Impact of dosing frequency (once daily or twice daily) on patient adherence to oral targeted therapies for hematologic malignancies: a retrospective cohort study among managed care enrollees.

PURPOSE: Existing studies evaluating patient adherence to oral targeted therapies such as tyrosine kinase inhibitors focus on small populations with single malignancies. This study evaluated patterns of use of oral agents in a larger population across multiple hematologic malignancies. METHODS: Adult patients diagnosed with a hematologic malignancy and prescribed oral targeted therapy between 2011 and 2016 (N = 18,976) were identified from the MarketScan Commercial Claims and Encounters, and Medicare Supplemental databases. Eligible patients were enrolled in monthly prescription plans 6 months before and 12 months after the index date (date of first prescription claim; n = 2442). Multivariable logistic regressions were used to determine predictors of adherence using the medication possession ratio (MPR) and persistence through prescription refill gaps. RESULTS: The overall median adherence was 0.9 (MPR ≥ 80%) and was comparable between once-daily (QD) and twice-daily (BID) groups. Overall, 59% of patients were persistent at 12 months. Patients on QD and BID products did not have any significant differences in adherence (fixed-interval MPR, odds ratio 0.94; 95% confidence interval (CI), 0.75-1.18) or persistence (odds ratio 0.93; 95% CI, 0.75-1.17) 12 months from index. Significant predictors of adherence and persistence included patient age, total inpatient admissions, number of adverse events, and total hospital visits. CONCLUSION: Patient-specific clinical factors, rather than regimen-specific factors, were the main predictors of oral targeted therapy adherence and persistence. Adherence to oral targeted therapies appears to be similar for patients on QD and BID regimens in the real-world setting.

Identification of Fast Progressors Among Patients With Nonalcoholic Steatohepatitis Using Machine Learning.

Background and Aims: There is a high unmet need to develop noninvasive tools to identify nonalcoholic fatty liver disease/nonalcoholic steatohepatitis (NAFLD/NASH) patients at risk of fast progression to end-stage liver disease (ESLD). This study describes the development of a machine learning (ML) model using data around the first clinical evidence of NAFLD/NASH to identify patients at risk of future fast progression. Methods: Adult patients with ESLD (cirrhosis or hepatocellular carcinoma) due to NAFLD/NASH were identified in Optum electronic health records (2007-2018 period). Patients were stratified into fast (0.5 and 3 years) and standard progressor (6-10 years) cohorts based on retrospectively established progression time between ESLD and the earliest observable disease, and characteristics were reported using descriptive statistics. Two ML models predicting fast progression were created, performance was compared, and top predictive features from the final model were compared between cohorts. Results: Among a total of 4013 NAFLD patients with cirrhosis or hepatocellular carcinoma (mean age 58.6 ± 12.5; 65% female), 24% were fast (n = 951) and 25% standard (n = 992) progressors that were used for modeling. The cohorts were comparable for gender, body mass index, type 2 diabetes, and arterial hypertension, but differed significantly for obesity, hyperlipidemia, and age at index. The final model (NASH FASTmap) is a 44 feature light gradient boosting model which performed better (area under the curve [0.77], F1-score [0.74], accuracy [0.71], and precision [0.71]) than eXtreme gradient boosting model to predict fast progression. Conclusion: Future fast progression to ESLD in NAFLD/NASH patients can be predicted from clinical data using ML. Electronic health record implementation of NASH FASTmap could support clinical assessment for risk stratification and potentially improve disease management.

Effect of COVID-19 on Bronchiectasis Exacerbation Rates: A Retrospective U.S. Insurance Claims Study.

Rationale: Bronchiectasis is a chronic, progressive disease of bronchial dilation, inflammation, and scarring leading to impaired mucociliary clearance and increased susceptibility to infection. Identified causes include previous severe respiratory infections. A small, single-center UK study demonstrated a reduction in bronchiectasis exacerbations during the first year of the coronavirus disease (COVID-19) pandemic. No studies have been conducted in a U.S. (commercially insured) cohort to date. Objectives: To explore the impact of the COVID-19 pandemic on the frequency of exacerbations in a large cohort of commercially insured U.S. patients with bronchiectasis by testing the hypothesis that U.S. patients with bronchiectasis had fewer exacerbations during the pandemic. Methods: This retrospective observational cohort study used health insurance claims data from Optum's deidentified Clinformatics Data Mart database, which included U.S. patients and their covered dependents. Eligible patients were ⩾18 years of age with bronchiectasis; patients with other respiratory conditions were excluded. The main study cohort excluded patients with frequent asthma and/or chronic obstructive pulmonary disease diagnoses. The primary objective was to compare the bronchiectasis exacerbation rates before and during the COVID-19 pandemic. Results: The median number of exacerbations per patient per year decreased significantly from the year before the COVID-19 pandemic to the first year of the pandemic (1 vs. 0; P < 0.01). More patients had zero exacerbations during the first year of the pandemic than the year prior (57% vs. 24%; McNemar's chi-square = 122.56; P < 0.01). Conclusions: In a U.S. population-based study of patients with International Classification of Diseases codes for bronchiectasis, the rate of exacerbations during Year 1 of the COVID-19 pandemic was reduced compared with the 2-year time period preceding the pandemic.