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.

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.

A mass-balance approach to evaluate arsenic intake and excretion in different populations.

Unless a toxicant builds up in a deep compartment, intake by the human body must on average balance the amount that is lost. We apply this idea to assess arsenic (As) exposure misclassification in three previously studied populations in rural Bangladesh (n = 11,224), Navajo Nation in the Southwestern United States (n = 619), and northern Chile (n = 630), under varying assumptions about As sources. Relationships between As intake and excretion were simulated by taking into account additional sources, as well as variability in urine dilution inferred from urinary creatinine. The simulations bring As intake closer to As excretion but also indicate that some exposure misclassification remains. In rural Bangladesh, accounting for intake from more than one well and rice improved the alignment of intake and excretion, especially at low exposure. In Navajo Nation, comparing intake and excretion revealed home dust as an important source. Finally, in northern Chile, while food-frequency questionnaires and urinary As speciation indicate fish and shellfish sources, persistent imbalance of intake and excretion suggests imprecise measures of drinking water arsenic as a major cause of exposure misclassification. The mass-balance approach could prove to be useful for evaluating sources of exposure to toxicants in other settings.

Association of COVID-19 Vaccination With SARS-CoV-2 Infection in Patients With Cancer: A US Nationwide Veterans Affairs Study.

Importance: Patients with cancer are at increased risk for severe COVID-19, but it is unknown whether SARS-CoV-2 vaccination is effective for them. Objective: To determine the association between SARS-CoV-2 vaccination and SARS-CoV-2 infections among a population of Veterans Affairs (VA) patients with cancer. Design, Setting, and Participants: Retrospective, multicenter, nationwide cohort study of SARS-CoV-2 vaccination and infection among patients in the VA health care system from December 15, 2020, to May 4, 2021. All adults with solid tumors or hematologic cancer who received systemic cancer-directed therapy from August 15, 2010, to May 4, 2021, and were alive and without a documented SARS-CoV-2 positive result as of December 15, 2020, were eligible for inclusion. Each day between December 15, 2020, and May 4, 2021, newly vaccinated patients were matched 1:1 with unvaccinated or not yet vaccinated controls based on age, race and ethnicity, VA facility, rurality of home address, cancer type, and treatment type/timing. Exposures: Receipt of a SARS-CoV-2 vaccine. Main Outcomes and Measures: The primary outcome was documented SARS-CoV-2 infection. A proxy for vaccine effectiveness was defined as 1 minus the risk ratio of SARS-CoV-2 infection for vaccinated individuals compared with unvaccinated controls. Results: A total of 184 485 patients met eligibility criteria, and 113 796 were vaccinated. Of these, 29 152 vaccinated patients (median [IQR] age, 74.1 [70.2-79.3] years; 95% were men; 71% were non-Hispanic White individuals) were matched 1:1 to unvaccinated or not yet vaccinated controls. As of a median 47 days of follow-up, 436 SARS-CoV-2 infections were detected in the matched cohort (161 infections in vaccinated patients vs 275 in unvaccinated patients). There were 17 COVID-19-related deaths in the vaccinated group vs 27 COVID-19-related deaths in the unvaccinated group. Overall vaccine effectiveness in the matched cohort was 58% (95% CI, 39% to 72%) starting 14 days after the second dose. Patients who received chemotherapy within 3 months prior to the first vaccination dose were estimated to have a vaccine effectiveness of 57% (95% CI, -23% to 90%) starting 14 days after the second dose vs 76% (95% CI, 50% to 91%) for those receiving endocrine therapy and 85% (95% CI, 29% to 100%) for those who had not received systemic therapy for at least 6 months prior. Conclusions and Relevance: In this cohort study, COVID-19 vaccination was associated with lower SARS-CoV-2 infection rates in patients with cancer. Some immunosuppressed subgroups may remain at early risk for COVID-19 despite vaccination, and consideration should be given to additional risk reduction strategies, such as serologic testing for vaccine response and a third vaccine dose to optimize outcomes.

A mass-balance model to assess arsenic exposure from multiple wells in Bangladesh.

BACKGROUND: Water arsenic (As) sources beyond a rural household's primary well may be a significant source for certain individuals, including schoolchildren and men working elsewhere. OBJECTIVE: To improve exposure assessment by estimating the fraction of drinking water that comes from wells other than the household's primary well in a densely populated area. METHODS: We use well water and urinary As data collected in 2000-2001 within a 25 km2 area of Araihazar upazila, Bangladesh, for 11,197 participants in the Health Effects of Arsenic Longitudinal Study (HEALS). We estimate the fraction of water that participants drink from different wells by imposing a long-term mass-balance constraint for both As and water. RESULTS: The mass-balance model suggest that, on average, HEALS participants obtain 60-75% of their drinking water from their primary household wells and 25-40% from other wells, in addition to water from food and cellular respiration. Because of this newly quantified contribution from other wells, As in drinking water rather than rice was identified as the largest source of As exposure at baseline for HEALS participants with a primary household well containing ≤50 µg/L As. SIGNIFICANCE: Dose-response relationships for As based on water As should take into account other wells. The mass-balance approach could be applied to study other toxicants.

Evaluation of a field kit for testing arsenic in paddy soil contaminated by irrigation water.

Rice is the primary crop in Bangladesh and rice yield is diminished due to the buildup of arsenic (As) in soil from irrigation with high-As groundwater. Soil testing with an inexpensive kit could help farmers target high-As soil for mitigation or decide to switch to a different crop that is less sensitive to As in soil. A total of 3,240 field kit measurements of As in 0.5 g of fresh soil added to 50 mL of water were compared with total soil As concentrations measured on oven-dried homogenized soil by X-ray fluorescence (XRF). For sets of 12 soil samples collected within a series of rice fields, the average of kit As measurements was a linear function of the average of XRF measurements (r2=0.69). Taking into account that the kit overestimates water As concentrations by about a factor of two, the relationship suggests that about a quarter of the As in paddy soil is released in the kit's reaction vessel. Using the relationship and considering XRF measurements as the reference, the 12-sample average determined correctly whether soil As was above or below a 30 mg/kg threshold in 86% of cases where soil As was above the threshold and in 79% of cases where soil As was below the threshold. We also used a Bayesian approach using 12 kit measurements to estimate the probability that soil As was above a given threshold indicated by XRF measurements. The Bayesian approach is theoretically optimal but was only slightly more accurate than the linear regression. These results show that rice farmers can identify high-As portions of their fields for mitigation using a dozen field kit measurements on fresh soil and base their decisions on this information.