A claims-based, machine-learning algorithm to identify patients with pulmonary arterial hypertension.

Many patients with pulmonary arterial hypertension (PAH) experience substantial delays in diagnosis, which is associated with worse outcomes and higher costs. Tools for diagnosing PAH sooner may lead to earlier treatment, which may delay disease progression and adverse outcomes including hospitalization and death. We developed a machine-learning (ML) algorithm to identify patients at risk for PAH earlier in their symptom journey and distinguish them from patients with similar early symptoms not at risk for developing PAH. Our supervised ML model analyzed retrospective, de-identified data from the US-based Optum® Clinformatics® Data Mart claims database (January 2015 to December 2019). Propensity score matched PAH and non-PAH (control) cohorts were established based on observed differences. Random forest models were used to classify patients as PAH or non-PAH at diagnosis and at 6 months prediagnosis. The PAH and non-PAH cohorts included 1339 and 4222 patients, respectively. At 6 months prediagnosis, the model performed well in distinguishing PAH and non-PAH patients, with area under the curve of the receiver operating characteristic of 0.84, recall (sensitivity) of 0.73, and precision of 0.50. Key features distinguishing PAH from non-PAH cohorts were a longer time between first symptom and the prediagnosis model date (i.e., 6 months before diagnosis); more diagnostic and prescription claims, circulatory claims, and imaging procedures, leading to higher overall healthcare resource utilization; and more hospitalizations. Our model distinguishes between patients with and without PAH at 6 months before diagnosis and illustrates the feasibility of using routine claims data to identify patients at a population level who might benefit from PAH-specific screening and/or earlier specialist referral.

Aripiprazole Plasma Concentrations Delivered from Two 2-Month Long-Acting Injectable Formulations: An Indirect Comparison.

Aripiprazole 2-month ready-to-use 960 mg (Ari 2MRTU 960) is a novel long-acting injectable (LAI) formulation of aripiprazole monohydrate for administration once every 2 months, developed for the treatment of schizophrenia or maintenance monotherapy treatment of bipolar I disorder in adults (indication will vary by country). Aripiprazole lauroxil 1064 mg (AL 1064) is an LAI formulation of aripiprazole lauroxil, an aripiprazole prodrug, for administration once every 2 months, indicated for the treatment of schizophrenia in adults. This analysis provides an indirect comparison of aripiprazole plasma concentrations following multiple doses of either formulation. Clinical trial data were used to determine average steady-state aripiprazole plasma concentration (Cavg,ss), maximum aripiprazole plasma concentration (Cmax), and other pharmacokinetic parameters of either formulation following four administrations (96 patients received Ari 2MRTU 960; 28 patients received AL 1064). All pharmacokinetic parameters were considered in the context of a minimum aripiprazole therapeutic concentration (Cmin) of ≥95 ng/mL. An exposure-response analysis using data from two Phase III trials of aripiprazole once-monthly (an aripiprazole monohydrate LAI, administered monthly), showed that patients with a Cmin ≥95 ng/mL are 4.41 times less likely to relapse than patients with a Cmin <95 ng/mL. A similar analysis has not been performed for AL 1064. However, consensus guidelines for therapeutic drug monitoring recommend a range of 100-350 ng/mL for aripiprazole. Following four administrations, mean (standard deviation [SD]) Cavg,ss over the 2-month dosing interval was 263 (133) ng/mL for Ari 2MRTU 960 and 140.7 (57.3) ng/mL for AL 1064. Mean (SD) Cmax during the fourth dosing interval was 342 (157) ng/mL for Ari 2MRTU 960 and 188.8 (79.8) ng/mL for AL 1064. This indirect comparison showed that, following four administrations, Ari 2MRTU 960 and AL 1064 delivered mean aripiprazole plasma concentrations that remained above the minimum therapeutic concentration of aripiprazole over the 2-month dosing interval.

Timely PAH Identification in Adults With Repaired Congenital Heart Disease? The ACHD-QuERI Registry Insights.

Background: The Quality Enhancement Research Initiative (QuERI) in adults with congenital heart disease (ACHD) was developed to improve detection of pulmonary arterial hypertension (PAH) after repair of systemic-to-pulmonary arterial shunt lesions. Objectives: This study sought to standardize use of accepted criteria for PAH diagnosis and evaluate utility in at-risk patients with ACHD. Methods: Patients ≥18 years of age with ACHD repaired ≥1 year before enrollment and with additional risk factors for developing PAH were eligible. History, physical examination, electrocardiogram, transthoracic echocardiogram, World Health Organization functional class, and 6-minute walk distance were evaluated at baseline and yearly for 3 years. Pop-up reminders of patient-specific evidence-based recommendations for PAH detection appeared during data entry. Results: Among 217 eligible patients, mean age (enrollment) was 44.0 ± 15.9 years, 72.3% were women, and 82.0% were World Health Organization functional class I. Electrocardiogram was performed in >80% and TTE in >70% of patients annually; capture of required transthoracic echocardiography (TTE) measures and alignment between study- and core-center interpretation improved over time, with more frequent assessment of pulmonary arterial flow acceleration time and documentation of right ventricular outflow tract Doppler notching. Approximately 40% of patients had ≥2 high-risk features for PAH on TTE, but only 7% (6/82) underwent right heart catheterization (RHC). Using current definitions, 2 patients were confirmed by RHC to have a diagnosis of PAH (maximum follow-up 3 years). Conclusions: A structured protocol may improve screening for patients with repaired ACHD at risk of developing PAH. RHC may be underutilized in patients with ACHD with TTE findings suggestive of PAH. (Adult Congenital Heart Disease Registry [QuERI]; NCT01659411).

Development and evaluation of a predictive algorithm for unsatisfactory response among patients with pulmonary arterial hypertension using health insurance claims data.

OBJECTIVE: This study aimed to develop and validate a predictive algorithm for unsatisfactory response to initial pulmonary arterial hypertension (PAH) therapy using health insurance claims. METHODS: Adult patients with PAH initiated on a first PAH therapy (index date) were identified from Optum's de-identified Clinformatics Data Mart Database (1/1/2010-12/31/2019). A random survival forest algorithm was developed using patient-month data and predicted the "survival function" (i.e. risk of not having unsatisfactory response) over time. For each patient-month observation, risk factors were assessed in the 12 months prior. Unsatisfactory response was defined as the first instance of (1) new PAH therapy, (2) PAH-related hospitalization or emergency room visit, (3) lung transplant or atrial septostomy, (4) PAH-related death or (5) chronic oxygen therapy initiation. To facilitate use in clinical practice, a simplified risk score was also developed based on a linear combination of the most important risk factors identified in the algorithm. RESULTS: In total, 4781 patients were included (median age = 69.0 years; 58.6% female). Over a median follow-up of 14.0 months, 3169 (66.3%) had an unsatisfactory response. The most important risk factors included in the algorithm were healthcare resource use (i.e. PAH-related outpatient visits, pulmonologist visits, cardiologist visits, all-cause hospitalizations), time since first PAH diagnosis, time since index date, Charlson Comorbidity Index, dyspnea, and age. Predictive accuracy was good for the full algorithm (C-statistic: 0.732) but was slightly lower for the simplified risk score (C-statistic: 0.668). CONCLUSION: The present claims-based algorithm performed well in predicting time to unsatisfactory response following initial PAH therapy.

Treatment Effect With Paliperidone Palmitate Compared With Oral Antipsychotics in Black/African American Patients With Schizophrenia and a History of Criminal Justice System Involvement: A Post Hoc Analysis of the PRIDE Study.

OBJECTIVE: To examine the efficacy and safety of paliperidone palmitate once-monthly (PP1M) versus oral antipsychotics (OAPs) in Black/African American patients with schizophrenia and a history of criminal justice system involvement. METHODS: This was a post hoc analysis of a 15-month prospective, randomized, open-label, parallel-group, multicenter US study conducted from May 2010 to December 2013 that examined a subpopulation of Black/African American patients with schizophrenia (Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition criteria). The primary objective was to compare time to first treatment failure in patients treated with PP1M versus OAPs. Secondary objectives were to compare time to first institutionalization (psychiatric hospitalization or arrest/incarceration) and mean number of treatment failure events and institutionalizations over 15 months in PP1M-treated and OAP-treated patients. RESULTS: The intention-to-treat population included 275 Black/African American patients (PP1M, n = 145; OAPs, n = 130). Median time to first treatment failure was not reached for PP1M-treated patients and was 270 days for OAP-treated patients; hazard ratio (HR) was 1.39 (95% CI, 0.97-1.99; P = .075). Median time to first institutionalization was not reached for PP1M-treated patients and was 304 days for OAP-treated patients; HR was 1.49 (95% CI, 1.01-2.19; P = .043). Mean numbers of treatment failure events and institutionalizations were lower with PP1M than OAPs. The safety profile of PP1M was consistent with that of previous PP1M studies. CONCLUSIONS: In a Black/African American subpopulation of patients with schizophrenia and prior criminal justice system involvement, PP1M reduced the number of treatment failures, thereby reducing the number of psychiatric hospitalizations and/or arrests/incarcerations compared with daily OAPs. TRIAL REGISTRATION: ClinicalTrials.gov identifier: NCT01157351.

Paliperidone palmitate once-every-3-months in adults with early illness schizophrenia.

AIM: This post hoc analysis of a double-blind (DB), randomized, placebo-controlled, relapse-prevention study evaluated the effects of paliperidone palmitate once-every-3-months (PP3M) in a subpopulation of adults with early illness schizophrenia (duration ≤5 years) from a clinical trial. METHODS: Patients received either PP3M or placebo every 3 months in the DB phase. The primary efficacy variable was time from randomization to first relapse. Symptom severity, patient functioning, and safety were also assessed. RESULTS: A total of 119 patients who entered the DB phase met the criteria for early illness schizophrenia (PP3M, n = 62; placebo, n = 57). PP3M significantly delayed time to relapse vs placebo (P = .035; hazard ratio, 3.08; 95% CI, 1.08-8.80). Symptomatic control and patient functioning were maintained in the PP3M group but significantly worsened in the placebo group. There were no unexpected tolerability findings. CONCLUSIONS: PP3M reduced relapse risk and maintained symptomatic and functional improvements compared with placebo in patients with early illness schizophrenia.