What is data science?
Data science is a multi-disciplinary field which draws from mathematics, computer science, statistics and information science. It combines the domain expertise, programming skills and knowledge of mathematics and statistics to extract meaningful insights from data and model future projections.
Data science applications in precision medicine
Data science allows us to make use of large amounts of data generated from numerous sources such as patient health records, diagnosis, treatment, genomic sequencing, medical research, smart devices and wearables.
Through the use of computer models, algorithms and advanced analytics, diverse datasets can inform useful clinical understanding. Machine learning, artificial intelligence, natural language processing and deep learning enable faster mining of big data. Through data science, we can identify patterns in patient populations, identify mutations in large sets of genetic data, help automate workflows and more. This has the potential to transform the healthcare industry, and spur wide-ranging advancements from precision-based medicine and drug research to the creation of clinical decision support tools.
Creating integrated databases for research
The Center for Precision Medicine and Data Sciences has leveraged our Department of Defense research grant on traumatic brain injury and burns to develop an integrated database. The database aggregates large data sets, integrating and transforming multiple data sources into a single database that can be interrogated by biostatisticians and informaticians. The model integrates data from multiple disparate sources which include electronic medical records, metabolomics, genomics, laboratory data from systems like OpenSpecimen and medical registry databases like REDCap.
We build integrated data science platforms
A platform is a system of technologies that are used as a base upon which other applications, processes or technologies are developed. Platform technologies allow for the flow of data from multiple sources such as the electronic medical record (EMR) and genetics, -omics, laboratory, image or census databases into a single platform. This integrated platform allows researchers or medical providers to query, analyze, and identify patterns of interest.
The Center for Precision Medicine and Data Sciences can build integrated platforms for research, and offer data science and data architecture expertise to build a platform best suited for your specific research goals. These platforms have the potential to:
- Use data to deliver the right treatment to the right person at the right time.
- Help hone research questions.
- Look for patterns, variations and outcomes in data.
- Assist with predictive modeling, providing health care professionals tools to identify high-risk health issues before they develop into serious problems.
- Allow healthcare institutions to make meaningful use out of their data systems, enabling them to provide more efficient, higher quality care, as well as build relationships with the communities they serve.
This model demonstrates the service we provide in creating an integrated data science platform. We first combine data from a variety of sources such as the electronic medical record, research registries, waveform or other data and text files into a data hub. Then, this data is merged and enriched within the Precision Medicine data hub. The hub gives researchers a warehouse for their data that is ready to be analyzed in any format they want. Upon request, data can also be summarized based on the required parameters of the project. Data from the hub can then be pulled in the form of Tableau reports or raw data to be used for machine learning or biostatistical analysis.
Security and ethical handling of health data
Advances in data science and the increasing use of big data in medicine call for ethical handling of health data. Our Center believes that the secure storage and handling of vast amounts of personal health and demographic is of utmost importance. Data needs to be shared and stored securely across different platforms. Healthcare providers and patients should have equal access to this data. Providers can use large databases to identify patterns, make decisions and improve patient care. With access to their own data, patients can be in control of their health records and better collaborate with their physicians in their wellness.