An AI spin-out from the University of Birmingham has launched, with an aim to speed up the process of extracting data from EHRs to support medical researchers and reduce the time for drug safety and effectiveness studies.
Dexter AI is based on a software developed by a team from the Birmingham Department of Applied Health Sciences, Professor Krishnarajah Nirantharakumar, Dr Krishna Gokhale, and Professor Joht Singh Chandan. Its website outlines the potential for use in the design of epidemiological studies, cohort identification, emulating clinical trials with real world data, automating clinical audits, and enabling population health management.
The team has developed a web-based application that users can “take to their data”, meaning data can be extracted and analysed without the need to transfer it to another platform.
Professor Nirantharakumar shares that the solution has already been used to enable over 150 studies for publications such as the BMJ and The Lancet, helping to democratise access to large-scale health data research.
Dexter AI has now been transformed into a commercial venture, with CEO Christian Billinghurst noting: “Dexter has proven transformative in a university setting, contributing to the department growth in scale, impact and grant success. Our move into industry through the University has enabled us to build key partnerships while evolving Dexter into an industry-ready platform tested across diverse data types.”
Wider trend: AI and data
OpenAI has introduced EHR and public data integration into ChatGPT for Healthcare, said to enable AI-assisted workflows and provide clinical teams with a variety of patient information, context, and insights from public health sources. The EHR integration is capable of bringing authorised patient information from Epic into ChatGPT for Healthcare, OpenAI states, whilst the Healthcare Public Data plugin grants direct access to official healthcare datasets such as PubMed and DailyMed.
An award of up to $35 million from the US Department for Health and Human Services’ rare disease AI/ML for precision integrated diagnostics programme is set to support UNC Health to build a data resource for rare disease AI. According to UNC Health, the new data resource will support clinicians and researchers identify patterns and develop research further into rare disease diagnosis and care. New and existing tools will help enable analysis of this large-scale clinical and biological data, with the ambition of promoting earlier diagnosis and treatment discovery.
The North West Secure Data Environment (SDE) has made seven funding awards through its data accelerator fund for novel and emerging assets, designed to support “better use of health and care data”. Funding of between £36,000 and £132,000 has been awarded to seven NHS trust and University-led projects, with recipients including Mersey Care, Cheshire and Wirral Partnership, and research teams from the University of Liverpool; Clatterbridge Cancer Centre and research teams from the University of Liverpool; University Hospitals of Liverpool Group and research teams from the University of Liverpool; and Wrightington, Wigan and Leigh.
