THANK YOU FOR SUBSCRIBING
Medical Tech Outlook Weekly Brief
Be first to read the latest tech news, Industry Leader's Insights, and CIO interviews of medium and large enterprises exclusively from Medical Tech Outlook
A new study led by a research team of one university faculty and alumni created and applied AI, or machine learning algorithms, to physiological data from patients with chronic pain suffering from sickle cell disease, including respiratory rate, oxygen levels, pulse rate, body temperature, blood pressure, and so on. The scientists' methodology outperformed baseline models in determining subjective pain levels and detected changes in pain and atypical pain swings.
The researchers used data from 46 adults and children with sickle cell disease who were hospitalized for a total of 105 days, looking at physiological data and patient-reported pain scores to construct models that could estimate pain levels and detect changes in pain levels using machine learning. Patients should currently rate their pain on a scale of zero to ten. This can be a difficult task because many people experience pain in different ways, and little children and comatose patients cannot rate their discomfort in any way.
According to the researchers, these subjective pain assessments might be improved with a more objective, less intrusive, data-driven approach to aid clinicians in developing a more appropriate treatment plan. The researchers then compared their new models to others that attempted to assess pain levels but did not use physiological estimations, and the new models outflanked the current models. With the research, the team aimed to understand better how people experience pain, and they hope that the long-term upshot of this line of study is a more quantitative approach to pain management.
The possibilities for AI applications in healthcare are vast, ranging from emergency rooms to primary care to home care. AI can be used in healthcare to automate patient evaluation and remove assessor bias. It can assess a patient's risk of developing a specific disease, such as analyzing illness by deciphering ECG results and X-ray images, choosing the best treatment based on a patient's clinical history and clinical trial results, and monitoring disease and recognizing early warning signs of deterioration.
Read Also
