Related Experiment Video
Updated: Jan 11, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Developing and validating a clinical prediction model to predict epilepsy-related emergency department attendance,
Gashirai K Mbizvo1,2,3,4, Glen P Martin5, Laura J Bonnett6
1Liverpool Centre for Cardiovascular Science at University of Liverpool, Liverpool John Moores University and Liverpool Heart & Chest Hospital, Liverpool, United Kingdom.
Introduction:
This retrospective open cohort study develops and externally validates a clinical prediction model (CPM) to predict the joint risk of two important outcomes occurring within the next year in people with epilepsy (PWE). These are: A) seizure-related emergency department or hospital admission; and B) epilepsy-related death. This will provide clinicians with a tool to predict either or both of these common outcomes. This has not previously been done despite both being potentially avoidable, interrelated, and devastating for patients and their families. We hypothesise that the CPM will identify individuals at high or low risk of either or both outcomes. We will guide clinicians on proposed actions to take based on the overall risk score.
Methods And Analysis:
Routinely collected, anonymised, electronic health data from the following research platforms will be used: i) Clinical Practice Research Datalink (CPRD); ii) Secure Anonymised Information Linkage databank (SAIL); iii) Combined Intelligence for Population Health Action (CIPHA); and iv) TriNetX. We will study PWE aged ≥16 years having outcomes A and/or B between 2010-2024 within these datasets. Sample sizes of over 100,000 PWE are expected across these datasets. Candidate predictors will include demographic, lifestyle, clinical, and management variables. Logistic regression and multistate modelling will be used to develop a suitable CPM. The choice of modelling approach will be informed by consultation with clinicians and members of the public. We will assess the model's predictive performance using CPRD as a development dataset, and conduct external validation using SAIL, CIPHA, and TriNetX.
Conclusions:
This large study will develop and validate a CPM for PWE, creating an internationally generalisable tool for subsequent clinical implementation. It will predict the joint risk of acute admission and death in PWE. Mortality prediction is highlighted by NICE as a key recommendation for epilepsy research. The study has been co-developed by epilepsy researchers and members of the public affected by epilepsy.
