Department of Clinical Nutrition, Daping Hospital, Army Medical University (Third Military Medical University), Chongqing, China; Institute of Hepatopancreatobiliary Surgery, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, China.
Cancer Center, The First Hospital of Jilin University, Changchun, Jilin, China.
Am J Clin Nutr. 2022 Nov;116(5):1229-1239. doi: 10.1093/ajcn/nqac251. Epub 2023 Feb 10.
Diagnosing cancer cachexia relies extensively on patient-reported historic weight, and failure to accurately recall this information can lead to severe underestimation of cancer cachexia.
The present study aimed to develop inexpensive tools to facilitate the identification of cancer cachexia in patients without weight loss information.
This multicenter cohort study included 12,774 patients with cancer. Cachexia was retrospectively diagnosed using Fearon et al.'s framework. Baseline clinical features, excluding weight loss, were modeled to mimic a situation where the patient is unable to recall their weight history. Multiple machine learning (ML) models were trained using 75% of the study cohort to predict cancer cachexia, with the remaining 25% of the cohort used to assess model performance.
The study enrolled 6730 males and 6044 females (median age = 57.5 y). Cachexia was diagnosed in 5261 (41.2%) patients and most diagnoses were made based on the weight loss criterion. A 15-variable logistic regression (LR) model mainly comprising cancer types, gastrointestinal symptoms, tumor stage, and serum biochemistry indexes was selected among the various ML models. The LR model showed good performance for predicting cachexia in the validation data (AUC = 0.763; 95% CI: 0.747, 0.780). The calibration curve of the model demonstrated good agreement between predictions and actual observations (accuracy = 0.714, κ = 0.396, sensitivity = 0.580, specificity = 0.808, positive predictive value = 0.679, negative predictive value = 0.733). Subgroup analyses showed that the model was feasible in patients with different cancer types. The model was deployed as an online calculator and a nomogram, and was exported as predictive model markup language to permit flexible, individualized risk calculation.
We developed an ML model that can facilitate the identification of cancer cachexia in patients without weight loss information, which might improve decision-making and lead to the development of novel management strategies in cancer care. This trial was registered at https://www.chictr.org.cn as ChiCTR1800020329.
癌症恶病质的诊断在很大程度上依赖于患者报告的既往体重，而未能准确回忆这些信息可能会导致癌症恶病质的严重低估。
本研究旨在开发经济实惠的工具，以帮助识别没有体重减轻信息的癌症恶病质患者。
这项多中心队列研究纳入了 12774 名癌症患者。回顾性使用 Fearon 等人的框架诊断恶病质。模拟患者无法回忆体重史的情况，对排除体重减轻的基线临床特征进行建模。使用研究队列的 75%来训练多种机器学习（ML）模型，以预测癌症恶病质，其余 25%的队列用于评估模型性能。
本研究纳入了 6730 名男性和 6044 名女性（中位年龄=57.5 岁）。5261 名（41.2%）患者被诊断为恶病质，大多数诊断是基于体重减轻标准做出的。在各种 ML 模型中，选择了一个主要由癌症类型、胃肠道症状、肿瘤分期和血清生化指标组成的 15 变量逻辑回归（LR）模型。该 LR 模型在验证数据中的预测恶病质表现良好（AUC=0.763；95%CI：0.747，0.780）。模型的校准曲线显示了预测值与实际观察值之间的良好一致性（准确性=0.714，κ=0.396，敏感性=0.580，特异性=0.808，阳性预测值=0.679，阴性预测值=0.733）。亚组分析表明，该模型在不同癌症类型的患者中是可行的。该模型被开发为在线计算器和诺模图，并以预测模型标记语言导出，以允许灵活的、个体化的风险计算。
我们开发了一种机器学习模型，可以帮助识别没有体重减轻信息的癌症恶病质患者，这可能会改善决策，并导致癌症护理中新型管理策略的发展。这项试验在 https://www.chictr.org.cn 注册，注册号为 ChiCTR1800020329。
