Online time and resource management based on surgical workflow time series analysis

PurposeHospitals’ effectiveness and efficiency can be enhanced by automating the resource and time management of the most cost-intensive unit in the hospital: the operating room (OR). The key elements required for the ideal organization of hospital staff and technical resources (such as instruments in the OR) are an exact online forecast of both the surgeon’s resource usage and the remaining intervention time.MethodsThis paper presents a novel online approach relying on time series analysis and the application of a linear time-variant system. We calculated the power spectral density and the spectrogram of surgical perspectives (e.g., used instrument) of interest to compare several surgical workflows.ResultsConsidering only the use of the surgeon’s right hand during an intervention, we were able to predict the remaining intervention time online with an error of 21 min 45 s ±9 min 59 s for lumbar discectomy. Furthermore, the performance of forecasting of technical resource usage in the next 20 min was calculated for a combination of spectral analysis and the application of a linear time-variant system (sensitivity: 74 %; specificity: 75 %) focusing on just the use of surgeon’s instrument in question.ConclusionThe outstanding benefit of these methods is that the automated recording of surgical workflows has minimal impact during interventions since the whole set of surgical perspectives need not be recorded. The resulting predictions can help various stakeholders such as OR staff and hospital technicians. Moreover, reducing resource conflicts could well improve patient care.

[1]  Nassir Navab,et al.  Modeling and Online Recognition of Surgical Phases Using Hidden Markov Models , 2008, MICCAI.

[2]  Nassir Navab,et al.  Statistical modeling and recognition of surgical workflow , 2012, Medical Image Anal..

[3]  D. Wolfe,et al.  Nonparametric Statistical Methods. , 1974 .

[4]  James G Wright,et al.  Improving on-time surgical starts in an operating room. , 2010, Canadian journal of surgery. Journal canadien de chirurgie.

[5]  Alan V. Oppenheim,et al.  Discrete-time signal processing (2nd ed.) , 1999 .

[6]  Steven C. Horii,et al.  Workflow in the operating room: review of Arrowhead 2004 seminar on imaging and informatics (Invited Paper) , 2005, SPIE Medical Imaging.

[7]  Kevin Cleary,et al.  OR 2020: the operating room of the future. , 2004, Journal of laparoendoscopic & advanced surgical techniques. Part A.

[8]  Stefanie Speidel,et al.  Ontology-based prediction of surgical events in laparoscopic surgery , 2013, Medical Imaging.

[9]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[10]  Davide Caramella,et al.  Multislice computed tomography (MSCT) and 3D reconstruction of Etruscan funerary urns in archaeology , 2012, CARS 2012.

[11]  David A. Lubarsky,et al.  Use of Operating Room Information System Data to Predict the Impact of Reducing Turnover Times on Staffing Costs , 2003, Anesthesia and analgesia.

[12]  Julian M Goldman,et al.  Introducing new technology into the operating room: measuring the impact on job performance and satisfaction. , 2005, Surgery.

[13]  Jont B. Allen.  Applications of the short time Fourier transform to speech processing and spectral analysis , 1982, IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Nassir Navab,et al.  Recovery of Surgical Workflow Without Explicit Models , 2006, MICCAI.

[15]  Michael W. Vannier,et al.  The operating room and the need for an IT infrastructure and standards , 2006, International Journal of Computer Assisted Radiology and Surgery.

[16]  Thomas Neumuth,et al.  Multi-perspective workflow modeling for online surgical situation models , 2015, J. Biomed. Informatics.

[17]  Sophocles J. Orfanidis,et al.  Introduction to signal processing , 1995 .

[18]  J. Ledolter,et al.  Automatic Updating of Times Remaining in Surgical Cases Using Bayesian Analysis of Historical Case Duration Data and “Instant Messaging” Updates from Anesthesia Providers , 2009, Anesthesia and analgesia.

[19]  Pierre Jannin,et al.  Surgical process modelling: a review , 2014, International Journal of Computer Assisted Radiology and Surgery.

[20]  Eve A. Riskin,et al.  Signals, Systems, and Transforms , 1994 .

[21]  E. Steyerberg,et al.  Predicting the Unpredictable: A New Prediction Model for Operating Room Times Using Individual Characteristics and the Surgeon's Estimate , 2010, Anesthesiology.

[22]  Germain Forestier,et al.  Optimal Sub-Sequence Matching for the Automatic Prediction of Surgical Tasks , 2015, AIME.

[23]  André Baumgart,et al.  Status quo and current trends of operating room management in Germany , 2010, Current opinion in anaesthesiology.

[24]  Thomas Neumuth,et al.  Similarity metrics for surgical process models , 2012, Artif. Intell. Medicine.

[25]  Thomas Neumuth,et al.  Analysis of surgical intervention populations using generic surgical process models , 2010, International Journal of Computer Assisted Radiology and Surgery.

[26]  Steven C. Horii,et al.  Workflow in the operating room: A summary review of the Arrowhead 2004 Seminar on Imaging and Informatics , 2005 .

[27]  T. Neumuth,et al.  Structured recording of intraoperative surgical workflows , 2006, SPIE Medical Imaging.

[28]  Germain Forestier,et al.  Classification of surgical processes using dynamic time warping , 2012, J. Biomed. Informatics.

[29]  T. Neumuth,et al.  Recording of Surgical Processes: A Study Comparing Senior and Junior Neurosurgeons During Lumbar Disc Herniation Surgery , 2010, Neurosurgery.

[30]  F. Hlawatsch,et al.  Linear and quadratic time-frequency signal representations , 1992, IEEE Signal Processing Magazine.

[31]  Animesh Kumar,et al.  Towards an intelligent hospital environment: OR of the future. , 2005, Studies in health technology and informatics.

[32]  Thomas Neumuth,et al.  Vision-based online recognition of surgical activities , 2014, International Journal of Computer Assisted Radiology and Surgery.

[33]  Thomas Neumuth,et al.  Online recognition of surgical instruments by information fusion , 2012, International Journal of Computer Assisted Radiology and Surgery.

[34]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[35]  Hong-Wei Li,et al.  Automatic subarachnoid space segmentation and hemorrhage detection in clinical head CT scans , 2012, International Journal of Computer Assisted Radiology and Surgery.

[36]  S. Mitra,et al.  Handbook for Digital Signal Processing , 1993 .

[37]  Pieter S. Stepaniak,et al.  Modeling and prediction of surgical procedure times , 2009 .

[38]  Nick Sevdalis,et al.  Managing intraoperative stress: what do surgeons want from a crisis training program? , 2009, American journal of surgery.

[39]  Thomas Neumuth,et al.  Intervention time prediction from surgical low-level tasks , 2013, J. Biomed. Informatics.