If you’re a regular Geneia blog reader, you already know I’m very proud of the Geneia Data Intelligence Lab, and our work building predictive and prescriptive models to reduce future health costs and improve health outcomes. We’re working to improve:
- Healthcare quality with models that predict inpatient probability and the likelihood of a readmissions within 30 days,
- Health outcomes with models that identify patients at risk for opioid abuse or complications due to chronic diseases such as diabetes, and
- Costs by predicting patients likely to incur high costs as well as the most impactable care pathways.
The work we’re doing in the Geneia Data Intelligence Lab informs the predictive analytics baked into the Theon® platform as well has given rise to analytics-as-a-service. In our new white paper, How a Phased Approach to Value-Based Care Works: For health plans, hospitals and their value-based partners, we featured a health plan using this service to help support independent physicians in value-based care. As the first phase, the plan is working with Geneia to create a data science strategy and deploy models at the organizational level including 30-day readmissions, high-cost claimants, type 2 diabetes and heart failure complications.
Shelly has a Ph.D. in biology from the University of Vermont. She’s a registered pharmacist, and previously worked as a pharmacist in the 340B Drug Pricing Program at the Central Vermont Medical Center. As a data science fellow, she created machine learning algorithms to help a start-up pharmacy predict drug demand, optimize drug inventory and reduce costs.
Like many of her fellow Geneia data scientists, Shelly enjoys the freedom she’s given to explore all possible ideas that can help improve patient outcomes. She’s quite passionate about using leading-edge data science techniques to improve patients’ health.
Shelly’s also excited about how AI can help physicians. In her words, “AI tools can analyze data from various sources, such as EHRs, genetic tests, labs and claims data, to provide timely alerts and recommendations to care teams. That means, AI and machine learning tools will assist physicians to make more informed decisions and patients to receive timely and personalized care.”
So far, Shelly’s work at Geneia has focused on improving health outcomes:
- Drug adherence: Identifying, and subsequently engaging, patients who don’t regularly pick up their prescriptions, and
- High-risk pregnancy: Predicting pregnant women at risk for preterm delivery or miscarriage and connecting them with a care manager.
Zhipeng holds a Master of Science in statistics and a Ph.D. in pharmacology from Purdue University. During his five years at Purdue, he studied how genetics factors contribute to the development of metabolic diseases such as fatty liver and type 2 diabetes, and published six peer-reviewed papers in high-impact journals. As a data science fellow, he created a predictive model that uses data in the EHR to identify people at high risk for developing fatty liver diseases. Zhipeng also has a master’s in biochemistry and bachelor of engineering in bioengineering.
As a data scientist, Zhipeng is grateful for his innate curiosity. “Data scientists not only solve existing problems, but also need to proactively identify gaps that can be bridged using data science skills. The best data scientists are quick learners, not only of the newest data science techniques but also the other parts of the business such as sales, marketing and operations.”
At Geneia, Zhipeng is working on models that identify people at high risk for developing chronic diseases such as hypertension and diabetes and help care managers provide personalized management for high-risk patients. He’s optimistic about how AI can improve disease diagnosis and suggest personalized treatment and care.
To read more about the important work of the Geneia Data Intelligence Lab, click here.