Published:
bursty_dynamics is a Python package designed to facilitate the analysis of temporal patterns in longitudinal data. It provides functions to calculate the burstiness parameter (BP) and memory coefficient (MC), detect event trains, and visualise results.
Published:
Published:
A Python package for point-in-time, leakage-safe feature engineering from event data.
Published:
A privacy-first desktop app that analyses CSV files and generates plain English or technical reports using a local AI model — no cloud, no data exposure.
Published in , 2023
Recommended citation: Eto F, Samuel M, Henkin R, Mahesh M, Ahmad T, Angdembe A, et al. (2023) Ethnic differences in early onset multimorbidity and associations with health service use, long-term prescribing, years of life lost, and mortality: A cross-sectional study using clustering in the UK Clinical Practice Research Datalink. PLoS Med 20(10): e1004300. https://doi.org/10.1371/journal.pmed.1004300
Open Paper
Published in , 2024
Recommended citation: Angdembe, A., Iqbal, W. A., Hamad, R. A., Casement, J., AI-Multiply Consortium, Missier, P., Reynolds, N., Henkin, R., & Barnes, M. R. (2024). bursty_dynamics: A Python package for exploring the temporal properties of longitudinal data. arXiv. https://arxiv.org/abs/2411.03210
Open Paper
Published in , 2026
Recommended citation: (2025)
Published in , 2026
Recommended citation: (2025)
Published:
I represented the AI for Multiple Long-Term Conditions research programme at AI-UK 2024. I engaged with attendees at our stand, discussing the project and its goals, and shared insights about how AI is being applied to improve the understanding and management of multiple long-term health conditions.
Published:
Topic: Building Trust for Meaningful Engagement.
Published:
Problem-Based Learning (PBL) Facilitator for first-year medical students at Barts and The London School of Medicine and Dentistry (9-week programme).
Published:
Presented research on modelling patient journeys using temporal and bursty event dynamics at an AI-Multiply public engagement event, highlighting how temporal patterns in patient records can provide insights into disease progression and outcomes, and discussing real-world implications with a multidisciplinary audience.