Precision-Recall curves comparing 7 machine learning models and a baseline value.

<p>PR curves are computed using the withheld test data. SVM is the model with the highest area under the curve.</p>

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Andres Portocarrero-Bonifaz (21367929) (author)
مؤلفون آخرون:	Salman Syed (18880470) (author), Maxwell Kassel (21367932) (author), Grant W. McKenzie (21367935) (author), Vishwa M. Shah (21367938) (author), Bryce M. Forry (21367941) (author), Jeremy T. Gaskins (9281129) (author), Keith T. Sowards (21367944) (author), Thulasi Babitha Avula (21367947) (author), Adrianna Masters (21367950) (author), Jose G. Schneider (21367953) (author), Scott R. Silva (14975143) (author)
منشور في:	2025
الموضوعات:	Biotechnology Cancer Infectious Diseases Virology Biological Sciences not elsewhere classified Information Systems not elsewhere classified without grade 3 support vector machines rectum differed significantly predicting grade 3 predict grade 3 normmcc testing scores gaussian naive bayes f1 testing scores external beam radiotherapy charlson comorbidity index applying exclusion criteria achieving satisfactory performance accuracy testing scores deep learning networks creating multivariable models final model performance machine learning presents predict patient outcomes advancing patient care machine learning models traditional statistical analysis predict specific toxicities high dose rate gynecological cancer patients underwent hdr brachytherapy machine learning applied models ranking model xlink "> women worldwide toxicity data retrospective analysis recent studies random forest prevalent cancers ovoid applicators often used novel solution nearest neighbors logistic regression hyperparameter tuning higher toxicities dosimetric variables data availability characterized using 233 patients
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

_version_	1852020398442414080
author	Andres Portocarrero-Bonifaz (21367929)
author2	Salman Syed (18880470) Maxwell Kassel (21367932) Grant W. McKenzie (21367935) Vishwa M. Shah (21367938) Bryce M. Forry (21367941) Jeremy T. Gaskins (9281129) Keith T. Sowards (21367944) Thulasi Babitha Avula (21367947) Adrianna Masters (21367950) Jose G. Schneider (21367953) Scott R. Silva (14975143)
author2_role	author author author author author author author author author author author
author_facet	Andres Portocarrero-Bonifaz (21367929) Salman Syed (18880470) Maxwell Kassel (21367932) Grant W. McKenzie (21367935) Vishwa M. Shah (21367938) Bryce M. Forry (21367941) Jeremy T. Gaskins (9281129) Keith T. Sowards (21367944) Thulasi Babitha Avula (21367947) Adrianna Masters (21367950) Jose G. Schneider (21367953) Scott R. Silva (14975143)
author_role	author
dc.creator.none.fl_str_mv	Andres Portocarrero-Bonifaz (21367929) Salman Syed (18880470) Maxwell Kassel (21367932) Grant W. McKenzie (21367935) Vishwa M. Shah (21367938) Bryce M. Forry (21367941) Jeremy T. Gaskins (9281129) Keith T. Sowards (21367944) Thulasi Babitha Avula (21367947) Adrianna Masters (21367950) Jose G. Schneider (21367953) Scott R. Silva (14975143)
dc.date.none.fl_str_mv	2025-05-15T14:48:20Z
dc.identifier.none.fl_str_mv	10.1371/journal.pone.0312208.g002
dc.relation.none.fl_str_mv	https://figshare.com/articles/figure/Precision-Recall_curves_comparing_7_machine_learning_models_and_a_baseline_value_/29074611
dc.rights.none.fl_str_mv	CC BY 4.0 info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv	Biotechnology Cancer Infectious Diseases Virology Biological Sciences not elsewhere classified Information Systems not elsewhere classified without grade 3 support vector machines rectum differed significantly predicting grade 3 predict grade 3 normmcc testing scores gaussian naive bayes f1 testing scores external beam radiotherapy charlson comorbidity index applying exclusion criteria achieving satisfactory performance accuracy testing scores deep learning networks creating multivariable models final model performance machine learning presents predict patient outcomes advancing patient care machine learning models traditional statistical analysis predict specific toxicities high dose rate gynecological cancer patients underwent hdr brachytherapy machine learning applied models ranking model xlink "> women worldwide toxicity data retrospective analysis recent studies random forest prevalent cancers ovoid applicators often used novel solution nearest neighbors logistic regression hyperparameter tuning higher toxicities dosimetric variables data availability characterized using 233 patients
dc.title.none.fl_str_mv	Precision-Recall curves comparing 7 machine learning models and a baseline value.
dc.type.none.fl_str_mv	Image Figure info:eu-repo/semantics/publishedVersion image
description	<p>PR curves are computed using the withheld test data. SVM is the model with the highest area under the curve.</p>
eu_rights_str_mv	openAccess
id	Manara_df47d7dfe4a7e85f2eefa3fdaf09ef08
identifier_str_mv	10.1371/journal.pone.0312208.g002
network_acronym_str	Manara
network_name_str	ManaraRepo
oai_identifier_str	oai:figshare.com:article/29074611
publishDate	2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv	CC BY 4.0
spelling	Precision-Recall curves comparing 7 machine learning models and a baseline value.Andres Portocarrero-Bonifaz (21367929)Salman Syed (18880470)Maxwell Kassel (21367932)Grant W. McKenzie (21367935)Vishwa M. Shah (21367938)Bryce M. Forry (21367941)Jeremy T. Gaskins (9281129)Keith T. Sowards (21367944)Thulasi Babitha Avula (21367947)Adrianna Masters (21367950)Jose G. Schneider (21367953)Scott R. Silva (14975143)BiotechnologyCancerInfectious DiseasesVirologyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedwithout grade 3support vector machinesrectum differed significantlypredicting grade 3predict grade 3normmcc testing scoresgaussian naive bayesf1 testing scoresexternal beam radiotherapycharlson comorbidity indexapplying exclusion criteriaachieving satisfactory performanceaccuracy testing scoresdeep learning networkscreating multivariable modelsfinal model performancemachine learning presentspredict patient outcomesadvancing patient caremachine learning modelstraditional statistical analysispredict specific toxicitieshigh dose rategynecological cancer patientsunderwent hdr brachytherapymachine learningapplied modelsranking modelxlink ">women worldwidetoxicity dataretrospective analysisrecent studiesrandom forestprevalent cancersovoid applicatorsoften usednovel solutionnearest neighborslogistic regressionhyperparameter tuninghigher toxicitiesdosimetric variablesdata availabilitycharacterized using233 patients<p>PR curves are computed using the withheld test data. SVM is the model with the highest area under the curve.</p>2025-05-15T14:48:20ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0312208.g002https://figshare.com/articles/figure/Precision-Recall_curves_comparing_7_machine_learning_models_and_a_baseline_value_/29074611CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/290746112025-05-15T14:48:20Z
spellingShingle	Precision-Recall curves comparing 7 machine learning models and a baseline value. Andres Portocarrero-Bonifaz (21367929) Biotechnology Cancer Infectious Diseases Virology Biological Sciences not elsewhere classified Information Systems not elsewhere classified without grade 3 support vector machines rectum differed significantly predicting grade 3 predict grade 3 normmcc testing scores gaussian naive bayes f1 testing scores external beam radiotherapy charlson comorbidity index applying exclusion criteria achieving satisfactory performance accuracy testing scores deep learning networks creating multivariable models final model performance machine learning presents predict patient outcomes advancing patient care machine learning models traditional statistical analysis predict specific toxicities high dose rate gynecological cancer patients underwent hdr brachytherapy machine learning applied models ranking model xlink "> women worldwide toxicity data retrospective analysis recent studies random forest prevalent cancers ovoid applicators often used novel solution nearest neighbors logistic regression hyperparameter tuning higher toxicities dosimetric variables data availability characterized using 233 patients
status_str	publishedVersion
title	Precision-Recall curves comparing 7 machine learning models and a baseline value.
title_full	Precision-Recall curves comparing 7 machine learning models and a baseline value.
title_fullStr	Precision-Recall curves comparing 7 machine learning models and a baseline value.
title_full_unstemmed	Precision-Recall curves comparing 7 machine learning models and a baseline value.
title_short	Precision-Recall curves comparing 7 machine learning models and a baseline value.
title_sort	Precision-Recall curves comparing 7 machine learning models and a baseline value.
topic	Biotechnology Cancer Infectious Diseases Virology Biological Sciences not elsewhere classified Information Systems not elsewhere classified without grade 3 support vector machines rectum differed significantly predicting grade 3 predict grade 3 normmcc testing scores gaussian naive bayes f1 testing scores external beam radiotherapy charlson comorbidity index applying exclusion criteria achieving satisfactory performance accuracy testing scores deep learning networks creating multivariable models final model performance machine learning presents predict patient outcomes advancing patient care machine learning models traditional statistical analysis predict specific toxicities high dose rate gynecological cancer patients underwent hdr brachytherapy machine learning applied models ranking model xlink "> women worldwide toxicity data retrospective analysis recent studies random forest prevalent cancers ovoid applicators often used novel solution nearest neighbors logistic regression hyperparameter tuning higher toxicities dosimetric variables data availability characterized using 233 patients

Precision-Recall curves comparing 7 machine learning models and a baseline value.

مواد مشابهة