Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Anna Tosteson"'
Autor:
Yu-Ru Su, Diana S.M. Buist, Janie M. Lee, Laura Ichikawa, Diana L. Miglioretti, Erin J. Aiello Bowles, Karen J. Wernli, Karla Kerlikowske, Anna Tosteson, Kathryn P. Lowry, Louise M. Henderson, Brian L. Sprague, Rebecca A. Hubbard
Publikováno v:
Cancer Epidemiology, Biomarkers & Prevention. 32:561-571
Background: 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 perf
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Table S1 shows the calibration assessment in a sensitivity analysis on LASSO and Elastic-net by enforcing the adjustment of the matching factor.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a968cccd14d412b11c342b2936e1082
https://doi.org/10.1158/1055-9965.22494787
https://doi.org/10.1158/1055-9965.22494787
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Figure S1 shows frequency of predictor inclusion in regression-based models for surveillance failure and benefit across imputed datasets.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0beae06a87d35acb285a23ef3a668132
https://doi.org/10.1158/1055-9965.22494799.v1
https://doi.org/10.1158/1055-9965.22494799.v1
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Background: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 perfo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::528f974dce8fcbe9b320e7053c2cf2d1
https://doi.org/10.1158/1055-9965.c.6534625
https://doi.org/10.1158/1055-9965.c.6534625
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Figure S2 shows ranking of variable importance for random forests and gradient boosting machines for surveillance failure.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a4cef1d95e601cb7c5327e5802e528ae
https://doi.org/10.1158/1055-9965.22494796
https://doi.org/10.1158/1055-9965.22494796
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Table S2 shows the estimated effect sizes on log-odds scale for regression-based modeling approaches for surveillance failure and benefit averaged across 10 imputed datasets.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0254b3f4e1b354175fbe46791d552398
https://doi.org/10.1158/1055-9965.22494784
https://doi.org/10.1158/1055-9965.22494784
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Methods show the detailed information of model fitting using the machine learning approaches in this work.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::19af56dd0187cf683a6118c406f16d5d
https://doi.org/10.1158/1055-9965.22494790
https://doi.org/10.1158/1055-9965.22494790
Autor:
Rebecca A. Hubbard, Brian L. Sprague, Louise M. Henderson, Kathryn P. Lowry, Anna Tosteson, Karla Kerlikowske, Karen J. Wernli, Erin J. Aiello Bowles, Diana L. Miglioretti, Laura Ichikawa, Janie M. Lee, Diana S.M. Buist, Yu-Ru Su
Supplementary Figure S3 shows ranking of variable importance plot for random forests and gradient boosting machines for surveillance benefit.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::708ffb377131c7dd1934992c593b6fc9
https://doi.org/10.1158/1055-9965.22494793
https://doi.org/10.1158/1055-9965.22494793
Autor:
Christi Ann Hayes, Kenneth R. Meehan, Elizabeth A O'Donnell, Aricca Van Citters, Kate L. Caldon, Charlotte M Coughenour, Dorothy R. McKenna, Carla Tarzia, Wenyan Zhao, Kimberley R Holt, Christopher H. Lowrey, John M. Hill, Tiffany D'Cruze, Megan M Holthoff, Tor Tosteson, Anna Tosteson
Publikováno v:
Blood. 140:8113-8114
Publikováno v:
Circulation. 144
Introduction: Based on the results of PARADIGM-HF and PIONEER-HF, angiotensin-receptor neprilysin inhibitors (ARNI) offer improved survival and lower readmission rates for HFrEF compared to angiotensin converting enzyme inhibitors (ACEi) or angiotens