{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T02:39:26Z","timestamp":1787884766234,"version":"build-2784847793"},"reference-count":17,"publisher":"BMJ","issue":"4","license":[{"start":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T00:00:00Z","timestamp":1745625600000},"content-version":"unspecified","delay-in-days":25,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut and Alice Wallenberg foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100005760","name":"Gothenburg University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005760","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,4,14]]},"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>In-hospital cardiac arrest (IHCA) presents a critical challenge with low survival rates and limited prediction tools. Despite advances in resuscitation, predicting 30-day survival remains difficult, and current methods lack interpretability for timely decision-making. This study developed a machine learning (ML) model to predict 30-day survival after IHCA, using peri-arrest variables available on the rescue team\u2019s arrival, while ensuring a balance between predictive accuracy and clinical interpretability through Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A nationwide, registry-based observational study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Data were sourced from the Swedish Cardiopulmonary Resuscitation Registry (2010\u20132020), merged with the Patient Registry.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>We analysed 25\u2009905 IHCA cases with attempted resuscitation, of which 8166 patients survived for 30 days.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Outcome measure and analysis<\/jats:title>\n                    <jats:p>30-day survival after IHCA was the outcome measure. An ML model was developed using fivefold cross-validation. Key predictors were identified through in-built variable importance and validated using SHAP. Model performance was evaluated with metrics such as area under the receiver operating characteristics (AUROC), calibration, sensitivity, specificity, false negative rate (FNR) and F-score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The CatBoost model achieved an AUROC of 0.9136 (95% CI 0.9075 to 0.9191) with all features, and 0.9034 (95% CI 0.8955 to 0.9037) with the top 15 features, along with Brier scores of 0.1028 and 0.1103, respectively. Performance plateaued after including the top 15 predictors, with few key variables, such as epinephrine administration, age, initial rhythm, ROSC within 15\u2009min, breathing on rescue team arrival and witnessed cardiac arrest, being most influential. The model showed strong calibration for patients with low predicted survival probabilities and demonstrated high sensitivity with a low FNR across relevant survival thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      The CatBoost model provides an effective and interpretable tool for predicting 30-day survival after IHCA. Key predictors such as epinephrine administration, age and initial rhythm inform clinical decision-making. This model has strong clinical utility and can be externally validated via the open-access Application Programming Interface (API) at\n                      <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"www.gocares.se\">www.gocares.se<\/jats:ext-link>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2024-090493","type":"journal-article","created":{"date-parts":[[2025,4,27]],"date-time":"2025-04-27T04:45:24Z","timestamp":1745729124000},"page":"e090493","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":4,"title":["Predicting 30-day survival after in-hospital cardiac arrest: a nationwide cohort study using machine learning and SHAP analysis"],"prefix":"10.1136","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3785-8380","authenticated-orcid":false,"given":"Vibha","family":"Gupta","sequence":"first","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Wallenberg Center for Molecular and Translational Medicine, Wallenberg Laboratory, University of Gothenburg, Goteborg, Sweden"},{"name":"Centre for Digital Health, Omr\u00e5de Digitalisering, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aidin","family":"Rawshani","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Lundgren","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Centre for Digital Health, Omr\u00e5de Digitalisering, Sahlgrenska University Hospital, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mats","family":"B\u00f6rjesson","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Truls","family":"R\u00e5munddal","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Per","family":"Nordberg","sequence":"additional","affiliation":[{"name":"Department of Clinical Science and Education, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5905-157X","authenticated-orcid":false,"given":"Therese","family":"Dj\u00e4rv","sequence":"additional","affiliation":[{"name":"Molecular Medicine and Surgery, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Herlitz","sequence":"additional","affiliation":[{"name":"University of Bor\u00e5s, Faculty of Caring Science, Work Life and Social Welfare, Bor\u00e5s, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joakim","family":"Sundstr\u00f6m","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carl","family":"Magnusson","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antros","family":"Louca","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Wallenberg Center for Molecular and Translational Medicine, Wallenberg Laboratory, University of Gothenburg, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0567-2020","authenticated-orcid":false,"given":"Erik","family":"Andersson","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Wallenberg Center for Molecular and Translational Medicine, Wallenberg Laboratory, University of Gothenburg, Goteborg, Sweden"},{"name":"Centre for Digital Health, Omr\u00e5de Digitalisering, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristofer","family":"Skoglund","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2066-3533","authenticated-orcid":false,"given":"Araz","family":"Rawshani","sequence":"additional","affiliation":[{"name":"Department of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden"},{"name":"Wallenberg Center for Molecular and Translational Medicine, Wallenberg Laboratory, University of Gothenburg, Goteborg, Sweden"},{"name":"Centre for Digital Health, Omr\u00e5de Digitalisering, Sahlgrenska University Hospital, Goteborg, Sweden"},{"name":"Department of Cardiology, Sahlgrenska University Hospital, Goteborg, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,4,27]]},"reference":[{"key":"2025120619203630000_15.4.e090493.1","doi-asserted-by":"crossref","first-page":"4817","DOI":"10.1093\/eurheartj\/ehac414","article-title":"Trends in survival after cardiac arrest: a Swedish nationwide study over 30 years","volume":"43","author":"Jerkeman","year":"2022","journal-title":"Eur Heart J"},{"key":"2025120619203630000_15.4.e090493.2","unstructured":"Herlitz J . Swedish cardio-pulmonary registry-yearly report. Swedish, 2021."},{"key":"2025120619203630000_15.4.e090493.3","doi-asserted-by":"crossref","DOI":"10.1186\/s12910-021-00604-8","article-title":"Do-not-attempt-resuscitation orders: attitudes, perceptions and practices of Swedish physicians and nurses","volume":"22","author":"Bremer","year":"2021","journal-title":"BMC Med Ethics"},{"key":"2025120619203630000_15.4.e090493.4","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.resuscitation.2020.11.016","article-title":"In-Hospital vs. Out-of-Hospital Cardiac Arrest: Patient Characteristics and Survival","volume":"158","author":"H\u00f8ybye","year":"2021","journal-title":"Resuscitation"},{"key":"2025120619203630000_15.4.e090493.5","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s13054-023-04306-y","article-title":"Prognostic models for outcome prediction following in-hospital cardiac arrest using pre-arrest factors: a systematic review, meta-analysis and critical appraisal","volume":"27","author":"Grandbois van Ravenhorst","year":"2023","journal-title":"Crit Care"},{"key":"2025120619203630000_15.4.e090493.6","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1001\/jamainternmed.2013.10037","article-title":"Development and validation of the Good Outcome Following Attempted Resuscitation (GO-FAR) score to predict neurologically intact survival after in-hospital cardiopulmonary resuscitation","volume":"173","author":"Ebell","year":"2013","journal-title":"JAMA Intern Med"},{"key":"2025120619203630000_15.4.e090493.7","doi-asserted-by":"crossref","unstructured":"Harrell FE . Multivariable modeling strategies. In: Harrell J , Frank E , eds. Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis. Cham: Springer International Publishing, 2015: 63\u2013102.","DOI":"10.1007\/978-3-319-19425-7_4"},{"key":"2025120619203630000_15.4.e090493.8","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA: ACM, 2016: 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"2025120619203630000_15.4.e090493.9","unstructured":"Prokhorenkova L , Gusev G , Vorobev A , et al . CatBoost: unbiased boosting with categorical features. In: Advances in Neural Information Processing Systems. 31. Curran Associates, Inc, 2018."},{"key":"2025120619203630000_15.4.e090493.10","unstructured":"Ke G . LightGBM: a highly efficient gradient boosting decision tree. In: Advances in Neural Information Processing Systems. 30. Curran Associates, Inc, 2017."},{"key":"2025120619203630000_15.4.e090493.11","unstructured":"Grinsztajn L , Oyallon E , Varoquaux G . Why do tree-based models still outperform deep learning on typical tabular data?"},{"key":"2025120619203630000_15.4.e090493.12","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09896-5"},{"key":"2025120619203630000_15.4.e090493.13","doi-asserted-by":"publisher","DOI":"10.1016\/S0300-9572(00)00158-1"},{"key":"2025120619203630000_15.4.e090493.14","doi-asserted-by":"crossref","unstructured":"Akiba T , Sano S , Yanase T , et al . Optuna: a next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2019:2623\u201331. doi:10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"key":"2025120619203630000_15.4.e090493.15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"2025120619203630000_15.4.e090493.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2004.01.035"},{"key":"2025120619203630000_15.4.e090493.17","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1016\/j.resuscitation.2019.12.001","article-title":"Predicting the probability of survival with mild or moderate neurological dysfunction after in-hospital cardiopulmonary arrest: The GO-FAR 2 score","volume":"146","author":"George","year":"2020","journal-title":"Resuscitation"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-090493","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,7]],"date-time":"2025-12-07T03:20:49Z","timestamp":1765077649000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-090493"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":17,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,27]]},"published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1136\/bmjopen-2024-090493"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-090493","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}