AI enabled self management to address health inequalities

Early during the COVID-19 pandemic, it became clear that people with multiple conditions such as heart disease, chronic respiratory disease, diabetes, cancer and high blood pressure are particularly clinically vulnerable to COVID 19\.

What has also now become clear is that people of British Black, Asian, and minority ethnic (BAME) origin are at a higher likelihood of testing positive and dying with COVID-19\.

A recent report from Public Health England stated that an analysis of survival among confirmed COVID-19 cases showed that, after accounting for the effect of sex, age, deprivation and region, people of Bangladeshi ethnicity had around twice the risk of death when compared to people of White British ethnicity. People of Chinese, Indian, Pakistani, Other Asian, Caribbean and Other Black ethnicity had between 10 and 50% higher risk of death when compared to White British.

In order to move forward, the report and experts made a number of recommendations to meet the challenge that this provided to the UK. In particular one of the recommendations ( recommendation 5 ) stated that was to develop and implement culturally competent COVID-19 education and prevention campaigns. Another key recommendation was to ( recommendation 6 ) Accelerate efforts to target culturally competent health promotion and disease prevention programmes for non-communicable diseases promoting healthy weight, physical activity, smoking cessation, mental wellbeing and effective management of chronic conditions including diabetes, hypertension and asthma.

Health Fabric has been a pioneer in the Digital Health space. Our current platform accredited on the NHS App Library and has over 2000 users across different conditions. The apps on the NHS library are trusted by patients and practitioners as they have gone through an exacting level of due diligence on compliance around Effectiveness, Clinical Safety, Adherence to clinical regulation, Data Protection, Security, Usability & Accessibility, Interoperability, and Technical Stability. As a result, we have a deep understanding of the data points around effective self-management.

To address the challenge, we propose we extend the capabilities of our existing platform and develop an novel AI model and algorithm that presents self-help information to users of BAME origin so it has a cultural fit and supports self-management. The second feature of the novel AI model will be to orchestrate proactive support across a network of friends, and family and clinicians.