Background/Objectives: Artificial intelligence (AI) has emerged as a promising field in the era of personalized oncology due to its potential to save time and workforce while serving as a supportive tool in patient management decisions. Although several studies in the literature have explored the integration of AI into oncology practice across different tumor types, available data remain limited. In our study, we aimed to evaluate the role of AI in the management of complex cancer cases by comparing the decisions of an in-house tumor board and ChatGPT-4o for patients with various tumor types. Methods: A total of 102 patients with diverse cancer types were included. Treatment and follow-up decisions proposed by both the tumor board and ChatGPT-4o were independently evaluated by two medical oncologists using a 5-point Likert scale. Results: Analysis of agreement levels showed high inter-rater reliability (κ = 0.722, p < 0.001 for tumor board decisions; κ = 0.794, p < 0.001 for ChatGPT decisions). However, concordance between the tumor board and ChatGPT was low, as reflected in the assessments of both raters (Rater 1: κ = 0.211, p = 0.003; Rater 2: κ = 0.376, p < 0.001). Both raters more frequently agreed with the tumor board decisions, and a statistically significant difference between tumor board and AI decisions was observed for both (Rater 1: Z = +4.548, p < 0.001; Rater 2: Z = +3.990, p < 0.001). Conclusions: These findings suggest that AI, in its current form, is not yet capable of functioning as a standalone decision-maker in the management of challenging oncology cases. Clinical experience and expert judgment remain the most critical factors in guiding patient care.

Background: Conventional disproportionality analysis assumes comparable background event rates between case and control cohorts. In patients with primary endocrine malignancies treated with immune checkpoint inhibitors (ICIs), this assumption fails: disease-inherent hormonal dysregulation and therapy-related sequelae inflate background event rates and may produce signals misattributed to ICI exposure. No prior study has used tumor-type-specific reference populations to separate drug-attributable from disease-inherent signals in this setting. Methods: Forty quarterly FAERS cycles (Q1 2015 to Q4 2024) were analyzed after deduplication of 2,264,070 reports. In a pooled analysis, 329 ICI-treated endocrine cancer cases were compared with 80,191 ICI-treated non-endocrine cancer controls across six pre-specified endocrine immune-related adverse event categories, with false discovery rate (FDR) correction. The central step was a confounding-aware reanalysis comparing ICI-exposed patients of a given tumor type against a reference cohort with the same malignancy but no ICI exposure, using logistic regression adjusted for age and sex. The thyroid carcinoma association was tested using reporter type, Firth penalized regression, multiple imputation, and a tipping-point analysis. Results: Pooled adrenal insufficiency did not reach the signal threshold after FDR correction (ROR = 1.922; 95% CI 1.051–3.513; q = 0.143). This non-significance concealed two opposing patterns. In ACC, adrenal insufficiency was the strongest uncorrected subgroup signal yet was not associated with ICI exposure after adjustment (OR = 0.58; 95% CI 0.09–1.95); with four exposed events and 12.6% power, this subgroup cannot confirm or exclude an association. In thyroid carcinoma, ICI exposure showed markedly higher adrenal insufficiency reporting odds (OR = 13.33; 95% CI 4.81–31.85), remaining positive under reporter adjustment, Firth regression, and multiple imputation, with a tipping-point analysis indicating only implausibly extreme confounding could nullify it. Conclusion: Pooled pharmacovigilance can misclassify drug-attributable and disease-inherent events. Tumor-type-specific reference modeling separates them: ACC data are most consistent with disease-inherent pathophysiology, whereas thyroid carcinoma shows a robust adrenal insufficiency signal. We interpret the thyroid signal as hypothesis-generating, since differential endocrine surveillance may contribute to its magnitude, and prospective validation is warranted.

Aims: Hypercalcemia is a malignancy-associated oncologic emergency, and evaluating short-term mortality in hospitalized patients is critical for predicting prognosis and guiding treatment. This study assessed 30-, 60-, and 90-day mortality rates in patients hospitalized for hypercalcemia and compared short-term survival according to the corrected calcium (dCa) level determined by receiver operating characteristic (ROC) analysis based on 90-day mortality. Methods: A total of 135 patients were included. ROC analysis was performed to identify the optimal dCa cutoff for predicting 90-day mortality. Patients were divided into low and high dCa groups, and survival was compared using the Kaplan–Meier method. A p-value

Aims: Malignancy-associated hypercalcemia (MAH) is a severe metabolic complication affecting 2-3% of cancer patients, with higher prevalence in multiple myeloma (20-30%), lung cancer (12-15%), and breast cancer (10-20%). Median survival following MAH diagnosis ranges from 25 to 68 days, highlighting its status as an oncological emergency. This retrospective study examines demographic characteristics, clinical findings, treatment responses, and survival outcomes in patients with malignant hypercalcemia, with particular emphasis on the influence of bone metastasis on the presentation, severity, and management of hypercalcemia.Methods: This retrospective cohort study included 124 cancer patients aged 18 years or older who were hospitalized for malignant hypercalcemia at a tertiary oncology training and research hospital between January 2018 and December 2023. Inclusion criteria were a corrected serum calcium level of at least 10.5 mg/dl and a diagnosis of active malignancy. Collected data encompassed demographic characteristics, primary cancer diagnosis, disease stage, presence of bone metastases, laboratory values, treatment modalities, treatment responses, and survival times. Statistical analyses were performed using SPSS 26.0. Survival was assessed using the Kaplan-Meier method, and inter-group comparisons were performed using the log-rank test. A p-value below 0.05 was considered statistically significant. Results: The median age of the cohort was 58 years (range: 21-90 years), with an equal gender distribution (50.0% female, 50.0% male). The median corrected calcium level at diagnosis was 12.77 mg/dl (range: 10.5-21.0 mg/dl). Bone metastases were identified in 66.9% of patients at the time of malignant hypercalcemia diagnosis, with primary tumor distribution as follows: breast cancer 33.9%, lung cancer 20.1%, and other cancers 46.0%. Treatment modalities comprised bisphosphonates (66.9%), hydration alone (23.4%), and denosumab (9.7%). The median time to normalization of hypercalcemia was 4.0 days (range: 1-16), varying by treatment: hydration-diuretic 3.0 days, bisphosphonates 4.0 days, and denosumab 3.0 days (p=0.032). After hypercalcemia diagnosis, the median survival was 2.0 months (range: 0-60), with a 75% mortality rate within 6 months. Prior bisphosphonate use correlated with improved survival in breast cancer patients (57.0 vs 22.0 months, p=0.002), but not in lung cancer patients (8.0 vs 8.0 months, p>0.05). At the end of follow-up, 91.9% of patients had died.Conclusion: Malignant hypercalcemia mostly affects patients with advanced cancer and a high rate of bone metastasis (66.9%). However, having bone involvement did not independently affect survival or the time it took for calcium levels to return to normal. The only factor that predicted poor survival after hypercalcemia was Eastern Cooperative Oncology Group (ECOG) performance status, which suggests that systemic factors are more important than the extent of bone disease in determining outcomes. The longer survival seen in breast cancer patients who had used bisphosphonates before should be viewed with caution, as this may be due to immortal time bias and confounding by indication. Overall, these results highlight the poor outlook for malignant hypercalcemia and stress the need for early detection and proper treatment.

Aims: Small cell lung cancer (SCLC) is an aggressive malignancy with limited survival, underscoring the need for accessible prognostic markers. This study aimed to evaluate the prognostic value of the hemoglobin, albumin, lymphocyte, and platelet (HALP) score and the Systemic Immune-inflammation Index (SII) in patients with SCLC. Methods: We retrospectively analyzed 132 patients diagnosed with metastatic SCLC. Baseline laboratory data were used to calculate HALP and SII scores. Optimal cut-off values were determined by ROC analysis. Survival outcomes were assessed using Kaplan-Meier and Cox regression analyses. Results: The optimal cut-off values were 17.23 for HALP (AUC: 0.611, 95% CI: 0.50-0.72, p=0.04) and 747.27 for SII (AUC: 0.628, p=0.02, 95% CI: 0.52–0.73). High SII was an independent predictor of shorter progression-free survival (PFS) (HR=1.82, 95% CI: 1.02–3.26, p=0.04), but not overall survival (OS). HALP score predicted 6-month survival but showed no significant effect on OS or PFS. Liver (HR=1.72, 95% CI: 1.02-2.90, p=0.04) and brain metastases (HR=1.74, 95% CI: 1.08-2.80, p=0.02) were independent predictors of shorter PFS. Conclusion: SII may serve as a reliable prognostic marker for PFS in SCLC, while HALP showed limited predictive value. Metastatic sites, particularly liver and brain involvement, significantly impact prognosis. Larger, prospective studies are needed to validate these findings.

Background/Objectives: Datopotamab deruxtecan was approved in 2025 for hormone receptor-positive, HER2-negative metastatic breast cancer and for EGFR-mutated non-small cell lung cancer (NSCLC); its safety profile in routine use has not been described. We characterized adverse event reporting for the agent and asked whether the events reported most disproportionately are those that carry the reported harm. Methods: Reports naming datopotamab deruxtecan as a primary suspect in the FDA Adverse Event Reporting System (FAERS, 2025Q1–2026Q1) were stratified by recorded indication and compared with all other reports recording the same indication. A signal required at least three reports and pre-specified frequentist (reporting odds ratio (ROR), proportional reporting ratio, chi-square), Bayesian (lower credibility bound of the information component, IC₀₂₅), and multiplicity-adjusted thresholds. Sacituzumab govitecan served as a within-class comparator, reference pools were pruned of agents causing the same event, and outcomes were recalculated after excluding reports coding disease progression. Results: Among 416 reports (196 breast, 118 NSCLC), mucosal and ocular events dominated: the ROR for stomatitis was 21.50 (95% CI: 15.04–30.74) and 17.72 (9.93–31.63), with keratitis, oral candidiasis, and dry eye also qualifying. Against sacituzumab govitecan, stomatitis persisted (19.75), while myelosuppressive and gastrointestinal terms were markedly less reported. Interstitial lung disease met the Evans criteria but not the Bayesian or multiplicity threshold in the breast stratum (2.51), and did not meet any criterion in the lung stratum (2.09) or against the comparator; the reports carrying it nevertheless recorded the heaviest harm, with eighteen out of nineteen being serious (94.7%, 95% CI: 74.0–99.9) and five out of nineteen being fatal (26.3%, 95% CI: 9.1–51.2), while no fatal outcome remained among the 66 progression-free mucosal reports. Trastuzumab deruxtecan supplied 30.3% of pulmonary reports in the breast reference pool; removing it raised the estimate to 3.70 with an IC₀₂₅ of 0.41. Conclusions: Reporting for datopotamab deruxtecan is dominated by mucosal and ocular toxicity, whereas interstitial lung disease is reported less often but in reports recording a far higher proportion of serious and fatal outcomes. Its absence from the primary signal lists reflects a comparison base containing agents that cause the same event rather than an absence of risk, and monitoring intensity should not follow the magnitude of disproportionality. Spontaneous reports are subject to under-reporting, stimulated reporting, and incomplete data, and disproportionality describes patterns of reporting rather than incidence or risk.