AiSeptron
Designing a Paediatric Sepsis Prediction Tool using Machine Learning.
-
Background: Sepsis is a serious and preventable condition that can be fatal for children all over the world. Researchers have created computer programs applying artificial intelligence (AI) to electronic medical records of patients. These programs are really good at predicting sepsis and what might happen to children who come to the emergency department.
Aims: The main goal of this study is to make a strong and accurate computer program that can identify the risk of sepsis and serious infections in children.
-
Dr Sylvester Gomes
Founder & Chief Investigator
Sylvester is a Consultant in Paediatric Emergency Medicine at Evelina London Children's Hospital and a clinical researcher with a focus on digital health and artificial intelligence in acute paediatric care. As site lead for PERUKI (Paediatric Emergency Research in the UK and Ireland), he plays a key role in national research collaborations and serves as Principal Investigator for several multicentre studies. Outside the hospital, he enjoys high-octane driving, flying model airplanes, and the occasional salsa dance.
Ewan Carr
Statistician
Ewan holds a MSc in Social Research Methods and Statistics and a PhD in Social Statistics. His research interests are in applying novel statistical techniques to longitudinal and routine clinical datasets. His experience extends over a wide range of analytical methods, including latent variable techniques, multilevel modelling, and more recently, machine learning and topological data analysis. He is a keen user of R and Python, and has many years of experience with Mplus and Stata. He teaches on a wide range of statistical techniques and lectures on courses in R, ‘Statistical Programming’, ‘Statistical Modelling’, ‘Research methods for multilevel data’ and supports delivery of other modules within the department.
Lawrence Adams
Lead Analytics Engineer
Lawrence is a data engineer and data scientist at Guy’s and St Thomas’ and King’s College Hospital, where he leads work to transform complex electronic health records into research-ready data. Drawing on his clinical background, he helps connect data from multiple NHS trusts to support large-scale research, using modern tools to ensure the data is accurate, consistent, and meaningful for improving patient care.
Emily Jin
Senior Product Data Scientist
Emily Jin is a medical doctor and data scientist at the London AI Centre (part of Guy’s and St Thomas’ NHS Foundation Trust), where she applies her clinical expertise to develop AI-based solutions using electronic health data. She sits at the intersection of healthcare and technology, helping translate complex hospital data into insights that drive improved patient outcomes.
Aleksandra Foy
Data Analyst
Aleksandra is the Natural Language Processing (NLP) lead for Cogstack and is based at the Guys and St Thomas' Hospital. She will play a crucial role for data extraction from EPIC and our NLP platform, CogStack. She will guide the methodology and undertake the data analysis aspects of this project, coordinate with the data teams, develop the machine learning algorithms, and analyse results in conjunction with the clinical experts and statisticians.
Anthony Shek
Data Scientist
Anthony is a data scientist with a PhD in Clinical Neuroscience/Data science. His current work involves creating and deploying state of the art NLP pipelines in and across large London hospitals. He has experience with large language models and implementing and integrating them into real-world electronic health records systems and doctor workflows. He builds tools to aid clinicians uncover trends from millions of records for service improvement and insights into disease progression.
Vitaliy Onlinyk
Senior Product Developer
Vitaliy is a passionate and innovative software engineer who leads the product development team at Guy’s and St. Thomas’ NHS Trust. He is responsible for designing, developing and delivering cutting-edge solutions that improve the quality and efficiency of healthcare services. He has over 10 years of experience in various domains such as web development, cloud computing and artificial intelligence. He is also a Scrum Master and a mentor for junior developers. He enjoys learning new technologies and sharing his knowledge with others.
Dr Harpreet Dhanoa
Data Scientist, Phase 1
Harpreet has PhD in Astrochemistry and Computational Astrophysics from the University College, London. She is a DiRAC (Distributed Research Utilising Advanced Computing) Fellow seconded to the Guys and St Thomas’s Hospital. She has as expertise in working with large datasets, using machine learning in multiple contexts including healthcare, and working with clinical teams to support and improve patient care through data analysis.
Phil Assheton
Statistician, Phase 1
Phil has extensive experience in tutoring and advising statistics for courses and academic projects at the University of Lincoln. He has years of experience in coding statistical models at investment banks in London. He has a PhD in Probabilistic Neural Networks (Durham/ Lincoln Universities), MSc in Applied Mathematics from the University of Oxford and a BSc in Artificial Intelligence from Durham University (First Class Honours).
Dr Ranj Singh
Patient and Public Engagement Lead
Dr. Ranj Singh is a Locum Consultant in Paediatric Emergency Medicine at the Evelina London, BAFTA-award-winning television presenter, magazine columnist and best-selling author. He has also held ambassador roles for various charities, including the UK Sepsis Trust. He has a keen interest in health promotion and science communication with the public and has received many awards for his work on-screen, in-print and online.
View Our Synthetic Data:
The information you see here is synthetic data. It’s not real data, does not contain real patient details, and cannot be traced back to any real patients. It is only designed to look like real health records.
We created these data to show the kind of information used in a research project called AiSeptron. This study aims to make a strong and accurate computer program that can identify the risk of sepsis and serious infections in children. The founder and Chief Investigator for the project is Dr Sylvester Gomes.
Because this data is randomly generated using a tool called datafaker, some parts may not make sense — for example, a birth date might appear after a death date. That’s because the columns are made separately and don’t always link together in a realistic way.
Please note that this data is part of our preliminary version of synthetic datasets. We’re actively improving our process so that over time, more datasets will be available, and the data will look more and more like real-world data, without ever containing any real patient details.
This dataset is only for demonstration and learning purposes. Any similarity to real people is purely coincidental.
How to browse our synthetic data:
1) In the embedded table above, click the ‘view’ button next to the file you’d like to look at.
2) A new window will open up to Figshare, where the file is stored. You will see a collection of tiles containing the file folder on the top half of the page, and a project description on the bottom half of the page.
3) To view the data in your web browser, click the ‘eye’ icon on your desired file tile.
4) The tabular data will display in your browser. You can expand the screen as needed using the double headed arrow ‘full screen’ icon in the bottom right corner of the table.
5) To download the data, click the ‘download file’ icon on your desired file tile.
6) The files are in CSV format, which is like a simple version of an Excel spreadsheet.
Tip: Each row in the file is a ‘record’ (like a line in a spreadsheet), and each column is a type of information (like date, condition, or measurement).
