Promoting breast cancer screening after multiplex genetic panel testing (MGPT) and genetic counseling.

Idos, Gregory; Kurian, Allison W.; Ricker, Charité; Sturgeon, Duveen; Culver, Julie O.; Kingham, Kerry; Koff, Rachel; Chun, Nicolette M.; Rowe‐Teeter, Courtney; Kidd, John; Evans, Brent; Brown, Krystal; Mills, Meredith; Ma, Cindy; Hong, Christine; McDonnell, Kevin; Ladabaum, Uri; Ford, James M.; Gruber, Stephen B.

doi:10.1200/jco.2018.36.15_suppl.1581

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply our methods to data from the University of Southern California (USC) Norris Comprehensive Cancer Center and the Stanford Cancer Institute Cancer Genetics Hereditary Cancer Panel (HCP) study (Idos et al, 2018). Investigators collected these data to study the impact of several genetic mutations on cancer outcomes as well as the role of genetic testing in clinical settings.…”

Section: Usc-stanford Datamentioning

confidence: 99%

“…In Section 4, we conduct a simulation study to compare the effectiveness of GB and Mendelian models in incorporating cancer family history information. In Section 5, we apply this approach to data from the USC-Stanford Cancer Genetics Hereditary Cancer Panel (HCP) study (Idos et al, 2018). Finally, we conclude with a discussion in Section 6.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extending Models Via Gradient Boosting: An Application to Mendelian Models

Huang¹,

Idos²,

Hong³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Improving existing widely-adopted prediction models is often a more efficient and robust way towards progress than training new models from scratch. Existing models may (a) incorporate complex mechanistic knowledge, (b) leverage proprietary information and, (c) have surmounted barriers to adoption. Compared to model training, model improvement and modification receive little attention. In this paper we propose a general approach to model improvement: we combine gradient boosting with any previously developed model to improve model performance while retaining important existing characteristics. To exemplify, we consider the context of Mendelian models, which estimate the probability of carrying genetic mutations that confer susceptibility to disease by using family pedigrees and health histories of family members. Via simulations we show that integration of gradient boosting with an existing Mendelian model can produce an improved model that outperforms both that model and the model built using gradient boosting alone. We illustrate the approach on genetic testing data from the USC-Stanford Cancer Genetics Hereditary Cancer Panel (HCP) study.

show abstract

Section: Usc-stanford Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%