Blogs

What’s the best way to make a sandwich? One hundred sandwich artisans from across the globe could synthesize all their notes, and you could still end up with a PB&J while craving a turkey on rye. What’s the best approach to health care? It might just be easier to teach the computer to think about that one.

700 TRILLION points of data. In his Opening Plenary Session during the SOT 61st Annual Meeting and ToxExpo, Dr. Atul Butte described how we can synthesize tremendous volumes of health care data—molecular sequencing data, imaging data, environmental pollution data (and even claims data)—to shape a physician’s understanding of a patient’s health. This is fascinating! However, what’s even more interesting is how these data can help shape a machine’s understanding of a patient’s health.

The standard computer is programmed with rules defined by humans. With machine learning, computers can make their own rules and have the potential to outperform the human brains that they mimic. By feeding computers health care data, these machines can model complex relationships, like gene-by-environment interactions, and make inferences about appropriate interventions to improve patient outcomes.

At the University of California San Francisco, Dr. Butte’s lab is developing tools that convert “big data” (trillions of points of molecular, clinical, behavioral, and epidemiological data) into new disease insights. Using machine learning algorithms, they create maps relating health conditions, which can then be used to predict potential adverse health outcomes and intervention strategies.

In an era where we have access to electronic medical records and genomic databases, Dr. Atul Butte proclaims that it would be a “national tragedy” if we failed to leverage these data. Improved models and data utilization could be the key to refining precision medicine.

Interested in learning more about personalized medicine and big data analysis? Here are Sarah’s reading recommendations:

1. Alyass, A., Turcotte, M. & Meyre, D. From big data analysis to personalized medicine for all: challenges and opportunities. BMC Med Genomics 8, 33 (2015). https://doi.org/10.1186/s12920-015-0108-y
2. Ashley, E. Towards precision medicine. Nat Rev Genet 17, 507–522 (2016). https://doi.org/10.1038/nrg.2016.86
3. Costa FF. Big data in biomedicine. Drug Discov Today. 2014 Apr;19(4):433-40. doi: 10.1016/j.drudis.2013.10.012.
4. Fröhlich, H., Balling, R., Beerenwinkel, N. et al. From hype to reality: data science enabling personalized medicine. BMC Med 16, 150 (2018). https://doi.org/10.1186/s12916-018-1122-7
5. Greener, J.G., Kandathil, S.M., Moffat, L. et al. A guide to machine learning for biologists. Nat Rev Mol Cell Biol 23, 40–55 (2022). https://doi.org/10.1038/s41580-021-00407-0
6. Hong JC, Butte AJ. Assessing Clinical Outcomes in a Data-Rich World—A Reality Check on Real-World Data. JAMA Netw Open. 2021;4(7):e2117826. doi:10.1001/jamanetworkopen.2021.17826
7. Rudrapatna, V.A. and Butte, A.J. Opportunities and challenges in using real-world data for health care. J Clin Invest. 2020;130(2):565-574. https://doi.org/10.1172/JCI129197.

This blog was prepared by an SOT Reporter and represents the views of the author. SOT Reporters are SOT members who volunteer to write about sessions and events in which they participate during the SOT Annual Meeting and ToxExpo. SOT does not propose or endorse any position by posting this article. If you are interested in participating in the SOT Reporter program in the future, please email Giuliana Macaluso.

On-demand recordings of all Featured and Scientific Sessions delivered during the 2022 SOT Annual Meeting and ToxExpo will be available to meeting registrants in the SOT Event App and Online Planner after their conclusion, through July 31, 2022.