CDM Seminar Series 2003-04


Medical Appointment Scheduler
Ronilda Lacson, MD
MIT Lab for Computer Science and Artificial Intelligence
Doctoral Student in the Clinical Decision Making Group
Thursday, Dec. 5
2:00pm, MIT CSAIL

The first part of this presentation identifies
questions that home hemodialysis patients ask most
frequently from recorded calls that they made to a
dialysis clinic. Knowing these questions that are
important to patients enhance our understanding of how
to best improve their care. The use of automated
systems may enable a quicker response to patients’
needs and alleviate time demands on the personnel that
have to answer these calls. From an initial analysis
of the recorded conversations, the second most
frequent reason for patient calls was for scheduling
concerns. An automated scheduling system was designed
and implemented to address this concern.

The SCHEDULER is a mixed-initiative spoken dialogue
system that allows a patient to schedule an
appointment with a provider over the telephone. The
system was implemented using SPEECHBUILDER, a utility
developed by the Spoken Language System group at
M.I.T. that helps automatically configure human
language technology servers to create a new
conversational system. I will describe the system,
its problems, an initial evaluation and future plans
to address the most common set of questions.

CDM Abstract Archive