What if you could turn communication skills from an art into a science? I led the development of software that can automatically analyse and visualise aspects of a conversation from a video and transcript. This is a meaningful application of machine analysis to a human domain, and cuts the time it takes someone to examine or explore a conversation dramatically.
Poor communication is a major factor in 40% of adverse patient events (medical error) and 70% of those that cause patients serious harm. This project was set up to see if we could bring science (and computer science) to bear on how medical communication skills are assessed. I was the first (and often only) full-time employee on the project, and managed the development of the technology.
The project was unusual within NICTA, as the Research Leader (A/Prof Marcus Watson) was a part-time member of staff - he was a senior director in the Queensland health service, theoretically contributed to us one day per week although his schedule meant he had much less contact with the project team than that. My role as the senior engineer and technical lead was to manage the day-to-day running of the project -- everything from chief architect, to product management, hiring other programmers, communicating with the public, and writing the research papers. We also had by far the smallest budget of any project within NICTA, and needed to deliver a complex and novel product in a short timeframe. I am pleased to say that we succeeded.
(More to come - experimental application of the software within University of Queensland ocurring in 2011)