Phenotyping Hepatic Immune-Related Adverse Events in the Setting of Immune Checkpoint Inhibitor Therapy.

PURPOSE: We present and validate a rule-based algorithm for the detection of moderate to severe liver-related immune-related adverse events (irAEs) in a real-world patient cohort. The algorithm can be applied to studies of irAEs in large data sets. METHODS: We developed a set of criteria to define hepatic irAEs. The criteria include: the temporality of elevated laboratory measurements in the first 2-14 weeks of immune checkpoint inhibitor (ICI) treatment, steroid intervention within 2 weeks of the onset of elevated laboratory measurements, and intervention with a duration of at least 2 weeks. These criteria are based on the kinetics of patients who experienced moderate to severe hepatotoxicity (Common Terminology Criteria for Adverse Events grades 2-4). We applied these criteria to a retrospective cohort of 682 patients diagnosed with hepatocellular carcinoma and treated with ICI. All patients were required to have baseline laboratory measurements before and after the initiation of ICI. RESULTS: A set of 63 equally sampled patients were reviewed by two blinded, clinical adjudicators. Disagreements were reviewed and consensus was taken to be the ground truth. Of these, 25 patients with irAEs were identified, 16 were determined to be hepatic irAEs, 36 patients were nonadverse events, and two patients were of indeterminant status. Reviewers agreed in 44 of 63 patients, including 19 patients with irAEs (0.70 concordance, Fleiss' kappa: 0.43). By comparison, the algorithm achieved a sensitivity and specificity of identifying hepatic irAEs of 0.63 and 0.81, respectively, with a test efficiency (percent correctly classified) of 0.78 and outcome-weighted F1 score of 0.74. CONCLUSION: The algorithm achieves greater concordance with the ground truth than either individual clinical adjudicator for the detection of irAEs.

Matching Patients to Accelerate Clinical Trials (MPACT): Enabling Technology for Oncology Clinical Trial Workflow.

Clinical trial enrollment is impeded by the significant time burden placed on research coordinators screening eligible patients. With 50,000 new cancer cases every year, the Veterans Health Administration (VHA) has made increased access for Veterans to high-quality clinical trials a priority. To aid in this effort, we worked with research coordinators to build the MPACT (Matching Patients to Accelerate Clinical Trials) platform with a goal of improving efficiency in the screening process. MPACT supports both a trial prescreening workflow and a screening workflow, employing Natural Language Processing and Data Science methods to produce reliable phenotypes of trial eligibility criteria. MPACT also has a functionality to track a patient's eligibility status over time. Qualitative feedback has been promising with users reporting a reduction in time spent on identifying eligible patients.

Transfer Learning for Mortality Prediction in Non-Small Cell Lung Cancer with Low-Resolution Histopathology Slide Snapshots.

High-resolution whole slide image scans of histopathology slides have been widely used in recent years for prediction in cancer. However, in some cases, clinical informatics practitioners may only have access to low-resolution snapshots of histopathology slides, not high-resolution scans. We evaluated strategies for training neural network prognostic models in non-small cell lung cancer (NSCLC) based on low-resolution snapshots, using data from the Veterans Affairs Precision Oncology Data Repository. We compared strategies without transfer learning, with transfer learning from general domain images, and with transfer learning from publicly available high-resolution histopathology scans. We found transfer learning from high-resolution scans achieved significantly better performance than other strategies. Our contribution provides a foundation for future development of prognostic models in NSCLC that incorporate data from low-resolution pathology slide snapshots alongside known clinical predictors.

Building Research Infrastructure to Develop Greater Learning Efficiencies (BRIDGE).

In this manuscript, we outline our developed version of a Learning Health System (LHS) in oncology implemented at the Department of Veterans Affairs (VA). Transferring healthcare into an LHS framework has been one of the spearpoints of VA's Central Office and given the general lack of evidence generated through randomized control clinical trials to guide medical decisions in oncology, this domain is one of the most suitable for this change. We describe our technical solution, which includes a large real-world data repository, a data science and algorithm development framework, and the mechanism by which results are brought back to the clinic and to the patient. Additionally, we propose the need for a bridging framework that requires collaboration between informatics specialists and medical professionals to integrate knowledge generation into the clinical workflow at the point of care.

Brain tumors in United States military veterans.

BACKGROUND: Comprehensive analysis of brain tumor incidence and survival in the Veteran population has been lacking. METHODS: Veteran data were obtained from the Veterans Health Administration (VHA) Medical Centers via VHA Corporate Data Warehouse. Brain tumor statistics on the overall US population were generated from the Central Brain Tumor Registry of the US data. Cases were individuals (≥18 years) with a primary brain tumor, diagnosed between 2004 and 2018. The average annual age-adjusted incidence rates (AAIR) and 95% confidence intervals were estimated per 100 000 population and Kaplan-Meier survival curves evaluated overall survival outcomes among Veterans. RESULTS: The Veteran population was primarily white (78%), male (93%), and between 60 and 64 years old (18%). Individuals with a primary brain tumor in the general US population were mainly female (59%) and between 18 and 49 years old (28%). The overall AAIR of primary brain tumors from 2004 to 2018 within the Veterans Affairs cancer registry was 11.6. Nonmalignant tumors were more common than malignant tumors (AAIR:7.19 vs 4.42). The most diagnosed tumors in Veterans were nonmalignant pituitary tumors (AAIR:2.96), nonmalignant meningioma (AAIR:2.62), and glioblastoma (AAIR:1.96). In the Veteran population, survival outcomes became worse with age and were lowest among individuals diagnosed with glioblastoma. CONCLUSIONS: Differences between Veteran and US populations can be broadly attributed to demographic composition differences of these groups. Prior to this, there have been no reports on national-level incidence rates and survival outcomes for Veterans. These data provide vital information that can drive efforts to understand disease burden and improve outcomes for individuals with primary brain tumors.

Determinants of Achieving Serum Urate Goal with Treat-to-Target Urate-Lowering Therapy in Gout.

OBJECTIVE: Using trial data comparing treat-to-target allopurinol and febuxostat in gout, we examined participant characteristics associated with serum urate (SU) goal achievement. METHODS: Participants with gout and SU ≥6.8 mg/dL were randomized to allopurinol or febuxostat, titrated during weeks 0 to 24, and maintained weeks 25 to 48. Participants were considered to achieve SU goal if the mean SU from weeks 36, 42, and 48 was <6.0 mg/dL or <5 mg/dL if tophi were present. Possible determinants of treatment response were preselected and included sociodemographics, comorbidities, diuretic use, health-related quality of life (HRQoL), body mass index, and gout measures. Determinants of SU response were assessed using multivariable logistic regression with additional analyses to account for treatment adherence. RESULTS: Of 764 study participants completing week 48, 618 (81%) achieved SU goal. After multivariable adjustment, factors associated with a greater likelihood of SU goal achievement included older age (adjusted odds ratio [aOR] 1.40 per 10 years), higher education (aOR 2.02), and better HRQoL (aOR 1.17 per 0.1 unit). Factors associated with a lower odds of SU goal achievement included non-White race (aORs 0.32-0.47), higher baseline SU (aOR 0.83 per 1 mg/dL), presence of tophi (aOR 0.29), and the use of diuretics (aOR 0.52). Comorbidities including chronic kidney disease, hypertension, diabetes, and cardiovascular disease were not associated with SU goal achievement. Results were not meaningfully changed in analyses accounting for adherence. CONCLUSIONS: Several patient-level factors were predictive of SU goal achievement among patients with gout who received treat-to-target urate-lowering therapy (ULT). Approaches that accurately predict individual responses to treat-to-target ULT hold promise in facilitating personalized management and improving outcomes in patients with gout.

Prostate cancer patient stratification by molecular signatures in the Veterans Precision Oncology Data Commons.

Veterans are at an increased risk for prostate cancer, a disease with extraordinary clinical and molecular heterogeneity, compared with the general population. However, little is known about the underlying molecular heterogeneity within the veteran population and its impact on patient management and treatment. Using clinical and targeted tumor sequencing data from the National Veterans Affairs health system, we conducted a retrospective cohort study on 45 patients with advanced prostate cancer in the Veterans Precision Oncology Data Commons (VPODC), most of whom were metastatic castration-resistant. We characterized the mutational burden in this cohort and conducted unsupervised clustering analysis to stratify patients by molecular alterations. Veterans with prostate cancer exhibited a mutational landscape broadly similar to prior studies, including KMT2A and NOTCH1 mutations associated with neuroendocrine prostate cancer phenotype, previously reported to be enriched in veterans. We also identified several potential novel mutations in PTEN, MSH6, VHL, SMO, and ABL1 Hierarchical clustering analysis revealed two subgroups containing therapeutically targetable molecular features with novel mutational signatures distinct from those reported in the Catalogue of Somatic Mutations in Cancer database. The clustering approach presented in this study can potentially be used to clinically stratify patients based on their distinct mutational profiles and identify actionable somatic mutations for precision oncology.

Baseline correlates of frailty and its association with survival in United States veterans with acute myeloid leukemia.

Frailty is an important construct to measure in acute myeloid leukemia (AML). We used the Veterans Affairs Frailty Index (VA-FI) - calculated using readily available data within the VA's electronic health records - to measure frailty in U.S. veterans with AML. Of the 1166 newly diagnosed and treated veterans with AML between 2012 and 2022, 722 (62%) veterans with AML were classified as frail (VA-FI > 0.2). At a median follow-up of 252.5 days, moderate-severely frail veterans had significantly worse survival than mildly frail, and non-frail veterans (median survival 179 vs. 306 vs. 417 days, p < .001). Increasing VA-FI severity was associated with higher mortality. A model with VA-FI in addition to the European LeukemiaNet (ELN) risk classification and other covariates statistically outperformed a model containing the ELN risk and other covariates alone (p < .001). These findings support the VA-FI as a tool to expand frailty measurement in research and clinical practice for informing prognosis in veterans with AML.

Machine learning-based natural language processing to extract PD-L1 expression levels from clinical notes.

Introduction: PD-L1 expression is used to determine oncology patients' response to and eligibility for immunologic treatments; however, PD-L1 expression status often only exists in unstructured clinical notes, limiting ability to use it in population-level studies. Methods: We developed and evaluated a machine learning based natural language processing (NLP) tool to extract PD-L1 expression values from the nationwide Veterans Affairs electronic health record system. Results: The model demonstrated strong evaluation performance across multiple levels of label granularity. Mean precision of the overall PD-L1 positive label was 0.859 (sd, 0.039), recall 0.994 (sd, 0.013), and F1 0.921 (0.024). When a numeric PD-L1 value was identified, the mean absolute error of the value was 0.537 on a scale of 0 to 100. Conclusion: We presented an accurate NLP method for deriving PD-L1 status from clinical notes. By reducing the time and manual effort needed to review medical records, our work will enable future population-level studies in cancer immunotherapy.

Epidemiology of Cancer-Associated Venous Thromboembolism in Patients With Solid and Hematologic Neoplasms in the Veterans Affairs Health Care System.

Importance: Identifying changes in epidemiologic patterns of the incidence and risk of cancer-associated thrombosis (CAT), particularly with evolving cancer-directed therapy, is essential for risk stratification. Objective: To assess the incidence of CAT over time and to determine pertinent patient-specific, cancer-specific, and treatment-specific factors associated with its risk. Design, Setting, and Participants: This longitudinal, retrospective cohort study was conducted from 2006 to 2021. Duration of follow-up was from the date of diagnosis until first venous thromboembolism (VTE) event, death, loss of follow-up (defined as a 90-day gap without clinical encounters), or administrative censoring on April 1, 2022. The study took place within the US Department of Veterans Affairs national health care system. Patients with newly diagnosed invasive solid tumors and hematologic neoplasms were included in the study. Data were analyzed from December 2022 to February 2023. Exposure: Newly diagnosed invasive solid tumors and hematologic neoplasms. Main Outcomes: Incidence of VTE was assessed using a combination of International Classification of Diseases, Ninth Revision, Clinical Modification and International Statistical Classification of Diseases, Tenth Revision, Clinical Modification and natural language processing confirmed outcomes. Cumulative incidence competing risk functions were used to estimate incidence of CAT. Multivariable Cox regression models were built to assess the association of baseline variables with CAT. Pertinent patient variables included demographics, region, rurality, area deprivation index, National Cancer Institute comorbidity index, cancer type, staging, first-line systemic treatment within 3 months (time-varying covariate), and other factors that could be associated with the risk of VTE. Results: A total of 434 203 patients (420 244 men [96.8%]; median [IQR] age, 67 [62-74] years; 7414 Asian or Pacific Islander patients [1.7%]; 20 193 Hispanic patients [4.7%]; 89 371 non-Hispanic Black patients [20.6%]; 313 157 non-Hispanic White patients [72.1%]) met the inclusion criteria. Overall incidence of CAT at 12 months was 4.5%, with yearly trends ranging stably from 4.2% to 4.7%. The risk of VTE was associated with cancer type and stage. In addition to confirming well-known risk distribution among patients with solid tumors, a higher risk of VTE was observed among patients with aggressive lymphoid neoplasms compared with patients with indolent lymphoid or myeloid hematologic neoplasms. Compared with no treatment, patients receiving first-line chemotherapy (hazard ratio [HR], 1.44; 95% CI, 1.40-1.49) and immune checkpoint inhibitors (HR, 1.49; 95% CI, 1.22-1.82) had a higher adjusted relative risk than patients receiving targeted therapy (HR, 1.21; 95% CI, 1.13-1.30) or endocrine therapy (HR, 1.20; 95% CI, 1.12-1.28). Finally, adjusted VTE risk was significantly higher among Non-Hispanic Black patients (HR, 1.23; 95% CI, 1.19-1.27) and significantly lower in Asian or Pacific Islander patients (HR, 0.84; 95% CI, 0.76-0.93) compared with Non-Hispanic White patients. Conclusions and Relevance: In this cohort study of patients with cancer, a high incidence of VTE was observed, with yearly trends that remained stable over the 16-year study period. Both novel and known factors associated with the risk of CAT were identified, providing valuable and applicable insights in this current treatment landscape.

Trends in Fracture Rates Over Two Decades Among Veterans With Ankylosing Spondylitis.

OBJECTIVE: There is an increased risk of fracture in individuals with ankylosing spondylitis (AS) compared to the general population, possibly due to systemic inflammatory effects. The use of tumor necrosis factor inhibitors (TNFi) may reduce fracture risk by inhibiting inflammation. We assessed fracture rates in AS versus non-AS comparators and whether these rates have changed since the introduction of TNFi. METHODS: We used the national Veterans Affairs database to identify adults ≥18 years old with ≥1 International Classification of Diseases, Ninth Revision (ICD-9)/ICD-10 code for AS and at least 1 disease-modifying antirheumatic drug prescription. As comparators, we selected a random sample of adults without AS diagnosis codes. We calculated fracture incidence rates for AS and comparators, with direct standardization to the cohort structure in 2017. To compare fracture rates from 2000 to 2002 (pre-TNFi) versus 2004-2020 (TNFi era), we performed an interrupted time series analysis. RESULTS: We included 3,794 individuals with AS (mean age 53 years, 92% male) and 1,152,805 comparators (mean age 60 years, 89% male). For AS, the incidence rate of fractures increased from 7.9/1,000 person-years in 2000 to 21.6/1,000 person-years in 2020. The rate also increased among comparators, although the ratio of fracture rates (AS/comparators) remained relatively stable. In the interrupted time series, the fracture rate for AS patients in the TNFi era was nonsignificantly increased compared to the pre-TNFi era. CONCLUSION: Fracture rates have increased over time for both AS and non-AS comparators. The fracture rate in individuals with AS did not decrease after TNFi introduction in 2003.

Venous thromboembolism risk in cancer patients receiving first-line immune checkpoint inhibitor versus chemotherapy.

It remains unclear if immune checkpoint inhibitor (ICI) therapy is associated with higher rate of venous thromboembolism (VTE) compared with cytotoxic chemotherapy (chemo) in patients with comparable cancer type, staging, and comorbidities. Using the national Veterans Affairs healthcare system database from 2016 to 2021, we performed a propensity score (PS)-weighted retrospective cohort study to compare the incidence of VTE in patients with selected stage III/IV cancer receiving first-line ICI versus chemo. The PS model utilized overlap weights to balance age, sex, race, treatment year, VTE history, paralysis/immobilization, prolonged hospitalization, cancer type, staging, time between diagnosis and treatment, and National Cancer Institute comorbidity index. Weighted Cox regressions with robust standard error were used to assess the hazard ratio (HR) and 95% confidence interval (CI). We found that among comparable advanced cancers, first-line ICI (n = 1823) and first-line chemo (n = 6345) had similar rates of VTE (8.49% for ICI and 8.36% for chemo at 6 months). The weighted HR was 1.06 (95% CI 0.88-1.26) for ICI versus chemo. In a subgroup analysis restricted to lung cancers, first-line ICI/chemo (n = 828), ICI monotherapy (n = 428), and chemo monotherapy (n = 4371) had similar rates of VTE (9.60% for ICI/chemo, 10.04% for ICI, and 8.91% for chemo at 6 months). The weighted HR was 1.05 (95% CI 0.77-1.42) for ICI versus chemo, and 1.08 (95% CI 0.83-1.42) for ICI/chemo versus chemo. In conclusion, ICI as a systemic therapy has a similarly elevated risk as cytotoxic chemo for VTE occurrence in cancer patients. This finding can inform future prospective studies exploring thromboprophylaxis strategies.

A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories.

Pancreatic cancer is an aggressive disease that typically presents late with poor outcomes, indicating a pronounced need for early detection. In this study, we applied artificial intelligence methods to clinical data from 6 million patients (24,000 pancreatic cancer cases) in Denmark (Danish National Patient Registry (DNPR)) and from 3 million patients (3,900 cases) in the United States (US Veterans Affairs (US-VA)). We trained machine learning models on the sequence of disease codes in clinical histories and tested prediction of cancer occurrence within incremental time windows (CancerRiskNet). For cancer occurrence within 36 months, the performance of the best DNPR model has area under the receiver operating characteristic (AUROC) curve = 0.88 and decreases to AUROC (3m) = 0.83 when disease events within 3 months before cancer diagnosis are excluded from training, with an estimated relative risk of 59 for 1,000 highest-risk patients older than age 50 years. Cross-application of the Danish model to US-VA data had lower performance (AUROC = 0.71), and retraining was needed to improve performance (AUROC = 0.78, AUROC (3m) = 0.76). These results improve the ability to design realistic surveillance programs for patients at elevated risk, potentially benefiting lifespan and quality of life by early detection of this aggressive cancer.

Risk factors of SARS-CoV-2 infection and complications from COVID-19 in lung cancer patients.

BACKGROUND: Identifying lung cancer patients at an increased risk of getting SARS-CoV-2-related complications will facilitate tailored therapy to maximize the benefit of anti-cancer therapy, while decreasing the likelihood of COVID-19 complications. This analysis aimed to identify the characteristics of lung cancer patients that predict for increased risk of death or serious SARS-CoV-2 infection. PATIENTS AND METHODS: This was a retrospective cohort study of patients with lung cancer diagnosed October 1, 2015, and December 1, 2020, and a diagnosis of COVID-19 between February 2, 2020, and December 1, 2020, within the Veterans Health Administration. Serious SARS-CoV-2 infection was defined as hospitalization, ICU admission, or mechanical ventilation or intubation within 2 weeks of COVID-19 diagnosis. For categorical variables, differences were assessed using Χ2 tests, while Kruskal-Wallis rank-sum test was used for continuous variables. Multivariable logistic regression models were fit relative to onset of serious SARS-CoV-2 infection and death from SARS-CoV-2 infection. RESULTS: COVID-19 infection was diagnosed in 352 lung cancer patients. Of these, 61 patients (17.3%) died within four weeks of diagnosis with COVID-19, and 42 others (11.9%) experienced a severe infection. Patients who had fatal or severe infection were older and had lower hemoglobin levels than those with mild or moderate infection. Factors associated with death from SARS-CoV-2 infection included increasing age, immune checkpoint inhibitor therapy and low hemoglobin level. CONCLUSIONS:  The mortality of lung cancer patients from COVID-19 disease in the present cohort was less than previously reported in the literature. The identification of risk factors associated with severe or fatal outcomes informs management of patients with lung cancer who develop COVID-19 disease.

Practical issues in pragmatic trials: the implementation of the Diuretic Comparison Project.

BACKGROUND/AIMS: The US Department of Veterans Affairs Point of Care Clinical Trial Program conducts studies that utilize informatics infrastructure to integrate clinical trial protocols into routine care delivery. The Diuretic Comparison Project compared hydrochlorothiazide to chlorthalidone in reduction of major cardiovascular events in subjects with hypertension. Here we describe the cultural, technical, regulatory, and logistical challenges and solutions that enabled successful implementation of this large pragmatic comparative effectiveness Point of Care clinical trial. METHODS: Patients were recruited from 72 Veterans Affairs Healthcare Systems using centralized processes for subject identification, obtaining informed consent, data collection, safety monitoring, site communication, and endpoint identification with minimal perturbation of the local clinical care ecosystem. Patients continued to be managed exclusively by their clinical care providers without protocol specified study visits, treatment recommendations, or data collection extraneous to routine care. Centralized study processes were operationalized through the application layer of the electronic health record via a data coordinating center staffed by clinical nurses, data scientists, and statisticians without site-based research coordinators. Study data was collected from the Veterans Affairs electronic health record supplemented by Medicare and National Death Index data. RESULTS: The study exceeded its enrolled goal (13,523 subjects) and followed subjects for the 5-year study duration. The key determinant of program success was collaboration between researchers, regulators, clinicians, and administrative staff at the site level to customize study procedures to align with local clinical practice. This flexibility was enabled by designation of the study as minimal risk and determination that clinical care providers were not engaged in research by the Veterans Affairs Central Institutional Review Board. Cultural, regulatory, technical, and logistical problems were identified and solved through iterative collaboration between clinical and research entities. Paramount among these problems was customization of the Veterans Affairs electronic health record and data systems to accommodate study procedures. CONCLUSIONS: Leveraging clinical care for large-scale clinical trials is feasible but requires a rethinking of traditional clinical trial design (and regulation) to better meet requirements of clinical care ecosystems. Study designs must accommodate site-specific practice variation to reduce the impact on clinical care. A tradeoff thus exists between designing trial processes tailored to expedite local study implementation versus those to produce a more refined response to the research question. The availability of a uniform and flexible electronic health record in the Department of Veterans Affairs played a major role in the success of the trial. Conducting Point of Care research in other healthcare systems without such research-friendly infrastructure presents a more formidable challenge.

Derivation and Validation of a Clinical Risk Assessment Model for Cancer-Associated Thrombosis in Two Unique US Health Care Systems.

PURPOSE: Venous thromboembolism (VTE), especially pulmonary embolism (PE) and lower extremity deep vein thrombosis (LE-DVT), is a serious and potentially preventable complication for patients with cancer undergoing systemic therapy. METHODS: Using retrospective data from patients diagnosed with incident cancer from 2011-2020, we derived a parsimonious risk assessment model (RAM) using least absolute shrinkage and selection operator regression from the Harris Health System (HHS, n = 9,769) and externally validated it using the Veterans Affairs (VA) health care system (n = 79,517). Bootstrapped c statistics and calibration curves were used to assess external model discrimination and fit. Dichotomized risk strata using integer scores were created and compared against the Khorana score (KS). RESULTS: Incident VTE and PE/LE-DVT at 6 months occurred in 590 (6.2%) and 437 (4.6%) patients in HHS and 4,027 (5.1%) and 3,331 (4.2%) patients in the VA health care system. Assessed at the time of systemic therapy initiation, the new RAM included components of the KS with the modified cancer subtype, cancer staging, systemic therapy class, history of VTE, history of paralysis/immobility, recent hospitalization, and Asian/Pacific Islander race. The c statistic was 0.71 in HHS and 0.68 in the VA health care system (compared with 0.65 and 0.60, respectively, for KS). Furthermore, the new RAM appropriately reclassified 28% of patients and increased the proportion of VTEs in the high-risk group from 37% to 68% in the validation data set. CONCLUSION: The novel RAM stratified patients with cancer into a high-risk group with 8%-10% cumulative incidence of VTE and 7% PE/LE-DVT at 6 months (v 3% and 2%, respectively, in the low-risk group). The model had improved performance over the original KS and doubled the number of VTE events in the high-risk stratum. We encourage additional external validation from prospective studies.[Media: see text].

Sentiment analysis of medical record notes for lung cancer patients at the Department of Veterans Affairs.

Natural language processing of medical records offers tremendous potential to improve the patient experience. Sentiment analysis of clinical notes has been performed with mixed results, often highlighting the issue that dictionary ratings are not domain specific. Here, for the first time, we re-calibrate the labMT sentiment dictionary on 3.5M clinical notes describing 10,000 patients diagnosed with lung cancer at the Department of Veterans Affairs. The sentiment score of notes was calculated for two years after date of diagnosis and evaluated against a lab test (platelet count) and a combination of data points (treatments). We found that the oncology specific labMT dictionary, after re-calibration for the clinical oncology domain, produces a promising signal in notes that can be detected based on a comparative analysis to the aforementioned parameters.

Validation of algorithms to select patients with multiple myeloma and patients initiating myeloma treatment in the national Veterans Affairs Healthcare System.

BACKGROUND: We aimed to evaluate and compare the performance of multiple myeloma (MM) selection algorithms for use in Veterans Affairs (VA) research. METHODS: Using the VA Corporate Data Warehouse (CDW), the VA Cancer Registry (VACR), and VA pharmacy data, we randomly selected 500 patients from 01/01/1999 to 06/01/2021 who had (1) either one MM diagnostic code OR were listed in the VACR as having MM AND (2) at least one MM treatment code. A team reviewed oncology notes for each veteran to annotate details regarding MM diagnosis and initial treatment within VA. We evaluated inter-annotator agreement and compared the performance of four published algorithms (two developed and validated external to VA data and two used in VA data). RESULTS: A total of 859 patients were reviewed to obtain 500 patients who were annotated as having MM and initiating MM treatment in VA. Agreement was high among annotators for all variables: MM diagnosis (98.3% agreement, Kappa = 0.93); initial treatment in VA (91.8% agreement; Kappa = 0.77); and initial treatment classification (87.6% agreement; Kappa = 0.86). VA Algorithms were more specific and had higher PPVs than non-VA algorithms for both MM diagnosis and initial treatment in VA. We developed the "VA Recommended Algorithm," which had the highest PPV among all algorithms in identifying patients diagnosed with MM (PPV = 0.98, 95% CI = 0.95-0.99) and in identifying patients who initiated their MM treatment in VA (PPV = 0.93, 95% CI = 0.90-0.96). CONCLUSION: Our VA Recommended Algorithm optimizes sensitivity and PPV for cohort selection and treatment classification.

Chlorthalidone vs. Hydrochlorothiazide for Hypertension-Cardiovascular Events.

BACKGROUND: Whether chlorthalidone is superior to hydrochlorothiazide for preventing major adverse cardiovascular events in patients with hypertension is unclear. METHODS: In a pragmatic trial, we randomly assigned adults 65 years of age or older who were patients in the Department of Veterans Affairs health system and had been receiving hydrochlorothiazide at a daily dose of 25 or 50 mg to continue therapy with hydrochlorothiazide or to switch to chlorthalidone at a daily dose of 12.5 or 25 mg. The primary outcome was a composite of nonfatal myocardial infarction, stroke, heart failure resulting in hospitalization, urgent coronary revascularization for unstable angina, and non-cancer-related death. Safety was also assessed. RESULTS: A total of 13,523 patients underwent randomization. The mean age was 72 years. At baseline, hydrochlorothiazide at a dose of 25 mg per day had been prescribed in 12,781 patients (94.5%). The mean baseline systolic blood pressure in each group was 139 mm Hg. At a median follow-up of 2.4 years, there was little difference in the occurrence of primary-outcome events between the chlorthalidone group (702 patients [10.4%]) and the hydrochlorothiazide group (675 patients [10.0%]) (hazard ratio, 1.04; 95% confidence interval, 0.94 to 1.16; P = 0.45). There were no between-group differences in the occurrence of any of the components of the primary outcome. The incidence of hypokalemia was higher in the chlorthalidone group than in the hydrochlorothiazide group (6.0% vs. 4.4%, P<0.001). CONCLUSIONS: In this large pragmatic trial of thiazide diuretics at doses commonly used in clinical practice, patients who received chlorthalidone did not have a lower occurrence of major cardiovascular outcome events or non-cancer-related deaths than patients who received hydrochlorothiazide. (Funded by the Veterans Affairs Cooperative Studies Program; ClinicalTrials.gov number, NCT02185417.).