WEKO3
アイテム
{"_buckets": {"deposit": "201e644d-c623-488d-a076-b99fc1672eeb"}, "_deposit": {"created_by": 26, "id": "889", "owners": [26], "pid": {"revision_id": 0, "type": "depid", "value": "889"}, "status": "published"}, "_oai": {"id": "oai:oist.repo.nii.ac.jp:00000889", "sets": ["40"]}, "author_link": ["4630", "4627", "4626", "4629", "4628"], "item_10001_biblio_info_7": {"attribute_name": "Bibliographic Information", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018-08-31", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "8", "bibliographicPageStart": "e0202344", "bibliographicVolumeNumber": "13", "bibliographic_titles": [{}, {"bibliographic_title": "PLOS ONE", "bibliographic_titleLang": "en"}]}]}, "item_10001_creator_3": {"attribute_name": "Author", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Steele, Andrew J."}], "nameIdentifiers": [{"nameIdentifier": "4626", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Denaxas, Spiros C."}], "nameIdentifiers": [{"nameIdentifier": "4627", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Shah, Anoop D."}], "nameIdentifiers": [{"nameIdentifier": "4628", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Hemingway, Harry"}], "nameIdentifiers": [{"nameIdentifier": "4629", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Luscombe, Nicholas M."}], "nameIdentifiers": [{"nameIdentifier": "4630", "nameIdentifierScheme": "WEKO"}]}]}, "item_10001_description_5": {"attribute_name": "Abstract", "attribute_value_mlt": [{"subitem_description": "Prognostic modelling is important in clinical practice and epidemiology for patient management and research. Electronic health records (EHR) provide large quantities of data for such models, but conventional epidemiological approaches require significant researcher time to implement. Expert selection of variables, fine-tuning of variable transformations and interactions, and imputing missing values are time-consuming and could bias subsequent analysis, particularly given that missingness in EHR is both high, and may carry meaning. Using a cohort of 80,000 patients from the CALIBER programme, we compared traditional modelling and machine-learning approaches in EHR. First, we used Cox models and random survival forests with and without imputation on 27 expert-selected, preprocessed variables to predict all-cause mortality. We then used Cox models, random forests and elastic net regression on an extended dataset with 586 variables to build prognostic models and identify novel prognostic factors without prior expert input. We observed that data-driven models used on an extended dataset can outperform conventional models for prognosis, without data preprocessing or imputing missing values. An elastic net Cox regression based with 586 unimputed variables with continuous values discretised achieved a C-index of 0.801 (bootstrapped 95% CI 0.799 to 0.802), compared to 0.793 (0.791 to 0.794) for a traditional Cox model comprising 27 expert-selected variables with imputation for missing values. We also found that data-driven models allow identification of novel prognostic variables; that the absence of values for particular variables carries meaning, and can have significant implications for prognosis; and that variables often have a nonlinear association with mortality, which discretised Cox models and random forests can elucidate. This demonstrates that machine-learning approaches applied to raw EHR data can be used to build models for use in research and clinical practice, and identify novel predictive variables and their effects to inform future research.", "subitem_description_type": "Other"}]}, "item_10001_publisher_8": {"attribute_name": "Publisher", "attribute_value_mlt": [{"subitem_publisher": "Public Library of Science"}]}, "item_10001_relation_13": {"attribute_name": "PubMedNo.", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:pmid/30169498", "subitem_relation_type_select": "PMID"}}]}, "item_10001_relation_14": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isIdenticalTo", "subitem_relation_type_id": {"subitem_relation_type_id_text": "info:doi/10.1371/journal.pone.0202344", "subitem_relation_type_select": "DOI"}}]}, "item_10001_relation_16": {"attribute_name": "情報源", "attribute_value_mlt": [{"subitem_relation_name": [{"subitem_relation_name_text": "http://creativecommons.org/licenses/by/4.0/"}]}]}, "item_10001_relation_17": {"attribute_name": "Related site", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0202344", "subitem_relation_type_select": "URI"}}]}, "item_10001_rights_15": {"attribute_name": "Rights", "attribute_value_mlt": [{"subitem_rights": "© 2018 Steele et al."}]}, "item_10001_source_id_9": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "1932-6203", "subitem_source_identifier_type": "ISSN"}]}, "item_10001_version_type_20": {"attribute_name": "Author\u0027s flag", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2019-05-21"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "journal.pone.0202344.pdf", "filesize": [{"value": "2.2 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensefree": "Creative Commons \nAttribution 4.0 International\n(http://creativecommons.org/licenses/by/4.0/)", "licensetype": "license_free", "mimetype": "application/pdf", "size": 2200000.0, "url": {"label": "journal.pone.0202344", "url": "https://oist.repo.nii.ac.jp/record/889/files/journal.pone.0202344.pdf"}, "version_id": "e72bdcaa-f93d-4b1e-a437-b16bf2ac2f9c"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease", "subitem_title_language": "en"}]}, "item_type_id": "10001", "owner": "26", "path": ["40"], "permalink_uri": "https://oist.repo.nii.ac.jp/records/889", "pubdate": {"attribute_name": "公開日", "attribute_value": "2019-05-21"}, "publish_date": "2019-05-21", "publish_status": "0", "recid": "889", "relation": {}, "relation_version_is_last": true, "title": ["Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease"], "weko_shared_id": 26}
Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease
https://oist.repo.nii.ac.jp/records/889
https://oist.repo.nii.ac.jp/records/8890caefb7c-ac03-4e5b-8d8d-54131b1cf682
名前 / ファイル | ライセンス | アクション |
---|---|---|
journal.pone.0202344 (2.2 MB)
|
Creative Commons
Attribution 4.0 International (http://creativecommons.org/licenses/by/4.0/) |
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-05-21 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
著者(英) |
Steele, Andrew J.
× Steele, Andrew J.× Denaxas, Spiros C.× Shah, Anoop D.× Hemingway, Harry× Luscombe, Nicholas M. |
|||||
書誌情報 |
en : PLOS ONE 巻 13, 号 8, p. e0202344, 発行日 2018-08-31 |
|||||
抄録 | ||||||
内容記述タイプ | Other | |||||
内容記述 | Prognostic modelling is important in clinical practice and epidemiology for patient management and research. Electronic health records (EHR) provide large quantities of data for such models, but conventional epidemiological approaches require significant researcher time to implement. Expert selection of variables, fine-tuning of variable transformations and interactions, and imputing missing values are time-consuming and could bias subsequent analysis, particularly given that missingness in EHR is both high, and may carry meaning. Using a cohort of 80,000 patients from the CALIBER programme, we compared traditional modelling and machine-learning approaches in EHR. First, we used Cox models and random survival forests with and without imputation on 27 expert-selected, preprocessed variables to predict all-cause mortality. We then used Cox models, random forests and elastic net regression on an extended dataset with 586 variables to build prognostic models and identify novel prognostic factors without prior expert input. We observed that data-driven models used on an extended dataset can outperform conventional models for prognosis, without data preprocessing or imputing missing values. An elastic net Cox regression based with 586 unimputed variables with continuous values discretised achieved a C-index of 0.801 (bootstrapped 95% CI 0.799 to 0.802), compared to 0.793 (0.791 to 0.794) for a traditional Cox model comprising 27 expert-selected variables with imputation for missing values. We also found that data-driven models allow identification of novel prognostic variables; that the absence of values for particular variables carries meaning, and can have significant implications for prognosis; and that variables often have a nonlinear association with mortality, which discretised Cox models and random forests can elucidate. This demonstrates that machine-learning approaches applied to raw EHR data can be used to build models for use in research and clinical practice, and identify novel predictive variables and their effects to inform future research. | |||||
出版者 | ||||||
出版者 | Public Library of Science | |||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 1932-6203 | |||||
PubMed番号 | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | PMID | |||||
関連識別子 | info:pmid/30169498 | |||||
DOI | ||||||
関連タイプ | isIdenticalTo | |||||
識別子タイプ | DOI | |||||
関連識別子 | info:doi/10.1371/journal.pone.0202344 | |||||
権利 | ||||||
権利情報 | © 2018 Steele et al. | |||||
情報源 | ||||||
関連名称 | http://creativecommons.org/licenses/by/4.0/ | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0202344 | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 |