AI-based Healum calls for participants to help build datasets

Healum, an AI-powered healthcare platform, has opened its “live learning network” to allow patients and healthcare professionals to contribute to its datasets.

The firm’s research has been supported by the National Institute for Health and Care Research and UK Research and Innovation, and Healum’s AI platform has been in development for five years. Healum’s aim is to provide healthcare professionals with intervention recommendations personalised to individual patients.

In trial results published earlier this year, patients given recommendations from Healum to manage Type 2 diabetes showed an average 9.5% reduction in blood glucose levels, compared to a 2% reduction in a control group. The study lasted 18 months with 36 volunteers – Healum is now involved in a larger trial with more than 400 participants.

Follow The Stack on LinkedIn

The Live Learning Network research community is aimed at building up Healum’s datasets, in order to provide more accurate recommendations for patients with long-term conditions such as diabetes.

Healum emphasises participants are in control of the data they provide to the study.

“The technology that we will study will make it easier for you to manage your health, from wherever you are, in a way that gives you full control over how your data is used and full transparency around the discoveries it leads to. The community will encourage dialogue around how information and technology can be used in an ethical, effective and safe way,” Healum explained on its website.

Healum is also involved in the You & Type 2 project, which covers around 35 GP practices in London – more than 6,000 patients are part of the project. The company said participants using its app consistently for three months had seen an 8.29% reduction in blood glucose levels.

The firm hosts its systems on Google Cloud Product servers in the UK, and makes a big play of its adherence to regulations and best practices around data – unsurprisingly, as this is one of the biggest concerns about the use of AI and machine learning in healthcare.

See also: Healthcare AI environment ‘very confusing’ for devs: National Data Guardian

Healum also claims not to use historical datasets which may be problematic or lacking full consent. In a blog post on its use of AI and data, Jonathan Abraham, CEO and co-founder of Healum, said the company needed to use historical datasets to train and validate its data gathered from the Live Learning Network – but there were some sets it does not use.

“There is an issue of consent and governance around the ethical use of research datasets for AI development. We found that some private research companies were operating in a grey area, and selling anonymised extracted patient information. That was not what patients and healthcare professionals told us they wanted and went against our values,” said Abraham.

“Instead, we chose to only work with research databases that have rigorous ethical standards, such as the Royal College of General Practitioners’ Research Surveillance Environment, governed by the Primary Health Sciences department at Oxford University. Their data is anonymised and can only be used under a strict protocol that adheres to the standards of their Scientific Ethics Committee.”

Along with funding from UK government bodies, Healum has also received investment from the Northern Powerhouse Investment Fund, backed by the European Regional Development Fund, and Catapult Ventures, backed by the Greater Manchester and Cheshire Life Sciences Fund.