Citations

PURPOSE Large language models (LLMs) have demonstrated remarkable versatility in oncology applications, such as cancer staging and survival analysis. Despite their potential, ethical concerns such as data privacy breaches, bias in training data, lack of transparency, and risks associated with erroneous outputs pose significant challenges to their adoption in high-stakes oncology settings. Therefore, we aim to explore the ethical challenges associated with LLM-based applications in oncology and evaluate emerging techniques designed to address these issues. METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, a systematic review was conducted to evaluate publications related to ethical issues of LLMs in oncology across eight academic databases (eg, PubMed, Web of Science, and Embase) between January 1, 2019, and December 31, 2024. RESULTS The search retrieved 4,319 published articles, of which 65 publications were preserved and included in our analysis. We identified six prevalent ethical challenges in oncology, including trust, equity, privacy, transparency, nonmaleficence, and accountability. We then evaluated emerging technical solutions to mitigate ethical challenges and summarized evaluation metrics used to assess these solutions' effectiveness. CONCLUSION This review provides actionable recommendations for responsibly deploying LLMs in oncology, ensuring adherence to ethical guidelines, and fostering improved patient outcomes. By bridging technical and clinical perspectives, this review offers a foundational framework for advancing ethical artificial intelligence applications in oncology and highlights areas for future research.

ABSTRACT Introduction A novel therapy for heavily pretreated triple‐class–exposed multiple myeloma (TCE MM) is B‐cell maturation antigen (BCMA)‐targeted immunotherapy. While the number of TCE+BCMA‐exposed patients is growing, real‐world data for this group are limited. Methods We present real‐world data from patients with TCE+BCMA‐exposed MM who initiated a subsequent line of therapy (LOT) using a US‐based claims database, Komodo's Healthcare Map. Results We identified 656 TCE+BCMA‐exposed patients; mean age was 66.5 years. Time from MM diagnosis to index was 5.4 years; mean number of prior LOTs was 5.9. The most prevalent prior therapy received within each drug class was daratumumab (98.5%), pomalidomide (86.0%), carfilzomib (85.8%) and belantamab mafodotin (74.5%). A total of 137 different subsequent treatment regimens were observed following TCE+BCMA exposure; the most common regimen was teclistamab (10.4%). The top three targeted agents within the subsequent regimen were carfilzomib (20.2%), pomalidomide (20.1%) and bortezomib (16.6%). Among this TCE+BCMA‐exposed population who received subsequent treatment, the median time to next treatment or death was 6.8 (95% CI, 6.1–7.5) months; time to treatment discontinuation or death was 3.5 (95% CI, 3.2–3.7) months. Conclusion This first real‐world analysis of patients with heavily pretreated TCE+BCMA‐exposed MM shows poor clinical outcomes, frequent therapy retreatment and no standard‐of‐care, highlighting the need for novel treatments. Clinical Trial Registration The authors have confirmed clinical trial registration is not needed for this submission.

Summary We investigated the outcomes of patients with advanced systemic mastocytosis (AdvSM) undergoing allogeneic haematopoietic cell therapy (alloHCT) in the US. Twenty‐seven adult (median age, 58 years) patients with AdvSM received alloHCT from 2014 to 2021. Most patients were white (93%), male (63%) and had systemic mastocytosis (SM) with associated haematological neoplasm (SM‐AHN, 70%), received peripheral blood grafts (89%) and non‐myeloablative regimens. KIT mutation was detected in 14 of the reported 16 patients (87.5%). Post‐transplantation cyclophosphamide (PTCy) was used in approximately 50% of the cohort. Approximately 1 year after alloHCT, median bone marrow mast cell burden decreased from 15% pre‐alloHCT to 1.5% (range 0–8) at 1 year post‐alloHCT. The median serum tryptase decreased from 55 ng/mL (range 3–400 ng/mL) pre‐alloHCT to 18 ng/mL (range 0–481 ng/mL) at 1 year post‐alloHCT. At 1 year, progression‐free survival (PFS) and overall survival (OS) were 59% (95% confidence interval [CI], 41%–77%) and 74% (95% CI, 56%–89%) respectively. In the subset of patients with SM‐AHN, 1‐year PFS and OS were 74% (52%–91%) and 79% (95% CI, 58%–94%) respectively. The cumulative incidence of relapse/progression for the entire population of patients with SM ( n = 27) was 4% (95% CI, 0–14) at 100 days and 15% (95% CI, 4–31) at 1 year. For the subset of patients with AHN, the cumulative incidence was 11% (95% CI, 1–28) at 100 days and 21% (95% CI, 6–42) at 1 year. Relapse/progression was the cause of death in six of 12 patients (5 died of AHN and 1 died of SM progression). Eighteen and nine patients received a KIT inhibitor before alloHCT and after alloHCT respectively. In addition, six patients received a KIT inhibitor for the treatment of relapse/progression of SM after alloHCT. Although it is difficult to delineate the exact effect of alloHCT and KIT inhibitors because of the size of the study in this era, the use of alloHCT and KIT inhibitors pre‐ and post‐ alloHCT is increasing. In the near future, larger studies are required to provide further insights into this subject.

Objective To establish a framework for validating candidate biomarkers of cerebral small vessel diseases (SVD) associated with cognitive impairment and characterize individuals enrolled by the MarkVCID2 consortium under this framework. Methods Participants age 60 to 90 years were enrolled across 17 MarkVCID2 sites. Recruitment was targeted to enrich in cognitive symptoms (mild dementia, mild cognitive impairment, subjective cognitive decline), defined risk factors (diabetes mellitus, advanced hypertension), and Black/African American, White, and Hispanic/Latino subgroups. Enrolled participants underwent baseline visits that included cognitive testing, multimodal magnetic resonance imaging (MRI), and biofluid collection. Provisional risk for SVD‐related cognitive decline was estimated primarily by baseline cognitive symptoms plus SVD risk factors. Adjudicated risk status was estimated by cognitive symptoms plus presence of moderate‐to‐severe white matter hyperintensities, microbleeds, or lacunes on baseline MRI. Results MarkVCID2 enrolled 1883 individuals age 73.4 ± 7.5 years, 65.0% female, 24.2% Hispanic, and 27.1% non‐Hispanic Black. Among enrollees, 44.8% were provisionally designated high‐risk. After baseline MRI, 48.5% were categorized as adjudicated high‐risk status, with substantial recategorization both from low‐ to high‐risk (primarily because of MRI lesions without SVD risk factors) and high‐ to low‐risk (primarily suspected cognitive impairment at screening not confirmed by baseline testing). Interpretation MarkVCID2 baseline data indicate successful enrollment of diverse individuals enriched in factors associated with SVD‐related cognitive decline. Changes over 3 years of longitudinal follow‐up will be analyzed to validate the candidate biomarkers for 2 projected contexts of use: subject selection (identifying likelihood of future SVD progression) and study outcome (efficiently measuring SVD progression). ANN NEUROL 2026;99:449–458

Abstract Background Lung adenocarcinoma in never-smokers is a major public health burden, especially among East Asian women. Polygenic risk scores (PRSs) are promising for risk stratification but are primarily developed in European-ancestry populations. We aimed to develop and validate single- and multi-ancestry PRSs for East Asian never-smokers to improve lung adenocarcinoma risk prediction. Methods PRSs were developed using genome-wide association study summary statistics from East Asian (8002 cases; 20 782 controls) and European (2058 cases; 5575 controls) populations. Single-ancestry models included a PRS with 25 single nucleotide variants (PRS-25), PRS clumping and thresholding (CT), and LDpred2; multi-ancestry models included LDpred2 plus European PRS-128, PRS-CSx, and clumping and thresholding, super learning, empirical Bayes (CT-SLEB). Performance was evaluated in independent East Asian data from the Female Lung Cancer Consortium and externally validated in the Nanjing Lung Cancer Cohort. We assessed predictive accuracy via area under the curve operating procedure (AUC), with 10-year and (ages 30-80 years) absolute risks estimates. Results The best multi-ancestry PRS, using East Asian and European data via CT-SLEB, outperformed the best East Asian-only (LDpred2; AUC = 0.629, 95% confidence interval [CI] = 0.618 to 0.641), achieving an AUC of 0.640 (95% CI = 0.629 to 0.653) and odds ratio of 1.71 (95% CI = 1.61 to 1.82) per standard deviation increase. Nanjing Lung Cancer Cohort validation confirmed robust performance (AUC = 0.649, 95% CI = 0.623 to 0.676). The top 20% PRS group had a 3.92-fold higher lung adenocarcinoma risk than the bottom 20%. Further, the top 5% PRS group reached a 6.69% lifetime absolute risk. Notably, this group reached the average population 10-year lung adenocarcinoma risk at age 50 years (0.42%) by age 41 years, 9 years earlier. Conclusions Multi-ancestry PRS approaches enhance lung adenocarcinoma risk stratification in East Asian never-smokers, with consistent external validation, suggesting future clinical utility.

ABSTRACT Objective The optimal treatment for neurosarcoidosis myelitis is uncertain. We characterize incident neurosarcoidosis myelitis and assess treatment response by MRI and clinical scales. Methods Incident probable or definite neurosarcoidosis myelitis in adults was retrospectively identified from 13 academic medical centers. Cases were analyzed by initial treatment. The primary outcome was T1 post‐contrast gadolinium enhancement resolution at 6 months post‐treatment. Secondary outcomes were changes in modified Rankin scale (mRS) and Expanded Disability Status Scale (EDSS) from nadir to final follow‐up. Results Two hundred two patients were identified (median diagnosis age: 47 years (IQR 39–55); male: female 1.3:1). Median nadir mRS and EDSS were 2 (IQR 2–3) and 4 (IQR 2.5–6). At initial treatment, 129 (63.9%) received prolonged corticosteroids ≥ 4 weeks (group A 1 ), 36 (17.8%) received corticosteroids < 4 weeks (B 1 ), 21 (10.4%) received corticosteroids plus sarcoidosis‐directed immunosuppressant (E), and 16 (7.9%) received corticosteroids plus non‐sarcoidosis‐directed agents (F). In 167 cases with sufficient imaging, there were no significant differences in contrast enhancement resolution at 6 months (A 1 27/106 (25.5%), B 1 9/28 (32.1%), E 5/19 (26.3%), F 5/14 (35.7%); Fisher's exact p = 0.76). There were no significant differences in changes in mRS or EDSS among treatment groups (Kruskal–Wallis p = 0.69 and 0.63, respectively) after median follow‐up of 46.5 months (IQR 18–91.3). Interpretation Different initial immunosuppression strategies did not correlate with MRI contrast enhancement resolution at 6 months or clinical scales (mRS, EDSS). However, conclusions are limited by retrospective design, imbalanced cohorts, and insensitivity of binary MRI outcomes and available clinical scales for treatment response in neurosarcoidosis.

ABSTRACT Objective Autosomal dominant progranulin ( GRN ) pathogenic variants are a genetic cause of frontotemporal lobar degeneration. Though clinical trials for GRN ‐related therapies are underway, there is an unmet need for biomarkers that can predict symptom onset and track disease progression. We previously showed that asymptomatic GRN variant carriers exhibit thalamocortical hyperconnectivity that increases with age, presumably as they are approaching symptom onset. Whether hyperconnectivity arises concomitantly with markers of neurodegeneration remains unclear. Methods Utilizing T1 and task‐free functional magnetic resonance imaging from 49 asymptomatic and 26 symptomatic GRN variant carriers, we determined the relationships between functional connectivity, as measured by voxelwise whole‐brain degree, and GRN ‐relevant markers of disease progression, including plasma neurofilament light chain concentrations, cerebrospinal fluid complement C1q and C3b protein levels, obsessive‐compulsive disorder symptom severity, and gray matter volume. Results Neurofilament light chain concentrations were associated with frontotemporoparietal and thalamic hyperconnectivity in asymptomatic GRN variant carriers and extensive regions of atrophy in symptomatic carriers. Complement levels were associated with regions of hyperconnectivity, but not gray matter volume, in symptomatic carriers. Obsessive‐compulsive disorder symptom severity was associated with hypoconnectivity across all GRN carriers. Asymptomatic carriers with thalamic hyperconnectivity tended to have lower gray matter volume in the bilateral insula and left lateral parietal cortex, early regions of atrophy in GRN ‐frontotemporal dementia. Interpretation In asymptomatic carriers, the co‐occurrence of hyperconnectivity, high neurofilament light chain, and low gray matter volume suggests that functional hyperconnectivity may portend the onset of clinical decline. These findings point toward hyperconnectivity as an indicator of approaching symptomatic onset.

Abstract Context Patients with mild autonomous cortisol secretion (MACS) can develop adrenal insufficiency after unilateral adrenalectomy. Objective This work aimed to determine the prevalence, duration, and predictors of adrenal insufficiency, and compare postoperative basal cortisol and cosyntropin stimulation test (CST). Methods In this multicenter retrospective study of patients with MACS, adrenal insufficiency was diagnosed when postoperative basal cortisol was less than 10 µg/dL and/or CST &lt; 18 µg/dL. The results were concordant when both tests met cutoffs. Biochemical (BSS) and clinical severity scores (CSS) were calculated. Results Among 281 patients with MACS (80% women), postoperative adrenal insufficiency was diagnosed in 153 (54.5%) patients. Adrenal insufficiency inversely correlated with age (odds ratio [OR] 0.67 per 10 years; 95% CI, 0.53-0.84). Low basal cortisol and CST were associated with younger age (OR 0.64 per 10 years for both) and higher BSS (OR 1.17 and 1.22, respectively). Basal cortisol and CST were discordant in 22% of patients, and the discordance rate was more common in patients with bilateral nodules (32% vs 19%; P &lt; .001). The median time to adrenal insufficiency recovery was 3.9 months (IQR, 3-5.9 months), with longer duration associated with higher BSS and CSS: 3 months for mild, 4 to 5 months for moderate, and 12 to 14 months for severe BSS and CSS. Conclusion Approximately half of patients with MACS developed postoperative adrenal insufficiency, with 50% recovering by 3.9 months after surgery. BSS correlated with basal cortisol, CST, and duration of adrenal insufficiency. As discordant results were noted in 22%, performing both basal cortisol and CST postoperatively should be considered.