Scroll Top

An Artful Merger Of Precision Medicine And Baseball

David Sable

Healthcare business doesn’t get more obscure than this: a development-stage diagnostics company listed on the TSX Venture Exchange with a headquarters located in a Mississauga, Ontario strip mall. But despite this modest description, Genenews had a hell of a board of directors. It included Rory Riggs, who founded and developed some of the most innovative companies in biotechnology and in healthcare finance, and Heiner Driesman, ex-CEO of Roche Diagnostics. But the real conversation stopper on the board, the one person whose opinion nobody thought to argue with, was Harry Glorikian.

I’ve introduced Harry to a number of people over the years, and the follow-up phone calls usually included the question: “How do we get Harry to come work for us?”

Because in the diagnostics sector, no one knows more than Harry.

His latest book, Moneyball Medicine, patterned after Michael Lewis’ profile of the digitalization of decision making in professional baseball, is an exhaustive overview of the predicted evolution of precision medicine in the coming decade. Extensively researched and annotated (its 200 pages are followed by 38 pages of references), he lays out the case for efficiencies at the practitioner, research, laboratory, payer, and public health levels.

Harry and his co-author, Malorye Allison Branca, straddle the worlds of healthcare and technology with equal fluency. Chapters one and two layout the challenge of taming the conflicting interests of healthcare providers and facilities that want to maintain ownership of proprietary methods, laboratories and research facilities with their own vocabularies to describe the same procedures and processes, and disappointing and counterproductive medical record systems. And let’s not forget the willfully misunderstood HIPAA system, used by everyone in healthcare as an excuse to avoid even the most beneficial data integration. Despite these impediments, the combination of benefits from process optimization, the ongoing transformation of medical data collection along the analog to digital continuum, and the availability of cheap memory and processing power and coding talent make the evolution of precision medicine inevitable.

This movement is described in oncology, genomics- and genetics-based reproductive medicine, and the development of treatments for orphan diseases. We’ve come a long way in each, although each area poses unique challenges for further development. In oncology we have successfully teased out highly specific markers for many tumors, but a fuller understanding of the ultimate complexity of the disease, the relationship between the data points that we are discovering and what will consistently and accurately affect its progression is ongoing. In reproductive medicine the combination of assisted reproduction with in vitro fertilization (IVF) coupled with parental prenatal and embryo preimplantation diagnostics offers the prospect of stopping disease at the conception level. And progress in orphan diseases, typically defined by much more specific pathophysiologic parameters, is often limited by our inability to accrue enough patients to satisfactorily test new hypotheses.

Ultimately, these are only logistical problems, and a gradual reorganization of healthcare in a data-driven fashion will push us past these barriers.

Once we internalize a system of measurement, process optimization, and rationalization of decision making a treatment plan, we can apply these data to a more accurate value basis for cost and payment. Similarly, greater comfort with genomic, gene expression, proteomic and phenotypic data analyzed in aggregate will drive an even more efficient and data-driven drug discovery and development process.

What emerges is a model for a new healthcare system, one less handicapped by traditional but imprecise categorizations of disease, patient groups, and treatment methodologies, offering a vision of a democratized practice of medicine, where we base diagnostic and treatment decision on a higher order level of data, come of it population-based and generated by the healthcare system itself and some by patients’ own observations, with the assistance of consumer healthcare hybrid devices– more powerful versions of the wearables and watch-based relatively primitive devices available now.

To extend the baseball analogy, Moneyball Medicine is in its early innings, the starting pitchers are still fresh, there have been a couple of hits but there are few runs on the board. But unlike baseball, where the replacement of “I know it when I see it” with data-driven decision support still results in one winner and one loser after nine innings, the future of precision medicine continues has no endpoint, and we all stand to gain.