessed the precision of the ML algorithms relative to the best-performing traditional equation, the MHDE.
This was a secondary analysis of the Rutgers Nutrition and Kidney Database. To build the ML models we divided the population into test and validation sets. Eleven ML models were run and optimized, with the best three selected by the lowest root mean squared error (RMSE) from measured REE. Values for eREE were generated for each ML model and for the MHDE. We compared precision using Bland-Altman plots.
Individuals were 41.4% female and 82.0% African American. The mean age was 56.4 ± 11.1 years, and the median BMI was 28.8 (IQR = 24.8 - 34.0) kg/m. The best ML models were SVR, Linear Regression and Elastic net with RMSE of 103.6 kcal, 119.0 kcal and 121.1 kcal respectively. The SVR demonstrated the greatest precision, with 91.2% of values falling within acceptable limits. This compared to 47.1% for the MHDE. The models using non-linear techniques were precise across extremes of BMI.
ML improves precision in calculating eREE for dialysis patients, including those most vulnerable for PEW. Further development for clinical use is a priority.
美国约有 70 万人患有需要透析的慢性肾脏疾病。蛋白能量消耗（PEW）是一种晚期分解代谢状态，导致三年生存率为 50%。PEW 发生在身体质量指数（BMI）的所有水平，但对处于极端水平的人来说是毁灭性的。PEW 的治疗取决于对能量消耗的准确理解。先前的研究表明，目前确定 PEW 和评估适当治疗的方法不够精确。这包括用于估计静息能量消耗（REE）的特定疾病方程。在这项研究中，我们将机器学习（ML）建模技术应用于透析患者的临床数据库。我们评估了 ML 算法相对于表现最佳的传统方程 MHDE 的精确性。
这是罗格斯营养与肾脏数据库的二次分析。为了构建 ML 模型，我们将人群分为测试集和验证集。运行了 11 个 ML 模型并进行了优化，选择了三个 RMSE（均方根误差）最低的最佳模型。为每个 ML 模型和 MHDE 生成了 eREE 值。我们使用 Bland-Altman 图比较精度。
个体中 41.4%为女性，82.0%为非裔美国人。平均年龄为 56.4±11.1 岁，中位数 BMI 为 28.8（IQR=24.8-34.0）kg/m。最佳 ML 模型分别为 SVR、线性回归和弹性网络，RMSE 分别为 103.6、119.0 和 121.1 kcal。SVR 显示出最大的精度，91.2%的值落在可接受范围内。这与 MHDE 的 47.1%相比。使用非线性技术的模型在 BMI 的极端范围内都很精确。
ML 提高了计算透析患者 eREE 的精度，包括那些最易患 PEW 的患者。进一步开发用于临床使用是当务之急。
