Publications by authors named "V Lorman"
The long-term complications of COVID-19, known as the post-acute sequelae of SARS-CoV-2 infection (PASC), significantly burden healthcare resources. Quantifying the demand for post-acute healthcare is essential for understanding patients' needs and optimizing the allocation of valuable medical resources for disease management. Driven by this need, we developed a heterogeneous latent transfer learning framework (Latent-TL) to generate critical insights for individual health systems in a distributed research network.
View Article and Find Full Text PDFArticle Synopsis
- Sparse data bias is an issue in data analysis, especially for rare binary outcomes, and while a two-step meta-analysis can help, it doesn't fully eliminate bias in effect estimation.
- The authors propose a new algorithm called ODAP-B, which utilizes modified Poisson regression to estimate relative risk more accurately and efficiently than traditional methods.
- Evaluations through simulations and real-world data reveal that ODAP-B provides closer effect estimates and is more privacy-preserving since it only requires aggregated data.
Article Synopsis
- * Conducted across 26 children's hospitals in the US from March 2020 to May 2023, the research involved analyzing data from over 172,000 eligible children and young adults aged 5 to 20 with confirmed COVID-19.
- * The findings aim to establish a clear association between pre-infection BMI categories—ranging from healthy weight to severe obesity—and the likelihood of experiencing PASC, with statistical analyses adjusting for various demographic and clinical
Pediatric Long COVID has been associated with a wide variety of symptoms, conditions, and organ systems, but distinct clinical presentations, or subphenotypes, are still being elucidated. In this exploratory analysis, we identified a cohort of pediatric (age <21) patients with evidence of Long COVID and no pre-existing complex chronic conditions using electronic health record data from 38 institutions and used an unsupervised machine learning-based approach to identify subphenotypes. Our method, an extension of the Phe2Vec algorithm, uses tens of thousands of clinical concepts from multiple domains to represent patients' clinical histories to then identify groups of patients with similar presentations.
View Article and Find Full Text PDFObjectives: This study seeks to identify demographic and clinical factors prompting clinician prescribing of nirmatrelvir/ritonavir to pediatric patients for management of coronavirus disease 2019 (COVID-19) infection.
Methods: Patients aged 12 to 17 years with a COVID-19 infection and nirmatrelvir/ritonavir prescription during an outpatient clinical encounter within a PEDSnet-affiliated institution between January 2022 and August 2023 were identified using electronic health record data. A multivariate logistic regression analysis was used to estimate odds of nirmatrelvir/ritonavir prescription after adjusting for various factors.