Clinical NLP and Electronic Health Record Data Mining Lab @ Cincinnati Children's Hospital Medical Center


Our mission is to develop informatics algorithms and tools to extract all relevant information from the Electronic Health Record, including information buried in narrative text, and to utilize the extracted information in computerized clinical care, patient safety and outcome improvement systems. 


Imre Solti is Assistant Professor on Tenure-Track at the Department of Pediatrics, Division of Biomedical Informatics at Cincinnati Children's Hospital Medical Center. He has secondary faculty appointments as Assistant Professor at the Anderson Center for Health Systems Excellence, Cincinnati Children's Hospital Medical Center and Affiliate Assistant Professor appointment at the Department of Linguistics, University of Washington.

The long term research goal of the Solti Lab is to utilize all the information that is collected and stored in the Electronic Health Record (EHR) in computerized clinical decision support systems. As a substantial portion of the EHR's information content is buried in narrative text (e.g. physician or nursing notes) and inaccessible by current information extraction methods the lab develops new and adapts existing clinical Natural Language Processing (NLP) algorithms and tools. Developing high performance clinical NLP methods for Information Extraction (IE) is the focus of the lab's foundational (basic science) efforts.

The Solti Lab's applied informatics endeavors are focused on utilizing the information that was extracted from the EHR in computerized clinical decision support systems. Current research activities include the internally funded 1) Automated Appendicitis Risk Stratification, 2) EHR-Based Medication Safety, and 3) Predictive Modeling for Clinical Outcome; and the NIH funded 4) Semi-Automated Clinical Trial Eligibility Screening, 5) Pediatric eMERGE, and 6) EHR-based Neonatal Intensive Care Automated Error Detection projects.


The Solti Lab draws its methods from multiple disciplines:
  • Statistics
  • Computational Linguistics
  • Artificial Intelligence
  • Health Services Research