Infected pancreatic necrosis (IPN) represents a severe complication of acute pancreatitis, commonly linked with mortality rates ranging from 15% to 35%. However, the present mortality prediction tools for IPN are limited and lack sufficient sensitivity and specificity. This study aims to develop and validate an explainable machine learning (ML) model for death prediction among patients with IPN. We performed a prospective cohort study of 344 patients with IPN consecutively enrolled from a large Chinese tertiary hospital from January 2011 to January 2023. Ten ML models were developed to predict 90-day mortality in these patients. A benchmarking test, involving nested resampling, automatic hyperparameter tuning and random search techniques, was conducted to select the ML model. Sequential forward selection method was employed to select the optimal feature subset from 31 candidate subsets to simplify the model and maximize predictive performance. The final model was internally validated with the 1000 bootstrap method and externally validated using an independent cohort of 132 patients with IPN retrospectively collected from another Chinese tertiary hospital from January 2018 to January 2023. The SHapley Additive exPlanations (SHAP) method was employed to interpret the model in terms of features importance and features effect. The final model constructed with optimal feature subset was deployed as an interactive web-based Shiny app. Random survival forest (RSF) model showed the best predictive performance than other 9 ML models (internal validation, C-index = 0.863 [95% CI: 0.854-0.875]; external validation, C-index = 0.857 [95% CI: 0.850-0.865]). Multiple organ failure, Acute Physiology and Chronic Health Examination II (APACHE II) score ≥20, duration of organ failure ≥21 days, bloodstream infection, time from onset to first intervention <30 days, Bedside Index of Severity in Acute Pancreatitis score ≥3, critical acute pancreatitis, age ≥ 50 years, and hemorrhage were 9 most important features associated with mortality. Furthermore, SHAP algorithm revealed insightful nonlinear interactive associations between important predictors and mortality, identifying 9 features pairs with high interaction SHAP value and clinical significance. Two interactive web-based Shiny apps were developed to enhance clinical practicability: https://rsfmodels.shinyapps.io/IPN_app/ for cases where the APACHE II score was available and https://rsfmodels.shinyapps.io/IPNeasy/ for cases where it was not. An explainable ML model for death prediction among IPN patients was feasible and effective, suggesting its superior potential in guiding clinical management and improving patient outcomes. Two publicly accessible web tools generated for the optimized model facilitated its utility in clinical settings. The Natural Science Foundation of Hunan Province (2023JJ30885), Postdoctoral Fellowship Program of CPSF (GZB20230872), The Youth Science Foundation of Xiangya Hospital (2023Q13), The Project Program of National Clinical Research Center for Geriatric Disorders of Xiangya Hospital (2021LNJJ19).

Background: Endoscopic thyroidectomy has been preliminarily proven effective and safe for thyroid diseases. The cosmetic outcomes and life quality are critical contents of postoperative assessment. This review will primarily focus on the assessment methods and results related to cosmetic outcomes, sensory alteration of surgical area, and quality of life following endoscopic thyroidectomy. Methods: A comprehensive search of published articles within the last decade was conducted using the terms “endoscopic/robotic thyroidectomy,” “patient satisfaction scores,” “questionnaire,” “quality of life,” and “cosmetic” in PubMed. Results: Assessment methods for postoperative cosmetic satisfaction and sensory alterations encompassed verbal/visual analog scales, scar evaluations, Semmes–Weinstein monofilament tests, and more. The evaluation of postoperative quality of life in endoscopic thyroidectomy involved tools such as SF-36, SF-12, thyroid-specific questionnaires, thyroid cancer-specific quality of life questionnaires (THYCA-QOL), as well as assessments related to voice and swallow function. The cosmetic results of endoscopic thyroidectomy generally surpassed those of open thyroidectomy, while the quality of life in endoscopic procedures was either superior or equivalent to that in open thyroidectomy, especially with respect to general health, role emotion, and vitality. Conclusions: Assessments of cosmetic outcomes and sensory alterations following endoscopic thyroidectomy predominantly relied on patients’ subjective feelings. The objective and subjective perspectives of scar assessments remain underutilized. In addition, postoperative laryngoscopy and voice function assessments in endoscopic thyroidectomy procedures require more attention.

The prevalence of genetic mutations in thyroid cancer varies significantly among different ethnic backgrounds. The present study aimed to investigate the clinical potential of BRAF V600E in a large group of homogenous Han Chinese patients. From 2018 to 2021, 6232 thyroid disease patients who underwent thyroidectomy at our hospital were enrolled. We measured the diagnostic value of BRAF and plotted ROC curves. Patients with full clinical-pathological data were selected and divided into the BRAF mutation and wild type groups. We conducted univariate and multivariate analyses to quantify the differences in potential predictive factors of papillary thyroid carcinoma (PTC) patients between the groups. Kaplan–Meier survival analysis was used to estimate overall recurrence and recurrence rate. The prevalence of BRAF V600E mutation was 86.0% in PTCs. The sensitivity and specificity of BRAF mutation for diagnosing PTC from suspicious lesions were 85.5% and 100%, respectively. The sensitivity and specificity of BRAF analysis in the indeterminate cytology group were 72.5% and 100%, respectively. BRAF mutation showed an independent association with older age, negative HT, larger tumor size, extrathyroidal extension, and multifocality in PTCs. In micro-PTCs (tumor size ≤ 1), the mutation was also positively correlated with progressive phenotypes of extrathyroidal extension and multifocality. BRAF mutation was associated with poorer recurrence-free probability in Kaplan–Meier survival analysis. This large single-center study reveals that BRAF V600E is highly prevalent in the Han Chinese population and demonstrates BRAF V600E mutation testing has high diagnostic accuracy and its strong association with the progress of aggressiveness in PTCs and a higher probability of recurrence. BRAF mutation can serve as an accurate marker for diagnosis and decision-making with great value.

Immunogenic cell death (ICD) is a novel cell death mechanism that activates and regulates the immune system against cancer. However, its prognostic value in liver cancer remains unclear. Here, several algorithms such as correlation analysis, Cox regression analysis, and Lasso regression analysis were carried out to evaluate the prognostic value of ICD-related genes in patients with liver cancer. Three ICD-related prognostic genes, the prion protein gene (PRNP), dynamin 1-like gene (DNM1L), and caspase-8 (CASP8), were identified and used to construct a risk signature. Patients with liver cancer were categorized into high- and low-risk groups using the ICD-related signature. Subsequently, a multivariate regression analysis revealed that the signature was an independent risk factor in liver cancer [hazard ratio (HR) = 6.839; 95% confidence interval (CI) = 1.625–78.785]. Patient survival was also predicted using the risk model, with area under the curve values of 0.75, 0.70, and 0.69 for 1-, 3-, and 5-year survival, respectively. Finally, a prognostic nomogram containing the clinical characteristics and risk scores of patients was constructed. The constructed ICD-related signature could serve as a prognostic and immunotherapeutic biomarker in liver cancer.

Purpose: This retrospective cohort study aimed to reevaluate the prognostic impact of sex and determine whether age modifies the effect of sex on cancer-specific survival (CSS) in PTC patients. Methods: Data for PTC patients diagnosed between 2004 and 2015 were retrieved from the SEER database. The primary outcome was CSS. The effect of Sex was evaluated using both relative (hazard ratios, HRs) and absolute measures (survival differences). Additionally, the effect of sex modified by age was assessed using restricted cubic spline curves from the Cox and Poisson models, with further analysis of the interaction between sex and age. Results: Of 77,349 patients, 16,152 (20.9%) were male. Men exhibited older age, more aggressive clinicopathological features, and received more radioactive iodine treatment. Multivariate Cox analysis determined male sex as an independent risk factor (adjusted HR: 1.46 (1.24–1.70). The 10-year and 15-year survival differences between men and women were 0.46% (95% CI, 0.25%−0.67%) and 0.77% (95% CI, 0.31%−1.22%), respectively. Moreover, a nonlinear effect for sex across age was observed, with HRs for men plateauing below age 50 and decreasing thereafter. Importantly and conversely, before age 50, the absolute survival difference increased slightly with age, but after 50, it significantly widened. Furthermore, A significant negative multiplicative interaction between sex and age was found. Conclusions: Our analyses provide robust evidence that male sex is indeed an independent risk factor for CSS in PTC patients. Although younger female patients show a relative survival advantage, this does not translate into a substantial absolute benefit, which widens with advancing age.