Natural Language Processing Algorithm to Extract Multiple Myeloma Stage From Oncology Notes in the Veterans Affairs Healthcare System.

PURPOSE: Stage in multiple myeloma (MM) is an essential measure of disease risk, but its measurement in large databases is often lacking. We aimed to develop and validate a natural language processing (NLP) algorithm to extract oncologists' documentation of stage in the national Veterans Affairs (VA) Healthcare System. METHODS: Using nationwide electronic health record (EHR) and cancer registry data from the VA Corporate Data Warehouse, we developed and validated a rule-based NLP algorithm to extract oncologist-determined MM stage. To that end, a clinician annotated MM stage within over 5,000 short snippets of clinical notes, and annotated MM stage at MM treatment initiation for 200 patients. These were allocated into snippet- and patient-level development and validation sets. We developed MM stage extraction and roll-up algorithms within the development sets. After the algorithms were finalized, we validated them using standard measures in held-out validation sets. RESULTS: We developed algorithms for three different MM staging systems that have been in widespread use (Revised International Staging System [R-ISS], International Staging System [ISS], and Durie-Salmon [DS]) and for stage reported without a clearly defined system. Precision and recall were uniformly high for MM stage at the snippet level, ranging from 0.92 to 0.99 for the different MM staging systems. Performance in identifying for MM stage at treatment initiation at the patient level was also excellent, with precision of 0.92, 0.96, 0.90, and 0.86 and recall of 0.99, 0.98, 0.94, and 0.92 for R-ISS, ISS, DS, and unclear stage, respectively. CONCLUSION: Our MM stage extraction algorithm uses rule-based NLP and data aggregation to accurately measure MM stage documented in oncology notes and pathology reports in VA's national EHR system. It may be adapted to other systems where MM stage is recorded in clinical notes.

Construct validity of the electronic Veterans Affairs Frailty Index against clinician frailty assessment.

BACKGROUND: Electronic frailty indices (eFIs) can expand measurement of frailty in research and practice and have demonstrated predictive validity in associations with clinical outcomes. However, their construct validity is less well studied. We aimed to assess the construct validity of the VA-FI, an eFI developed for use in the U.S. Veterans Affairs Healthcare System. METHODS: Veterans who underwent comprehensive geriatric assessments between January 31, 2019 and June 6, 2022 at VA Boston and had sufficient data documented for a comprehensive geriatric assessment-frailty index (CGA-FI) were included. The VA-FI, based on diagnostic and procedural codes, and the CGA-FI, based on geriatrician-measured deficits, were calculated for each patient. Geriatricians also assessed the Clinical Frailty Scale (CFS), functional status (ADLs and IADLs), and 4-meter gait speed (4MGS). RESULTS: A total of 132 veterans were included, with median age 81.4 years (IQR 75.8-88.7). Across increasing levels of VA-FI (<0.2; 0.2-0.4; >0.4), mean CGA-FI increased (0.24; 0.30; 0.40). The VA-FI was moderately correlated with the CGA-FI (r 0.45, p < 0.001). Every 0.1-unit increase in the VA-FI was associated with an increase in the CGA-FI (linear regression beta 0.05; 95% confidence interval [CI] 0.03-0.06), higher CFS category (ordinal regression OR 1.69; 95% CI 1.24-2.30), higher odds of ADL dependency (logistic regression OR 1.59; 95% CI 1.20-2.11), IADL dependency (logistic regression OR 1.68; 95% CI 1.23-2.30), and a decrease in 4MGS (linear regression beta -0.07, 95% CI -0.12 to -0.02). All models were adjusted for age and race, and associations held after further adjustment for the Charlson Comorbidity Index. CONCLUSION: Our results demonstrate the construct validity of the VA-FI through its associations with clinical measures of frailty, including summary frailty measures, functional status, and objective physical performance. Our findings complement others' in showing that eFIs can capture functional and mobility domains of frailty beyond just comorbidity and may be useful to measure frailty among populations and individuals.

More intensive therapy as more effective treatment for frail patients with multiple myeloma [corrected].

Although randomized controlled trial data suggest that the more intensive triplet bortezomib-lenalidomide-dexamethasone (VRd) is superior to the less intensive doublet lenalidomide-dexamethasone (Rd) in patients newly diagnosed with multiple myeloma (MM), guidelines have historically recommended Rd over VRd for patients who are frail and may not tolerate a triplet. We identified 2573 patients (median age, 69.7 years) newly diagnosed with MM who were initiated on VRd (990) or Rd (1583) in the national US Veterans Affairs health care System from 2004 to 2020. We measured frailty using the Veterans Affairs Frailty Index. To reduce imbalance in confounding, we matched patients for MM stage and 1:1 based on a propensity score. Patients who were moderate-severely frail had a higher prevalence of stage III MM and myeloma-related frailty deficits than patients who were not frail. VRd vs Rd was associated with lower mortality (hazard ratio [HR], 0.81; 95% confidence interval [CI], 0.70-0.94) in the overall matched population. Patients who were moderate-severely frail demonstrated the strongest association (HR 0.74; 95% CI, 0.56-0.97), whereas the association weakened in those who were mildly frail (HR, 0.80; 95% CI, 0.61-1.05) and nonfrail (HR, 0.86; 95% CI, 0.67-1.10). VRd vs Rd was associated with a modestly higher incidence of hospitalizations in the overall population, but this association weakened in patients who were moderate-severely frail. Our findings confirm the benefit of VRd over Rd in US veterans and further suggest that this benefit is strongest in patients with the highest levels of frailty, arguing that more intensive treatment of myeloma may be more effective treatment of frailty itself.

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.

Deletion of ΔdblGata motif leads to increased predisposition and severity of IgE-mediated food-induced anaphylaxis response.

BACKGROUND: Previous studies have revealed an important role for the transcription factor GATA-1 in mast cell maturation and degranulation. However, there have been conflicting reports with respect to the requirement of GATA-1 function in mast cell dependent inflammatory processes. Herein, we examine the requirement of GATA-1 signaling in mast cell effector function and IgE-mast cell-dependent anaphylaxis. OBJECTIVE: To study the requirement of GATA-1 dependent signaling in the development and severity of IgE-mast cell-dependent anaphylaxis in mice. METHODS: Wild type (Balb/c) and mutant ΔdblGata (Balb/c) mice were employed to study the role of GATA-1 signaling in in vitro IgE-mediated activation of bone marrow derived mast cells (BMMCs). Murine models of passive IgE-mediated and oral antigen-induced IgE-mediated anaphylaxis were employed in mice. Frequency of steady state mast cells in various tissues (duodenum, ear, and tongue), peritoneal cavity, and clinical symptoms (diarrhea, shock, and mast cell activation) and intestinal Type 2 immune cell analysis including CD4+ Th2 cells, type 2 innate lymphoid cells (ILC2), and IL-9 secreting mucosal mast cells (MMC9) were assessed. RESULTS: In vitro analysis revealed that ΔdblGata BMMCs exhibit a reduced maturation rate, decreased expression of FcεRIα, and degranulation capacity when compared to their wildtype (WT) counterparts. These in vitro differences did not impact tissue resident mast cell numbers, total IgE, and susceptibility to or severity of IgE-mediated passive anaphylaxis. Surprisingly, ΔdblGata mice were more susceptible to IgE-mast cell-mediated oral antigen induced anaphylaxis. The increased allergic response was associated with increased Type 2 immunity (antigen-specific IgE, and CD4+ TH2 cells), MMC9 cells and small intestine (SI) mast cell load. CONCLUSION: Diminished GATA-1 activity results in reduced in vitro mast cell FcεRIα expression, proliferation, and degranulation activity. However, in vivo, diminished GATA-1 activity results in normal homeostatic tissue mast cell levels and increased antigen-induced CD4+ Th2 and iMMC9 cell levels and heightened IgE-mast cell mediated reactions.