Document Type

Technical Report

Publication Date


Technical Report Number



As information technology permeates healthcare (particularly provider-facing systems), maximizing system effectiveness requires the ability to document and analyze tricky or troublesome usage scenarios. However, real-world medical applications are typically replete with privacy-sensitive data regarding patients, diagnoses, clinicians, and EMR user interface details; any instrumentation for screen capture (capturing and recording the scenario depicted on the screen) needs to respect these privacy constraints. Furthermore, real-world medical informatics systems are typically composed of modules from many sources, mission-critical and often closed-source; any instrumentation for screen capture cannot rely on access to structured output or software internals. In this paper, we present a solution: a system that combines keyboard video mouse (KVM) capture with automatic text redaction (and interactively selectable unredaction) to produce precise technical content that can enrich stakeholder communications and improve end-user influence on system evolution. KVM-based capture makes our system both application and operating-system independent because it eliminates software-interface dependencies on capture targets. Using a corpus of EMR screenshots, we present empirical measurements of redaction effectiveness and processing latency to demonstrate system performances. We discuss how these techniques can translate into instrumentation systems that improve real-world medical informatics deployments.