Too Ultra-Rare for Care? Orphan Drug Availability for People Living With Ultra-Rare Respiratory Diseases in the Pre, Present and Post Pandemic Worlds

Objectives: To compare the current and potential availability of treatments for seven index ultra-rare respiratory diseases before and after the peak of the COVID-19 pandemic. Method(s): At the 2019 ISPOR EU Conference, a landscape review of available treatments for ultra-rare respiratory diseases was presented. Therefore, 3 years on, we sought to explore if treatment access has improved for ultra-rare respiratory diseases. A landscape review was undertaken to seek evidence of treatment developments for ataxia telangiectasia (AT), lymphangiomatosis (LYMF), pulmonary alveolar proteinosis (PAP), pleuroparenchymal fibroelastosis (PPFE), pulmonary alveolar microlithiasis (PAM), pulmonary dendriform ossification (PDO), and light chain deposition disorders (LCDD). Information from clinicaltrials.gov, orpha.net, the EMA and FDA archives and websites of five health technology assessment (HTA) bodies was narratively synthesised. Result(s): The 2019 clinicaltrials.gov search identified 24 studies and the 2022 search 25 studies at various stages of the clinical trial process. They concerned PAP (2019/2022: 11/10), AT (6/10), LCDD (5/4), LYMF (1/0) and PPFE (1/1). No studies were identified for PAM or PDO. The 2019 review found treatments for AT and PAP were granted orphan status by the EMA and the FDA, and in 2021 the FDA granted orphan status to another AT treatment. Neither search found reimbursement submissions for any of the ultra-rare respiratory disease. Conclusion(s): There still remains an obvious lack of proven and available treatments for ultra-rare respiratory diseases. Over the past 3 years, only 1 new treatment has been granted regulatory approval and no treatments have yet to result in therapies that are licensed or approved by HTA bodies. It is our hope that as we enter the post-pandemic world, we as industry professionals and researchers start to adequately address the treatment needs of people living with these debilitating conditions. Copyright © 2022

COVID-19 Patient Outcome Prediction Using Selected Features from Emergency Department Data and Feed-Forward Neural Networks

The severity of COVID-19 varies dramatically, ranging from asymptomatic infection to severe respiratory failure and death. Currently, few prognostic markers for disease outcomes exist, impairing patient triaging and treatment. Here, we train feed-forward neural networks on electronic health records of 819 confirmed SARS-CoV-2 positive patients admitted to a two-site NHS Trust hospital in London, England. To allow early risk assessment, the models ingest data collected in the emergency department (ED) to predict subsequent admission to intensive care, need for mechanical ventilation and in-hospital mortality. We apply univariate selection and recursive feature elimination to find the minimal subset of clinical variables needed for accurate prediction. Our models achieve AUC-ROC scores of 0.78 to 0.87, outperforming standard clinical risk scores. This accuracy is reached with as few as 13% of clinical variables routinely collected within the ED, which increases the practical applicability of such algorithms. Hence, state-of-the-art neural networks can predict severe COVID-19 accurately and early from a small subset of clinical variables. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.