By Richard Loomis, M.D., Fierce Healthcare | May 10, 2019
With the rise of artificial intelligence (AI), the healthcare industry is now exploring how this technology can be used to improve patient outcomes.
AI and machine learning have been around for many years. In fact, they’ve been around for as long as people have been considering the idea of a machine mimicking the human mind and building a virtual brain. AI research has grown by 12.9% over the last 5 years, according to a recent study. But what does that mean for patients?
All healthcare providers aim to reduce variability in practice, personalize care for patients and deliver better outcomes with lower costs. The increased knowledge AI offers can help achieve these goals.
RELATED: Verily’s India project reveals the work of applying AI to real-world clinical care
With the growing amount of data available, it can be impossible to sort through those data without AI technology. According to a report (PDF) from Dell EMC and research firm IDC, health data volumes increase by a staggering 48% annually each year.
Using AI, we can now analyze massive quantities of data to inform clinical decision-making at the point of care. Through clinical decision support (CDS) tools, physicians now have the ability to understand, access and analyze a wealth of real-world data, closing the gap between experimental, artificial study settings and clinical realities to produce trusted best practices that can be rapidly applied to their clinical practice.
Supported by advanced algorithms and machine-learning capabilities, CDS tools use AI to analyze existing patient data and draw new findings and hypotheses that are often not covered in larger or more traditional scientific research.
Moreover, data collected from the physicians who use these tools help continually strengthen the recommendations these tools deliver, providing a continuous process of improvement in clinical decision-making. This feedback loop will allow reduction in unwarranted variations and enable insights to be delivered back into clinical practice, benchmarking clinical improvement across hospitals.
RELATED: Harvard, Dana-Farber AI challenge uses crowdsourcing to improve cancer care
By using AI to sift through data and deliver the right information at the right time, CDS tools have been proven to prevent medical errors and reduce costs. For example, with the help of a CDS diagnostic tool, radiologists have been shown to reduce diagnostic errors by 19%, saving costs on unnecessary testing and re-testing.
AI technology will remain a prominent method of understanding our world of data; but it’s the physicians, researchers and institutions who harness the data to deliver better care, treatments and outcomes that are going to be most impactful for patients.
Richard Loomis, M.D., is the chief informatics officer, clinical solutions at Elsevier.