Machine-learning approaches that combine predictive performance with model interpretability may improve lung cancer status classification. This study aimed to develop and internally evaluate an Explainable Precision Screening Framework for lung cancer risk classification using demographic, behavioral, and symptom-based variables from a publicly available dataset.

This retrospective cross-sectional study analyzed a publicly available Kaggle dataset containing 309 records, including 270 labeled as lung cancer and 39 as non-cancer. Six models—logistic regression, support vector machine (SVM), random forest, LightGBM, XGBoost, and a stacking ensemble—were compared using a stratified hold-out test set and repeated stratified five-fold cross-validation. Performance was assessed using classification metrics with bootstrap 95% confidence intervals (CIs). A separate Shapley additive explanations (SHAP) analysis was applied to the standalone SVM model for exploratory feature attribution.

Across all models, accuracy ranged from 85% to 92% (ROC-AUC: 0.93–0.95). The stacking ensemble achieved 0.92 accuracy (95% CI: 0.85–0.98), 0.94 sensitivity (95% CI: 0.88–1.00), 0.75 specificity (95% CI: 0.40–1.00), 0.96 precision (95% CI: 0.89–1.00), 0.95 F1 score (95% CI: 0.91–0.99), and 0.95 ROC-AUC (95% CI: 0.89–0.99). Its PR-AUC was 0.993 (95% CI: 0.981–0.999), and its Brier score was 0.074 (95% CI: 0.037–0.121). SHAP analysis identified smoking, yellow fingers, coughing, chest pain, wheezing, shortness of breath, and age as the features contributing most strongly to its predictions.

Within this public retrospective dataset, the stacking ensemble was among the highest-performing models, whereas separate SHAP analysis of the standalone SVM model identified the features contributing most strongly to its predictions. Given the marked class imbalance, the absence of a reported clinical reference standard for the source labels, the framework requires independent validation in clinically verified multicenter cohorts before clinical use.

Upper gastrointestinal precancerous lesions are important targets for cancer screening and prevention. This study evaluated the diagnostic accuracy of artificial intelligence (AI)-assisted endoscopy for upper gastrointestinal precancerous lesions.

PubMed, Embase, MEDLINE, Cochrane Library, and IEEE Xplore were searched from inception to March 31, 2026. Studies reporting sensitivity and specificity, or sufficient data for their calculation, were included. Two reviewers independently extracted data. Pooled sensitivity, specificity, and the area under the receiver operating characteristic curve were estimated using a bivariate random-effects model.

Fifteen studies comprising 24 datasets and 19,578 records were included. Pooled sensitivity and specificity were 0.930 (95% confidence interval (CI): 0.886–0.958) and 0.944 (95% CI: 0.906–0.967), respectively; the diagnostic odds ratio was 223.79 (95% CI: 92.24–542.94), and the area under the receiver operating characteristic curve was 0.9661. Substantial heterogeneity was observed (bivariate I² = 73%). Among the variables formally evaluated by meta-regression, imaging modality was associated with heterogeneity (global test P = 0.005); image-enhanced endoscopy had higher sensitivity than white-light endoscopy (0.960 vs. 0.875). No significant publication bias was detected by Egger’s test (P = 0.833), Begg’s test (P = 0.641), or Deeks’ funnel plot asymmetry test (P = 0.053).

AI-assisted endoscopy shows high diagnostic accuracy for upper gastrointestinal precancerous lesions. Multicenter prospective studies are needed for validation.

Balloon-occluded transarterial chemoembolization (B-TACE) has emerged as a significant advancement in the locoregional treatment of hepatocellular carcinoma. This technique utilizes a balloon microcatheter selectively placed in target hepatic arteries to occlude blood flow and enhance drug accumulation within tumors while minimizing systemic exposure. The feasibility, safety, and effectiveness of the balloon occlusion technique have been verified. Recent studies have demonstrated that B-TACE achieves superior tumor response rates and potentially improves survival outcomes compared with conventional transarterial chemoembolization (C-TACE) techniques, particularly in cases with complex tumor vasculature or C-TACE-refractory disease. However, determining which patients would benefit from B-TACE requires comprehensive assessment. It remains to be determined in clinical practice whether this technique increases the risk of liver function impairment or is associated with specific complications. Further research is needed to better understand the technical conditions required for its clinical application, prognostic factors, and how it can be combined with other interventional techniques. This review summarizes the current literature on B-TACE, focusing on its technical principles, clinical efficacy, safety profile, and evolving role within the contemporary treatment landscape for advanced hepatocellular carcinoma, including its integration with systemic therapies.

Anal canal melanoma (ACM) is a rare, aggressive malignancy with an ominous prognosis. However, its associated factors are largely unknown. Therefore, we investigated potential independent associations of sex and self-reported race with ACM and physiological anal canal pigmentation.

Two case-control cohorts from a single institution in Miami, Florida, were evaluated. The biopsy cohort comprised 117 sequential patients evaluated prospectively for melanocytic cells/pigment and anal intraepithelial neoplasia (AIN)/squamous intraepithelial lesion (SIL) in anal transitional zone biopsies between January 2021 and August 2022. The melanoma cohort consisted of 28 patients diagnosed with ACM between January 2003 and August 2021 and 116 of the patients in the pigmentation cohort. Multivariable logistic regression analysis was conducted to examine independent factor associations.

In the biopsy cohort, anal transitional melanocytic cells/pigment were identified in 48% (26/54) of Black patients compared to 17% (10/59) of White patients. Multivariable analysis demonstrated that White race was inversely associated with mucosal pigmentation (odds ratio (OR) = 0.19, 95% confidence interval (CI): 0.08–0.48, P < 0.001). Conversely, White race was associated with ACM (OR = 6.25, 95% CI: 2.07–18.81, P = 0.001). Male sex was also inversely associated with ACM (OR = 0.18, 95% CI: 0.07–0.47, P < 0.001). No significant correlations were observed between mucosal pigmentation and AIN/SIL or human immunodeficiency virus status.

Anal transitional zone pigmentation is more prevalent in self-reported Black individuals but is not associated with neoplastic squamous cell precursors. White (versus Black) individuals and female (versus male) individuals both have a significant association with ACM.

Metabolic dysfunction-associated fatty liver disease (MAFLD) is a multifactorial disorder driven by complex interactions among genetic, epigenetic, transcriptional, proteomic, metabolic, and microbiome factors. Single-omics technologies have provided valuable insights into disease mechanisms, yet each layer captures only a partial view of MAFLD pathogenesis. Recent advances in multi-omics integration allow systematic dissection of molecular networks, cell differentiation trajectories, intercellular communication, and spatial organization, revealing causal links between molecular alterations and tissue phenotypes. Horizontal integration connects different omic layers within the same biological state, while longitudinal integration captures dynamic changes across disease stages. Emerging spatial transcriptomics, proteomics, and metabolomics techniques further enable in situ mapping of cellular and molecular heterogeneity, uncovering spatially defined pathogenic niches and regulatory hubs. Collectively, these integrated approaches offer a multidimensional framework for understanding MAFLD progression, identifying potential biomarkers, and guiding precision therapeutic strategies. Future efforts should focus on standardized multi-omics pipelines, interdisciplinary collaboration, and functional validation to translate these insights into clinical applications.

Biliary atresia (BA) is a severe pediatric cholangiopathy characterized by rapidly progressive liver fibrosis. This study aimed to characterize scar-associated macrophages and investigate the role of PLG–PLGRKT signaling in BA-associated fibrogenesis.

Single-cell RNA sequencing and spatial transcriptomics were applied to liver tissues from patients with BA and non-BA controls. Key findings were validated in an independent cohort using quantitative polymerase chain reaction and multiplex immunohistochemistry. The functional role of the PLGRKT pathway was further examined using primary human peripheral blood mononuclear cell-derived macrophages with small interfering RNA (siRNA)-mediated PLGRKT knockdown, together with co-culture systems involving LX-2 hepatic stellate cells and human liver organoids. In vivo therapeutic potential was evaluated in a murine bile duct ligation model of cholestatic liver fibrosis using macrophage-targeted Plgrkt–Trem2 antibody–siRNA conjugates.

In BA, scar-associated macrophages (SAMs) increased with fibrosis progression and co-localized with hepatic stellate cells in fibrotic areas. PLGRKT was upregulated in BA liver tissue and increased during monocyte-to-macrophage differentiation. In primary human macrophages, plasminogen induced a PLGRKT-dependent pro-fibrotic phenotype, and conditioned medium from these cells increased COL1A1 deposition in hepatic stellate cells and human liver organoids. In vivo, macrophage-targeted Plgrkt–Trem2 antibody–siRNA conjugates reduced SAM accumulation and attenuated bile duct ligation-induced liver fibrosis.

These findings support a role for SAMs and the PLGRKT–SAM axis in BA-associated liver fibrosis and suggest that PLGRKT warrants further investigation as a potential macrophage-directed anti-fibrotic target.

Non-muscle-invasive bladder cancer (NMIBC) is characterized by a high recurrence rate and a substantial long-term surveillance burden. However, current detection and surveillance strategies rely largely on invasive cystoscopy and urine cytology, which are limited by patient discomfort, suboptimal adherence, and insufficient sensitivity, particularly for low-grade disease. This mini review examines the role of liquid biopsy in the detection, risk stratification, and surveillance of NMIBC. It summarizes current evidence on circulating tumor DNA, circulating tumor cells, exosomes and extracellular vesicles, urinary tumor DNA, and DNA methylation and protein biomarkers in blood or urine. For detection, urine-based molecular assays complement cystoscopy and cytology in the noninvasive assessment of patients with suspected bladder cancer. For risk stratification, molecular detection of residual disease and longitudinal biomarker changes help identify patients at increased risk of recurrence or progression. During surveillance, urine-based assays support earlier recurrence detection and, in selected settings, help reduce the frequency of cystoscopy. Overall, liquid biopsy is a promising minimally invasive complement to conventional NMIBC management although technical standardization and prospective clinical validation are required before routine implementation.