RESUMO
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.
RESUMO
The COVID-19 pandemic prompted widespread closures of primary and secondary schools. Routine testing of asymptomatic students and staff members, as part of a comprehensive mitigation program, can help schools open safely. "Pooling in a pod" is a public health surveillance strategy whereby testing cohorts (pods) are based on social relationships and physical proximity. Pooled testing provides a single laboratory test result for the entire pod, rather than a separate result for each person in the pod. During the 2020-2021 school year, an independent preschool-grade 12 school in Washington, DC, used pooling in a pod for weekly on-site point-of-care testing of all staff members and students. Staff members and older students self-collected anterior nares samples, and trained staff members collected samples from younger students. Overall, 12 885 samples were tested in 1737 pools for 863 students and 264 staff members from November 30, 2020, through April 30, 2021. The average pool size was 7.4 people. The average time from sample collection to pool test result was 40 minutes. The direct testing cost per person per week was $24.24, including swabs. During the study period, 4 surveillance test pools received positive test results for COVID-19. A post-launch survey found most parents (90.3%), students (93.4%), and staff members (98.8%) were willing to participate in pooled testing with confirmatory tests for pool members who received a positive test result. The proportion of students in remote learning decreased by 62.2% for students in grades 6-12 (P < .001) and by 92.4% for students in preschool to grade 5 after program initiation (P < .001). Pooling in a pod is a feasible, cost-effective surveillance strategy that may facilitate safe, sustainable, in-person schooling during a pandemic.