Machine Learning for Medical Coding in Healthcare Surveys.

Objectives Medical coding, or the translation of healthcare information into numeric codes, is expensive and time intensive. This exploratory study evaluates the use of machine learning classifiers to perform automated medical coding for large statistical healthcare surveys.

Web-Based Quality Assurance Process Drives Improvements in Obstetric Ultrasound in 5 Low- and Middle-Income Countries.

High quality is important in medical imaging, yet in many geographic areas, highly skilled sonographers are in short supply. Advances in Internet capacity along with the development of reliable portable ultrasounds have created an opportunity to provide centralized remote quality assurance (QA) for ultrasound exams performed at rural sites worldwide. We sought to harness these advances by developing a web-based tool to facilitate QA activities for newly trained sonographers who were taking part in a cluster randomized trial investigating the role of limited obstetric ultrasound to improve pregnancy outcomes in 5 low- and middle-income countries. We were challenged by connectivity issues, by country-specific needs for website usability, and by the overall need for a high-throughput system. After systematically addressing these needs, the resulting QA website helped drive ultrasound quality improvement across all 5 countries. It now offers the potential for adoption by future ultrasound- or imaging-based global health initiatives.