Managers of operating rooms (ORs) and of units upstream (e.g., ambulatory surgery) and downstream (e.g., intensive care and post-anesthesia care) of the OR require real-time information about OR occupancy. Which ORs are in use, and when will each ongoing operation end? This information is used to make decisions about how to assign staff, when to prepare patients for the OR, when to schedule add-on cases, when to move cases, and how to prioritize room cleanups (Dexter et at. 2004). It is typically gathered by OR managers manually, by walking to each OR and estimating the time to case completion. This paper presents a system for determining the state of an ongoing operation automatically from video. Support vector machines are trained to identify relevant image features, and hidden Markov models are trained to use these features to compute a sequence of OR states from the video. The system was tested on video captured over a 24 hour period in one of the 19 operating rooms in Baltimore's R. Adams Crowley Shock Trauma Center. It was found to be more accurate and have less delay while providing more fine-grained state information than the current state-of-the-art system based on patient vital signs used by the Shock Trauma Center.
[1]
Thorsten Joachims,et al.
Making large-scale support vector machine learning practical
,
1999
.
[2]
Shih-Fu Chang,et al.
Structure analysis of soccer video with hidden Markov models
,
2002,
2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[3]
Yan Xiao,et al.
An Algorithm for Processing Vital Sign Monitoring Data to Remotely Identify Operating Room Occupancy in Real-Time
,
2005,
Anesthesia and analgesia.
[4]
Andrew J. Viterbi,et al.
Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
,
1967,
IEEE Trans. Inf. Theory.
[5]
Yan Xiao,et al.
Making Management Decisions on the Day of Surgery Based on Operating Room Efficiency and Patient Waiting Times
,
2004,
Anesthesiology.
[6]
Lawrence R. Rabiner,et al.
A tutorial on hidden Markov models and selected applications in speech recognition
,
1989,
Proc. IEEE.
[7]
Alexander J. Smola,et al.
Learning with kernels
,
1998
.