“The promise of artificial intelligence in medicine is to provide composite, panoramic views of individuals’ medical data; to improve decision making; to avoid errors such as misdiagnosis and unnecessary procedures; to help in the ordering and interpretation of appropriate tests; and to recommend treatment.”
― Eric Topol
Artificial intelligence, AI, has been generally defined as technologies with the ability to perform tasks that would otherwise require human intelligence i.e. any software with the following characteristics: automation, self-learning and the ability to make decisions.
Artificial Intelligence was established as an academic area of research in the 1950’s and has since undergone periods of both hype and skepticism as research develops novel findings and encounters challenges.
In healthcare, the potential application of AI is massive due to the ability of AI to mimic human cognitive capabilities through techniques such as classic machine learning, modern deep learning, natural language processing, or automation and robotics. As regards the healthcare field, some of the ways AI has been applied include:
- Risk prediction and Intervention: AI-driven predictive modeling with electronic health record data can now outperform traditional predictive models in forecasting in-hospital mortality.
- Risk-adjusted paneling and resourcing: involves increasing or decreasing panel sizes based on patient complexity.
- Diagnostics and clinical decision making: AI-powered algorithms for diagnosing disease is now outperforming physicians in detecting skin cancer, breast cancer, colorectal cancer, brain cancer and cardiac arrhythmias.
- Practice management: One of the most anticipated applications of AI in medicine is the automation of repetitive clerical tasks that are suffocating practices.
- Population health management: improving clinical health outcomes of a defined group of individuals through improved care coordination and patient engagement supported by appropriate financial and care models.
- Medical advice and digital health coaching
Despite these impressive applications of AI in healthcare, there still exists limitations to the successful application of AI in health care in Nigeria. Some of these limitations are related to the lack of data collecting infrastructure, lack of regulation of AI and the lack of patient trust in AI.
Other limitations of AI in healthcare, especially in Nigeria, include improper infrastructure and implementation, high cost of developing and implementing AI systems, lack of quality data i.e., inconsistent, incomplete data, bias in AI predictions due to “bad” data, improper regulation to ensure patient safety, as well as reluctance of patients and healthcare workers to adopt new technology.
To address these limitations and ensure the responsible and effective use of AI in healthcare, ongoing research, collaboration between technologists and clinicians, regulatory oversight, and transparent reporting of AI methodologies are all essential.
IREOLUWA ADEGOKE
