Artificial intelligence projects in healthcare: 10 practical tips for success in a clinical environment

Abstract

There is much discussion concerning 'digital transformation' in healthcare and the potential of artificial intelligence (AI) in healthcare systems. Yet it remains rare to find AI solutions deployed in routine healthcare settings. This is in part due to the numerous challenges inherent in delivering an AI project in a clinical environment. In this article, several UK healthcare professionals and academics reflect on the challenges they have faced in building AI solutions using routinely collected healthcare data.These personal reflections are summarised as 10 practical tips. In our experience, these are essential considerations for an AI healthcare project to succeed. They are organised into four phases: conceptualisation, data management, AI application and clinical deployment. There is a focus on conceptualisation, reflecting our view that initial set-up is vital to success. We hope that our personal experiences will provide useful insights to others looking to improve patient care through optimal data use.

Keywords: health care sector; information science; medical informatics.

Figure 1

The four typical phases which AI healthcare projects will go through. The circular form highlights the iterative way in which such projects are often conducted. AI, artificial intelligence.

Figure 2

An example of a data flow diagram using the Gane and Sarson nomenclature. In this example, multiple disparate sources of data from individual patients in the ICU are aggregated into a single research database. In-built, role-based access controls allow the data to be accessed by multiple different users while meeting data privacy requirements. EPR, electronic patient record; HCP, healthcare professional; ICNARC, intensive care nationaI audit and research centre; ICU, intensive care unit; SQL, structured query language.