Clinicians use free-text to conveniently capture rich information about patients. Care providers are likely to continue using narratives and first-person stories in Electronic Medical Records (EMRs) due to their convenience and utility, which complicates information extraction for computation and analysis. Despite advances in Natural Language Processing (NLP) techniques, building models is often expensive and time-consuming. Current approaches require a long collaboration between clinicians and data-scientists. Clinicians provide annotations and training data, while data-scientists build the models. With the current approaches, the domain experts - clinicians and clinical researchers - do not have provisions to inspect these models and give feedback. This forms a barrier to NLP adoption in the clinical domain by limiting the power and utility of real-world applications.
Building models interactively can help narrow the gap between clinicians and data-scientists. Interactive learning systems may allow clinicians, without machine learning experience, to build NLP models on their own and also reduce the need for prior annotations upfront. These systems make it feasible to extract understanding from unstructured text in patient records; classifying documents against clinical concepts, summarizing records and other sophisticated NLP tasks. Interactive systems enable end-users to review model outputs and make corrections to build model revisions within an closed feedback loop.
Interactive methods are particularly attractive for clinical text due to the diversity of tasks that need customized training data. I demonstrate this approach by building and evaluating prototype systems for both clinical care and research applications. I built NLPReViz as an interactive tool for clinicians to train and build binary NLP models on their own for retrospective review of colonoscopy procedure notes. Next, I extended this effort to design an intelligent signout tool to identify incidental findings in a clinical care setting. I followed a two-step evaluation with clinicians as study participants: a usability evaluation to demonstrate feasibility and overall usefulness of the tool, followed by an empirical evaluation to evaluate model correctness and utility. Lessons learned from the development and evaluation of these prototypes will provide insight into the generalized design of interactive NLP systems for wider clinical applications.
After participating in this activity, the learner should be better able to:
- Understand interactive system development
- Discuss the use of NLP for clinical work
- Understand usability studies of interactive NLP development
Gaurav Trivedi, MS, B.Tech
University of Pittsburgh
Gaurav is a PhD Candidate in Intelligent Systems Program (Artificial Intelligence), School of Computing and Information at University of Pittsburgh. His dissertation work is on designing interactive methods for natural language processing on clinical records. He is working with Dr. Harry Hochheiser from the Department of Biomedical Informatics, along with a group led by Dr. Shyam Visweswaran on an NIH funded project on “Development and Evaluation of a Learning Electronic Medical Record System." Previously, he worked in collaboration with the NLP group: Dr. Janyce Wiebe, Dr. Rebecca Hwa and Dr. Wendy Chapman on an NIH funded project on interactive review and revision of NLP models for retrospective research on clinical notes. He holds a Master of Science degree from University of Pittsburgh and an engineering bachelor’s degree in Information Technology from National Institute of Technology Karnataka, Surathkal. He worked with Nvidia before joining graduate school.