معرفی
Lucinda Archer serves as an Assistant Professor in Biostatistics at the Applied Health Sciences Institute for Interdisciplinary Data Science and AI, University of Birmingham. She is actively engaged in methodological research focused on clinical prediction models and statistical methodology for healthcare applications.
Her research interests center on developing robust statistical methods for clinical prediction modeling, with particular emphasis on sample size calculations, validation of prediction models, and ensuring fairness in AI-based healthcare tools. Her work bridges biostatistics, machine learning, and clinical medicine to improve risk prediction and decision support in healthcare settings.
Analysis of her recent publications reveals a strong focus on methodological advancements in clinical prediction models, particularly regarding sample size requirements for developing and validating prediction tools. Her research addresses critical challenges in translating statistical models to clinical practice, with applications in hypertension management, electrolyte disorders, and time-to-event prediction.
Dr. Archer has secured significant research funding as Co-Investigator on multiple major projects including:
- AI-enabled frontline workers (FLWs): benchmarks & tool evidence (Bill & Melinda Gates Foundation)
- BRC CF11: Developing and validating predictive models for clinical outcomes in mild autonomous cortisol secretion (NIHR)
- Systematic Reviews and Meta-Analysis of Prognosis Studies (REVAMP) (UK Research and Innovation)
- Sample Size guidance for UPDATing clinical prediction models (SS-UPDATE) (Medical Research Council)
- NIHR BRC Theme - Data, Diagnostics & Decision Tools
She collaborates extensively with leading researchers in the field, particularly with R.D. Riley, J. Ensor, and K.I.E. Snell, contributing to high-impact publications in journals including Diagnostic and Prognostic Research, Journal of Hypertension, BMC Medical Research Methodology, and The Lancet Digital Health.
