A Framework for Implementing Intelligent Systems and Data-Driven Algorithms in Healthcare: Overcome Key Challenges

The healthcare sector and efficiency with regards to the delivery of care is expected to expand drastically with the introduction of AI and Machine Learning technologies. Although the potential of AI tools and technologies are widely accepted, and the market for it is blooming, the actual implementation is very low, which is quite surprising. This phenomenon is known as the ‘graveyard of models’, defined by how these innovative AI tools are never used in a realistic setting, which is called clinical settings. This research seeks to understand the barriers that impede such AI tools developed in research from being utilized practically. National and regional barriers such as communication difficulties, data contrasts and regulations are some of the limiting factors. In order to solve the above challenges, it is advised that a framework is provided which looks at the importance of the abovementioned barriers, and industry input. This would further allow for a better-defined process and framework for AI computing that is industry-focused. In addition to this, we present a practical example that depicts a clinically focused AI Technical that serves to facilitate processes and improve the experience of patients. Such research focuses on practical relevant aspects and as the first step to orient the study on practicality and relevance, feedback and pilot testing mechanisms are put in place to determine ease of use and effectiveness. The emphasis on these targeted themes should help improve the chances of adoption of AI technologies in clinical practice and that way, limit the gap between the theory and practice of any given intervention.