Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction

Sangkyu Lee; Harry Ostrer; Sarah Kerns; Joseph O. Deasy; Barry Rosenstein; Jung Hun Oh

doi:10.1145/3107411.3108201

Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction

Sangkyu Lee, Harry Ostrer, Sarah Kerns, Joseph O. Deasy, Barry Rosenstein, Jung Hun Oh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Urinary toxicity after radiotherapy (RT) limits the quality of life of prostate cancer patients, and clinically actionable prediction has yet to be achieved. We aim to exploit genome-wide variants to accurately identify patients at higher congenital toxicity risk. We applied preconditioned random forest regression (PRFR) to predict four urinary symptoms. For a weak stream endpoint, the PRFR model achieved an area under the curve (AUC) of 0.7 on holdout validation. Preconditioning enhanced the performance of random forest. Gene ontology (GO) analysis showed that neurogenic biological processes are associated with the toxicity. Upon further validation, the predictive model can be used to potentially benefit the health of prostate cancer patients treated with radiotherapy.

Original language	English (US)
Title of host publication	ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
Publisher	Association for Computing Machinery, Inc
Number of pages	1
ISBN (Electronic)	9781450347228
DOIs	https://doi.org/10.1145/3107411.3108201
State	Published - Aug 20 2017
Event	8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017 - Boston, United States Duration: Aug 20 2017 → Aug 23 2017

Other

Other	8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017
Country/Territory	United States
City	Boston
Period	8/20/17 → 8/23/17

Keywords

Genome wide association studies
Radiotherapy
Random forests

ASJC Scopus subject areas

Software
Biomedical Engineering
Health Informatics
Computer Science Applications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3107411.3108201

Cite this

Lee, S., Ostrer, H., Kerns, S., Deasy, J. O., Rosenstein, B., & Oh, J. H. (2017). Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction. In ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics Association for Computing Machinery, Inc. https://doi.org/10.1145/3107411.3108201

Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction. / Lee, Sangkyu; Ostrer, Harry; Kerns, Sarah et al.
ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lee, S, Ostrer, H, Kerns, S, Deasy, JO, Rosenstein, B & Oh, JH 2017, Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction. in ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017, Boston, United States, 8/20/17. https://doi.org/10.1145/3107411.3108201

Lee S, Ostrer H, Kerns S, Deasy JO, Rosenstein B, Oh JH. Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction. In ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2017 doi: 10.1145/3107411.3108201

@inproceedings{8b540c983ab14e3d98f37d9beb05e9af,

title = "Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction",

abstract = "Urinary toxicity after radiotherapy (RT) limits the quality of life of prostate cancer patients, and clinically actionable prediction has yet to be achieved. We aim to exploit genome-wide variants to accurately identify patients at higher congenital toxicity risk. We applied preconditioned random forest regression (PRFR) to predict four urinary symptoms. For a weak stream endpoint, the PRFR model achieved an area under the curve (AUC) of 0.7 on holdout validation. Preconditioning enhanced the performance of random forest. Gene ontology (GO) analysis showed that neurogenic biological processes are associated with the toxicity. Upon further validation, the predictive model can be used to potentially benefit the health of prostate cancer patients treated with radiotherapy.",

keywords = "Genome wide association studies, Radiotherapy, Random forests",

author = "Sangkyu Lee and Harry Ostrer and Sarah Kerns and Deasy, {Joseph O.} and Barry Rosenstein and Oh, {Jung Hun}",

year = "2017",

month = aug,

day = "20",

doi = "10.1145/3107411.3108201",

language = "English (US)",

booktitle = "ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics",

publisher = "Association for Computing Machinery, Inc",

note = "8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017 ; Conference date: 20-08-2017 Through 23-08-2017",

}

TY - GEN

T1 - Preconditioned random forest regression

T2 - 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017

AU - Lee, Sangkyu

AU - Ostrer, Harry

AU - Kerns, Sarah

AU - Deasy, Joseph O.

AU - Rosenstein, Barry

AU - Oh, Jung Hun

PY - 2017/8/20

Y1 - 2017/8/20

N2 - Urinary toxicity after radiotherapy (RT) limits the quality of life of prostate cancer patients, and clinically actionable prediction has yet to be achieved. We aim to exploit genome-wide variants to accurately identify patients at higher congenital toxicity risk. We applied preconditioned random forest regression (PRFR) to predict four urinary symptoms. For a weak stream endpoint, the PRFR model achieved an area under the curve (AUC) of 0.7 on holdout validation. Preconditioning enhanced the performance of random forest. Gene ontology (GO) analysis showed that neurogenic biological processes are associated with the toxicity. Upon further validation, the predictive model can be used to potentially benefit the health of prostate cancer patients treated with radiotherapy.

AB - Urinary toxicity after radiotherapy (RT) limits the quality of life of prostate cancer patients, and clinically actionable prediction has yet to be achieved. We aim to exploit genome-wide variants to accurately identify patients at higher congenital toxicity risk. We applied preconditioned random forest regression (PRFR) to predict four urinary symptoms. For a weak stream endpoint, the PRFR model achieved an area under the curve (AUC) of 0.7 on holdout validation. Preconditioning enhanced the performance of random forest. Gene ontology (GO) analysis showed that neurogenic biological processes are associated with the toxicity. Upon further validation, the predictive model can be used to potentially benefit the health of prostate cancer patients treated with radiotherapy.

KW - Genome wide association studies

KW - Radiotherapy

KW - Random forests

UR - http://www.scopus.com/inward/record.url?scp=85031322640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031322640&partnerID=8YFLogxK

U2 - 10.1145/3107411.3108201

DO - 10.1145/3107411.3108201

M3 - Conference contribution

AN - SCOPUS:85031322640

BT - ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

Y2 - 20 August 2017 through 23 August 2017

ER -

Preconditioned random forest regression: Application to genome-wide study for radiotherapy toxicity prediction

Abstract

Other

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this