UK-based healthtech startup Abtrace has raised £2.1M (€2.4M) of seed funding. The round was led by the Lisbon-based VC fund Faber, with participation from Ganexa Capital, and includes £1M (€1.1M) in project funding from Innovate UK.
Led by NHS doctors, Abtrace has built an AI tool that can plug into the Electronic Health Record (EHR) database and identify which tests or treatments a patient with a long-term health condition needs or might benefit from. The software allows GPs and healthcare assistants (HCAs) to make more informed decisions, automate key elements of disease monitoring, and ensure patients receive consistent, effective care.
With the proceeds, the startup plans to enhance its technological acumen and come up with new ways for GP practices across the UK. It is also planning to hire more people for its engineering and data science teams.
Abtrace co-founder and CEO, Dr Umar Naeem Ahmad, who is also a practicing NHS doctor, says, “Our technology is incredibly simple to use – it takes each GP practice just 30 mins of training to get started – but delivers significant results. Through machine learning, we can scour millions of data points to give healthcare workers the information they need to provide the best for their patient. This means making each appointment as useful as possible, ensuring patients with long-term conditions get the support they need at the right time and, eventually, leveraging the technology to pick-up on the early signs of serious conditions such as cancer.”
Abtrace has recently built an AI tool that helps in extracting crucial information from the Electronic Health Record (EHR) database and then helps in identifying tests for patients. It basically takes note of an individual’s medical history and takes actions accordingly.
The healthtech startup said that the technology will enable the management of long-term health conditions to move from a reactive, often piecemeal approach, to a proactive process informed by rich data.
For example, if a patient with a long-term condition such as diabetes attends their GP surgery for a routine blood test, the Abtrace system would show their GP or HCA which other tests are due, as well as suggest additional tests which the patient might benefit from. This means multiple tests or monitoring can be completed during one appointment. This minimises the need for repeat trips, ensures key tests aren’t missed, and automates routine interventions – creating a safer, better experience for the patient and saving each GP practice time and money.
Following a pilot of the technology, which involved several GP practices and 15,000 patients, Abtrace led to a 30% reduction in the number of HCA appointments needed and halved the number of repeat prescriptions that required a GP appointment. As a result, practices using the platform saw a significant decrease in their covid-induced backlog of appointments and an increase in patient satisfaction, the company said in a statement.
In future, the startup’s machine learning and natural language processing technology will also be used to spot early signs of emerging conditions. By taking into account a patient’s symptoms or health issues over a period of time, Abtrace’s ML algorithm will be able to accurately recognize the first signs of serious conditions, including cancer. The team is developing the application of this product in partnership with the NHS, academic partners and cancer charities.
Founded in 2018, Abtrace is a healthtech start-up that uses machine learning to transform how chronic and long-term health conditions are detected, monitored and treated. The company claims to have spent the last 3 years building its robust deep-learning platform in partnership with clinicians and the NHS.
Abtrace scans the entire patient record to identify the multiple reasons why a patient might require monitoring tests and support clinicians deliver these in a single appointment. The same platform is being used to identify early signals that a patient might be developing a disease like cancer and support the clinician initiate an earlier diagnosis.