{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["21"],"submitter":["Nayshool O"],"pubmed_abstract":["<h4>Motivation</h4>Prediction of cancer outcome is a major challenge in oncology and is essential for treatment planning. Repositories such as The Cancer Genome Atlas (TCGA) contain vast amounts of data for many types of cancers. Our goal was to create reliable prediction models using TCGA data and validate them using an external dataset.<h4>Results</h4>For 16 TCGA cancer type cohorts we have optimized a Random Forest prediction model using parameter grid search followed by a backward feature elimination loop for dimensions reduction. For each feature that was removed, the model was retrained and the area under the curve of the receiver operating characteristic (AUC-ROC) was calculated using test data. Five prediction models gave AUC-ROC bigger than 80%. We used Clinical Proteomic Tumor An"],"journal":["Cancer informatics"],"pagination":["11769351221127875"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9549197"],"repository":["biostudies-literature"],"pubmed_title":["SurviveAI: Long Term Survival Prediction of Cancer Patients Based on Somatic RNA-Seq Expression."],"pmcid":["PMC9549197"],"pubmed_authors":["Nayshool O","Kol N","Javaski E","Rechavi G","Amariglio N"],"additional_accession":[]},"is_claimable":false,"name":"SurviveAI: Long Term Survival Prediction of Cancer Patients Based on Somatic RNA-Seq Expression.","description":"<h4>Motivation</h4>Prediction of cancer outcome is a major challenge in oncology and is essential for treatment planning. Repositories such as The Cancer Genome Atlas (TCGA) contain vast amounts of data for many types of cancers. Our goal was to create reliable prediction models using TCGA data and validate them using an external dataset.<h4>Results</h4>For 16 TCGA cancer type cohorts we have optimized a Random Forest prediction model using parameter grid search followed by a backward feature elimination loop for dimensions reduction. For each feature that was removed, the model was retrained and the area under the curve of the receiver operating characteristic (AUC-ROC) was calculated using test data. Five prediction models gave AUC-ROC bigger than 80%. We used Clinical Proteomic Tumor An","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-21T16:53:05.969Z","creation":"2025-04-21T16:53:05.969Z"},"accession":"S-EPMC9549197","cross_references":{"pubmed":["36225330"],"doi":["10.1177/11769351221127875"]}}