Abstract
Artificial intelligence (AI) in healthcare holds great potential to expand access to high‐quality medical care, while reducing systemic costs. Despite hitting headlines regularly and many publications of proofs‐of‐concept, certified products are failing to break through to the clinic. AI in healthcare is a multiparty process with deep knowledge required in multiple individual domains. A lack of understanding of the specific challenges in the domain is the major contributor to the failure to deliver on the big promises. Herein, a “decision perspective” framework for the development of AI‐driven biomedical products from conception to market launch is presented. The framework highlights the risks, objectives, and key results which are typically required to navigate a three‐phase process to market‐launch of a validated medical AI product. Clinical validation, regulatory affairs, data strategy, and algorithmic development are addressed. The development process proposed for AI in healthcare software strongly diverges from modern consumer software development processes. Key time points to guide founders, investors, and key stakeholders throughout the process are highlighted. This framework should be seen as a template for innovation frameworks, which can be used to coordinate team communications and responsibilities toward a viable product development roadmap, thus unlocking the potential of AI in medicine.
Highlights
Healthcare systems all over the world face tremendous challenges
The development process we propose for Artificial Intelligence (AI) in healthcare software strongly diverges from modern consumer software development processes
We have developed a framework following three consecutive phases and covering 4 domains for AI/ML-driven clinical product development
Summary
Healthcare systems all over the world face tremendous challenges. The age-related illness burden is increasing, in wealthy countries, due to ageing populations. Modern ML methods constitute the new state-ofthe-art in computer vision [14], natural language processing [15] and recommender systems [16,17,18] facilitating technologies from smart-assistants to self-driving cars. They are applied for healthcare use cases. They have the potential to deliver personalised treatments [19,20,21] and monitoring [22,23], with lower error rates [23,24], at greatly reduced costs [20,23]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
