Discovery of distinct cancer cachexia phenotypes using an unsupervised machine-learning algorithm

• Published in: Nutrition (Burbank, Los Angeles County, Calif.) Vol. 119; p. 112317
• Main Authors: Wu, Hao-Fan, Yan, Jiang-Peng, Wu, Qian, Yu, Zhen, Xu, Hong-Xia, Song, Chun-Hua, Guo, Zeng-Qing, Li, Wei, Xiang, Yan-Jun, Xu, Zhe, Luo, Jie, Cheng, Shu-Qun, Zhang, Feng-Min, Shi, Han-Ping, Zhuang, Cheng-Le
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.03.2024; Elsevier Limited
• Subjects: Algorithms; artificial intelligence; At risk populations; Body mass index; Cachexia; Cachexia - etiology; Cancer; Cancer cachexia; China; Classification; Clinical trials; Cluster analysis; Clustering; Datasets; Hemoglobin; Heterogeneity; Humans; Learning algorithms; Machine Learning; Medical prognosis; Mortality; Neoplasms - complications; Nutrition; Observational studies; Patients; Performance prediction; Phenotype; Phenotypes; Quality of life; Regression analysis; China; Cancer cachexia; Phenotype; Machine learning; Classification

•This is the first establishment of a machine learning-based model for stratifying cancer cachexia.•Our model performed better than the previous method in predicting overall survival.•Our model reflects dynamic changes in body condition during cachexia deterioration. Cancer cachexia is a debilitatin...