Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology

Fumbeya Marungo, Scott Robertson, Harry Quon, John Rhee, Hilary Paisley, Russell H Taylor, Todd McNutt

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

Abstract

The common approach to assessing risk in radiation oncology treatment uses Lyman-Kutcher-Burman (LKB) derived models to calculate normal tissue complication probability (NTCP). LKB is not sufficiently robust to capture the modern clinical reality of three-dimensional intensity modulated radiation therapy (IMRT) treatments, the approach accounts for only two factors - Dmax and Veff. We present a data science platform designed to facilitate the rapid creation of data-derived NTCP models. The platform extracts native Philips Pinnacle data such as dose grids and contoured regions using the cross-vendor DICOM RT standard. Further, outcome data is encoded using Common Terminology Criteria for Adverse Events 4.0. Thus, the platform exploits the normal clinical workflow and information encoded with a standard ontology. Over the course of less than three weeks we used the platform to create NTCP models for two complications (xerostomia and voice dysfunction due to parotid and larynx irradiation, respectively). We assess the resulting platform with a focus on its context within a Learning Health System (LHS). We believe that the system reported can serve as a guide to the development of radiation oncology data science platforms in particular and local-level LHS components in general.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Hawaii International Conference on System Sciences
PublisherIEEE Computer Society
Pages3132-3140
Number of pages9
Volume2015-March
ISBN (Print)9781479973675
DOIs
StatePublished - Mar 26 2015
Event48th Annual Hawaii International Conference on System Sciences, HICSS 2015 - Kauai, United States
Duration: Jan 5 2015Jan 8 2015

Other

Other48th Annual Hawaii International Conference on System Sciences, HICSS 2015
CountryUnited States
CityKauai
Period1/5/151/8/15

Fingerprint

Oncology
Tissue
Radiation
Planning
Health
Digital Imaging and Communications in Medicine (DICOM)
Radiotherapy
Terminology
Ontology
Irradiation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Marungo, F., Robertson, S., Quon, H., Rhee, J., Paisley, H., Taylor, R. H., & McNutt, T. (2015). Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology. In Proceedings of the Annual Hawaii International Conference on System Sciences (Vol. 2015-March, pp. 3132-3140). [7070193] IEEE Computer Society. https://doi.org/10.1109/HICSS.2015.378

Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology. / Marungo, Fumbeya; Robertson, Scott; Quon, Harry; Rhee, John; Paisley, Hilary; Taylor, Russell H; McNutt, Todd.

Proceedings of the Annual Hawaii International Conference on System Sciences. Vol. 2015-March IEEE Computer Society, 2015. p. 3132-3140 7070193.

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

Marungo, F, Robertson, S, Quon, H, Rhee, J, Paisley, H, Taylor, RH & McNutt, T 2015, Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology. in Proceedings of the Annual Hawaii International Conference on System Sciences. vol. 2015-March, 7070193, IEEE Computer Society, pp. 3132-3140, 48th Annual Hawaii International Conference on System Sciences, HICSS 2015, Kauai, United States, 1/5/15. https://doi.org/10.1109/HICSS.2015.378
Marungo F, Robertson S, Quon H, Rhee J, Paisley H, Taylor RH et al. Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology. In Proceedings of the Annual Hawaii International Conference on System Sciences. Vol. 2015-March. IEEE Computer Society. 2015. p. 3132-3140. 7070193 https://doi.org/10.1109/HICSS.2015.378
Marungo, Fumbeya ; Robertson, Scott ; Quon, Harry ; Rhee, John ; Paisley, Hilary ; Taylor, Russell H ; McNutt, Todd. / Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology. Proceedings of the Annual Hawaii International Conference on System Sciences. Vol. 2015-March IEEE Computer Society, 2015. pp. 3132-3140
@inproceedings{4e82e2af930940deaf285d53bdaf58d7,
title = "Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology",
abstract = "The common approach to assessing risk in radiation oncology treatment uses Lyman-Kutcher-Burman (LKB) derived models to calculate normal tissue complication probability (NTCP). LKB is not sufficiently robust to capture the modern clinical reality of three-dimensional intensity modulated radiation therapy (IMRT) treatments, the approach accounts for only two factors - Dmax and Veff. We present a data science platform designed to facilitate the rapid creation of data-derived NTCP models. The platform extracts native Philips Pinnacle data such as dose grids and contoured regions using the cross-vendor DICOM RT standard. Further, outcome data is encoded using Common Terminology Criteria for Adverse Events 4.0. Thus, the platform exploits the normal clinical workflow and information encoded with a standard ontology. Over the course of less than three weeks we used the platform to create NTCP models for two complications (xerostomia and voice dysfunction due to parotid and larynx irradiation, respectively). We assess the resulting platform with a focus on its context within a Learning Health System (LHS). We believe that the system reported can serve as a guide to the development of radiation oncology data science platforms in particular and local-level LHS components in general.",
author = "Fumbeya Marungo and Scott Robertson and Harry Quon and John Rhee and Hilary Paisley and Taylor, {Russell H} and Todd McNutt",
year = "2015",
month = "3",
day = "26",
doi = "10.1109/HICSS.2015.378",
language = "English (US)",
isbn = "9781479973675",
volume = "2015-March",
pages = "3132--3140",
booktitle = "Proceedings of the Annual Hawaii International Conference on System Sciences",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Creating a data science platform for developing complication risk models for personalized treatment planning in radiation oncology

AU - Marungo, Fumbeya

AU - Robertson, Scott

AU - Quon, Harry

AU - Rhee, John

AU - Paisley, Hilary

AU - Taylor, Russell H

AU - McNutt, Todd

PY - 2015/3/26

Y1 - 2015/3/26

N2 - The common approach to assessing risk in radiation oncology treatment uses Lyman-Kutcher-Burman (LKB) derived models to calculate normal tissue complication probability (NTCP). LKB is not sufficiently robust to capture the modern clinical reality of three-dimensional intensity modulated radiation therapy (IMRT) treatments, the approach accounts for only two factors - Dmax and Veff. We present a data science platform designed to facilitate the rapid creation of data-derived NTCP models. The platform extracts native Philips Pinnacle data such as dose grids and contoured regions using the cross-vendor DICOM RT standard. Further, outcome data is encoded using Common Terminology Criteria for Adverse Events 4.0. Thus, the platform exploits the normal clinical workflow and information encoded with a standard ontology. Over the course of less than three weeks we used the platform to create NTCP models for two complications (xerostomia and voice dysfunction due to parotid and larynx irradiation, respectively). We assess the resulting platform with a focus on its context within a Learning Health System (LHS). We believe that the system reported can serve as a guide to the development of radiation oncology data science platforms in particular and local-level LHS components in general.

AB - The common approach to assessing risk in radiation oncology treatment uses Lyman-Kutcher-Burman (LKB) derived models to calculate normal tissue complication probability (NTCP). LKB is not sufficiently robust to capture the modern clinical reality of three-dimensional intensity modulated radiation therapy (IMRT) treatments, the approach accounts for only two factors - Dmax and Veff. We present a data science platform designed to facilitate the rapid creation of data-derived NTCP models. The platform extracts native Philips Pinnacle data such as dose grids and contoured regions using the cross-vendor DICOM RT standard. Further, outcome data is encoded using Common Terminology Criteria for Adverse Events 4.0. Thus, the platform exploits the normal clinical workflow and information encoded with a standard ontology. Over the course of less than three weeks we used the platform to create NTCP models for two complications (xerostomia and voice dysfunction due to parotid and larynx irradiation, respectively). We assess the resulting platform with a focus on its context within a Learning Health System (LHS). We believe that the system reported can serve as a guide to the development of radiation oncology data science platforms in particular and local-level LHS components in general.

UR - http://www.scopus.com/inward/record.url?scp=84944269566&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944269566&partnerID=8YFLogxK

U2 - 10.1109/HICSS.2015.378

DO - 10.1109/HICSS.2015.378

M3 - Conference contribution

AN - SCOPUS:84944269566

SN - 9781479973675

VL - 2015-March

SP - 3132

EP - 3140

BT - Proceedings of the Annual Hawaii International Conference on System Sciences

PB - IEEE Computer Society

ER -