Publications by authors named "Daniel Key"
Several publications have indicated potential benefit from collaboration with industry regarding wider use of anonymised routine NHS healthcare data. However, there is limited guidance regarding exactly how such collaborations between NHS hospitals and industry partners should best be carried out, and specific issues that need to be addressed at an individual project or collaboration level to achieve desired benefit. Specifically, routine health data are complex, not collected in a format optimised for secondary use, and often require interpretation based on clinical understanding of the medical conditions or patients.
View Article and Find Full Text PDFArticle Synopsis
- The study explores the use of machine learning (ML) on electronic healthcare record (EHR) data from a pediatric hospital to identify clusters of diseases categorized by patient age, emphasizing the current limitations in data-driven decision-making in hospitals.
- Using observational data from over 61,000 patients, K-means clustering was applied, resulting in four distinct age clusters for diseases that align with known patterns of illness presentation and progression.
- The findings highlight the potential of unsupervised ML in enhancing clinical decisions, while also noting that biases and uncertainties in data preprocessing can significantly affect results, necessitating careful communication of such uncertainties.
Objective: The COVID-19 pandemic and subsequent government restrictions have had a major impact on healthcare services and disease transmission, particularly those associated with acute respiratory infection. This study examined non-identifiable routine electronic patient record data from a specialist children's hospital in England, UK, examining the effect of pandemic mitigation measures on seasonal respiratory infection rates compared with forecasts based on open-source, transferable machine learning models.
Methods: We performed a retrospective longitudinal study of respiratory disorder diagnoses between January 2010 and February 2022.