Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362495708> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4362495708 abstract "<div>AbstractBackground:<p>Machine learning (ML) approaches facilitate risk prediction model development using high-dimensional predictors and higher-order interactions at the cost of model interpretability and transparency. We compared the relative predictive performance of statistical and ML models to guide modeling strategy selection for surveillance mammography outcomes in women with a personal history of breast cancer (PHBC).</p>Methods:<p>We cross-validated seven risk prediction models for two surveillance outcomes, failure (breast cancer within 12 months of a negative surveillance mammogram) and benefit (surveillance-detected breast cancer). We included 9,447 mammograms (495 failures, 1,414 benefits, and 7,538 nonevents) from years 1996 to 2017 using a 1:4 matched case–control samples of women with PHBC in the Breast Cancer Surveillance Consortium. We assessed model performance of conventional regression, regularized regressions (LASSO and elastic-net), and ML methods (random forests and gradient boosting machines) by evaluating their calibration and, among well-calibrated models, comparing the area under the receiver operating characteristic curve (AUC) and 95% confidence intervals (CI).</p>Results:<p>LASSO and elastic-net consistently provided well-calibrated predicted risks for surveillance failure and benefit. The AUCs of LASSO and elastic-net were both 0.63 (95% CI, 0.60–0.66) for surveillance failure and 0.66 (95% CI, 0.64–0.68) for surveillance benefit, the highest among well-calibrated models.</p>Conclusions:<p>For predicting breast cancer surveillance mammography outcomes, regularized regression outperformed other modeling approaches and balanced the trade-off between model flexibility and interpretability.</p>Impact:<p>Regularized regression may be preferred for developing risk prediction models in other contexts with rare outcomes, similar training sample sizes, and low-dimensional features.</p></div>" @default.
- W4362495708 created "2023-04-05" @default.
- W4362495708 creator A5001077788 @default.
- W4362495708 creator A5004918315 @default.
- W4362495708 creator A5008134033 @default.
- W4362495708 creator A5008335692 @default.
- W4362495708 creator A5008337139 @default.
- W4362495708 creator A5020615352 @default.
- W4362495708 creator A5035204101 @default.
- W4362495708 creator A5038929684 @default.
- W4362495708 creator A5049271778 @default.
- W4362495708 creator A5050357899 @default.
- W4362495708 creator A5053382377 @default.
- W4362495708 creator A5077710776 @default.
- W4362495708 creator A5085257013 @default.
- W4362495708 date "2023-04-03" @default.
- W4362495708 modified "2023-09-26" @default.
- W4362495708 title "Data from Performance of Statistical and Machine Learning Risk Prediction Models for Surveillance Benefits and Failures in Breast Cancer Survivors" @default.
- W4362495708 doi "https://doi.org/10.1158/1055-9965.c.6534625" @default.
- W4362495708 hasPublicationYear "2023" @default.
- W4362495708 type Work @default.
- W4362495708 citedByCount "0" @default.
- W4362495708 crossrefType "posted-content" @default.
- W4362495708 hasAuthorship W4362495708A5001077788 @default.
- W4362495708 hasAuthorship W4362495708A5004918315 @default.
- W4362495708 hasAuthorship W4362495708A5008134033 @default.
- W4362495708 hasAuthorship W4362495708A5008335692 @default.
- W4362495708 hasAuthorship W4362495708A5008337139 @default.
- W4362495708 hasAuthorship W4362495708A5020615352 @default.
- W4362495708 hasAuthorship W4362495708A5035204101 @default.
- W4362495708 hasAuthorship W4362495708A5038929684 @default.
- W4362495708 hasAuthorship W4362495708A5049271778 @default.
- W4362495708 hasAuthorship W4362495708A5050357899 @default.
- W4362495708 hasAuthorship W4362495708A5053382377 @default.
- W4362495708 hasAuthorship W4362495708A5077710776 @default.
- W4362495708 hasAuthorship W4362495708A5085257013 @default.
- W4362495708 hasConcept C119857082 @default.
- W4362495708 hasConcept C121608353 @default.
- W4362495708 hasConcept C126322002 @default.
- W4362495708 hasConcept C136764020 @default.
- W4362495708 hasConcept C148483581 @default.
- W4362495708 hasConcept C154945302 @default.
- W4362495708 hasConcept C169258074 @default.
- W4362495708 hasConcept C203868755 @default.
- W4362495708 hasConcept C2780472235 @default.
- W4362495708 hasConcept C2781067378 @default.
- W4362495708 hasConcept C37616216 @default.
- W4362495708 hasConcept C41008148 @default.
- W4362495708 hasConcept C44249647 @default.
- W4362495708 hasConcept C45804977 @default.
- W4362495708 hasConcept C530470458 @default.
- W4362495708 hasConcept C71924100 @default.
- W4362495708 hasConceptScore W4362495708C119857082 @default.
- W4362495708 hasConceptScore W4362495708C121608353 @default.
- W4362495708 hasConceptScore W4362495708C126322002 @default.
- W4362495708 hasConceptScore W4362495708C136764020 @default.
- W4362495708 hasConceptScore W4362495708C148483581 @default.
- W4362495708 hasConceptScore W4362495708C154945302 @default.
- W4362495708 hasConceptScore W4362495708C169258074 @default.
- W4362495708 hasConceptScore W4362495708C203868755 @default.
- W4362495708 hasConceptScore W4362495708C2780472235 @default.
- W4362495708 hasConceptScore W4362495708C2781067378 @default.
- W4362495708 hasConceptScore W4362495708C37616216 @default.
- W4362495708 hasConceptScore W4362495708C41008148 @default.
- W4362495708 hasConceptScore W4362495708C44249647 @default.
- W4362495708 hasConceptScore W4362495708C45804977 @default.
- W4362495708 hasConceptScore W4362495708C530470458 @default.
- W4362495708 hasConceptScore W4362495708C71924100 @default.
- W4362495708 hasLocation W43624957081 @default.
- W4362495708 hasOpenAccess W4362495708 @default.
- W4362495708 hasPrimaryLocation W43624957081 @default.
- W4362495708 hasRelatedWork W2033803508 @default.
- W4362495708 hasRelatedWork W2147626660 @default.
- W4362495708 hasRelatedWork W2156332695 @default.
- W4362495708 hasRelatedWork W2989850715 @default.
- W4362495708 hasRelatedWork W2991486385 @default.
- W4362495708 hasRelatedWork W3174196512 @default.
- W4362495708 hasRelatedWork W3210526060 @default.
- W4362495708 hasRelatedWork W4281483251 @default.
- W4362495708 hasRelatedWork W4313478509 @default.
- W4362495708 hasRelatedWork W4361733514 @default.
- W4362495708 isParatext "false" @default.
- W4362495708 isRetracted "false" @default.
- W4362495708 workType "article" @default.