Background: Multidisciplinary Tumor Councils (MDTs) are vital platforms that provide tailored treatment plans for cancer patients by combining expertise from various medical disciplines. Recently, Artificial Intelligence (AI) tools have been investigated as decision-support systems within these councils. Methods: In this prospective study, the compatibility of AI (ChatGPT-4.0) with MDT decisions was evaluated in 100 cancer patients presented to the tumor council between November 2024 and January 2025. AI-generated treatment recommendations based on anonymized, detailed clinical summaries were compared with real-time MDT decisions. Cohen’s Kappa and Spearman correlation tests were used for statistical analysis. Results: Neoadjuvant treatment (45%) and surgery (36%) were the most frequent MDT decisions. AI recommended surgery (39%) and neoadjuvant treatment (37%) most frequently. A high concordance rate of 76.4% was observed between AI and MDT decisions (κ = 0.764 [95% CI; 0.658–0.870] p < 0.001, ρ = 0.810 [95% CI; 0.729–0.868], p < 0.001). Most inconsistencies arose in cases requiring individualized decisions, indicating AI’s current limitations in incorporating contextual clinical judgment. Conclusion: AI demonstrates substantial agreement with MDT decisions, particularly in cases adhering to standardized oncological guidelines. However, for AI integration into clinical workflows, it must evolve to interpret real-time patient data and function transparently within ethical and legal frameworks.
Of the 4 molecular subtypes of endometrial cancer (EC), p53-abnormal (p53abn) EC is associated with abundant copy number alterations and the worst clinical outcome. Patients with p53abn EC have the highest risk of disease recurrence and death, independent of tumor grade and histologic subtype. Currently, all invasive p53abn ECs are considered high risk, and no prognostic biomarkers have yet been found that can aid in clinical management. Here, we aimed to test whether loss of retinoblastoma (RB) protein expression using immunohistochemistry has the potential for prognostic refinement of p53abn EC. A large cohort of 227 p53abn ECs collected from the PORTEC-1/2/3 clinical trials and the Medisch Spectrum Twente cohort study was investigated, and RB loss was identified in 7.0% (n = 16/227). RB-lost p53abn ECs were predominantly high-grade endometrioid ECs (n = 6, 37.5%) and carcinosarcomas with endometrioid-type epithelial component (n = 5, 31.3%). Histologically, RB-lost p53abn ECs were typified by high-grade nuclear atypia (n = 16, 100%), predominantly solid growth pattern (n = 15/16, 93.8%), and polypoid growth (n = 9/16, 56.3%). Copy number loss involving the RB1 locus was identified in the majority of RB-lost p53abn EC (n = 13/14, 92.9%), explaining the loss of RB expression. Comparative analysis also showed that RB-lost p53abn ECs were diagnosed at earlier stages than RB-retained p53abn EC (P = .014). Interestingly, RB-lost p53abn EC showed prolonged time to overall recurrence (P = .038), even within stage I alone (P = .040). These findings highlight distinct morphomolecular features in RB-lost p53abn ECs and confirm the utility of RB immunohistochemistry as a surrogate for underlying molecular RB1 alterations. To our knowledge, this is the first study to show the potential use of RB in prognostic refinement of p53abn EC, although validation is warranted.
PURPOSE: Geographical and racial diversity may influence endometrial cancer (EC) prognosis, yet its impact remains underexplored. In South Africa (SA), the rising incidence of EC underscores the need to investigate potential biologic differences. Molecular classification of EC offers valuable prognostic insights that could help address disparities and improve care. This study evaluated the prevalence and prognostic significance of molecular subtypes in a South African high-intermediate and high-risk EC cohort. MATERIALS AND METHODS: We included 133 patients with high-intermediate and high-risk EC diagnosed in SA between January 2017 and December 2021. Clinical, demographic (including self-identified race), and follow-up data were collected. Central pathology review assessed histotype, grade, lymphovascular space invasion, and International Federation of Gynecology and Obstetrics 2009 stage. Molecular subtyping followed the WHO 2020 algorithm using targeted next-generation sequencing and immunohistochemistry for p53, mismatch repair (MMR) proteins, and ER. Shallow whole-genome sequencing (sWGS) assessed genome-wide copy number alterations. RESULTS: Among 131 patients with complete molecular classification, the most common subtype was p53-abnormal (p53abn, n = 71; 54.2%), followed by MMR-deficient (MMRd, n = 30; 22.9%), no specific molecular profile (NSMP, n = 21; 16.0%), and POLE -ultramutated ( POLE mut, n = 9; 6.9%). Nonendometrioid EC (NEEC) predominated (n = 82; 61.7%). High-grade endometrioid EC and NEEC were more frequent in non-White patients ( P = .030). Molecular subtypes were significantly associated with overall recurrence ( P = .029), with no recurrences in POLE mut ECs and the worst outcomes in p53abn ECs. sWGS revealed higher CN burdens in p53abn ECs, with recurrent focal alterations involving CCNE1 amplification and RB1 loss. CONCLUSION: To our knowledge, this study is the first to demonstrate the prognostic value of EC molecular classification in a South African cohort. These findings support the global relevance of molecular EC subtyping. The urgent need for access to molecular diagnostics or cost-effective alternatives in resource-limited settings is highlighted.
Immunoglobulin heavy chain variable region (IGHV) mutational status and B-cell receptor (BCR) stereotypy are established prognostic markers in chronic lymphocytic leukemia (CLL). However, immunogenetic data from Türkiye and surrounding regions are scarce. We evaluated IGHV mutational status, BCR stereotypy including nearest subset assignment, and their clinical and cytogenetic correlates in a real-world Turkish CLL cohort. We retrospectively analyzed 145 patients with CLL at a tertiary referral center in Türkiye. IGHV mutational status was determined by next-generation sequencing (98% germline homology cutoff). BCR stereotypy was assigned using ARResT/AssignSubsets. Cytogenetic abnormalities were assessed by fluorescence in situ hybridization (FISH). Time-to-first treatment (TTFT), progression-free survival (PFS), and overall survival (OS) were analyzed by Kaplan–Meier method, with multivariate Cox regression for TTFT. Unmutated IGHV was detected in 55.2% of patients, higher than Western reports but consistent with Mediterranean and Middle Eastern cohorts. Unmutated cases showed adverse cytogenetics—del(11q) and multiple concurrent FISH abnormalities—whereas del(13q) predominated in mutated cases. At a median follow-up of 43.0 months unmutated status strongly predicted a profoundly shorter median TTFT compared to mutated cases (17.0 vs. 70.0 months; p < 0.0001). Notably, while an unmutated IGHV status strongly predicted a significantly shorter TTFT, it did not translate into worse PFS or OS compared to mutated cases, reflecting the transformative real-world impact and rescue capacity of modern targeted therapies utilized upon disease progression. Major stereotyped subsets were present in 15.9% of patients; subset #2 was absent, while subset #1 was predominant (39.1%). Subsets #1 and #64B were overrepresented among relapsed cases. Nearest subset #77 showed rapid progression despite mutated IGHV. CLL in Türkiye demonstrates region-specific immunogenetic features while preserving established clinico-biological correlations. Integration of IGHV status, cytogenetics, and BCR stereotypy may improve risk stratification in underrepresented populations.