Artificial Intelligence (AI) is poised to revolutionize numerous aspects of human life, with health care among the most critical fields set to benefit from this transformation. Medicine is a complex, costly and high-impact field, facing challenges in data management, diagnostics and cost reduction. AI offers solutions to these issues, enhancing care and cutting costs. However, its adoption lags behind other industries, underscoring the need to address key barriers.
In a comprehensive review, published in the journal Healthcare, researchers from the College of Engineering and Computer Science at Florida Atlantic University in collaboration with Marcus Neuroscience Institute, Boca Raton Regional Hospital – part of Baptist Health – identified the current shortcomings of AI in health care and explored its possibilities, realities and frontiers to provide a roadmap for future advancements.
“Artificial intelligence is revolutionizing modern medicine by optimizing administrative workflows, enhancing diagnostic accuracy, and potentially improving patient outcomes. With health care systems worldwide struggling with rising costs, staff shortages and the increasing demand for personalized care, AI presents a transformative opportunity,” said Frank D. Vrionis, M.D., senior author and Chief of Neurosurgery at Marcus Neuroscience Institute – part of Baptist Health – at Boca Raton Regional Hospital. “While AI offers promising solutions, its adoption remains hindered by issues such as data privacy concerns, regulatory hurdles and the complexity of AI models.”
According to the researchers, the health care industry faces numerous challenges, including administrative inefficiencies, diagnostic errors, high costs and a shortage of skilled professionals. Administrative inefficiencies in scheduling, billing and record management often lead to errors and delays. Integrating AI into legacy systems is difficult due to interoperability issues and data privacy regulations like HIPAA.
Predictive analytics could help hospitals better manage patient flow and resources, while in medical imaging, AI can assist radiologists in detecting abnormalities more quickly and accurately. AI also holds promise for personalized medicine, providing tailored treatment recommendations based on individual data.
In medical imaging, X-rays, MRIs and CT scans are essential but costly, limiting access in low-resource settings. AI can enhance efficiency but requires standardized methodologies to handle image noise and motion artifacts. Importantly, AI can improve early disease detection, but its effectiveness depends on high-quality, diverse datasets. Bias in training data can lead to differences in care across demographic groups, making it essential to ensure fairness and accessibility.
In addition, the researchers note that the cost of acquiring and maintaining robotic systems is prohibitive for many health care institutions, particularly in low- and middle-income countries. Integrating AI into the procedural workflow also requires extensive training for surgeons, and there are concerns regarding the reliability and safety of autonomous surgical procedures, as AI-driven systems may not be able to handle unexpected situations as effectively as human surgeons.
“Next-generation AI-augmented imaging systems could enable real-time, data-driven decision-making during surgeries and create personalized imaging protocols. AI could reduce imaging costs, making high-quality diagnostic tools accessible in impoverished areas,” said Maohua Lin, Ph.D., author and a research assistant professor, FAU Department of Biomedical Engineering.
In diagnostics, AI enables IoT solutions for self-monitoring, offering personalized preventative care and predictive models for chronic conditions. AI also shows promise in robotic-assisted surgery, enhancing precision in minimally invasive procedures, and enabling fully autonomous surgical robots. AI’s role in tele-surgery and real-time rehabilitation could further improve access and patient outcomes.
“AI-assisted surgery enhances precision but faces barriers such as high costs, regulatory concerns, and the need for extensive training. AI-driven systems must also address safety concerns in autonomous procedures and need to be validated against traditional methods,” said Vrionis. “AI also raises ethical and legal questions about accountability. When an AI system makes a wrong diagnosis, determining responsibility remains a challenge. Transparency in AI decision-making is essential to build trust among health care professionals and patients.”
To successfully integrate AI into health care, the researchers say collaboration between AI developers, medical professionals and regulators is crucial. Standardized practices, robust validation processes, and interdisciplinary cooperation will ensure safe, ethical and effective AI applications. Cross-institutional data sharing and AI-focused medical training will further enhance AI’s ability to improve patient outcomes and overall health care efficiency.
“The future of AI in health care is incredibly promising, but realizing its full potential requires overcoming several challenges,” said Stella Batalama, Ph.D., dean, FAU College of Engineering and Computer Science. “AI can streamline routine tasks, minimizing human error and allowing medical professionals to dedicate more time to patient care. Predictive analytics can enhance resource allocation and patient management, while AI-powered models aid in early disease detection and personalized treatments. Additionally, AI-driven robotic systems can increase precision in minimally invasive procedures and enable remote surgeries. Looking ahead, real-time AI-assisted rehabilitation could revolutionize patient recovery, improving outcomes on a global scale.”
Other review co-authors are Javad Hashemi, Ph.D., inaugural chair and professor of the Department of Biomedical Engineering and associate dean for research, FAU College of Engineering and Computer Science; Nan Lin, M.D., Department of Gastroenterology, The Affiliated Hospital of Putian University, China; Rudy Paul, FAU Department of Ocean and Mechanical Engineering; Santiago Guerra, a doctoral degree student, FAU Department of Ocean and Mechanical Engineering; Yan Liu, M.D., the Affiliated Hospital of Putian University; James Doulgeris, Ph.D., FAU Department of Biomedical Engineering; Min Shi, Ph.D., University of Louisiana at LaFayette; and Erik Engeberg, Ph.D., a professor, FAU Department of Biomedical Engineering and Department of Ocean and Mechanical Engineering, a member of the FAU Center for Complex Systems and Brain Sciences within the Charles E. Schmidt College of Science, and a member of the FAU Stiles-Nicholson Brain Institute.
-FAU-