Citations

This cross-sectional study of laboratory test records from US hospitals compares the total types of complete blood count results recorded in academic and community settings.

6073 Background: Laryngeal Squamous Cell Carcinoma (LaSCC) has varying outcomes based on the stage of cancer patients present with. Currently, a high proportion of patients are diagnosed with advanced-stage LaSCC complicating the treatment landscape and over-treating low risk patients. Risk stratification of LaSCC can help tailor treatment plans. Numerous studies have identified spatial architecture of tumor-infiltrating lymphocytes (TILs) as a prognostic biomarker in oral cavity and oropharyngeal SCC. In this work, we evaluate the prognostic value of an artificial intelligence (AI)-leveraged approach that characterizes the spatial architecture of TILs on digitized hematoxylin and eosin (H&E)-stained slides from patients with LaSCC. Methods: H&E slides from 192 patients with LaSCC were collected from Baylor Medical Center. This dataset was randomly divided into two equal cohorts, A and B. The slides were digitized as whole slide images at 40x magnification. The nuclei of all cells were automatically segmented using a deep-learning model (Hover-Net). Each nucleus was then classified as TIL or non-TIL based on morphological features. TILs and non-TILs were clustered based on proximity, and features related to the density and spatial distribution were extracted. The top features, determined by the least absolute shrinkage and selection operator, were used to train a Cox Proportional Hazards regression model that assigned a risk score for recurrence of cancer to each patient in cohort A. For validation, the model was applied to patients in cohort B. The 25 th percentile training risk score was used as a cutoff for classifying patients as high or low risk. The performance of the model in prognosticating loco-regional recurrence (LRR) was evaluated using survival analysis. Results: Patients in Cohort B identified as “high risk” by the model based on spatial organization of TILs had a significantly shorter survival time. Univariate survival analysis showed this model was prognostic for DFS with a hazard ratio of 2.57 (95% Confidence Interval: 1.12-5.89, p-value=0.048), meaning that patients classified as “high risk” are approximately 2.5 times more likely to develop LLR. Conclusions: We used computational pathology to characterize the architecture of TILs and develop a model to predict risk of LLR in LaSCC. With additional validation, this approach can be used to assist clinicians with making clinical decisions. Multivariate analysis. Variable Reference vs Comparison Pr(>|z|) HR (95% CI) Race Black vs Caucasian 0.93 0.92 (0.40 - 2.31) N N0 vs N+ 0.67 1.80 (0.12 - 26.06) T 1-2 vs 3-4 0.83 1.28 (0.13 - 12.38) Chemo Yes vs No 0.38 3.49 (0.21 - 56.90) Tobacco Yes vs No 0.26 2.08 (0.58 - 7.47) Alcohol Yes vs No 0.43 1.53 (0.54 - 4.35) TIL Architecture Risk High vs Low 0.03 * 0.26 (0.08 - 0.89)

e17064 Background: Analyses of clinical trials data suggest thatBlack men have equal or even improved overall survival (OS) with certain treatments for mCRPC compared with other races. Moreover, retrospective analysis of the PROCEED registry indicated that Black men who received Sip-T, an autologous cellular immunotherapy, had longer survival compared with other men with mCRPC. The Abi Race and PANTHER clinical trials prospectively assessed the effect of ARPIs on clinical outcomes among Black and White patient (pt) cohorts, and included pts who had received Sip-T either prior to or during study. We combined data from Abi Race and PANTHER to investigate associations between OS, Sip-T and race. Methods: Data from the Abi Race (N=100) and PANTHER (N=93) studies were retrospectively pooled for this analysis. Propensity scores for Sip-T treatment were calculated based on Karnofsky performance status, race, Gleason score, and study. Kaplan-Meier estimates for OS, with and without inverse propensity score weighting, were generated and stratified by Sip-T use. This analysis was stratified by race to examine whether the relationship between Sip-T use and OS differed by race. Results: Of the 93 Black pts and 100 White patients included from both studies, 123 patients did not receive Sip-T, while 70 patients did (60 before study, 10 on study). Pts who received Sip-T had a median OS (mOS) of 44 months (95% Confidence Interval (CI) 39, NR) compared to 36 months (95% CI 31, 48) for those who did not. Weighted by propensity scores, Black men who received Sip-T had a mOS of 72 months (95% CI 43, NR), while those who did not had a mOS of 38 months (95% CI 30, NR). Among White men, patients who received Sip-T had a mOS of 39 months (95% CI 30, NR), while those who did not had a mOS of 32 months (95% CI 29, 48) (see Table). Conclusions: Our findings from an investigator-led retrospective analysis independent of sponsors provide independent clinical trial support of prior retrospective findings that suggest Black men with mCRPC who receive Sip-T may have a greater OS than White men. While our analysis controlled for factors that may influence the use of Sip-T, it is limited by potential unmeasured confounders or timing of Sip-T. Further, adequately powered prospective trials specifically evaluating outcomes with Sip-T by race in earlier clinical settings are needed. Drug support and funding for Abi Race and PANTHER were provided by Janssen Scientific Affairs, LLC. Death counts and median overall survival (mOS) in months by race and Sipuleucel-T use. Black Men White Men Sipuleucel-T use Deaths / Total N No 36 / 64 38 / 59 Yes 12 / 29 24 / 41 Unweighted mOS (95% CI) No 36 (29, NR) 32 (29, 48) Yes 72 (43, NR) 39 (31, NR) Weighted mOS (95% CI) No 38 (30, NR) 32 (29, 48) Yes 72 (43, NR) 39 (30, NR) NR = not reached, mOS = median overall survival, CI = confidence interval.

Abstract RATIONALE: 4G4G/4G5G SERPINE1 genotypes produce high concentrations of plasminogen activator inhibitor-1 and are associated with worse asthma outcomes. A secondary analysis of the American Lung Association (ALA) SOYA trial showed that soy isoflavones significantly reduced asthma exacerbations versus placebo among patients with 4G4G/4G5G SERPINE1 genotypes. We hypothesized that baseline characteristics predict optimal responders to soy isoflavones among this subgroup. METHODS: ALA-SOYA was a randomized controlled trial that tested the efficacy of soy isoflavones vs. placebo for reducing asthma exacerbations among adolescents and adults with symptomatic asthma. In this responder analysis among participants with 4G4G/4G5G SERPINE1 genotypes, baseline demographic and clinical characteristics were tested for effect modification of the treatment assignment (soy/placebo) on the primary outcome of annualized number of asthma exacerbations using interaction terms in negative binomial regression models, with a significance threshold of p-interaction=0.15. RESULTS: Data were available for n=168 participants. Soy reduced the annualized number of asthma exacerbations relative to placebo among patients with 4G4G/4G5G SERPINE1 genotypes (incident rate ratio (IRR)=0.37, 95% confidence interval (CI): 0.15-0.90, p=0.028). Self-reported adherence to baseline controller therapy was the only significant effect modifier of this association (interaction p=0.115), with those using inhaled corticosteroid (ICS)/long-acting beta-agonist (LABA) controller therapy at least twice weekly experiencing reductions in asthma exacerbations with soy versus placebo (IRR = 0.25, 95% CI: 0.09-0.69; p= 0.007) but not among those using ICS/LABA controller therapy less frequently (IRR = 1.33, 95% CI: 0.22-8.02; p= 0.757). CONCLUSION: Soy isoflavones reduce asthma exacerbations among patients with the 4G4G/4G5G SERPINE1 genotypes and are most effective in those with greater adherence to asthma controller therapy regimens.

ASCO Guidelines provide recommendations with comprehensive review and analyses of the relevant literature for each recommendation, following the guideline development process as outlined in the ASCO Guidelines Methodology Manual . ASCO Guidelines follow the ASCO Conflict of Interest Policy for Clinical Practice Guidelines . Clinical Practice Guidelines and other guidance (“Guidance”) provided by ASCO is not a comprehensive or definitive guide to treatment options. It is intended for voluntary use by clinicians and should be used in conjunction with independent professional judgment. Guidance may not be applicable to all patients, interventions, diseases or stages of diseases. Guidance is based on review and analysis of relevant literature and is not intended as a statement of the standard of care. ASCO does not endorse third-party drugs, devices, services, or therapies and assumes no responsibility for any harm arising from or related to the use of this information. See complete disclaimer in Appendix 1 and 2 (online only) for more. PURPOSE To develop a clinical practice guideline and recommendations for symptom management of patients with well-differentiated grade 1 to grade 3 metastatic gastroenteropancreatic neuroendocrine tumors. METHODS ASCO convened an Expert Panel to develop a clinical practice guideline by reviewing the literature for relevant guidelines, systematic reviews, randomized controlled trials (RCTs), and observational studies to develop recommendations for clinical practice. RESULTS The literature review identified eight guidelines, 19 systematic reviews, and three RCTs that informed the development of guideline recommendations. RECOMMENDATIONS Recommendations are included for carcinoid syndrome, carcinoid heart disease and carcinoid crisis, and functional pancreatic neuroendocrine tumor syndromes. Recommendations are provided for surgical management, liver-directed therapy, and systemic therapy options, as well as palliative care. Limited guidance is provided for sequencing of interventions. Additional information is available at www.asco.org/gastrointestinal-cancer-guidelines .

INTRODUCTION: The risk of progression to esophageal adenocarcinoma in Barrett's esophagus (BE) increases with advancing degrees of dysplasia. There is a critical need to improve the diagnosis of BE dysplasia, given substantial interobserver variability and overcalls of dysplasia during manual community pathologist reads. We aimed to externally validate a previously cross-validated BE dysplasia diagnosis deep learning model (BEDDLM) that predicts dysplasia grade on whole slide images (WSIs). METHODS: We digitized nondysplastic BE (NDBE), low-grade (LGD), and high-grade dysplasia (HGD) histology slides from 3 external academic centers. A consensus read by 2 expert study pathologists was used as the criterion standard. Slide stain characteristics were normalized using cycle-generative adversarial networks. WSIs were assessed by BEDDLM using an ensemble approach, combining a “You Only Look Once” model followed by a ResNet101 classifier model. RESULTS: We included 489 WSIs. Consensus histopathology revealed 232 NDBE, 117 LGD, and 140 HGD WSIs. The mean age (SD) was 66.9 (11.4) years; 413 (84.7%) were men. Using the BEDDLM ensemble model, sensitivity and specificity for NDBE were 73.3% (95% confidence interval [CI]: 67.09%–78.85%) and 93.4% (95% CI: 89.62%–96.10%); for LGD, 84.6% (95% CI: 76.78%–90.62%) and 80.6% (95% CI: 76.26%–84.54%); and for HGD, 80.7% (95% CI: 73.19%–86.89%) and 94.8% (95% CI: 91.97%–96.91%), respectively. The F1 score was 0.81, 0 0.69, and 0.83 for NDBE, LGD, and HGD, respectively. DISCUSSION: Our externally validated deep learning model demonstrates substantial accuracy for the diagnosis of BE dysplasia grade on WSIs.