Learn more about RTI's work in data science at the 2020 International Conference on Health Policy Statistics (ICHPS), held January 6-8 in San Diego, CA.
Organized by the American Statistical Association, ICHPS provides a forum for discussing research needs and solutions to methodological challenges in the design of studies and analysis of data for health policy research. Throughout the last 25 years, ICHPS has played an important role in the dissemination process of health policy and health services statistics, and this year's conference theme is Leveraging Data to Shape the Future.
RTI experts will present their work at the following session:
CS04: Statistical Learning Methods for Health Care Innovation
Tuesday, Janaury 7, 2020 9:00am - 10:45am
Topic: Machine Learning for Medical Coding in Health Care Surveys
Abstract: Manually coding free-form text responses in surveys can be a time-intensive and expensive process. For health care surveys, the process of medical coding is particularly complex due to the need for medical domain knowledge, the varying quality of clinical notations, and the large number of classification codes. Given the challenges posed to medical coders and the constraints placed on statistical agencies to develop high-quality estimates within budget, machine learning techniques offer potential gains in both efficiency and quality. In this talk, we explore a machine learning approach for assigning medical codes to clinical verbatim text found in medical records for patient visits from the 2016 and 2017 National Ambulatory Medical Care Survey (NAMCS) and the National Hospital Ambulatory Medical Care Survey – Emergency Department (NHAMCS-ED). We discuss the process of creating machine learning models, evaluating the performance of a benchmark model, and potential use cases. While the current work suggests that models still underperform compared to trained medical coders for this difficult task, creative human-augmented solutions may benefit the manual coding process.
Steven B. Cohen, PhD
Topic: Fast-Track Innovations in Estimation and Analytics for Large National Health Surveys
Abstract: : A high degree of rigor is essential in the statistical integrity of analytic national data resources used to inform public health and healthcare policy and action. In this vein, statistical and analytic staff devote substantial time and effort to implement estimation, imputation and analytic tasks, which are essential components of the analytic databases derived from national or sub-national health care surveys and related data collections. This presentation focuses on the development and implementation of machine learning (ML) enhanced applications to fast track estimation procedures for national health and health care survey efforts that achieve efficiencies in terms of cost and time while satisfying well defined levels of accuracy that ensure data integrity. Attention is given to enhanced processes that serve as an alternative solution to manual, repetitive or time-intensive tasks. Examples are provided with applications to national health survey efforts that include the Medical Expenditure Panel Survey.
Learn more about RTI's growing capabilities in data science and how they can be applied to emerging issues in health care.