Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Simple Linear Cancer Risk Prediction Models With Novel Features Outperform Complex Approaches

Simple Linear Cancer Risk Prediction Models With Novel Features Outperform Complex Approaches PURPOSEThe ability to accurately predict an individual's risk for cancer is critical to the implementation of precision prevention measures. Current cancer risk predictions are frequently made with simple models that use a few proven risk factors, such as the Gail model for breast cancer, which are easy to interpret, but may theoretically be less accurate than advanced machine learning (ML) models.METHODSWith the UK Biobank, a large prospective study, we developed models that predicted 13 cancer diagnoses within a 10-year time span. ML and linear models fit with all features, linear models fit with 10 features, and externally developed QCancer models, which are available to more than 4,000 general practices, were assessed.RESULTSThe average area under the receiver operator curve (AUC) of the linear models (0.722, SE = 0.015) was greater than the average AUC of the ML models (0.720, SE = 0.016) when all 931 features were used. Linear models with only 10 features generated an average AUC of 0.706 (SE 0.015), which was comparable to the complex models using all features and greater than the average AUC of the QCancer models (0.684, SE 0.021). The high performance of the 10-feature linear model may be caused by the consideration of often omitted feature types, including census records and genetic information.CONCLUSIONThe high performance of the 10-feature linear models indicate that unbiased selection of diverse features, not ML models, may lead to impressively accurate predictions, possibly enabling personalized screening schedules that increase cancer survival. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png JCO: Clinical Cancer Informatics Wolters Kluwer Health

Simple Linear Cancer Risk Prediction Models With Novel Features Outperform Complex Approaches

Download PDF
8 pages

Loading next page...
 
/lp/wolters-kluwer-health/simple-linear-cancer-risk-prediction-models-with-novel-features-5x4AyL0Jka
Publisher
Wolters Kluwer Health
Copyright
© 2022 by American Society of Clinical Oncology
eISSN
2473-4276
DOI
10.1200/cci.21.00166
Publisher site
See Article on Publisher Site

Abstract

PURPOSEThe ability to accurately predict an individual's risk for cancer is critical to the implementation of precision prevention measures. Current cancer risk predictions are frequently made with simple models that use a few proven risk factors, such as the Gail model for breast cancer, which are easy to interpret, but may theoretically be less accurate than advanced machine learning (ML) models.METHODSWith the UK Biobank, a large prospective study, we developed models that predicted 13 cancer diagnoses within a 10-year time span. ML and linear models fit with all features, linear models fit with 10 features, and externally developed QCancer models, which are available to more than 4,000 general practices, were assessed.RESULTSThe average area under the receiver operator curve (AUC) of the linear models (0.722, SE = 0.015) was greater than the average AUC of the ML models (0.720, SE = 0.016) when all 931 features were used. Linear models with only 10 features generated an average AUC of 0.706 (SE 0.015), which was comparable to the complex models using all features and greater than the average AUC of the QCancer models (0.684, SE 0.021). The high performance of the 10-feature linear model may be caused by the consideration of often omitted feature types, including census records and genetic information.CONCLUSIONThe high performance of the 10-feature linear models indicate that unbiased selection of diverse features, not ML models, may lead to impressively accurate predictions, possibly enabling personalized screening schedules that increase cancer survival.

Journal

JCO: Clinical Cancer Informatics – Wolters Kluwer Health

Published: Mar 3, 2022

References

  • Cancer prevention as part of precision medicine: ‘plenty to be done.’
    Stewart, BW; Bray, F; Forman, D
  • Screening for breast cancer: U.S. Preventive Services Task Force recommendation statement
    Siu, AL
  • Screening for cervical cancer: U.S. Preventive Services Task Force recommendation statement
    Moyer, VA
  • Screening for colorectal cancer: U.S. Preventive Services Task Force recommendation statement
  • Screening for lung cancer: U.S. Preventive Services Task Force recommendation statement
    Moyer, VA
  • Gail model and breast cancer
    Gail, MH; Greene, MH
  • Colorectal cancer risk prediction tool for white men and women without known susceptibility
    Freedman, AN; Slattery, ML; Ballard-Barbash, R
  • Development and validation of risk prediction algorithms to estimate future risk of common cancers in men and women: Prospective cohort study
    Hippisley-Cox, J; Coupland, C
  • The UK biobank resource with deep phenotyping and genomic data
    Bycroft, C; Freeman, C; Petkova, D
  • Cohort profile: Estonian Biobank of the Estonian Genome Center, University of Tartu
    Leitsalu, L; Haller, T; Esko, T
  • Overview of the BioBank Japan project: Study design and profile
    Nagai, A; Hirata, M; Kamatani, Y
  • A new initiative on precision medicine
    Collins, FS; Varmus, H
  • Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants
    Alaa, AM; Bolton, T; Di Angelantonio, E
  • Cross-cancer evaluation of polygenic risk scores for 17 cancer types in two large cohorts
    Graff, RE; Cavazos, TB; Thai, KK
  • Scikit-learn: Machine learning in Python
    Pedregosa, F; Varoquaux, G; Gramfort, A
  • Xgboost
    Chen, T; Guestrin, C
  • Pan-cancer analysis demonstrates that integrating polygenic risk scores with modifiable risk factors improves risk prediction
    Kachuri, L; Graff, RE; Smith-Byrne, K
  • Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction
    Agrawal, S; Klarqvist, MDR; Emdin, C
  • Projecting individualized probabilities of developing breast cancer for white females who are being examined annually
    Gail, MH; Brinton, LA; Byar, DP
  • Development and validation of risk models to select ever-smokers for CT lung cancer screening
    Katki, HA; Kovalchik, SA; Berg, CD