Citations

Abstract Objective Data extraction from the published literature is the most laborious step in conducting living systematic reviews (LSRs). We aim to build a generalizable, automated data extraction workflow leveraging large language models (LLMs) that mimics the real-world 2-reviewer process. Materials and Methods A dataset of 10 trials (22 publications) from a published LSR was used, focusing on 23 variables related to trial, population, and outcomes data. The dataset was split into prompt development (n = 5) and held-out test sets (n = 17). GPT-4-turbo and Claude-3-Opus were used for data extraction. Responses from the 2 LLMs were considered concordant if they were the same for a given variable. The discordant responses from each LLM were provided to the other LLM for cross-critique. Accuracy, ie, the total number of correct responses divided by the total number of responses, was computed to assess performance. Results In the prompt development set, 110 (96%) responses were concordant, achieving an accuracy of 0.99 against the gold standard. In the test set, 342 (87%) responses were concordant. The accuracy of the concordant responses was 0.94. The accuracy of the discordant responses was 0.41 for GPT-4-turbo and 0.50 for Claude-3-Opus. Of the 49 discordant responses, 25 (51%) became concordant after cross-critique, increasing accuracy to 0.76. Discussion Concordant responses by the LLMs are likely to be accurate. In instances of discordant responses, cross-critique can further increase the accuracy. Conclusion Large language models, when simulated in a collaborative, 2-reviewer workflow, can extract data with reasonable performance, enabling truly “living” systematic reviews.

AbstractBackgroundGenome‐wide association studies (GWAS) in Alzheimer’s disease (AD) leveraging endophenotypes beyond case/control diagnosis, such as brain amyloid β pathology, have shown promise in identifying novel variants and understanding their potential functional impact. In this study, we leverage two brain amyloid β pathology measurement modalities, PET imaging and neuropathology, to address sample size limitations and to discover novel genetic drivers of disease.MethodWe conducted a meta‐analysis on an amyloid PET imaging GWAS (N = 7,036, 35% amyloid positive, 53.67% female, age = 71) and an autopsy GWAS of brain amyloidosis (N = 6,519, 63.08% amyloid positive, 51.34% female, age at death = 83), both adjusted for covariates including age, sex and principal components of genetic ancestry. All participants in both GWAS were unrelated individuals of European descent. We defined amyloid positivity as moderate or frequent neuritic plaques using the Consortium to Establish a Registry for Alzheimer’s Disease (CERAD) staging scores within each autopsy cohort. A Gaussian mixture model (GMM) was applied to each amyloid PET imaging cohort to identify the cohort and tracer‐specific cut‐offs that differentiate amyloid positive and negative populations.ResultThe genome‐wide significant results from the meta‐analysis identified three known AD loci (APOE, CR1, and BIN1) and a novel chromosome 17 locus (rs35635959, intergenic, MAF = 0.27, OR = 1.18, p = 1.47 × 10‐8). The MAGMA gene‐level analysis excluding the APOE region suggests significant associations between rs35635959 and COASY, PLEKHH3, and TUBG2 on chromosome 17, implying the potential roles of these genes on amyloidosis. Functional annotations of rs35635959 leveraging brain eQTL databases indicate its association with differential gene expression of COASY and TUBG2 in AD brains. ROSMAP bulk and single‐nucleus RNAseq analyses link TUBG2 downregulation to the higher amyloid burden and AD diagnosis while suggesting such observations are enriched in excitatory and inhibitory neurons, reaching FDR significance.ConclusionThis study is the most extensive European GWAS of brain amyloidosis, and our findings replicate known AD loci and identify a possible novel locus (index SNP rs35635959) on chromosome 17. Functional annotations of the novel variant indicate TUBG2, implicating in microtubule organization, warrants further assessment. Ongoing efforts aim to validate these novel effects using independent datasets.

Introduction Symptom burden in myeloproliferative neoplasms (MPN) is quantified using total symptom scores (TSS) calculated from the patient-reported scores for clinically meaningful symptoms. The impact of demographic, clinical, and laboratory features on these symptoms remains unclear and warrants further investigation. Methods Patients with polycythemia vera (PV), essential thrombocythemia (ET), and myelofibrosis (MF) were identified from the retrospective chart review. TSS, scores of individual symptoms (fatigue, early satiety, abdominal discomfort, inactivity, concentration difficulties, fever, night sweats, itching, bone pain, weight loss), demographic characteristics (race, ethnicity, age, and gender), clinical features (time since diagnosis, depression status, obesity status), laboratory results and season at the time of visit when the first TSS assessment was performed were recorded. Multicollinearity and homoscedasticity were assessed using variance inflation factors and visual inspection of the data, respectively. A multivariable regression analysis was performed using a robust variance estimator. A p-value <0.05 indicated a statistically significant association with the symptom scores. Results The chart review identified 557 (PV: 201; ET: 191; MF: 165) patients. The median age of patients with PV, ET, and MF was 65 (range: 27-93), 65 (20-96), and 69 (27-96) years, respectively. Most patients were white (PV: 92%; ET: 90%; MF: 93%) and non-Hispanic or Latino (PV: 93%; ET: 96%; MF: 92%). Most patients with PV and ET were female (PV: 51%; ET: 73%), while most patients with MF were male (55%). Among the included patients 22% (PV: 21%; ET: 27%; MF: 18%) had the diagnosis of depression at the time of the clinical visit. TSS was highest in MF (mean (SD): 18.1±14.6), followed by PV (15.7±14.5) and ET (15.1±14.0) patients. Fatigue was the most reported symptom by the patients (PV: 81%; ET: 82%; MF: 84%), whereas weight loss was the least reported symptom (PV: 4.5%; ET: 6.3%; MF: 16%). With regards to the TSS multivariable regression analysis showed that age (beta coefficient: 0.2; p=0.01), depression (7.2; 0.008), and low hemoglobin (1.2; 0.003) in PV, depression (11.7; 0.001) in ET, and depression (9.5; 0.001), splenomegaly (6.9; 0.01), and WBC count (0.16; 0.048) in MF patients were significantly associated with TSS. In terms of individual symptoms in PV, depression was associated with fatigue (beta coefficient: 1.31; p-value: 0.01) and concentration difficulties (1.7; <0.001), high WBC count was associated with early satiety (0.09; 0.03), and non-white race was associated with fever (1.4; 0.007). In ET, depression was associated with fatigue (1.6; <0.001), abdominal discomfort (1.4; <0.001), inactivity (2.5; <0.001), concentration difficulties (2.4; <0.001) and night sweats (1.4; <0.001), anemia was associated with fatigue (1.2; 0.03), fewer months since diagnosis was associated with inactivity (0.01; 0.02) and young age was associated with bone pain (0.02; 0.03). In MF, depression was associated with fatigue (1.8; 0.001), concentration difficulties (1.3; 0.01), fever (1.1; 0.02), and night sweats (2.2; 0.03), low hemoglobin was associated with fatigue (0.46; <0,001) and early satiety (0.31; 0.003), high WBC count was associated with fatigue (0.03; 0.04) and early satiety (0.04; 0.02), low platelet count was associated with abdominal discomfort (0.002; 0.03), splenomegaly was associated with inactivity (2.27; 0.003) and female gender was associated with itching (0.57; 0.01). Conclusions This study demonstrates that depression in PV and ET and depression, low hemoglobin, and a high WBC count in MF contribute to multiple symptoms seen in these patients. Identifying demographic groups at risk of a higher symptom burden and addressing the comorbidities that drive symptoms, in addition to disease-directed therapy, is crucial to improving the quality of life in these patients.

Introduction Prognostication in myelofibrosis (MF) currently relies on manual assessment of clinical, pathological, and laboratory variables, which is inefficient and error-prone. The potential of large language models (LLMs) and rule-based programming to automate data extraction and prognostication in these patients remains unexplored and merits investigation. Methods Patients with MF were identified from a retrospective chart review. Data regarding clinical (age, constitutional symptoms, transfusion requirements), laboratory (hemoglobin, circulating white blood cell, platelet, and blast counts), and pathological (grade of bone marrow fibrosis, chromosomal analyses, cytogenetics) features was extracted from the latest free-text clinical notes and pathology reports using the generative pretrained transformer-4 (GPT-4) model in a zero-shot setting with the prompting parameters set to generate deterministic responses. The patients were randomly sampled into development (15%) and test (85%) sets, with the documents of patients in the development set used for iterative prompt engineering. The finalized prompts were used for data extraction in the test set. Rule-based programming was used for post-processing of the extracted data and ascertaining prognosis via Dynamic International Prognostic Scoring System (DIPSS), DIPSS-plus (DIPSS+), and Mutation-enhanced International Prognostic Scoring System-70 (MIPSS-70). Automatically extracted data and prognostic categories were compared with the manually generated human annotations. Mean accuracy, precision, and recall with 95% confidence intervals (CI) were computed. Detailed error and sensitivity analyses were conducted to assess performance. Results The study included 100 patients (development: 15; test: 85) with 100 clinical notes (development: 15; test: 85) and 90 pathology reports (development: 13; test: 77). The mean age of these patients was 70 (SD: 10.6); 55 (55%) patients were men, and 93 (93%) patients were White. In the development set, the mean accuracy, precision, and recall for data extraction from clinical notes were 94% (95% CI: 90-98%), 92% (84-99%), and 99% (97-100%). For data extraction from pathology reports, the mean accuracy, precision, and recall were 96% (93-100%), 98% (92-100%), and 83% (63-100%). For prognostication, the mean accuracy, precision, and recall were 87% (79-94%), 80% (73-87%), and 100% using DIPSS (accuracy: 80%; precision: 73%; recall: 100%), DIPSS+ (accuracy: 93%; precision: 83%; recall: 100%) and MIPSS-70 (accuracy: 87%, precision: 83%; recall: 100%). In the test set, the mean accuracy, precision, and recall for data extraction from clinical notes were 96% (95% CI: 93-98%), 91% (87-96%), and 98% (97-100%). For data extraction from pathology reports, the mean accuracy, precision, and recall were 95% (92-98%), 93% (87-99%), and 90% (80-100%). For prognostication the mean accuracy, precision, and recall were 95% (94-96%), 89% (88-90%) and 99% (96-100%) using DIPSS (accuracy: 94%; precision: 89%; recall: 100%), DIPSS+ (accuracy: 95%; precision: 88%; recall: 95%) and MIPSS-70 (accuracy: 94%, precision: 90%; recall: 100%). Error analyses identified incorrect extractions by GPT-4 were related to the circulating blasts and constitutional symptoms variables from the clinical notes. Sensitivity analyses excluding the associated variables improved overall accuracy from 94% to 97% and 96% to 97% in the development and test sets, respectively. Similarly, incorrect extractions from the pathology reports were related to the CALR gene mutation variables. Sensitivity analyses excluding the associated variables improved the overall accuracy from 96% to 98% and 95% to 97% in the development and test sets, respectively. Conclusion LLMs and rule-based programming can accurately extract data from the electronic health records and prognosticate MF patients via DIPSS, DIPSS+, and MIPSS-70. The automated approach could significantly streamline clinical and research workflows, providing an efficient and less resource-intensive alternative to manual prognostication.

Background Lipoprotein(a) [Lp(a)] is an independent, causal risk factor for cardiovascular disease. However, it is still unclear whether controlling low-density lipoprotein cholesterol (LDL-C) to optimal levels can attenuate cardiovascular risk mediated by elevated Lp(a), especially in the setting of secondary prevention. Methods Adult patients with a baseline Lp(a) measurement who underwent percutaneous coronary intervention (PCI) and reached their LDL-C target levels (<70 mg/dl) at Mayo Clinic sites between 2006 and 2017 were included. Primary outcomes included major adverse cardiovascular events (MACE) and all-cause mortality. Kaplan–Meier curves were created to compare the survival probabilities among patients with Lp(a) ≥ 50 mg/dl compared with Lp(a) < 50 mg/dl. Multivariable Cox regression analyses were performed to quantify the association of elevated Lp(a) with our relevant outcomes and to control for possible confounders. Results In total, 878 patients (median age: 68 years, and 74% males) who underwent PCI were included for analysis. Of them, 29.7% had elevated Lp(a) ≥ 50 mg/dl. Kaplan–Meier curves did not reveal any significant difference in survival probabilities for elevated Lp(a) for any outcome including MACE (P = 0.91), all-cause mortality (P = 0.26), or the separate MACE components. Similarly, the multivariable analysis showed no significant association for MACE (hazard ratio: 1.07, 95% confidence interval: 0.84–1.37) or all-cause mortality (hazard ratio: 0.98, 95% confidence interval: 0.74–1.30). Conclusion In patients who underwent PCI and have their LDL-C controlled below 70 mg/dl, no significant association was found between elevated Lp(a) ≥ 50 mg/dl and risk for MACE or all-cause mortality.

Background: Hypertriglyceridemia, a common lipid disorder linked to increased risks of cardiovascular diseases and metabolic syndrome, remains a global health challenge. Traditional treatments, though widely used, often have limited efficacy and adverse effects. Olezarsen, a novel antisense oligonucleotide, targets apolipoprotein C-III and shows promise in significantly reducing triglyceride levels. Aim: To conduct a meta-analysis comparing Olezarsen with placebo in patients with hypertriglyceridemia. Methods: We performed an extensive literature search of PubMed, EMBASE, and Cochrane Library databases up to May 2024 to identify studies comparing Olezarsen and placebo in patients with hypertriglyceridemia, irrespective of comorbid cardiovascular disease. Effect estimates were pooled using a random-effects model and reported as risk ratios (RR) for dichotomous outcomes and standard mean differences (SMD) for continuous outcomes, with 95% confidence intervals (CIs) for each. Results: Three randomized controlled trials (RCTs) with a total of 334 participants were included. Olezarsen significantly reduced triglyceride levels at 6 months (SMD: -1.69; 95% CI -2.22 to -1.17; P < 0.00001; Figure ) and 12 months (SMD: -1.64; 95% CI -2.22 to -1.07; P < 0.00001; Figure ). VLDL levels also decreased at 6 months (SMD: -1.95; 95% CI -2.38 to -1.51; P < 0.00001) and 12 months (SMD: -0.83; 95% CI -1.13 to -0.53; P < 0.00001). Lipid profile improvements included reductions in total cholesterol, non-HDL cholesterol, and apoB levels, with increases in HDL cholesterol and apoA-1. Adverse events were comparable between Olezarsen and placebo, although serious adverse events were significantly higher in the Olezarsen group (RR: 2.55; 95% CI 1.17 to 5.58; p = 0.02). Conclusion: Olezarsen demonstrates significant efficacy in reducing triglyceride and VLDL levels while improving overall lipid profiles in hypertriglyceridemia patients. Despite higher rates of serious adverse events, its overall safety profile remains acceptable.

Purpose of review This review underscores the critical role and challenges associated with the widespread adoption of artificial intelligence in cancer care to enhance disease management, streamline clinical processes, optimize data retrieval of health information, and generate and synthesize evidence. Recent findings Advancements in artificial intelligence models and the development of digital biomarkers and diagnostics are applicable across the cancer continuum from early detection to survivorship care. Additionally, generative artificial intelligence has promised to streamline clinical documentation and patient communications, generate structured data for clinical trial matching, automate cancer registries, and facilitate advanced clinical decision support. Widespread adoption of artificial intelligence has been slow because of concerns about data diversity and data shift, model reliability and algorithm bias, legal oversight, and high information technology and infrastructure costs. Summary Artificial intelligence models have significant potential to transform cancer care. Efforts are underway to deploy artificial intelligence models in the cancer practice, evaluate their clinical impact, and enhance their fairness and explainability. Standardized guidelines for the ethical integration of artificial intelligence models in cancer care pathways and clinical operations are needed. Clear governance and oversight will be necessary to gain trust in artificial intelligence-assisted cancer care by clinicians, scientists, and patients.

6582 Background: Although high symptom burden indicates poor survival and informs treatment decisions, little is known about the impact of demographic, clinical, and laboratory features on total symptom score (TSS) in patients with myeloproliferative neoplasms (MPN). Methods: Patients with MPN (polycythemia vera (PV), essential thrombocythemia (ET), and myelofibrosis (MF)) were identified from the retrospective chart review. TSS, individual symptom scores (fatigue, early satiety, abdominal discomfort, inactivity, concentration problems, fever, night sweats, itching, bone pain, weight loss), demographic characteristics (race, ethnicity, age, gender), clinical features (time since diagnosis, depression status, obesity status, spleen size), laboratory results and season at the time of visit were recorded from the clinical encounter when index assessment of TSS was performed for each patient. Normality was assessed using visual inspection of data distribution, whereas multicollinearity was assessed using various inflation factors. A univariable regression followed by a multivariable regression analysis was conducted using a backward selection approach. A p-value <0.05 indicated a statistically significant association of a given feature with TSS. Results: The chart review identified 252 patients (PV: 78; ET: 81; MF: 93). Mean age was 59 (SD: 17.7), 67 (SD: 13.0), and 68 (SD: 10.9) years for ET, PV, and MF respectively. Most patients were white (PV, MF: 92%; ET: 83%) and females (ET: 75%; PV: 60%; MF: 53%). The TSS of patients was highest with PV (mean: 18.5; SD: 16.9) followed by MF (mean: 18.1; SD: 15.4) and ET (mean: 14.3; SD: 15.9). Fatigue was the most reported symptom whereas the least reported symptoms were fever and weight loss. Univariable regression analyses showed depression (B: 17.7; p=0.02), female gender (B: 10.6; p=0.01), platelet count (B: 0.03; p=0.03), and hemoglobin (Hb) (B: -2.6; p=0.01) in PV patients, depression (B: 19.8, p=2x10-5) in ET patients and depression (B: 11.0, p=0.03), white blood cell (WBC) count (B: 0.2; p=0.01), neutrophil count (B: 0.3, p=0.01), and non-neutrophil WBC count (B: 0.6; p=0.02) in MF patients to have significant association with TSS. Multivariable regression analyses ( Table) showed Hb (B: -2.5; p=0.01) and platelet count (B: 0.02; p=0.03) in PV patients, depression (B: 19.7; p=2x10-5) in ET patients and depression (B: 12.3, p=0.01) and WBC count (B: 0.3; p=0.002) in MF patients to have a significant association with TSS. Conclusions: Depression in ET and MF and low Hb in PV were identified as significant drivers of symptom burden. Identifying and managing patients with these comorbidities could improve their quality of life with a potential survival benefit. [Table: see text]

e19534 Background: Immunomodulatory drugs, proteasome inhibitors plus dexamethasone are the standard triplet induction regimen for TENDMM. We analyzed the efficacy of adding either anti-CD38 monoclonal antibodies (mAbs) or anti-SLAMF7 antibody to the triplet therapy. Methods: Ovid MEDLINE, EMBASE and published abstracts were systematically searched from each database’s inception through 01-31-2024 to identify II/III trials assessing quadruplet therapy versus triplet therapy in TENDMM patients. Hazard ratios (HR) for progression-free survival (PFS) and overall survival (OS), odds ratios (OR) for overall response rates (ORR), measurable residual disease (MRD) negativity rate (with sensitivity of 10 -5) and grade 3 or higher treatment-related adverse events (G≥3 TRAE) were summarized using random effects meta-analysis via inverse variance approach. Additional subgroup analyses based on the cytogenetic risk were performed. P-value of interaction (Pint ) < 0.1 was pre-specified as statistically significant for the difference between the two groups. Results: 3806 studies were screened and seven trials were included with a total of 3546 patients. Four trials (2303 patients) assessed the addition of anti-CD-38 mAbs and three (1243 patients) assessed anti-SLAMF7 mAb, elotuzumab to the triplet regimen. Quadruplet therapy significantly improved PFS as compared to triplet (HR: 0.63; 95% CI: 0.43-0.92), and the PFS benefit was also observed in standard risk group (HR 0.5; 95% CI 0.2-0.9); however, results were insignificant for high-risk group (HR 0.8; 95% CI 0.62-1.93). No significant OS benefit was observed (HR: 0.79; 95% CI 0.49–1.26); however, data for three trials (CASSIOPEIA, DSMM XVII, PERSEUS) is immature, with longer-term follow-up ongoing. Quadruplet therapy showed significant results for very good partial response or better (OR: 1.7; 95% CI 1.2-2.36), stringent complete response (OR: 1.74; 95% CI 1.27-2.07) and complete response or better (OR: 1.91; 95% CI 1.19-3.06). MRD rate shows benefit with quadruplet therapy (OR: 2.59; 95% CI 2.22-3.01). Improved MRD rate was also observed for high-risk (OR 2.13; 95% CI 1.4-3.2) and standard-risk group (OR 2.58; 95% CI 1.68-3.94). Secondary analysis for efficacy of anti-CD38 mAbs showed benefit for PFS (HR: 0.44; 95% CI: 0.35-0.56), ORR (OR: 1.77;95% CI: 1.02-3.06), and MRD (OR: 2.98; 95% CI 1.8-4.8). G ≥3 TRAE did not significantly differ between the groups (OR: 1.05; 95% CI 0.97-1.12). However, quadruplet therapy showed significant risk of infection (OR: 1.2; 95% 1.05-1.35) and thrombocytopenia (OR: 1.41; 95% CI 1.24-1.59). Conclusions: Quadruplet therapy improved PFS, ORR, and MRD rates compared to triplet regimen and has demonstrated promising benefits to be considered the new standard of care for TENDMM patients.