Identifying cancer cachexia in patients without weight loss information: machine learning approaches to address a real-world challenge

Abstract

Background Diagnosing cancer cachexia relies extensively on the patient-reported historic weight, and failure to accurately recall this information can lead to severe underestimation of cancer cachexia. Objectives The present study aimed to develop inexpensive tools to facilitate the identification of cancer cachexia in patients without weight loss information. Methods This multicenter cohort study included 12774 patients with cancer. Cachexia was retrospectively diagnosed using Fearon'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. Results The study enrolled 6730 males and 6044 females (median age = 57.5 years). 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 indices was selected among the various ML models. The LR model showed good performance for predicting cachexia in the validation data (area under the curve = 0.763, 95% confidence interval=[0.747, 0.780]). The calibration curve of the model demonstrated good agreement between predictions and actual observations (accuracy = 0.714, Kappa = 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. Conclusions We developed a 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.

Longitudinal Muscle Biopsies Reveal Inter- and Intra-Subject Variability in Cancer Cachexia: Paving the Way for Biopsy-Guided Tailored Treatment

“…Moreover, imaging studies can offer valuable information to calculate energy expenditure in patients with cancer, which consequently leads to negative energy balance and can be an essential determinant for cachexia [ 37 ]. As we are already traversing the artificial intelligence era [ 38 ], the potential linking of longitudinal imaging phenotyping and sequential muscle biopsies testing, as well as serum biomarker analyses, holds great promise for the future perspectives of cancer cachexia research.…”

Exploring the optimal indicator of short‐term peridiagnosis weight dynamics to predict cancer survival: A multicentre cohort study

“… 22 , 29 However, instead of being measured and retrospectively retrieved in prospectively designed research settings, weight loss was ‘naturally’ calculated based on patient‐reported previous weight in newly diagnosed cancer in clinical settings. 30 , 31 Recollection of weight data after months is reported to be less reliable. 28 A previous study conducted in patients with pancreatic cancer suggests that postdiagnosis weight loss over 60 days did not predict poor prognosis.…”

“…In general, weight changes (gain or loss) in early adulthood have been related to all‐cause and cancer‐specific mortality 22,29 . However, instead of being measured and retrospectively retrieved in prospectively designed research settings, weight loss was ‘naturally’ calculated based on patient‐reported previous weight in newly diagnosed cancer in clinical settings 30,31 . Recollection of weight data after months is reported to be less reliable 28 .…”