{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Seinen TM"],"funding":["European Health Data &amp; Evidence Network (EHDEN)","European Union's Horizon 2020 research","European Union’s Horizon 2020 research and innovation program and EFPIA","Innovative Medicines Initiative 2 Joint Undertaking (JU)","Innovative Medicines Initiative 2 Joint Undertaking","European Health Data &amp; Evidence Network","European Union's Horizon 2020 research and innovation program and EFPIA"],"pagination":["1292-1302"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9196702"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["29(7)"],"pubmed_abstract":["<h4>Objective</h4>This systematic review aims to assess how information from unstructured text is used to develop and validate clinical prognostic prediction models. We summarize the prediction problems and methodological landscape and determine whether using text data in addition to more commonly used structured data improves the prediction performance.<h4>Materials and methods</h4>We searched Embase, MEDLINE, Web of Science, and Google Scholar to identify studies that developed prognostic prediction models using information extracted from unstructured text in a data-driven manner, published in the period from January 2005 to March 2021. Data items were extracted, analyzed, and a meta-analysis of the model performance was carried out to assess the added value of text to structured-data mo"],"journal":["Journal of the American Medical Informatics Association : JAMIA"],"pubmed_title":["Use of unstructured text in prognostic clinical prediction models: a systematic review."],"pmcid":["PMC9196702"],"funding_grant_id":["806968"],"pubmed_authors":["van Mulligen EM","Kors JA","Rijnbeek PR","Ioannou S","Yang C","Seinen TM","John LH","Pera V","Markus AF","Rekkas A","Jeannetot D","Fridgeirsson EA","Williams RD"],"additional_accession":[]},"is_claimable":false,"name":"Use of unstructured text in prognostic clinical prediction models: a systematic review.","description":"<h4>Objective</h4>This systematic review aims to assess how information from unstructured text is used to develop and validate clinical prognostic prediction models. We summarize the prediction problems and methodological landscape and determine whether using text data in addition to more commonly used structured data improves the prediction performance.<h4>Materials and methods</h4>We searched Embase, MEDLINE, Web of Science, and Google Scholar to identify studies that developed prognostic prediction models using information extracted from unstructured text in a data-driven manner, published in the period from January 2005 to March 2021. Data items were extracted, analyzed, and a meta-analysis of the model performance was carried out to assess the added value of text to structured-data mo","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Jun","modification":"2025-04-22T05:58:08.862Z","creation":"2025-04-05T21:32:09.025Z"},"accession":"S-EPMC9196702","cross_references":{"pubmed":["35475536"],"doi":["10.1093/jamia/ocac058"]}}