By Erik Lickerman M.D.
It’s risky to summarize an entire field based on a name, but it seems to me the vision of “ digital medicine ” is to change our diagnosis/treatment paradigm to one in which:
- We have the blue prints, schematics, and service manual for every patient in the form of ‘omics data.
- Everyone has an array of sensors, always on, not only after the patient reports an issue.
- Advanced analytic technics based on buzz phrases like artificial intelligence, machine learning, big data, and blockchain, would determine from moment to moment to what extent a person is within a “normal operating range” with respect to a huge number of combinations of parameters.
- Those same techniques would detect patterns that warn of future trouble even when parameters are within “normal operating range”.
- The parameters will initially be traditional ones such as vital signs and serum electrolytes but these sensors and parameters will expand dramatically over time both in number and variety. We may be monitoring smells, analyzing visual appearance, sampling for nucleic acids in the blood, and detecting changes in social behaviour.
- When something goes out of range a doctor will run a set of diagnostics. These diagnostics will be more akin to what a modern auto repair shop, or software admin, or Star Trek doctor, would recognize as “diagnostics”.
- We will find problems early and deal with them early.
- Buzz-phrase powered analytics will make predictions and recommend repairs (err…treatments)
Current medical practice assumes this is impossible. It has been impossible, but it might not continue to be so. Maybe this vision of digital medicine is possible to realize, or maybe it’s partially possible.
Perhaps the end vision cannot be realized because of the small number of patients relative to the large number of parameters, but along the way we find just enough working applications to supplement or partially replace the current diagnostic (and therefore treatment) paradigm. Even this would be a worthy result of our investment in digital medicine.
Erik Lickerman M.D.
Erik studied biology as an undergraduate at M.I.T. Then medicine at the University of Illinois. After four years of anatomic and clinical pathology residency, he followed his lifelong passion for computer science by completing a fellowship in pathology informatics under Mike Becich at the University of Pittsburgh.
Rather than practice pathology and do informatics as a side pursuit, he went into commercial medical informatics, working for a succession of companies from “tiny startup” to Fortune 500. From the beginning his goal has been to transform the medical record from a handwritten notebook full of short stories we write about the patient, to a set of discrete well modeled data with proper standard terminology and amenable to search, query, analysis, and machine learning. He remains disappointed that we are only a quarter of the way there.
Erik considers himself a programmer first and a physician second. His focus is data modeling, programming and leading teams to create practical medical informatics products. His currently works at Varian Medical Systems and focuses on oncology informatics and the incorporation of clinical data and genomic data into analytics.