This papers reports on the development of spoken dialog system as a tool for real-time data collection for healthcare, life and behavioral science. Specifically, we implemented a dialog system, Pain Monitoring Voice Diary, for monitoring chronic pain patients. We discuss the requirements and characteristics of this application, specifically, the needs for adaptive level of user support and high and controllable accuracy of data capture, and show their implications for the design of Pain Monitoring Voice Diary. In usability study involving 118 dialog sessions with 24 volunteers we measured 98% data capture and 80% dialog efficiency, as estimated by percentage of task-oriented prompts.