98 papers
This study demonstrates that axillary de-escalation is a feasible strategy for ypN1 breast cancer patients with a single residual positive node after neoadjuvant therapy, but not for those with multiple residual nodes, highlighting the critical prognostic heterogeneity within this disease category.
This multi-phase validation study demonstrates that an agentic AI system significantly improves the efficiency, accuracy, and consistency of detecting and grading immune-related adverse events in clinical notes compared to manual review, while reducing annotation time by 40% and enhancing inter-annotator agreement.
This study utilizes spatial multi-omics and machine learning on 498 clear cell renal cell carcinoma patients to define three distinct survival ecotypes with unique cellular, genomic, and metabolic features, demonstrating that these profiles outperform standard clinical data in predicting outcomes and can be identified directly from routine H&E images to guide immunotherapy decisions.
This study presents an optimized MP V2 multi-cancer early detection classifier that, through refined model architecture, achieves significantly improved sensitivity for early-stage cancers compared to its predecessor (MP V1) while maintaining high specificity across independent validation cohorts.
This study demonstrates that frequent monitoring of serum IL-6 levels using a simple in-house microfluidic bead immunoassay can predict the onset of CAR-T-associated neurotoxicity (ICANS) the following day, offering a valuable tool for early intervention and improved patient management.
This study introduces GxSurv, a machine learning framework that utilizes a 3-month tumor growth rate (g-rate) derived from on-treatment PSA levels to accurately predict overall survival in metastatic castration-resistant prostate cancer, significantly outperforming traditional models and enabling timely, personalized clinical decision-making.
This paper uses a calibrated Monte Carlo simulation to demonstrate that systemic diagnostic delays in the NHS, rather than assay failure, caused "stage slip" (progression from early to late stages during workup) which masked the NHS-Galleri trial's success in reducing advanced cancer diagnoses and prevented it from meeting its primary endpoint.
This study challenges the traditional view of breast cancer heterogeneity by demonstrating, through a large-scale quantitative analysis of 1,652 specimens, that an ER/PR signaling hierarchy rather than distinct clinical subtypes governs the full spectrum of the disease and provides a more accurate prognostic framework for patient survival.
By analyzing over 5,000 breast tumors, this study establishes a unifying framework that classifies breast cancer into two distinct functional programs (proliferative vs. signaling), resolving the prognostic ambiguity of PIK3CA mutations and introducing the T-OMICS system to translate complex genomic data into clinically actionable, tiered tumor profiles for improved risk assessment and treatment stratification.
This study demonstrates that integrating high-dimensional radiomic features from perilesional oedema and white-matter disconnectome maps with clinical data significantly improves the prediction of progression-free survival in patients with IDH-wildtype glioblastoma compared to using clinical factors alone.
This study applies the Causal Analysis of Survival Trajectories (CAST) framework to 776 lower-grade glioma patients, revealing that chemotherapy provides consistent, sustained survival benefits with significant time-varying gains, while radiotherapy effects are more modest and sensitive to confounding, with age identified as the primary driver of treatment heterogeneity.
This study introduces NeuroMDAVIS-FS, an unsupervised deep learning framework that integrates genomic, transcriptomic, and proteomic data to identify robust molecular signatures for stratifying lung cancer patients into high- and low-risk survival groups, significantly outperforming traditional clinical models in prognostic accuracy.
This systematic review and network meta-analysis protocol aims to evaluate and rank the comparative efficacy of second-line or later systemic treatments for unresectable, advanced, or recurrent soft tissue sarcomas in patients previously treated with anthracyclines, addressing the current lack of consistent clinical guidelines due to insufficient head-to-head evidence.
This qualitative study of reproductive-aged women with gynecological cancers in Ghana reveals that cancer-related infertility constitutes a profound multidimensional burden threatening womanhood and social standing, necessitating the integration of fertility counseling, psychosocial support, and economic protection into local cancer care.
This randomized, double-blind, sham-controlled trial demonstrates that daily intraoral LED-based photobiomodulation is a safe and effective intervention that significantly reduces the incidence and severity of oral mucositis and associated complications in head and neck cancer patients undergoing radiotherapy.
This study demonstrates that combining Arylsulfatase B (ARSB), which promotes melanoma cell apoptosis via COP1 upregulation, with Pembrolizumab, which targets cytotoxic lymphocytes, yields synergistic effects that reduce tumor invasiveness and improve survival outcomes in metastatic B16F10 melanoma.
Onco-Shikshak V7 is a pioneering AI-native adaptive learning platform for medical oncology that mitigates LLM risks and addresses knowledge obsolescence by integrating a unified cognitive architecture of learning science principles, multi-disciplinary specialist agents, and closed-loop feedback mechanisms into authentic clinical workflows.
This study introduces and validates PROGRESS, a simplified machine-learning-derived risk stratification score for castration-resistant prostate cancer that utilizes three routinely available laboratory variables (PSA, ALP, and AST) to effectively distinguish patient risk subgroups and guide individualized clinical decision-making across diverse metastatic and non-metastatic settings.
This cross-sectional study of 3,141 U.S. counties reveals that within-group socio-behavioral risk profiles vary significantly across local cancer mortality gradients, demonstrating that analyzing domain-specific determinants rather than relying on group averages is essential for developing precise, equity-oriented strategies to address breast and prostate cancer disparities.
This Czech national study utilized linked administrative and registry data to evaluate stage-stratified quality indicators for non-small-cell lung cancer care, revealing that despite improvements in multidisciplinary team discussions and centralization, fewer than half of patients initiated treatment within eight weeks and significant regional disparities in biomarker testing persist, leading to the implementation of these metrics as a national tool for continuous quality evaluation.