As its techniques and technologies mature, medical AI will increasingly be used to predict the health trajectories of both outpatients and inpatients. But the modeling will only help direct care to the extent that projections are timely, accurate, individualized and actionable.
The qualified expectation gets fleshed out in an article posted in the Journal of Medical Internet Research.
Two of the piece’s three authors are affiliated with Taipei Medical University in Taiwan, the other with Harvard and MIT.
Iqbal, Li and Celi propose three levels on which AI trained with Big Data has potential for guiding what they call “earlier medicine.”
Here’s the gist of each:
1. Primary prevention using AI can target population subgroups of people who are well and want to stay that way. Early detection from measures such as cancer screening are well and good, but today’s programs are often under-targeted, the authors suggest.
“We believe that society would benefit more from increased precision in the selection of groups for screening with AI-based earlier risk reduction using AI prediction technology,” they write. “The incorporation of genomic information in electronic health records as part of one’s personalized treatment will drive the greater use of AI in primary prevention.”
2. Secondary prevention with AI would predict disease progression in acute-care patients as well as those with conditions that could become acute.
For patients in both those categories, AI “can compute a management plan tailored to the patient’s individual needs,” the authors write, giving as an example predicting recurrence of myocardial infarction for patients with chest pain.
3. Tertiary prevention aided by AI could help manage patients with chronic conditions. In these scenarios it would predict complications, disabilities and falloffs in overall quality of life.
Healthcare systems around the world are dealing with aging populations, the authors point out. Many if not most of these systems “leave much to be desired in terms of long-term care, palliative care and the expenses needed to maintain the system,” they write. For example, earlier medicine for tertiary prevention based on AI-computed individualized risk could help to prevent falls at home by 90% while reducing at least 10% of the dependent cost.
“We earnestly believe that AI for ‘Earlier Medicine’ will not only transform the practice of medicine but also radically reshape healthcare around the world,” Iqbal, Li and Celi conclude. “Harnessing the power of digital technologies is essential for achieving universal health coverage and to reviving humane medical practices for improving the quality of care.”
The article is available in full for free.