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 proceedingConference 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 languageEnglish (US)
Title of host publicationACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Number of pages1
ISBN (Electronic)9781450347228
DOIs
StatePublished - Aug 20 2017
Event8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017 - Boston, United States
Duration: Aug 20 2017Aug 23 2017

Other

Other8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2017
CountryUnited States
CityBoston
Period8/20/178/23/17

Fingerprint

Radiotherapy
Toxicity
Genes
Genome
Prostatic Neoplasms
Biological Phenomena
Gene Ontology
Insurance Benefits
Area Under Curve
Ontology
Quality of Life
Health
Forests

Keywords

  • Genome wide association studies
  • Radiotherapy
  • Random forests

ASJC Scopus subject areas

  • Software
  • Biomedical Engineering
  • Health Informatics
  • Computer Science Applications

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; Deasy, Joseph O.; Rosenstein, Barry; Oh, Jung Hun.

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 proceedingConference 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 https://doi.org/10.1145/3107411.3108201
Lee, Sangkyu ; Ostrer, Harry ; Kerns, Sarah ; Deasy, Joseph O. ; Rosenstein, Barry ; Oh, Jung Hun. / Preconditioned random forest regression : Application to genome-wide study for radiotherapy toxicity prediction. ACM-BCB 2017 - Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2017.
@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 = "8",
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",

}

TY - GEN

T1 - Preconditioned random forest regression

T2 - Application to genome-wide study for radiotherapy toxicity prediction

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

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

PB - Association for Computing Machinery, Inc

ER -