Search

Background and objective: Androgen deprivation therapy (ADT) is associated with reduced muscle and increased fat mass in patients with prostate cancer. However, the threshold for body composition changes associated with survival during ADT remains unclear. This study aimed to identify body composition change thresholds for all-cause mortality during ADT. Methods: We enrolled 538 patients with prostate cancer (332 and 206 in the derivation and external validation cohorts, respectively) who underwent radiotherapy and ADT at two tertiary centers. Computed tomography (CT) images at baseline and 6 mo after ADT initiation were retrieved for an analysis. Skeletal muscle index (SMI), subcutaneous adipose tissue index (SATI), and visceral adipose tissue index (VATI) were measured using CT at the L3 vertebral level. Optimal thresholds for body composition changes were determined using the Shapley Additive Explanations (SHAP) method and validated using a Cox proportional hazard model. Key findings and limitations: Changes in SMI, SATI, and VATI were the three most important features for predicting all-cause mortality. SMI change was inversely associated with the all-cause mortality risk, and changes in the SATI and VATI showed a U-shaped relationship with the all-cause mortality risk. SMI loss (≥4.0%), SATI gain (≥15.0%), and VATI gain (≥12.0%) were independently associated with an increased all-cause mortality risk (SMI loss: hazard ratio, 6.79, p

Abstract Background Skeletal muscle loss during treatment is associated with poor survival outcomes in patients with ovarian cancer. Although changes in muscle mass can be assessed on computed tomography (CT) scans, this labour‐intensive process can impair its utility in clinical practice. This study aimed to develop a machine learning (ML) model to predict muscle loss based on clinical data and to interpret the ML model by applying SHapley Additive exPlanations (SHAP) method. Methods This study included the data of 617 patients with ovarian cancer who underwent primary debulking surgery and platinum‐based chemotherapy at a tertiary centre between 2010 and 2019. The cohort data were split into training and test sets based on the treatment time. External validation was performed using 140 patients from a different tertiary centre. The skeletal muscle index (SMI) was measured from pre‐ and post‐treatment CT scans, and a decrease in SMI ≥ 5% was defined as muscle loss. We evaluated five ML models to predict muscle loss, and their performance was determined using the area under the receiver operating characteristic curve (AUC) and F1 score. The features for analysis included demographic and disease‐specific characteristics and relative changes in body mass index (BMI), albumin, neutrophil‐to‐lymphocyte ratio (NLR), and platelet‐to‐lymphocyte ratio (PLR). The SHAP method was applied to determine the importance of the features and interpret the ML models. Results The median (inter‐quartile range) age of the cohort was 52 (46–59) years. After treatment, 204 patients (33.1%) experienced muscle loss in the training and test datasets, while 44 (31.4%) patients experienced muscle loss in the external validation dataset. Among the five evaluated ML models, the random forest model achieved the highest AUC (0.856, 95% confidence interval: 0.854–0.859) and F1 score (0.726, 95% confidence interval: 0.722–0.730). In the external validation, the random forest model outperformed all ML models with an AUC of 0.874 and an F1 score of 0.741. The results of the SHAP method showed that the albumin change, BMI change, malignant ascites, NLR change, and PLR change were the most important factors in muscle loss. At the patient level, SHAP force plots demonstrated insightful interpretation of our random forest model to predict muscle loss. Conclusions Explainable ML model was developed using clinical data to identify patients experiencing muscle loss after treatment and provide information of feature contribution. Using the SHAP method, clinicians may better understand the contributors to muscle loss and target interventions to counteract muscle loss.

Early-term neonates (with a gestational age (GA) of 37 and 0/7 weeks to 38 and 6/7 weeks) face higher morbidities, including respiratory and neurodevelopmental issues, than full-term (39 and 0/7 weeks to 40 and 6/7 weeks) infants. This study explores whether hyperbilirubinemia necessitating phototherapy also differs between these groups. A retrospective study was conducted on neonates born from January 2021–June 2022, excluding those with specific conditions. Evaluated factors included GA, birth weight, bilirubin levels, glucose-6-phosphate dehydrogenase (G6PD) deficiency, and feeding type, with phototherapy given as per AAP guidelines. Of 1085 neonates, 356 met the criteria. When stratifying the neonates based on the need for phototherapy, a higher proportion of early-term neonates required phototherapy compared to full-term (p < 0.05). After factoring in various risks (GA; birth weight; gender; feeding type; G6PD deficiency; transcutaneous bilirubin levels at 24 h and 24–48 h postpartum; maternal diabetes; and the presence of caput succedaneum or cephalohematoma), early-term neonates were more likely to need phototherapy than full-term babies (OR: 2.15, 95% CI: 1.21 to 3.80). The optimal cut-off for transcutaneous bilirubin levels 24–48 h postpartum that were used to predict phototherapy need was 9.85 mg/dl. In conclusion, early-term neonates are at a greater risk for developing jaundice and requiring phototherapy than full-term neonates. Monitoring bilirubin 24–48 h postpartum enhances early prediction and intervention.

Psychotic disorders are complex and caused by interplay of genetic and environmental factors. Influenza is a common infectious disease in humans, and it has been suggested that maternal influenza is an estimated risk factor for psychotic disorders, especially for schizophrenia. In view of conflicting results of this association in literature, we performed the strict meta-analysis to examine whether maternal influenza is a risk factor for psychosis in the children. Four ecological studies and three birth cohort studies were included in our meta-analysis. It has been observed that the Risk Ratio (RR) of maternal influenza on psychosis is 1.062 (95% Confidence Interval (CI) = 1.004-1.123) for the analysis of ecological studies and the RR is 1.564(95%CI=1.051-2.324) for the analysis of birth cohort studies. Furthermore, a survey of pregnant women and fetus' health in Nanjing of China indicated that only 1.5% of women received the influenza vaccine before pregnancy, 0.4% received it during pregnancy, and 5.1% were willing to receive the influenza vaccine if necessary. These results showed that gestational influenza could increase mental disorders risks in adult offspring besides its established harms for gravidas. Results suggest it might be effective to increase attention to gravidas to protect them from influenza infection through encouragement of vaccinations.