Anomaly detection in time series radiotherapy treatment data

Tamara B. Sipes, Homa Karimabadi, Steve Jiang, Kevin Moore, Nan Li, Joseph R. Barr

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The work presented here resulted in a valuable innovative technology tool for automatic detection of catastrophic errors in cancer radiotherapy, adding an important safeguard for patient safety. We designed a tool for Dynamic Modeling and Prediction of Radiotherapy Treatment Deviations from Intended Plans (Smart Tool) to automatically detect and highlight potential errors in a radiotherapy treatment plan, based on the data from several thousand prostate cancer treatments at Moore Cancer Research Center at University of California San Diego. Smart Tool determines if the treatment parameters are valid, against a previously built Predictive Model of a Medical Error (PMME). Smart Tool has the following main features: 1) It communicates with a radiotherapy treatment management system, checking all the treatment parameters in the background prior to execution, and after the human expert QA is completed, 2) The anomalous treatment parameters, if any, are detected using an innovative intelligent algorithm in a completely automatic and unsupervised manner, 3) It is a self-learning and constantly evolving system, the model is dynamically updated with the new treatment data, 4) It incorporates expert knowledge through the feedback loop of the dynamic process which updates the model with any new false positives (FP) and false negatives (FN), 4) When an outlier treatment parameter is detected, Smart Tool works by preventing the plan execution and highlighting the parameter for human intervention, 5) It is aimed at catastrophic errors, not small errors.

Original languageEnglish (US)
Title of host publicationProceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014
PublisherIEEE Computer Society
Pages324-329
Number of pages6
ISBN (Print)9781479940028
DOIs
StatePublished - 2014
Event8th IEEE International Conference on Semantic Computing, ICSC 2014 - Newport Beach, CA, United States
Duration: Jun 16 2014Jun 18 2014

Other

Other8th IEEE International Conference on Semantic Computing, ICSC 2014
CountryUnited States
CityNewport Beach, CA
Period6/16/146/18/14

Fingerprint

Radiotherapy
Time series
Oncology
Feedback

Keywords

  • anomaly detection
  • semi-supervised learning
  • time series data analysis

ASJC Scopus subject areas

  • Software

Cite this

Sipes, T. B., Karimabadi, H., Jiang, S., Moore, K., Li, N., & Barr, J. R. (2014). Anomaly detection in time series radiotherapy treatment data. In Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014 (pp. 324-329). [6882049] IEEE Computer Society. https://doi.org/10.1109/ICSC.2014.64

Anomaly detection in time series radiotherapy treatment data. / Sipes, Tamara B.; Karimabadi, Homa; Jiang, Steve; Moore, Kevin; Li, Nan; Barr, Joseph R.

Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society, 2014. p. 324-329 6882049.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sipes, TB, Karimabadi, H, Jiang, S, Moore, K, Li, N & Barr, JR 2014, Anomaly detection in time series radiotherapy treatment data. in Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014., 6882049, IEEE Computer Society, pp. 324-329, 8th IEEE International Conference on Semantic Computing, ICSC 2014, Newport Beach, CA, United States, 6/16/14. https://doi.org/10.1109/ICSC.2014.64
Sipes TB, Karimabadi H, Jiang S, Moore K, Li N, Barr JR. Anomaly detection in time series radiotherapy treatment data. In Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society. 2014. p. 324-329. 6882049 https://doi.org/10.1109/ICSC.2014.64
Sipes, Tamara B. ; Karimabadi, Homa ; Jiang, Steve ; Moore, Kevin ; Li, Nan ; Barr, Joseph R. / Anomaly detection in time series radiotherapy treatment data. Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014. IEEE Computer Society, 2014. pp. 324-329
@inproceedings{66cbe61023a048d7bb54267d9b4975d8,
title = "Anomaly detection in time series radiotherapy treatment data",
abstract = "The work presented here resulted in a valuable innovative technology tool for automatic detection of catastrophic errors in cancer radiotherapy, adding an important safeguard for patient safety. We designed a tool for Dynamic Modeling and Prediction of Radiotherapy Treatment Deviations from Intended Plans (Smart Tool) to automatically detect and highlight potential errors in a radiotherapy treatment plan, based on the data from several thousand prostate cancer treatments at Moore Cancer Research Center at University of California San Diego. Smart Tool determines if the treatment parameters are valid, against a previously built Predictive Model of a Medical Error (PMME). Smart Tool has the following main features: 1) It communicates with a radiotherapy treatment management system, checking all the treatment parameters in the background prior to execution, and after the human expert QA is completed, 2) The anomalous treatment parameters, if any, are detected using an innovative intelligent algorithm in a completely automatic and unsupervised manner, 3) It is a self-learning and constantly evolving system, the model is dynamically updated with the new treatment data, 4) It incorporates expert knowledge through the feedback loop of the dynamic process which updates the model with any new false positives (FP) and false negatives (FN), 4) When an outlier treatment parameter is detected, Smart Tool works by preventing the plan execution and highlighting the parameter for human intervention, 5) It is aimed at catastrophic errors, not small errors.",
keywords = "anomaly detection, semi-supervised learning, time series data analysis",
author = "Sipes, {Tamara B.} and Homa Karimabadi and Steve Jiang and Kevin Moore and Nan Li and Barr, {Joseph R.}",
year = "2014",
doi = "10.1109/ICSC.2014.64",
language = "English (US)",
isbn = "9781479940028",
pages = "324--329",
booktitle = "Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Anomaly detection in time series radiotherapy treatment data

AU - Sipes, Tamara B.

AU - Karimabadi, Homa

AU - Jiang, Steve

AU - Moore, Kevin

AU - Li, Nan

AU - Barr, Joseph R.

PY - 2014

Y1 - 2014

N2 - The work presented here resulted in a valuable innovative technology tool for automatic detection of catastrophic errors in cancer radiotherapy, adding an important safeguard for patient safety. We designed a tool for Dynamic Modeling and Prediction of Radiotherapy Treatment Deviations from Intended Plans (Smart Tool) to automatically detect and highlight potential errors in a radiotherapy treatment plan, based on the data from several thousand prostate cancer treatments at Moore Cancer Research Center at University of California San Diego. Smart Tool determines if the treatment parameters are valid, against a previously built Predictive Model of a Medical Error (PMME). Smart Tool has the following main features: 1) It communicates with a radiotherapy treatment management system, checking all the treatment parameters in the background prior to execution, and after the human expert QA is completed, 2) The anomalous treatment parameters, if any, are detected using an innovative intelligent algorithm in a completely automatic and unsupervised manner, 3) It is a self-learning and constantly evolving system, the model is dynamically updated with the new treatment data, 4) It incorporates expert knowledge through the feedback loop of the dynamic process which updates the model with any new false positives (FP) and false negatives (FN), 4) When an outlier treatment parameter is detected, Smart Tool works by preventing the plan execution and highlighting the parameter for human intervention, 5) It is aimed at catastrophic errors, not small errors.

AB - The work presented here resulted in a valuable innovative technology tool for automatic detection of catastrophic errors in cancer radiotherapy, adding an important safeguard for patient safety. We designed a tool for Dynamic Modeling and Prediction of Radiotherapy Treatment Deviations from Intended Plans (Smart Tool) to automatically detect and highlight potential errors in a radiotherapy treatment plan, based on the data from several thousand prostate cancer treatments at Moore Cancer Research Center at University of California San Diego. Smart Tool determines if the treatment parameters are valid, against a previously built Predictive Model of a Medical Error (PMME). Smart Tool has the following main features: 1) It communicates with a radiotherapy treatment management system, checking all the treatment parameters in the background prior to execution, and after the human expert QA is completed, 2) The anomalous treatment parameters, if any, are detected using an innovative intelligent algorithm in a completely automatic and unsupervised manner, 3) It is a self-learning and constantly evolving system, the model is dynamically updated with the new treatment data, 4) It incorporates expert knowledge through the feedback loop of the dynamic process which updates the model with any new false positives (FP) and false negatives (FN), 4) When an outlier treatment parameter is detected, Smart Tool works by preventing the plan execution and highlighting the parameter for human intervention, 5) It is aimed at catastrophic errors, not small errors.

KW - anomaly detection

KW - semi-supervised learning

KW - time series data analysis

UR - http://www.scopus.com/inward/record.url?scp=84906969151&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84906969151&partnerID=8YFLogxK

U2 - 10.1109/ICSC.2014.64

DO - 10.1109/ICSC.2014.64

M3 - Conference contribution

AN - SCOPUS:84906969151

SN - 9781479940028

SP - 324

EP - 329

BT - Proceedings - 2014 IEEE International Conference on Semantic Computing, ICSC 2014

PB - IEEE Computer Society

ER -