Dr Sebastian Zeki is a consultant gastroenterologist at St Thomas’ Hospital in London. His research interests include upper gastrointestinal physiology, upper gastrointestinal cancer, natural language programming and quality metrics in endoscopy. He co-leads the Gastroenterology data sciences Institute in London.
PhD - Genomics of Barrett's related malignancy, 2013
University of London
Member of the Royal College of Physician, 2006
MSc Health Informatics, 2003
City University
MBBS MBChir Medicine, 2001
University College London
MA in experimental psychology, 1998
Cambridge University
For a full overview of my clinical and academic skills, please visit my professional website at sebastianzeki.co.uk.
An R package for extracting structured data from free-text endoscopy and pathology reports, linking pathology to procedures and tracking Barrett’s surveillance timelines. View on GitHub
An educational resource for gastroenterology data science, covering R, machine learning, and NLP applied to clinical data. Visit site
A free online resource for gastroenterology teaching aimed at medical students and junior doctors. Visit site
Using routinely collected endoscopic and pathology data to improve lesion recognition quality metrics across endoscopy units.
Research project exploring minimally invasive flow measurements in gastrointestinal physiology.
Package to automate extraction of oesophageal physiology metrics https://github.com/sebastiz/Physipopv2.0.3
Libraries written in R and python to automate analysis of oesophageal physiology results (ph impedance, high resolution manometry and wireless pH capsules) (https://github.com/sebastiz/PhysiMineRpy & https://github.com/sebastiz/PhysiMineR)
Python libraries for simplifying access to EPIC Clarity data and legacy data in the Enterprise Data Warehouse (EDW). (https://github.com/AgatheZ/pyEPIC & https://github.com/sebastiz/pySTH_Analytics)
Zeki SS. EndoMineR for the extraction of endoscopic and associated pathology data from medical reports. Journal of Open Source Software. 2018;3(24):701. doi:10.21105/joss.00701.
Dietary intervention is effective for the management of eosinophilic oesophagitis (EoE) in both adults and children. The majority of research has been conducted in Spain or the United States, with no studies of dietary intervention published in the United Kingdom. Restrictive elimination diets can be challenging…….
Medical data is increasingly kept in an electronic format worldwide (Bretthauer M. 2016).This serves many purposes including more efficient storage, distribution and accessibility of patient-focussed data. As important is the ability to analyse healthcare data for to optimize resource deployment and usage……
Barretts oesophagus represents the most significant risk factor for the development of oesophageal adenocarcinoma (OAC), although the majority of patients will not develop cancer. However, early detection of OAC……
Radiofrequency ablation (RFA) is used to successfully eliminate Barrett’s esophagus (BE)-related dysplasia or intramucosal carcinoma and aims to cause reversion to squamous epithelium. However, in 20% of cases RFA fails to return……
Webinar covering evidence-based guidance for IBS diagnosis and treatment, with approaches for empowering patients.
Research grants and awards
I contribute across the KCL–GSTT academic pathway: undergraduate, postgraduate, and faculty development.
Undergraduate (KCL MBBS).
Gastroenterology Small-Group Teaching Block (2016 to present),
Delivering teaching bedside and through lectures ~25 students annually.
Supervisor for scholarly project module 2025/6 Shan Lee “Is severe ineffective oesophageal motility at high resolution manometry related to gastro oesophageal reflux disease on impedance testing” Pierfrancesco Visaggi (June 2018 67(Suppl 1):A210.1-A210 DOI:10.1136/gutjnl-2018-BSGAbstracts.419 : “Oesophageal aperistalsis is under investigated in those without achalasia or reflux“ - oral presentation at British Society of Gastroenterology
Created innovative single subject per page online learning materials (www.gastroenteroloybook.com) with interactive multiple choice questions to improve Specialty Certificate Examination performance. Publication of MRCP book (Zeki S. The Illustrated MRCP PACES Primer. Abingdon: Radcliffe Publishing; 2009. doi:10.1201/9780429091254) to help OSCE preparation for exams Development of gastroenterology data science online teaching materials including full code examples to help manipulate large data sets using R (https://sebastiz.github.io/gastrodatascience//index.html) Endoscopy trainer Educational Supervisor Guy’s and St Thomas’ NHS Trust.
Primary/secondary supervisor for 2 PhD candidates (topics: NLP for endoscopy): One PhD completion to date: Zhang X. Automating Surveillance Timing for Barrett’s Oesophagus: An Information Extraction Approach Using Natural Language Processing [Doctoral thesis]. London: King’s College London; 2026. Current primary PhD Supervisor for a second PhD : PhD supervision via the DRIVE Health programme (Agathe Zecevic “Development and deployment of a single unified natural language model for the supervised and automated prediction of follow up for precancerous GI conditions.”) (DRIVE- Health Programme)- Topol Digital Fellow
Designed an “Introduction to Clinical NLP for Gastroenterologists” workshop (hands-on notebooks using de-identified endoscopy text) now adopted by
JAG trainer and DOPS assessor; Performance optimisation done with EndoMineR. Contribution to Nocgca submission as national audit. Development of automated adenoma detection rates for colonoscopy with demonstration (Regular feedback to individual endoscopists is associated with improved adenoma detection rate and other key performance indicators for colonoscopy.Lim S, Tritto G, Zeki S, DeMartino S.Frontline Gastroenterol. 2022 May 6;13(6):509-516. doi: 10.1136/flgastro-2022-102091. eCollection 2022)