Jajja, Salman Ayub

Abstract Background Diagnosis and risk stratification in rare hematologic malignancies such as myeloproliferative neoplasms (MPNs) – polycythemia vera (PV), essential thrombocythemia (ET), and myelofibrosis (MF) – require expert review of longitudinal, heterogeneous clinical records. This process is cognitively demanding, inconsistently applied, and difficult to scale beyond tertiary centers. No automated phenotyping workflow currently exists for hematologic malignancies. Methods A HIPAA-compliant large language model (LLM) framework for phenotyping MPN was developed to integrate (i) rule-based retrieval of bone marrow biopsy reports, clinical notes, and structured laboratory results from the electronic health record (EHR); (ii) zero-shot extraction of diagnostic and prognostic variables from unstructured text using GPT-4 Turbo; (iii) a clinician-informed source-prioritization algorithm to reconcile conflicting multi-source data; (iv) WHO/ICC-criteria–based diagnostic classification; and (v) NCCN-based risk stratification using the conventional risk model for PV, IPSET-thrombosis for ET, and DIPSS, DIPSS-plus, and MIPSS70/MIPSS70+ v2 for MF. Patients were identified via MPN-related ICD-9/10 codes; cases met 2017 WHO criteria or had a hematologist-documented diagnosis, and controls did not. The cohort was split into a prompt-development set (n = 60) and a held-out test set (n = 450; 75 cases and 75 controls per disease). Ground truth was established by independent dual-clinician chart review with consensus adjudication. LLM performance was evaluated against the ground truth: variable-level extraction using accuracy, F1 score, and Cohen’s kappa; patient-level diagnostic classification using sensitivity, specificity, and Cohen’s kappa; and prognostic risk stratification (among confirmed cases) using accuracy, weighted F1 score, and quadratic-weighted Cohen’s kappa. Wilson 95% confidence intervals (CIs) were used for proportions and bootstrap 95% CIs with 500 resamples for F1 scores. Results The held-out test set included 450 patients (PV: 150; ET: 150; MF: 150) with pathology reports and structured laboratory results, and 172 patients (PV: 52; ET: 55; MF: 65) with clinical notes. From pathology reports, overall variable extraction accuracy and F1 score were 99% (95% CI, 98–100) and 1.00 (0.99–1.00) for PV, 100% (99–100) and 0.99 (0.96–1.00) for ET, and 100% (99–100) and 0.99 (0.97–1.00) for MF. From clinical notes, overall accuracy and F1 score were 96% (91–100) and 0.94 (0.85–1.00) for PV, 100% (100–100) and 1.00 (1.00–1.00) for ET, and 100% (99–100) and 0.98 (0.95–1.00) for MF. Diagnostic sensitivity was 100% (95% CI, 95.1–100.0) for PV, ET, and MF; specificity was 98.7% (92.8–99.8) for PV and 100% (95.1–100.0) for both ET and MF, with Cohen’s kappa of 0.99 for PV and 1.00 for ET and MF. Risk stratification accuracy was 100% with weighted F1 score of 1.00 and quadratic-weighted Cohen’s kappa of 1.00 across all three diseases. A pre-specified source-ablation analysis showed that pathology reports alone were sufficient for diagnosis (sensitivity 98.7% for PV, 100% for ET, 96.0% for MF; specificity 100% across all three subtypes) but inadequate for prognostication (accuracy 69.3% for PV, 93.3% for ET, 77.3% for MF). Adding clinical notes to pathology reports recovered full prognostic accuracy of 100% across all three diseases. Conclusions This first-in-class automated framework achieved expert-level performance for MPN diagnosis and risk stratification from real-world EHR data, establishing a foundation for scalable, standardized phenotyping in rare hematologic malignancies. Prospective, multi-site validation is warranted before clinical deployment.

e17005 Background: We previously developed a hybrid framework combining LLMs and rule-based algorithms (RBA) for automated risk stratification in localized prostate cancer (locPCa), achieving 89% accuracy. However, clinical T-stage (cTS) inference from narrative MRI reports remained the primary source of errors. Herein, we evaluated whether ensemble approaches using multiple state-of-the-art LLMs could improve cTS inference and overall NCCN risk stratification accuracy. Methods: This study included patients with locPCa presenting with at least one positive prostate biopsy and MRI report available. Building on our previously validated hybrid framework that extracts structured phenotypic variables (PSA, prostate volume, cTS, Gleason patterns, grade group, positive and examined cores) from unstructured reports using LLMs and applies NCCN-concordant RBA for risk stratification, we focused on improving cTS inference. Four HIPAA-compliant LLMs (GPT-4.1, GPT-5.1, Gemini-2.5-Pro, Gemini-2.5-Flash) were evaluated using structured zero-shot prompts iteratively refined through oncologist feedback. Majority voting was employed to generate consensus cTS predictions. Performance was evaluated using weighted accuracy. Results: A total of 358 patients were included. The median age at diagnosis was 65 years (IQR: 60-69); the majority were White (92%) and non-Hispanic (94%). cTS distribution was T2a (51%), T2c (20%), T3a (16%), T3b (7%), T2b (4%), and T4 (2%). The most prevalent risk category was unfavorable intermediate (38%) followed by favorable intermediate (20%), high risk (19%), very high risk (16%), low (5%), and very low (1%). Individual LLM accuracy for cTS inference ranged from 85-90%, with Gemini-2.5-Pro achieving highest accuracy (90%), followed by GPT-4.1 (88%), GPT-5.1 (87%), and Gemini-2.5-Flash (85%). The four-model ensemble reached consensus in 92% of cases, achieving 93% cTS inference accuracy. When integrated into NCCN risk stratification schema, single-model approaches achieved 89-92% accuracy, while ensemble consensus cases achieved 95% accuracy. Conclusions: The ensemble framework using multiple LLMs significantly improves cTS inference and achieves 95% NCCN risk stratification accuracy in consensus cases (92% of patients), representing a 6-percentage-point improvement over our previous single-model framework (89%). This strategy demonstrates that ensemble methods can overcome individual model limitations for complex clinical tasks and holds promise for reliable AI-assisted risk stratification.

399 Background: The standard of care for resectable GEA adenocarcinomas is perioperative chemotherapy with the FLOT (fluorouracil, leucovorin, oxaliplatin, docetaxel) regimen. Recent studies investigating the addition of checkpoint inhibitors (CPIs) to perioperative chemotherapy have shown mixed results. An NMA can leverage both direct and indirect comparisons to evaluate the relative efficacies of available regimens in this setting. Methods: MEDLINE, EMBASE, Scopus, Web of Science and CENTRAL were searched until August 27th, 2025. Eligible studies included phase 3 randomized trials evaluating perioperative or neoadjuvant chemotherapy +/- CPIs ± radiation in resectable GEA. The primary outcomes were disease-free survival (DFS) and overall survival (OS). Hazard ratios and 95% confidence intervals (CIs) were estimated using a frequentist NMA framework. Results: Fifteen trials including 8072 patients were analyzed. For DFS, perioperative durvalumab + FLOT (dFLOT) ranked highest (P-score = 0.99), followed by FLOT (P-score = 0.84) (HR for dFLOT vs. FLOT was 0.71, 95% CI 0.58-0.86). dFLOT also ranked higher than perioperative pembrolizumab + cisplatin and fluorouracil/capecitabine (KN-585), though this comparison was not statistically significant (HR 0.65, 95% CI 0.40-1.04). Compared with CROSS, dFLOT showed superior DFS (HR of 0.48, 95% CI 0.36-0.63). For OS, dFLOT ranked the highest (P-score=0.95) and was superior to CROSS (HR 0.57, 95% CI 0.42-0.77). While dFLOT appeared favorable versus FLOT (HR 0.78, 95% CI 0.62-0.98), this finding was primarily driven by MATTERHORN, which did not meet its prespecified OS significance boundary (P = 0.03 vs threshold P < 0.0001), and the proportional hazards assumption was violated. Similarly, no significant OS difference was observed between dFLOT and the KN-585 arms (HR 0.75, 95% CI 0.45-1.23). Conclusions: In this NMA, perioperative FLOT remained the benchmark regimen for resectable GEA. dFLOT has shown promising early results, ranking the highest for DFS and showing favorable, but not statistically definitive OS trends in comparison to FLOT. Importantly, the network enabled indirect comparisons not tested in head-to-head trials, demonstrating that dFLOT ranked above pembrolizumab+CF/CX (KN-585) without reaching statistical significance, and also outperformed CROSS. However, these findings should be interpreted with caution, as they are primarily driven MATTERHORN data in which OS did not cross the prespecified threshold and proportional hazards assumptions were violated. Perioperative immunotherapy combinations appear promising, but final MATTERHORN results and further confirmatory studies are needed before dFLOT can be considered as a new standard of care.

Abstract Background: Patients with myelodysplastic syndromes (MDS) are at heightened risk for severe infections, including sepsis, due to underlying cytopenias and immune dysregulation. Hospital-level characteristics, including size and available resources, may influence clinical outcomes in these patients, but data remain limited. This study examines the association between hospital bed size and sepsis-related complications in patients with MDS using a nationally representative dataset. Methods: We conducted a retrospective cohort analysis using the National Inpatient Sample (NIS) from 2016 to 2022, identifying adult hospitalizations with co-diagnoses of MDS and sepsis. Hospitalizations were stratified by hospital bed size: small (n = 15,490), medium (n = 22,815), and large (n = 40,245). Multivariable logistic regression, adjusted for patient demographics, comorbidities, and hospital characteristics, was used to assess associations between hospital bed size and eight clinical outcomes: in-hospital mortality, septic shock, acute renal failure, respiratory failure, encephalopathy, disseminated intravascular coagulation (DIC), Clostridioides difficile infection (CDI), and fungal sepsis. Results: Compared to small hospitals, patients treated at large hospitals had significantly higher odds of in-hospital mortality (OR 1.43, p &lt; 0.001), septic shock (OR 1.25, p &lt; 0.001), acute renal failure (OR 1.10, p &lt; 0.001), encephalopathy (OR 1.11, p = 0.004), DIC (OR 1.48, p = 0.007), and fungal sepsis (OR 2.13, p = 0.028). Medium-sized hospitals were also associated with increased odds of mortality (OR 1.16, p = 0.021) and septic shock (OR 1.13, p = 0.038). No statistically significant differences were found in rates of CDI across hospital sizes. Respiratory failure showed a borderline association in medium hospitals (OR 1.05, p = 0.082) but not in large hospitals. Conclusion: Hospital bed size is independently associated with important variations in sepsis-related outcomes among patients with MDS. Large hospitals demonstrated significantly increased odds of multiple complications and mortality, possibly reflecting referral bias, higher disease acuity, or institutional coding practices. These findings underscore the importance of hospital-level factors in evaluating outcomes and resource planning for high-risk hematologic populations. Keywords: Myelodysplastic syndromes, hospital bed size, sepsis, mortality, ICU complications, NIS

Abstract Background: Myelodysplastic syndromes (MDS) are a heterogeneous group of clonal hematopoietic disorders often complicated by infections due to cytopenias. Sepsis is a frequent cause of hospitalization and mortality in MDS patients. Neutropenia, a common feature in MDS, may predispose patients to specific infectious complications, but its impact on sepsis-related outcomes remains poorly characterized. Methods: We conducted a retrospective cohort study using the National Inpatient Sample (NIS) database from 2016 to 2022. Adult hospitalizations with co-diagnoses of MDS and sepsis were identified using ICD-10-CM codes. Patients were stratified based on the presence or absence of neutropenia. Multivariable logistic regression models were used to evaluate the association between neutropenia and specific in-hospital outcomes, including Clostridioides difficile infection, fungal sepsis, and disseminated intravascular coagulation (DIC). Models were adjusted for age, sex, comorbidities, hospital characteristics, and illness severity. Results: A total of 78,549 hospitalizations involving MDS patients with sepsis were identified, including 11,295 (14.4%) with neutropenia. Neutropenic patients had significantly higher odds of C. difficile infection (adjusted odds ratio [aOR] 1.61, 95% CI 1.30–1.99, p &lt; 0.001) and fungal sepsis (aOR 2.08, 95% CI 1.22–3.54, p = 0.007) compared to those without neutropenia. However, neutropenia was not significantly associated with DIC (aOR 0.84, 95% CI 0.59–1.19, p = 0.322). Conclusion: In this large national cohort, neutropenia was associated with a significantly increased risk of C. difficile infection and fungal sepsis among MDS patients hospitalized with sepsis. These findings highlight the need for early recognition and targeted antimicrobial strategies in neutropenic MDS patients. No significant association was observed between neutropenia and DIC. Future studies should explore preventive strategies and risk stratification tools tailored to this high-risk population. Keywords: Myelodysplastic syndromes, neutropenia, sepsis, NIS, Clostridioides difficile, fungal sepsis, outcomes

Abstract Background: Myelodysplastic syndromes (MDS) are clonal hematopoietic disorders characterized by ineffective hematopoiesis, cytopenias, and an increased susceptibility to infections. Sepsis remains a common and serious cause of morbidity and mortality in this population. While racial disparities in sepsis-related outcomes have been described in the general population, their presence and magnitude among patients with MDS remain poorly understood. Methods: We performed a retrospective cohort study using the National Inpatient Sample (NIS) from 2016 to 2022 to identify adult hospitalizations with co-diagnoses of MDS and sepsis. Patients were stratified by race into White (reference), Black, Hispanic, Asian, Native American, and Other categories. Multivariable logistic regression models, adjusted for demographics, comorbidities, and hospital characteristics, were used to evaluate associations between race and seven key sepsis-related complications: septic shock, acute renal failure, respiratory failure, encephalopathy, disseminated intravascular coagulation (DIC), Clostridioides difficile infection (CDI), and fungal sepsis. Results: Among 78,549 hospitalizations for MDS with sepsis, significant racial disparities were observed. Asian patients had higher odds of developing septic shock (OR 1.26, 95% CI 1.05–1.50, p = 0.014), and both Black (OR 1.24, 95% CI 1.17–1.31, p &lt; 0.001) and Asian (OR 1.14, 95% CI 1.04–1.24, p = 0.004) patients had increased odds of acute renal failure. Respiratory failure was less likely among Black (OR 0.84, 95% CI 0.79–0.90, p &lt; 0.001) and Hispanic (OR 0.76, 95% CI 0.70–0.82, p &lt; 0.001) patients. Encephalopathy was significantly more common in Black (OR 1.29, 95% CI 1.18–1.41, p &lt; 0.001) and Other (OR 1.20, 95% CI 1.01–1.42, p = 0.042) patients. DIC was more frequent in Asian (OR 2.11, 95% CI 1.37–3.27, p = 0.001) and Hispanic (OR 1.53, 95% CI 1.09–2.14, p = 0.014) patients, with a borderline association in Black patients (OR 1.35, p = 0.082). No statistically significant racial differences were noted for CDI or fungal sepsis, although Asian patients trended toward lower odds of CDI (OR 0.64, p = 0.067), and Native American patients had high but non-significant odds for fungal sepsis (OR 3.03, p = 0.287). Conclusion: Our study highlights significant racial disparities in sepsis-related complications among hospitalized MDS patients. Black and Asian patients were more likely to experience acute renal failure and encephalopathy, while Asian and Hispanic patients had higher odds of developing DIC. Conversely, Black and Hispanic patients had lower risk of respiratory failure. These findings underscore the need for race-conscious approaches in sepsis management for patients with MDS and suggest that tailored interventions may be necessary to ensure equitable outcomes across racial groups. Keywords: Myelodysplastic syndromes, sepsis, racial disparities, acute kidney injury, encephalopathy, DIC, respiratory failure, fungal sepsis, National Inpatient Sample

Abstract Background: RUNX1 mutations are established high-risk features in acute myeloid leukemia (AML), associated with poor response to induction therapy and reduced overall survival (OS). Current prognostic models, including the ELN 2022 classification, incorporate RUNX1 mutation status but are based largely on cohorts of European ancestry. This raises concerns about their generalizability to underrepresented populations, particularly African American patients, who continue to experience worse outcomes in AML across treatment settings. Methods: We analyzed publicly available datasets, including TCGA-LAML, Beat AML, and a recent multi-omic study of 100 African American AML patients (Stiff et al., Nat Genet 2024). We evaluated RUNX1 mutation frequency, OS outcomes, and co-mutation patterns, stratified by race. To contextualize survival differences by ancestry, we performed a survival analysis of adult AML patients using the SEER 17 registries (2010–2020), accessed through SEER*Stat. Kaplan-Meier estimates and median OS were compared by race using disease-specific survival. Results: RUNX1 mutations were present in approximately 10–15% of AML cases and consistently associated with inferior OS (median 16–24 months) in both de novo and AML-MRC subsets. Co-mutations in DNMT3A and TET2 further worsened the prognosis. In the African American cohort described by Stiff et al., the frequency of RUNX1 mutations was similar to that in White patients; however, African American patients showed enrichment for IDH2, RAS, and WT1 mutations and lower incidence of NPM1 mutations. Despite comparable mutation rates, African American patients demonstrated significantly worse OS, even under standardized treatment. SEER 17 survival analysis of 5,932 AML cases (683 African American) confirmed shorter median OS in African American patients compared to non-African American patients (10.4 vs. 15.7 months, p&lt;0.01).Conclusions: RUNX1 mutations confer adverse prognosis in AML, but current risk models may not adequately reflect risk in African American patients due to differing co-mutation patterns and underrepresentation in genomic datasets. These findings highlight the need for ancestry-aware risk stratification and inclusive genomic profiling to reduce disparities in AML outcomes. References: Lew-Derivry et al. Leukemia. 2023 Jalili et al. PMCID: PMC5980915 Stiff et al. Nat Genet. 2024 Bhatnagar et al. PMCID: PMC7933110 Tang et al. Blood. 2009 Mendler et al. JCO. 2012 He et al. Scand J Clin Lab Invest. 2020 Döhner et al. Blood. 2022. PMID: 35926292

Abstract Background Accurate diagnosis and risk stratification in myeloproliferative neoplasms (MPNs) rely on expert interpretation of complex clinical records. Outside major academic centers, specialist expertise is scarce, and time-consuming chart reviews extend clinic visits and delay treatment decisions, underscoring the need for automated, point-of-care phenotyping for MPN patients. Methods Patients with the ICD codes of PV, ET and MF were identified from the electronic health record. Cases were defined as patients meeting the 2017 WHO diagnostic criteria for PV, ET or MF or those with a definitive MPN diagnosis determined by a hematologist. Controls were the patients who met neither the diagnostic criteria nor had a hematologist-assigned diagnosis. Two clinicians extracted demographic, clinical (symptoms, thrombotic history), laboratory (complete blood count, serum chemistry), genetic (mutations, karyotype), bone marrow morphology, diagnostic mentions and prognostic score information from unstructured clinical notes and pathology reports. Prognostic scores included the conventional risk model for PV, the International Prognostic Score of Thrombosis (IPSET) for ET and the Dynamic International Prognostic Scoring System (DIPSS), DIPSS-plus or Mutation-enhanced International Prognostic Scoring System (MIPSS-70) for MF. Discrepancies in data extraction were resolved by a consensus. A random sample of 510 patients (PV: 85, ET: 85, MF: 85, controls: 255) was split into prompt development (n=60) and test (n=450) sets for iterative workflow engineering and evaluation. The workflow included: (i) a rule-based algorithm for automated retrieval of demographic details, the first bone marrow biopsy report, the first clinical note after biopsy and the latest laboratory results within 90 days preceding biopsy (ii) a HIPAA-compliant LLM (GPT-4 turbo) for data extraction from the clinical notes and pathology reports (iii) a regular expressions-based algorithm for post-processing extracted data into structured tables, (iv) a clinician-informed source prioritization algorithm to select data from preferred sources, (v) a modified WHO-informed diagnostic characterization tool incorporating hematologist-assigned diagnoses to distinguish cases from controls and; (vi) an NCCN guidelines-based algorithm for prognostic tool selection and risk-stratification based on available data. Structured prompts were used to extract demographic, clinical, laboratory, genetic and pathological data in a zero-shot deterministic setting. The performance of automated data extraction, diagnostic characterization and prognostication was compared against the manually curated data. Accuracy and F1 scores were computed for data extraction and prognostication tasks while sensitivity and specificity were calculated to assess diagnostic performance. Results A total of 450 (PV: 150, ET: 150, MF: 150) pathology reports and 50 (PV: 52, ET: 55; MF: 65) clinical notes were identified for 450 test set patients. The test set data extraction accuracy was 95% (reports: 97%, notes: 92%) for PV, 93% (reports: 92%, notes: 94%) for ET and 98% (reports: 99%, notes 97%) for MF. The test set F1 score was 0.95 (reports: 0.96, notes: 0.93) for PV, 0.95 (reports: 0.95, notes: 0.96) for ET and 0.98 (reports: 0.99, notes: 0.97) for MF. PV patients were diagnosed with 100% sensitivity and 98% specificity whereas ET and MF patients were diagnosed with 100% sensitivity and specificity. The accuracy of risk stratification was 100% for PV and ET and 94% for MF. The F1 score for risk stratification was 1.00 for PV and ET and 0.94 for MF. Conclusions The first-in-class automated framework successfully identified pertinent clinical information, performed accurate data extraction from unstructured records and enabled clinician-guided source prioritization for accurate diagnosis and risk stratification of MPN patients. Prospective validation of the framework is required for widespread clinical implementation.

Following lung cancer, prostate cancer is the leading cause of cancer death in men. High-risk localized tumor burden or metastatic disease often progresses, refractory to initial treatment regimens. There is ongoing development of technology to appropriately identify high-risk patients, stage them correctly, and offer appropriate treatments to obtain the best clinical outcomes. Prostate cancer-specific membrane antigen (PSMA) is a transmembrane glutamate carboxypeptidase, which helps regulate folate absorption, and its overexpression is pathologically directly proportional and associated with prostate cancer. Increased PSMA expression is a known independent risk factor for poorer survival, and most metastatic lesions in CRPC are PSMA positive. Over the last decade, several PSMA-based PET radiopharmaceuticals have demonstrated superior sensitivities and specificities compared to traditional imaging methods. These outcomes have been demonstrated by several large clinical trials. As the data emerges, these diagnostics are being integrated into standard of care protocol to facilitate nuanced identification of malignant lesions. PSMA is also being targeted through several therapeutics, including radioligands and immunotherapies such as CAR-T, BiTEs, and ADCs. This review will discuss the landscape of PSMA-based theranostics in the context of prostate cancer.

e13154 Background: Triple-negative breast cancer (TNBC) is a less common but highly aggressive subtype of breast cancer with poor prognosis and limited therapeutic options. Despite advancements in oncology, significant survival disparities persist among racial, histologic, and socio-demographic groups. This study investigates these disparities and identifies factors contributing to unequal outcomes, providing actionable insights for improving care. Methods: Data on TNBC cases from 2000 to 2021 were extracted from the Surveillance, Epidemiology, and End Results (SEER) database, encompassing 17 registries and 76,265 patients. Patients were categorized by stage, marital status, age, race, and histology. Kaplan-Meier survival analysis was used to estimate median survival with 95% confidence intervals (CI), and the log-rank test assessed differences across groups. Cox proportional hazards regression determined the magnitude of disparities. A p-value < 0.05 was considered statistically significant. Results: Among the 76,265 patients analyzed, those with distant-stage disease had the poorest median survival (51 months; 95% CI: 46–60), compared to localized-stage patients (128 months; 95% CI: 127–129). The youngest cohort (15–19 years) exhibited the lowest survival (43 months), while individuals aged 80–84 had a median survival of 79 months (95% CI: 76–84). South Asians, particularly Pakistani individuals, had the shortest survival among racial groups (83 months). Single patients had lower survival (116 months) compared to married or divorced individuals. Histologically, median survival was 113 months (95% CI: 103–120) for epithelial neoplasms and 78 months for mucoepidermoid neoplasms. All observed differences were statistically significant (p < 0.05). Conclusions: Localized-stage TNBC, individuals aged 40–44, and patients from White or Black racial groups exhibited better survival outcomes, as did those with cystic, mucinous, or serous histologies compared to epithelial neoplasms. Addressing these disparities through tailored treatment strategies and improved access to care is critical. Limitations of this study include the lack of treatment-level data and the potential influence of unmeasured confounders. Stage Marital Status Age Group at Diagnosis Distant Localized Single Divorced 15-19 40-44 80-84 Median Survival(LCL-UCL) 51(46-60) 128(127-129) 116(114-118) 127(124-129) 43(14-NA) 132(130-135) 79(76-84) Neoplasm Histology Race Epithelial Muco-epidermoid Cystic, Mucinous& Serous Pakistani OtherAsian Black White Median Survival(LCL-UCL) 113 (103-120) 78(63-NA) 142(123-NA) 83 (63-NA) 97(91-108) 123 (121-125) 126 (125-127) LCL= Lower Confidence Limit, UCL= Upper Confidence Limit.