A new collection of studies released by the UK’s National Institute for Health and Care Research (NIHR) highlights the potential benefits of artificial intelligence (AI) in the field of healthcare.
One study focused on AI in breast cancer screening, demonstrating that it is safe and can significantly reduce radiologists’ workload by nearly 50%. This finding could greatly improve the efficiency of breast cancer detection.
The NIHR report showcases several research studies conducted between 2020 and 2023, revealing promising AI interventions in five key areas of healthcare.
Heart disease is a prevalent health issue, and researchers have shown that an easy-to-use smart stethoscope, supported by AI, can accurately detect heart failure in primary care settings. This technology could assist general practitioners in referring patients promptly, improving patient outcomes, and saving healthcare costs.
In terms of lung cancer, two studies utilizing different forms of AI discovered that abnormal growths observed on CT scans could be more accurately identified as cancerous. The AI systems outperformed the standard Brock score recommended by professional organizations. This advancement could lead to earlier diagnosis and better chances of survival for lung cancer patients.
AI has also shown promise in predicting disease progression. For instance, AI can predict the development of wet age-related macular degeneration (AMD) in the second eye based on scans from over 2,500 individuals. Additionally, an AI tool has been developed to forecast flare-ups in people with ulcerative colitis, aiding in timely assessment and accurate prognosis.
In the realm of personalized treatment, AI could help physicians determine the most effective drug combinations for cancer patients within a short timeframe of 12 hours. This could enhance treatment outcomes for patients receiving targeted anti-cancer drugs.
Furthermore, AI can predict the risk of death in patients with Covid-19 who undergo surgery. This information can assist healthcare professionals in providing necessary care and minimizing potential risks.
AI is not only beneficial in direct patient care but can also help address hospital pressures. Researchers have developed AI models to accurately predict which patients do not need to attend emergency departments, reducing unnecessary burdens. Predictive AI tools have also been devised to estimate future hospital bed demand, providing invaluable assistance to healthcare managers in resource allocation.
The NIHR emphasizes that these studies represent only a fraction of the research exploring the advantages of AI in healthcare and contribute to the growing body of evidence supporting its use. Author Dr. Jemma Kwint underscores the need for further research to understand the implementation and long-term impact of these AI tools on patient outcomes and cost-effectiveness in routine clinical practice.