Better algorithms, not more data, will transform healthcare in the not-too-distant future, say Harvard Medical School's Ziad Obermeyer and the University of Pennsylvania's Ezekiel Emanuel.
The authors, in an article published this week in The New England Journal of Medicine, cite the ability to consider millions of variables as the machine learning advantage over humans. For example, with dramatic advances in computational power, computers can look for anomalies at the pixel level of radiographs, they say.
Obermeyer and Emanuel foresee machine learning disrupting at least three areas of medicine:
- Establishing a prognosis: Data drawn from electronic health records or claims databases can help refine these models. They say prognostic algorithms will be used within five years, though several more years of data will be needed for validation.
- Taking over much of the work of radiologists and anatomical pathologists. They also see algorithms used on streaming data taking over aspects of anesthesiology and critical care within years, not decades.
- Improving diagnostic accuracy, suggesting high-value tests, and reducing overuse of testing. This will happen more slowly, they say, because some conditions don’t present clear or binary standards like radiology--malignant or benign--which make it harder to train algorithms (because of the prevalence of unstructured data in EHRs and because each diagnosis would require its own model).
“As patients’ conditions and medical technologies become more complex, the role of machine learning will grow, and clinical medicine will be challenged to grow with it,” they say.
However, one recent study called the current state of machine learning “voodoo,” and warned of inaccuracies.