Translational Medicine is a new field in the biosciences that is working to improve global health through translating preclinical science into workable solutions for populations and individual patients. The field is highly collaborative, working across disciplines to solve the challenges of implementing new health care. Machine learning platforms are at the nexus of this new science, able to find patterns in large amounts of data between disparate fields that will lead to new and innovative solutions.
What keeps research findings from laboratory studies from making the move into clinical trials and then into standard clinical practice? The Institute of Medicine’s Clinical Research Roundtable first described these two challenges as needing to be addressed by this new branch of medicine before preclinical and clinical research findings could begin to address urgent medical and population health needs.
Outside of the challenges facing science, there are regulatory, cultural, cross-border, gender, financing, and environmental issues that contribute to the complexity of the issue. Scientific inquiry has progressed in the social sciences as well as biomedicine and many other fields. But how to share possible solutions across highly specialized disciplines? Astronomers with a mapping problem would not first look to new social ventures that teach coding to girls for a problem-solving model. But that model might be the very one that’s the best fit.
Just like with prescribing a treatment for an ill patient, the first step is finding a proper diagnosis, then trying a treatment. If the treatment fails, one looks at two factors–was the diagnosis correct in the first place and if so, was the treatment correct? With translational medicine, scientists are looking at, first, if a research laboratory’s findings are appropriate for clinical use, and then what barriers exist to moving that change into a new clinical practice or therapeutic treatment.
The answers come from looking across a wide range of interdisciplinary sciences, at huge amounts of data. As scientists become more specialized, the need to coordinate findings with data from other fields is growing. This model of finding patterns in large amounts of disparate data is a perfect use for big data and machine learning.
For more information on healthcare uses for big data, please contact us.
The post The New Field of Translational Medicine appeared first on STRATECTA.