• Solti Lab Research

    The Solti lab seeks to develop informatics algorithms and tools to extract all relevant information from the Electronic Health Record (EHR), including information buried in narrative text (e.g. physician or nursing notes).   By developing high performance clinical natural language processing (NLP) methods, the lab seeks to extract information and apply it toward computerized clinical care, patient safety and outcome improvement systems. A long-term research goal is to leverage all EHR data for computerized clinical decision support systems.

    Current Projects

    • Building semi-automated clinical trial eligibility screening software - to provide individualized, electronic medical record-based clinical trial recommendations directly to the patients, resulting in patient empowerment and, it is hoped, gains in clinical trial accrual rates
    • Electronic health record-based medication safety - to develop an EHR-based adverse event detection system
    • Predictive modeling of clinical outcomes - develop new algorithms to model and predict the changes in the clinical status of the patient based on EHR content
    • Automated appendicitis risk stratification - develop an EHR-based automated risk stratification system for Emergency Department appendicitis patients

  • Lab Publications

    Show All

    Halgrim S, Xia F, Solti I, Cadag E, Uzuner O. Extracting Medication Information from Discharge Summaries. Annual Conference of the North American Chapter of the Association for Computational Linguistics, Second Louhi Workshop on Text and Data Mining of Health Documents, June 1-6, 2010; Los Angeles, CA.

    Yetisgen-Yildiz M, Solti I, Halgrim S, Xia F. Preliminary Experiments with Amazon’s Mechanical Turk for Annotating Medical Named Entities. Annual Conference of the North American Chapter of the Association for Computational Linguistics, Creating Speech and Language Data with Amazon's Mechanical Turk, Workshop, June 1-6, 2010; Los Angeles, CA.

    Uzuner O, Solti I, Xia F, Cadag E. Community Annotation Experiment for Ground Truth Generation for the i2b2 Medication Challenge. Journal of the American Medical Informatics Association. 17: 519-523. 2010.

    Uzuner O, Solti I, Cadag E. Extracting Medication Information from Clinical Text. Journal of the American Medical Informatics Association. 17: 514-518. 2010.

    Solti I, Cooke CR, Xia F, Wurfel MM. Automated classification of radiology reports for acute lung injury: Comparison of keyword and machine learning based natural language processing approaches. Proceedings IEEE International Conference Bioinformatics Biomed. 314-319. Nov, 2009.

    Solti I, Aaronson B, Fletcher G, Solti M, Gennari JH, Cooper M, Payne T. Building an automated problem list based on Natural Language Processing: Lessons learned in the early phase of development. AMIA Annual Symposium Proceedings. pp. 687-691. 2008.

  • Contact Us

    Imre Solti, MD, PhD, MA

    Phone: 513-636-2477
    Fax: 513-636-2056
    Email: imre.solti@cchmc.org

    Website: https://research.cchmc.org/solti/