Backgrounds: The relationship between sarcopenia, characterized by loss of muscle mass and strength, and survival outcomes of esophageal cancer is controversial. This study aimed to assess the effect of sarcopenia and skeletal muscle loss on overall survival (OS) and recurrence-free survival (RFS) of esophageal cancer patients. Methods: We retrospectively collected the medical records of 248 male patients diagnosed with squamous cell esophageal cancer and who underwent neoadjuvant chemoradiotherapy (NACRT) followed by surgery. We measured the cross-sectional area of the skeletal muscle at the L3 vertebra level using computed tomography images and calculated the skeletal muscle index (SMI). Sarcopenia was defined as SMI <52.4 cm²/m², and excessive muscle loss was defined as SMI change <−10.0%/50 days during NACRT. Moreover, laboratory test results, such as albumin, prognostic nutritional index (PNI), neutrophil-to-lymphocyte ratio (NLR), and platelet-to-lymphocyte ratio (PLR) before and after NACRT, were collected. Results: In the univariable Cox analysis, pre- (p = 0.689) and post-radiotherapy (RT) sarcopenia (p = 0.669) were not associated with OS. However, excessive muscle loss had a significant association with OS in both the univariable and multivariable analyses (all p = 0.001). Excessive muscle loss was also related to RFS in both the univariable (p = 0.011) and multivariable (p = 0.022) Cox analysis. Patients with excessive muscle loss had significantly lower levels of post-RT albumin (p < 0.001) and PNI (p < 0.001), higher levels of post-RT NLR (p = 0.031) and PLR (p = 0.071), larger decrease in albumin (p < 0.001) and PNI (p < 0.001) after NACRT, and larger increase in NLR (p = 0.051) and PLR (p = 0.088) after NACRT than in those with non-excessive muscle loss. Conclusion: Excessive muscle loss rather than pre- and post-RT sarcopenia was a significant prognostic factor for OS and RFS, and it was also related to nutritional and inflammatory markers.

Background: Excessive muscle loss is an important prognostic factor in esophageal cancer patients undergoing neoadjuvant chemoradiotherapy (NACRT), as reported in our previous research. Objective: In this pilot study, we prospectively tested the feasibility of a health coaching mobile app for preventing malnutrition and muscle loss in this patient population. Methods: Between July 2019 and May 2020, we enrolled 38 male patients with esophageal cancer scheduled for NACRT. For 8 weeks from the start of radiotherapy (RT), the patients used Noom, a health coaching mobile app that interactively provided online advice about food intake, exercise, and weight changes. The skeletal muscle index (SMI) measured based on computed tomography and nutrition-related laboratory markers were assessed before and after RT. We evaluated the changes in the SMI, nutrition, and inflammatory factors between the patient group that used the mobile app (mHealth group) and our previous study cohort (usual care group). Additionally, we analyzed the factors associated with walk steps recorded in the app. Results: Two patients dropped out of the study (no app usage; treatment changed to a definitive aim). The use (or activation) of the app was noted in approximately 70% (25/36) of the patients until the end of the trial. Compared to the 1:2 matched usual care group by propensity scores balanced with their age, primary tumor location, tumor stage, pre-RT BMI, and pre-RT SMI level, 30 operable patients showed less aggravation of the prognostic nutritional index (PNI) (–6.7 vs –9.8; P=.04). However, there was no significant difference in the SMI change or the number of patients with excessive muscle loss (∆SMI/50 days >10%). In patients with excessive muscle loss, the walk steps significantly decreased in the last 4 weeks compared to those in the first 4 weeks. Age affected the absolute number of walk steps (P=.01), whereas pre-RT sarcopenia was related to the recovery of the reduced walk steps (P=.03). Conclusions: For esophageal cancer patients receiving NACRT, a health care mobile app helped nutritional self-care with less decrease in the PNI, although it did not prevent excessive muscle loss. An individualized care model with proper exercise as well as nutritional support may be required to reduce muscle loss and malnutrition.

This study aimed to investigate the performance of a deep learning-based survival-prediction model, which predicts the overall survival (OS) time of glioblastoma patients who have received surgery followed by concurrent chemoradiotherapy (CCRT). The medical records of glioblastoma patients who had received surgery and CCRT between January 2011 and December 2017 were retrospectively reviewed. Based on our inclusion criteria, 118 patients were selected and semi-randomly allocated to training and test datasets (3:1 ratio, respectively). A convolutional neural network–based deep learning model was trained with magnetic resonance imaging (MRI) data and clinical profiles to predict OS. The MRI was reconstructed by using four pulse sequences (22 slices) and nine images were selected based on the longest slice of glioblastoma by a physician for each pulse sequence. The clinical profiles consist of personal, genetic, and treatment factors. The concordance index (C-index) and integrated area under the curve (iAUC) of the time-dependent area-under-the-curve curves of each model were calculated to evaluate the performance of the survival-prediction models. The model that incorporated clinical and radiomic features showed a higher C-index (0.768 (95% confidence interval (CI): 0.759, 0.776)) and iAUC (0.790 (95% CI: 0.783, 0.797)) than the model using clinical features alone (C-index = 0.693 (95% CI: 0.685, 0.701); iAUC = 0.723 (95% CI: 0.716, 0.731)) and the model using radiomic features alone (C-index = 0.590 (95% CI: 0.579, 0.600); iAUC = 0.614 (95% CI: 0.607, 0.621)). These improvements to the C-indexes and iAUCs were validated using the 1000-times bootstrapping method; all were statistically significant (p < 0.001). This study suggests the synergistic benefits of using both clinical and radiomic parameters. Furthermore, it indicates the potential of multi-parametric deep learning models for the survival prediction of glioblastoma patients.

Multidrug-resistant urinary tract infections (MDR UTIs) are a growing concern in patients with brain and spinal cord injuries due to their high susceptibility to UTIs and repeated antibiotic exposure. This study aimed to develop and externally validate a machine learning model for predicting MDR UTIs in patients with brain and spinal cord injuries. We retrospectively analyzed 849 patients with brain or spinal cord injuries and culture-confirmed UTIs. Data from a single institution were used for model training, and the other served as an external test set. Five machine learning models and ensemble models were trained and evaluated. Model performance was evaluated using accuracy, sensitivity, specificity, positive/negative predictive value, and area under the receiver operating characteristic curve. The finally selected ensemble model, combining Naive Bayes and Random Forest, achieved an area under the receiver operating characteristic curve of 0.8425, with an accuracy of 0.7688, sensitivity of 0.7647, specificity of 0.7697, positive predictive value of 0.4262, and negative predictive value of 0.9360. Important predictors included recent antibiotic use, total Functional Independence Measure score, neutrophil-to-platelet ratio, neutrophil-to-lymphocyte ratio, erythrocyte sedimentation rate, age, hematocrit, hemoglobin, serum protein, serum albumin, and urethral indwelling catheter. Externally validated, the model showed consistent performance across institutions. It may support early MDR risk stratification in patients with brain and spinal cord injuries. Early identification of at-risk individuals may guide antibiotic stewardship in neurorehabilitation settings.

Background: Excessive skeletal muscle loss during neoadjuvant concurrent chemoradiotherapy (NACRT) is significantly related to survival outcomes of oesophageal cancer. However, the conventional method for measuring skeletal muscle mass requires computed tomography (CT) images, and the calculation process is labour‐intensive. In this study, we built machine‐learning models to predict excessive skeletal muscle loss, using only body mass index data and blood laboratory test results. Methods: We randomly split the data of 232 male patients treated with NACRT for oesophageal cancer into the training (70%) and test (30%) sets for 1000 iterations. The naive random over sampling method was applied to each training set to adjust for class imbalance, and we used seven different machine‐learning algorithms to predict excessive skeletal muscle loss. We used five input variables, namely, relative change percentage in body mass index, albumin, prognostic nutritional index, neutrophil‐to‐lymphocyte ratio, and platelet‐to‐lymphocyte ratio over 50 days. According to our previous study results, which used the maximal χ ² method, 10.0% decrease of skeletal muscle index over 50 days was determined as the cut‐off value to define the excessive skeletal muscle loss. Results: The five input variables were significantly different between the excessive and the non‐excessive muscle loss group (all P < 0.001). None of the clinicopathologic variables differed significantly between the two groups. The ensemble model of logistic regression and support vector classifier showed the highest area under the curve value among all the other models [area under the curve = 0.808, 95% confidence interval (CI): 0.708–0.894]. The sensitivity and specificity of the ensemble model were 73.7% (95% CI: 52.6%–89.5%) and 74.5% (95% CI: 62.7%–86.3%), respectively. Conclusions: Machine learning model using the ensemble of logistic regression and support vector classifier most effectively predicted the excessive muscle loss following NACRT in patients with oesophageal cancer. This model can easily screen the patients with excessive muscle loss who need an active intervention or timely care following NACRT.