Prediction of the sarcopenia in peritoneal dialysis using simple clinical information: A machine learning‐based model

Abstract

IntroductionSarcopenia is associated with significant cardiovascular risk, and death in patients undergoing peritoneal dialysis (PD). Three tools are used for diagnosing sarcopenia. The evaluation of muscle mass requires dual energy X‐ray absorptiometry (DXA) or computed tomography (CT), which is labor‐intensive and relatively expensive. This study aimed to use simple clinical information to develop a machine learning (ML)‐based prediction model of PD sarcopenia.MethodsAccording to the newly revised Asian Working Group for Sarcopenia (AWGS2019), patients were subjected to complete sarcopenia screening, including appendicular skeletal muscle mass, grip strength, and five‐time chair stand time test. Simple clinical information such as general information, dialysis‐related indices, irisin and other laboratory indices, and bioelectrical impedance analysis (BIA) data were collected. All data were randomly split into training (70%) and testing (30%) sets. Difference, correlation, univariate, and multivariate analyses were used to identify core features significantly associated with PD sarcopenia.Result12 core features (C), namely, grip strength, body mass index (BMI), total body water value, irisin, extracellular water/total body water, fat‐free mass index, phase angle, albumin/globulin, blood phosphorus, total cholesterol, triglyceride, and prealbumin were excavated for model construction. Two ML models, the neural network (NN), and support vector machine (SVM) were selected with tenfold cross‐validation to determine the optimal parameter. The C‐SVM model showed a higher area under the curve (AUC) of 0.82 (95% confidence interval [CI]: 0.67–1.00), with a highest specificity of 0.96, sensitivity of 0.91, positive predictive value (PPV) of 0.96, and negative predictive value (NPV) of 0.91.ConclusionThe ML model effectively predicted PD sarcopenia and has clinical potential to be used as a convenient sarcopenia screening tool.

WITHDRAWN: Development and external validation of a practical diagnostic support tool, ‘ABC 2-Screener’, to predict sarcopenia among patients on maintenance haemodialysis: A multicentre cross-sectional study

“…The ABC 2 -Screener showed useful discriminative and calibration performance in external validation, particularly for web-based programmes. The discriminative ability of the ABC 2 -Screener in external validation was excellent for both the point-scoring system and web-based programme (0.9149 and 0.9708, respectively) and equal to or superior to those of the aforementioned clinical prediction models (especially the web-based programme) (12)(13)(14)17). The external validation calibration of our tool showed a good fit across low to high predicted risk for the web-based programme while the intermediate predicted risk was underestimated for the point score system.…”

“…Additionally, in a study evaluating a nomogram for sarcopenia in patients undergoing haemodialysis, the side of the MUAC measurement was not clarified (14). Other clinical prediction rules for patients on dialysis, including irisin and fat-free mass index, also have limitations due to the unavailability of measurements in usual care and the lack of external validation (17).…”

“…However, many of these are nomogram-based models (12)(13)(14) and may not be preferred in clinical practice because of the complexity at first sight and inaccuracies associated with translation to final outcomes (15,16). Additionally, in previously reported prediction rules, predictor variables included grip strength, a component of the criteria for diagnosing sarcopenia (14,17), and irisin and fat-free mass index, which are not measured in the usual course of care (17). Therefore, there is a need for a reliable method to screen for sarcopenia in dialysis care settings based on data available in routine dialysis care, without performing examinations required for diagnosing sarcopenia.…”

Irisin and Its Role in Postmenopausal Osteoporosis and Sarcopenia

“…The purpose of Wu et al's work was to generate a model that could predict sarcopenia in patients undergoing PD [63]. The characteristics examined are grip strength, BMI, total body water value, irisin, extracellular water/total body water, fat-free mass index, phase angle, albumin/globulin, blood phosphorus, total cholesterol, triglyceride, and prealbumin.…”

Machine-learning algorithms for the prediction of adverse prognosis in patients undergoing peritoneal dialysis

“…ML has demonstrated the power of using nonlinear methods to mine complex biomedical datasets to rapidly predict the ne reactivity and speci city of the human immune system and target antibiotic medication for early patient treatment [10] . Myopenia is associated with cardiovascular risk and mortality in patients with PD, and the ML model can effectively predict PD myopenia using simple clinical indicators [11] .…”