DrFinneasCatling

Summary

I am an academic Anaesthetic and Critical Care doctor, and a Wellcome Trust 4i Clinical PhD Fellow at Imperial.

My research aims at early diagnosis and improved treatment of critical illness, using methods from Bayesian statistics and machine learning. I am particularly interested in merging these methods with physiological models to provide bedside decision support, in disease heterogeneity, and in the role of uncertainty in clinical decision-making.

My recent work includes uncertainty-aware mortality risk prediction for patients undergoing emergency laparotomy, representing ICU patients’ status using time-series data to predict clinical events, using structured knowledge for automated clinical coding and phenotyping ventilator-associated pneumonia in electronic health records.

I am an NHS England Clinical Entrepreneurship Fellow, a fellow of the Faculty of Clinical Informatics and a member of the core advisory group for the Academic Health Science Networks Artificial Intelligence Programme. I co-founded and lecture on the Data Science for Doctors courses, and previously co-founded the medical education startup T-Log.

See my ResearchGate, Twitter or LinkedIn profiles for more information, or get in touch via f.catling@imperial.ac.uk

Selected publications

Mathiszig-Lee JF*, Catling FJR*, Moonesinghe SR, Brett SJ (*equal contribution). Highlighting uncertainty in clinical risk prediction using a model of emergency laparotomy mortality risk. npj Digital Medicine 2022;5:1–8.

Catling FJR, Wolff AH. Temporal convolutional networks allow early prediction of events in critical care. J Am Med Inform Assoc 2020;27:355–65.

Catling FJR, Spithourakis GP, Riedel S. Towards automated clinical coding. Int J Med Inform 2018;120:50–61.

Publications

Journals