Learning to Identify Locally Actionable Health Anomalies
Kuang Chen, Emma Brunskill1, Joseph M. Hellerstein and Tapan Parikh2
Local information access (LIA) programs tap into existing public health report flows and present data in simple and useful ways to ground staff. LIAs are a key component of rural health systems in developing regions. Their potential benefits include more evidence-based decision making and optimizations at a local scale, as well as improved service delivery and data quality. Our fledgling LIA program in rural Uganda currently provides clinicians with a small set of static data visualizations f or discussion. To increase the program effectiveness, we propose using active learning to automatically identify the clinically interesting and actionable data visualizations. We aim to create an adaptive tool that learns from local clinicians' decision making processes to predict and display the visualizations that show actionable anomalies.
2School of Information