Citations

AbstractPurposePart two of this consensus aimed to provide recommendations for the prevention of meniscus injuries, non‐operative treatment of acute tears and degenerative lesions, return to sports and patient‐reported outcome measures.MethodsThis consensus followed the European Society of Knee Surgery, Sports Traumatology and Arthroscopy (ESSKA) formal consensus methodology. For this combined ESSKA—American Orthopedic Society for Sports Medicine (AOSSM)—American Academy of Sports Physical Therapy (AASPT) initiative, 67 experts from 14 countries, including orthopedic surgeons and physiotherapists, were involved. The 26 Steering Group members established guiding questions, screened the existing evidence, and proposed statements, and provided Grades of recommendations. The 41 Rating Group members assessed the statements according to a Likert scale (1–9). Final documents were assessed by an international peer review group for geographical adaptability.ResultsLow to moderate scientific level of evidence was available, so that grades of recommendations were low (three Grade A ratings, four Grade B, three Grade C and 13 Grade D), underlining the relevance of this consensus. One strong and 17 relative agreements with overall median of 8 (8–9) and a mean of 7.92 ± 0.37 were achieved for 23 statements on 18 questions. Prevention of meniscus injuries is possible with general knee injury reduction programmes and through avoidance of certain activities. Non‐operative treatment including physical therapy is the first line approach for degenerative meniscus lesions and may be an option for some acute tears. Return to sports after meniscus tear surgery should be both criterion‐based and time‐based. Patient reported outcomes in combination with performance‐based measures are recommended to evaluate the rehabilitation process.ConclusionThis international EU–US consensus established recommendations for prevention strategies, describes rehabilitation of non‐operated patients and of patients after partial meniscectomy, meniscus repair and meniscus reconstruction, and establishes return to sport criteria. These updated and structured recommendations may be applied by surgeons and physiotherapists.Level of EvidenceLevel I, consensus.

Therapeutic clinical trial enrollment does not match glioma incidence across demographics. Traditional statistical methods have identified independent predictors of trial enrollment; however, our understanding of the interactions between these factors remains limited. To test the interactive effects of demographic, socioeconomic, and oncologic variables on trial enrollment, we designed boosted neural networks (BNNs) for all glioma patients ( n = 1042), women ( n = 445, 42.7%), and minorities ( n = 151, 14.5%) and externally validated these models [whole cohort, n = 230; women, n = 89 (38.7%); minority, n = 66 (28.7%)]. For the whole-cohort BNN, the most influential variables on enrollment were oncologic variables, including KPS [total effect (TE), 0.327], chemotherapy (TE, 0.326), tumor location (TE, 0.322), and seizures (TE, 0.239). The women-only BNN exhibited a similar trend. Conversely, for the minority-only BNN, socioeconomic variables [insurance status (TE, 0.213), occupation classification (TE, 0.204), and employment status (TE, 0.150)] were most influential. These results may help prioritize patient-specific initiatives to increase accrual.

Barriers to incorporating pharmacogenetics into routine clinical practice in the United States are well documented. Initial surveys by the Clinical Pharmacogenetics Implementation Consortium (CPIC) in 2009 and 2010 identified barriers across four key domains that have hindered the widespread adoption of clinical pharmacogenetic testing. These are presented verbatim as: (i) absence of a definition of the processes required to interpret genotype information and to translate genetic information into clinical actions; (ii) need for recommended drug/gene pairs to implement clinically now; (iii) clinician resistance to consider pharmacogenetic information at the bedside; and (iv) concerns about test costs and reimbursement. Over time, many of these challenges have been overcome, and clinical pharmacogenetic testing has subsequently reached broader implementation. Despite this progress, several barriers remain that block further adoption. This narrative review used authors' expertise and experience to identify and describe current barriers to pharmacogenetic implementation across seven domains in the United States: equity and inclusion; guidelines and supporting evidence; regulatory agency oversight; payer coverage and insurance; availability of quality pharmacogenetic tests; electronic health records; and provider and patient education. Within each domain, it revisits past successes and challenges and explores remaining barriers. We also propose solutions to address ongoing challenges across these domains, including further expansion of recommendations beyond pharmacogenetic‐specific guidelines, standards for designing clinical decision support tools, and broader pharmacogenetics education. Addressing these remaining obstacles directs work to enable broader adoption of clinical pharmacogenetic implementation to ultimately improve patient outcomes.

ABSTRACTPharmacogenetics is a promising strategy to facilitate individualized care for patients with Major Depressive Disorder (MDD). Research is ongoing to identify the optimal genetic markers for predicting outcomes to antidepressant therapies. The primary aim of this systematic review was to summarize antidepressant pharmacogenetic studies to enhance understanding of the genes, variants, datatypes/methodologies, and outcomes investigated in the context of MDD. The secondary aim was to identify clinical genetic panels indicated for antidepressant prescribing and summarize their genes and variants. Screening of N = 5793 articles yielded N = 390 for inclusion, largely comprising adult (≥ 18 years) populations. Top‐studied variants identified in the search were discussed and compared with those represented on the N = 34 clinical genetic panels that were identified. Summarization of articles revealed sources of heterogeneity across studies and low rates of replicability of pharmacogenetic associations. Heterogeneity was present in outcome definitions, treatment regimens, and differential inclusion of mediating variables in analyses. Efficacy outcomes (i.e., response, remission) were studied at greater frequency than adverse‐event outcomes. Studies that used advanced analytical approaches, such as machine learning, to integrate variants with complimentary biological datatypes were fewer in number but achieved higher rates of significant associations with treatment outcomes than candidate variant approaches. As large biological datasets become more prevalent, machine learning will be an increasingly valuable tool for parsing the complexity of antidepressant response. This review provides valuable context and considerations surrounding pharmacogenetic associations in MDD which will help inform future research and translation efforts for guiding antidepressant care.

Background: Evaluation of the performance of Cobas ® Pulse (Roche Diagnostics GmbH, Mannheim, Germany), a new blood glucose (BG) monitoring system (BGMS; referred to here as BGMSA) intended for point-of-care testing using samples from patients in diverse clinical settings by intended point-of-care test operators. Methods: Arterial, capillary, venous, or heel stick whole blood (WB) samples from patients in non-critical and critical care settings were collected and analyzed using BGMSA and the Nova StatStrip ® BGMS (Nova Biomedical, Waltham, MA; referred to here as BGMSB), and a hexokinase comparator (Cobas 6000 Analyzer Series; Roche Diagnostics GmbH). The blood glucose measurement accuracy was assessed by the Food and Drug Administration guidance criteria. Results: Two studies are presented. In the first, 2678 samples (622 arterial, 706 capillary, 1203 venous, 147 heel stick) were collected from 1577 patients in 14 US and three European sites. All accuracy criteria were met for arterial and venous samples considering all data combined. BGMSA showed better accuracy than BGMSB for arterial, venous, and heel stick, and similar results to BGMSB for capillary WB vs venous comparator. No endogenous interference from pO 2 , hematocrit, and sodium was identified. BGMSA was also accurate when analyzing contrived samples used to show accuracy over a wide range of glucose concentrations, alone and when combined with extreme hematocrit. In the second study, 117 capillary fingerstick samples collected at one US site were measured on both BGMSA and the comparator, and all accuracy criteria were met. No clinically significant medical risks were observed via Diabetes Technology Society Error Grids. Conclusions: BGMSA was effective for determining blood glucose in venous, arterial, neonatal arterial, neonatal heel stick, and capillary WB samples.

e21598 Background: While large language models (LLMs) like GPT-4 (OpenAI) and Claude Opus (Anthropic) perform well on general medical exams, limited data exist on their application in oncology, particularly in multiple-choice question (MCQ) scenarios. This study benchmarks the accuracy and assesses the clinical reasoning of LLMs on cutaneous oncology MCQs from the American Society of Clinical Oncology (ASCO) question bank. Methods: Skin oncology MCQs from the ASCO question bank were tested using GPT-4 (OpenAI) and Claude Opus (Anthropic). Questions were entered into OpenAI and Anthropic API playgrounds without additional prompting, with identical settings for both models (Temperature = 0, Token = Max). Each question was tested three times per model to assess response consistency and precision. Initial responses were collected, and chain-of-thought (COT) prompting was applied to encourage stepwise reasoning mimicking an oncologist’s thought process. The percentage of revised answers after COT prompting was analyzed. Accuracy before and after COT prompting was compared. Incorrect responses were reviewed by board-certified oncologists specializing in skin cancer at National Cancer Institute (NCI)-designated centers. Each oncologist scored the responses on clarity, clinical reasoning, bias, and confidence in the models’ utility in clinical practice. Qualitative feedback was collected via free-text comments and analyzed descriptively. Results: Of 66 skin oncology MCQs, Claude correctly answered 55 questions (83% accuracy, 95% CI: 72%–91%), while ChatGPT correctly answered 53 (80% accuracy, 95% CI: 68%–89%). Both models performed comparably, with overlapping confidence intervals. A chi-square test showed no significant difference between their performances (p = 0.65). After COT prompting, both tools remained at their respective accuracy level. Thematic analysis of incorrect answers revealed that LLM responses frequently deviated from clinical guidelines and failed to reflect evidence-based oncology practice, often neglecting key trial data like DREAMSeq and frontline therapeutic strategies. The most frequent errors were Treatment Planning Errors, where recommendations misaligned with NCCN guidelines, and Interpretation Errors, involving misinterpretation of clinical trials or patient data. Anchoring bias emerged as a recurring issue, with models fixating on details (e.g., BRAF mutation status) at the expense of broader reasoning. Conclusions: This study demonstrates that while large language models like GPT-4 and Claude Opus show promise in the field of oncology, they still face significant challenges in clinical reasoning and adherence to evidence-based practices. Continued refinement and training on specialized medical data are essential before these models can be reliably integrated into clinical workflows.

1593 Background: “Financial toxicity” refers to the financial burden imposed by treatment costs on individuals with cancer, constituting a major barrier to achieving equitable cancer outcomes. Recent literature increasingly demonstrates the detrimental impacts of financial toxicity on quality of life (QOL) among individuals with cancer, including individuals who have undergone hematopoietic stem cell transplantation (HSCT). This study evaluates associations among treatment cost burden and various aspects of QOL following HSCT. Methods: Seven hundred one HSCT recipients completed a survey examining their biopsychosocial health one year following transplant. The survey included the Functional Assessment of Cancer Therapy – Bone Marrow Transplantation (FACT-BMT), a multifactorial measure of QOL specific to this population. Treatment cost burden endorsement was measured on a 5-item Likert scale. Hierarchical regression models were developed to assess the incremental effects of demographic characteristics (i.e., Block 1), clinical predictors (Block 2), and cost burden (Block 3) on physical, emotional, social, functional, BMT-specific, general, and composite QOL outcomes. Results: Significant model improvement was observed with the addition of clinical factors ( ΔF(2,650) = 20.28, p < .001), and subsequently, treatment cost burden ( ΔF(1,649) = 110.29, p < .001). In the final model, higher cost burden was associated with poorer physical (β = -0.323, p < .001), emotional (β = -0.301, p < .001), social (β = -0.250, p < .001), functional (β = -0.317, p < .001), BMT-specific (β = -0.341, p < .001), general (β = -0.377, p < .001), and composite QOL (β = -0.381, p < .001). Poorer performance score was associated with each QOL indicator ( p < .001), with allogeneic transplant type associated with poorer functional (β = -0.001, p = .002), but higher emotional (β = 0.118, p = .002), wellbeing. Older age (β = 0.113, p = .003) and female sex predicted higher (β = 0.183, p < .001), while Hispanic ethnicity predicted poorer (β = -0.095, p = .010), social wellbeing. Female sex was associated with poorer QOL specific to BMT concerns (β = -0.118, p = .001). Conclusions: Higher treatment cost burden is associated with poorer overall QOL and its physical, emotional, social, functional, and BMT-specific components one year following HSCT, after controlling for demographic and clinical characteristics. This reflects a critical barrier to equitable cancer care, suggesting that financial toxicity may perpetuate preexisting inequities in QOL, treatment, disease, and survival outcomes that disproportionately impact the underserved. Future research should prioritize 1) better understanding relationships among complex indicators of financial toxicity, QOL, and their underpinning mechanisms and 2) developing solutions to mitigate financial toxicity of HSCT and overall cancer care.

1586 Background: Black and Hispanic breast cancer (BC) survivors have a higher prevalence of obesity and experience less success with weight loss interventions (WLI) than White BC survivors. The BWEL trial (Alliance A011401; NCT02750826) is a phase III randomized trial evaluating the impact of a 2-year telephone-based WLI on invasive disease-free survival in participants (pts) with stage II-III HER2-negative BC and a BMI ≥ 27 kg/m 2 . At 12-months, the WLI induced significant weight loss across demographic factors, including race and ethnicity. However, Black and Hispanic pts lost less weight and completed fewer calls than White pts. Here, we evaluate intervention adherence, engagement and tool utilization in BWEL pts by race and ethnicity. Methods: BWEL randomized pts to a WLI plus health education (HE) or HE alone. WLI pts received semi-structured telephone-based health coaching, delivered in English or Spanish, and received an activity monitor and wireless scale. Pts self-reported race and ethnicity. Mean values for call duration, call density (time to complete the initial 12-week intensive intervention phase), intervention attrition, and frequency of Fitbit use and weight tracking over 12-months were compared by race and ethnicity, comparing least squares means with Tukey-Kramer adjustment for multiple comparisons with adjusted p-values. Results: Of 3181 pts randomized to the study between 08/2016 and 02/2021, 1591 pts were allocated to the WLI arm. 80.5% of pts were White, 12.8% Black, and 7.1% Hispanic. Average BMI was 34.5 (±5.7) kg/m2. Compared to White pts, Black pts had fewer days of Fitbit usage (113.6 vs. 159.8, p<0.0001) and weight tracking (77.9 vs. 135.6 days, p< 0.0001). Hispanic pts had fewer days of Fitbit usage (108.8 vs. 154.9, p= 0.001) and weight tracking (87 vs. 129.5 days, p=0.0002) compared to non-Hispanic pts. There were no differences in attrition rate, average call duration, or call density by race or ethnicity. Conclusions: In a phase III WLI trial, engagement with tools designed to support weight loss was significantly lower in Black and Hispanic pts. Future work is needed to explore ways to enhance engagement and improve weight loss outcomes for racial and ethnic minority pts. Support: U10CA180821, U10CA180882, UG1CA189823; https://acknowledgments.alliancefound.org . Clinical trial information: NCT02750826 . Measure of engagement Race Ethnicity WhiteN=1281 BlackN=204 p-value Non-HispanicN=1459 HispanicN=113 p-value Withdrew from intervention n (%) 58 (4.5%) 13 (6.4%) 0.56 70 (4.8%) 6 (5.3%) 0.51 Call Duration (min)Mean (SD) 34.5 (7.6) 34.6 (9.1) 0.99 34.6 (7.8) 33.3 (7.9) 0.25 Call density(weeks)Mean (SD) 14.2 (7.2) 14.2 (8.8) 0.99 14.2 (7.3) 14.2 (9.7) 0.99 Days of Fitbit UseMean (SD) 159.8 (132.2) 113.6 (124.7) < 0.0001 154.9 (131.8) 108.8 (125.7) 0.001 Days of weight trackingMean (SD) 135.6 (109.5) 77.9 (87.5) < 0.0001 129.5 (108.8) 87 (96.5) 0.0002

e13637 Background: Large language models (LLMs) like GPT-4 (OpenAI) and Claude Opus (Anthropic) showed high accuracy in medical multiple-choice exams, but data on their oncology-specific clinical reasoning and performance is limited. This study evaluates their accuracy and clinical reasoning on breast oncology multiple-choice questions (MCQs) from the American Society of Clinical Oncology (ASCO) question bank. Methods: Using OpenAI and Anthropic Application Programming Interface (APIs), questions were tested without additional prompts under consistent settings (GPT-4 and Claude Opus; Temperature = 0, Tokens = Max). Each question was tested three times to assess precision. Then, Chain-of-thought (COT) prompting was applied to promote LLMs stepwise reasoning to increase their accuracy. Accuracy before and after COT prompting was compared. Incorrect responses were reviewed by board-certified medical oncologists speclized in breast cancer, who scored reasoning clarity, bias, and clinical relevance. Qualitative feedback was descriptively analyzed. Results: A total of 273 breast oncology MCQs were evaluated across the two LLMs. GPT-4 achieved an initial accuracy of 81.3% (222/273; 95% CI: 76.3%-85.5%), compared to Claude Opus, which achieved an accuracy of 79.5% (217/273; 95% CI: 74.3%-83.9%). The Chi-squared test for difference between the models before chain-of-thought (COT) prompting yielded a p-value of 0.59, indicating no statistically significant difference in accuracy between GPT-4 and Claude Opus prior to COT prompting. After COT prompting, the performance of the two models diverged significantly. GPT-4 saw a net decline in accuracy, decreasing by a net of 1 correct answer, resulting in an overall accuracy of 80.95% (221/273). In contrast, Claude Opus experienced a notable improvement, with a net of 19 additional correct answers, leading to an accuracy of 86.4% (236/273). A statistical analysis using a Chi-squared test revealed a difference in accuracy between the two models of 5.5% (p = 0.08), demonstrating that the improvement in accuracy for Claude Opus after COT prompting was borderline statistically significant compared to GPT-4. Thematic analysis of oncologists' feedback revealed that the most common reasons for incorrect answers were reliance on outdated guidelines, misinterpretation of clinical trial data, and failure to consider multidisciplinary or patient-specific approaches in clinical decision-making. Conclusions: Although AI models can achieve high scores on multiple-choice exams, they still require human supervision. These models rely on potentially outdated training data and lack the ability to individualize patient care or apply data from clinical trials. especially in unique or unconventional/non textbook scenarios.

569 Background: Several studies established the prognostic role of both the amount and locations of tumor-infiltrating lymphocytes (TILs) in TNBC. Three distinct immunotypes were described based on the amount and locations of TILs: immune enriched (IN), immune excluded, and immune desert. Using single-cell spatial transcriptomic analysis in the Mayo Clinic TNBC cohort, our previous studies showed the central role of interferon (IFN) signaling in IN phenotype. Herein, we evaluated the association between IFN and outcomes in TNBC in 3 independent datasets. Methods: NanoString IO360 was performed in 114 samples from FinXX (NCT00114816) to generate 22-gene IFNα and 33-gene IFNγ signatures. RNA sequencing was performed in 388 samples from CALGB 40603 (NCT00861705). 3038 TNBC samples were tested by WTS (NovaSeq; Caris Life Sciences, Phoenix, AZ). Median values were used as cut-offs for high vs low IFNγ RNA expression and 18-gene IFNγ signature scores. Caris Life Science CODEai was used to evaluate real-world overall survival (OS) obtained from insurance claims and calculated from tissue collection to last contact using Kaplan-Meier estimates. Chi-square, Mann-Whitney U, ANOVA, and Cox regression were used. Results: A high 22-gene IFNα signature score was associated with significantly improved recurrence-free survival (RFS) in FinXX (hazard ratio [HR] 0.32, 95% confidence interval [CI] 0.14-0.74, p 0.007) and OS (HR 0.28, 95%CI 0.12-0.66, p 0.003). Similar findings were observed with 33-gene IFNγ signature with significant improvement in RFS (HR 0.21, 95%CI 0.09-0.51, p < 0.001) and OS (HR 0.18, 95%CI 0.08-0.44, p < 0.001). Furthermore, in CALGB 40603, both IFNα and IFNγ scores were positively associated with pathologic complete response (pCR: IFNα p 0.019 and IFNγ p 0.007) and residual cancer burden (RCB: IFNα p 0.044 and IFNγ p 0.013). Using the Caris data platform to further validate, we identified 2899 TNBC patients (pts) with genomic and clinical outcome data. High IFNγ expression was associated with significant improvement in OS (25.95 vs 17.43 months; HR 0.65, 95% CI 0.59 – 0.72, p < 0.001). Similarly, pts with high IFNγ signature scores had significant improvement in median OS (25.79 vs 16.22 months; HR 0.66, 95% CI 0.6 – 0.73, p < 0.001). Conclusions: This study underscores the pivotal role of IFN signaling in TNBC. High IFNα and IFNγ signatures were consistently associated with improved RFS, OS, higher pCR rates, and lower RCB across clinical trial cohorts and real-world data. These findings signify IFN signaling as a potential key biomarker and therapeutic target in TNBC. Support: U10CA180821, U10CA180882, U24CA196171; Breast Cancer Research Foundation, Mayo Clinic Breast Cancer SPORE (P50CA116201-17), Bankhead Coley, W81XWH-15-1-0292, P50CA015083, R35CA253187; https://acknowledgments.alliancefound.org . Genentech. Clinical trial information: NCT00114816 and NCT00861705 .