Mayo Clinic
Software Engineer (Clinical Decision Support Systems)
October 2014 to October 2015 · Rochester, MN, USA
Mayo Clinic is an American nonprofit academic medical center based in Rochester, MN, focused on integrated patient care, education and research. It employs over 4,500 physicians and scientists, along with 58,400 administrative and allied health staff.
Highlights
- Co-authored “Patient-Like-Mine: A Real-Time Visual Analytics Tool for Clinical Decision Support” (IEEE International Conference on Big Data, 2015)
- Collaborated with physicians and data scientists to develop a real-time visual analytics platform helping clinicians identify similar patient profiles and improve treatment decisions.
- Engineered data pipelines transforming HL7 V2 RIM and FHIR medical schemas into hierarchical Elasticsearch documents, enabling high-speed patient similarity searches.
- Rewrote experimental prototypes for production reliability and speed.
- Optimized query performance for large-scale datasets to support responsive clinical workflows.
- Strengthened data integrity and patient-privacy practices — balancing innovation with ethical responsibility in health data visualization.
Patient Like Mine
The Patient Like Mine project was a real-time, visual analytics tool for clinical decision support. The System expands the “recall of past experience” approach that a provider (physician) uses to formulate a course of action for a given patient. By utilizing Big Data techniques, we enable the provider to recall all similar patients from an institution’s electronic medical record (EMR) repository, to explore “what-if” scenarios, and to collect these evidence-based cohorts for future statistical validation and pattern mining.
- Building all of the visualization tools of the project
- Optimizing Elasticsearch queries to provide real-time search on very-large large datasets, which included over 1 billion facts, each with over 1 thousand properties and up to 1 thousand data points per second
- Re-writing an internal tool used for creating complex nested Elasticsearch queries, using modern ES6 standards
- Presenting our work at monthly Lunch-and-Learn workshops, where we would share our progress with other teams within the Mayo Clinic
Publications
P. Li, S. Yates, J. Lovely, D. Larson. 2015. “Patient Like Mine: A Real Time, Visual Analytics Tool For Clinical Decision Support”. IEEE Big Data
Recognition
