Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database
Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), w...
Uložené v:
| Vydané v: | Frontiers in medicine Ročník 8; s. 662340 |
|---|---|
| Hlavní autori: | , , , , , , , , , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
Lausanne
Frontiers Media SA
01.07.2021
Frontiers Media S.A |
| Predmet: | |
| ISSN: | 2296-858X, 2296-858X |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Background:
Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission.
Methods:
A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of
k
-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported.
Results:
A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate.
Conclusion:
The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models. |
|---|---|
| AbstractList | Background:
Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission.
Methods:
A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of
k
-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported.
Results:
A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate.
Conclusion:
The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models. Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission. Methods: A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of k-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported. Results: A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate. Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models. Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission. Methods: A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of k-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported. Results: A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate. Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models.Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the Simplified Acute Physiology Score II (SAPS II), Oxford Acute Severity of Illness Score (OASIS), and Sequential Organ Failure Assessment (SOFA), widely used in the general ICU population. We aimed to establish prediction scores on mechanically ventilated patients with the combination of these disease severity scores and other features available on the first day of admission. Methods: A retrospective administrative database study from the Medical Information Mart for Intensive Care (MIMIC-III) database was conducted. The exposures of interest consisted of the demographics, pre-ICU comorbidity, ICU diagnosis, disease severity scores, vital signs, and laboratory test results on the first day of ICU admission. Hospital mortality was used as the outcome. We used the machine learning methods of k-nearest neighbors (KNN), logistic regression, bagging, decision tree, random forest, Extreme Gradient Boosting (XGBoost), and neural network for model establishment. A sample of 70% of the cohort was used for the training set; the remaining 30% was applied for testing. Areas under the receiver operating characteristic curves (AUCs) and calibration plots would be constructed for the evaluation and comparison of the models' performance. The significance of the risk factors was identified through models and the top factors were reported. Results: A total of 28,530 subjects were enrolled through the screening of the MIMIC-III database. After data preprocessing, 25,659 adult patients with 66 predictors were included in the model analyses. With the training set, the models of KNN, logistic regression, decision tree, random forest, neural network, bagging, and XGBoost were established and the testing set obtained AUCs of 0.806, 0.818, 0.743, 0.819, 0.780, 0.803, and 0.821, respectively. The calibration curves of all the models, except for the neural network, performed well. The XGBoost model performed best among the seven models. The top five predictors were age, respiratory dysfunction, SAPS II score, maximum hemoglobin, and minimum lactate. Conclusion: The current study indicates that models with the risk of factors on the first day could be successfully established for predicting mortality in ventilated patients. The XGBoost model performs best among the seven machine learning models. |
| Author | Yao, Renqi Liu, Shi Li, Lin Ren, Chao Du, Bin Li, Wei Guo, Junyang Guo, Qianqian Jin, Xin Chen, Yan Xi, Xiuming Huang, Huibin Zheng, Hua Zhang, Jin Chen, Ge Yu, Qian Wang, Guowei Zhu, Yibing Li, Yang |
| AuthorAffiliation | 5 Department of Burn Surgery, The First Affiliated Hospital of Naval Medical University , Shanghai , China 4 School of Computer Science and Technology, Wuhan University of Technology , Wuhan , China 13 Department of Critical Care Medicine, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University , Beijing , China 8 Beijing Big Eye Xing Tu Culture Media Co., Ltd. , Beijing , China 2 Department of Emergency, Guang'anmen Hospital, China Academy of Chinese Medical Sciences , Beijing , China 10 Medical ICU, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences , Beijing , China 9 School of Information Science and Engineering, Hebei North University , Shijiazhuang , China 7 Yidu Cloud Technology Inc. , Beijing , China 14 Academy for Advanced Interdisciplinary Studies, Peking University , Beijing , China 11 Department of Anesthesiology, Peking University Shougang Hospital , Beijing , China 1 Medical Research and Biometri |
| AuthorAffiliation_xml | – name: 3 School of Economics and Management, Beijing Institute of Technology , Beijing , China – name: 13 Department of Critical Care Medicine, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University , Beijing , China – name: 1 Medical Research and Biometrics Center, National Center for Cardiovascular Diseases, Fuwai Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College , Beijing , China – name: 6 Translational Medicine Research Center, Fourth Medical Center and Medical Innovation Research Division of the Chinese People's Liberation Army (PLA) General Hospital , Beijing , China – name: 8 Beijing Big Eye Xing Tu Culture Media Co., Ltd. , Beijing , China – name: 7 Yidu Cloud Technology Inc. , Beijing , China – name: 14 Academy for Advanced Interdisciplinary Studies, Peking University , Beijing , China – name: 5 Department of Burn Surgery, The First Affiliated Hospital of Naval Medical University , Shanghai , China – name: 9 School of Information Science and Engineering, Hebei North University , Shijiazhuang , China – name: 4 School of Computer Science and Technology, Wuhan University of Technology , Wuhan , China – name: 2 Department of Emergency, Guang'anmen Hospital, China Academy of Chinese Medical Sciences , Beijing , China – name: 10 Medical ICU, Peking Union Medical College Hospital, Peking Union Medical College and Chinese Academy of Medical Sciences , Beijing , China – name: 11 Department of Anesthesiology, Peking University Shougang Hospital , Beijing , China – name: 12 Department of Critical Care Medicine, Fuxing Hospital, Capital Medical University , Beijing , China |
| Author_xml | – sequence: 1 givenname: Yibing surname: Zhu fullname: Zhu, Yibing – sequence: 2 givenname: Jin surname: Zhang fullname: Zhang, Jin – sequence: 3 givenname: Guowei surname: Wang fullname: Wang, Guowei – sequence: 4 givenname: Renqi surname: Yao fullname: Yao, Renqi – sequence: 5 givenname: Chao surname: Ren fullname: Ren, Chao – sequence: 6 givenname: Ge surname: Chen fullname: Chen, Ge – sequence: 7 givenname: Xin surname: Jin fullname: Jin, Xin – sequence: 8 givenname: Junyang surname: Guo fullname: Guo, Junyang – sequence: 9 givenname: Shi surname: Liu fullname: Liu, Shi – sequence: 10 givenname: Hua surname: Zheng fullname: Zheng, Hua – sequence: 11 givenname: Yan surname: Chen fullname: Chen, Yan – sequence: 12 givenname: Qianqian surname: Guo fullname: Guo, Qianqian – sequence: 13 givenname: Lin surname: Li fullname: Li, Lin – sequence: 14 givenname: Bin surname: Du fullname: Du, Bin – sequence: 15 givenname: Xiuming surname: Xi fullname: Xi, Xiuming – sequence: 16 givenname: Wei surname: Li fullname: Li, Wei – sequence: 17 givenname: Huibin surname: Huang fullname: Huang, Huibin – sequence: 18 givenname: Yang surname: Li fullname: Li, Yang – sequence: 19 givenname: Qian surname: Yu fullname: Yu, Qian |
| BookMark | eNp1kktvEzEUhUeoiJbSPUtLbNhM8PvBAqkKr5ES0QUgdpZjexIHx27tCVL-PQ4pEq3Eyq9zv6tzfZ53Zykn33UvEZwRItWbcefdDEOMZpxjQuGT7gJjxXvJ5I-zf_bn3VWtWwghIphRRJ5154RiIThjF93PpbGbkDxYeFNSSGtwU7wLdgo5gWV2PlYw5gKW3m5MCtbEeADffZpCNJN34MZMoZ3qW3CdTDxUX0EewbTxYDksh3k_DAN4byazMtW_6J6OJlZ_db9edt8-fvg6_9wvvnwa5teL3lIupr65WSlqBORKWMyxddLZFRHII4QtZKNQfrRWMuaEktxhQwiXI3VMSgIlIZfdcOK6bLb6toSdKQedTdB_LnJZa1OmYKPXwhlGrGpcBSkVdIVG6ClX1irRetHGendi3e5Xbd62eS0mPoA-fElho9f5l5ZYQiFUA7y-B5R8t_d10rtQrY_RJJ_3VWPGCKaYCtSkrx5Jt3lf2lirJlhgLhRGRyA_qWzJtRY_ahsmc_yv1j9EjaA-xkMf46GP8dCneLRC-Kjwr4v_lvwGE8y88g |
| CitedBy_id | crossref_primary_10_1186_s12889_024_19261_8 crossref_primary_10_1016_j_ins_2022_08_028 crossref_primary_10_1111_1756_185X_14956 crossref_primary_10_3390_app132212263 crossref_primary_10_1016_j_procs_2023_01_173 crossref_primary_10_1186_s12967_023_04205_4 crossref_primary_10_1371_journal_pone_0309383 crossref_primary_10_3390_app13106138 crossref_primary_10_1016_j_engappai_2025_112267 crossref_primary_10_3390_diagnostics12051068 crossref_primary_10_1088_1742_6596_2138_1_012009 crossref_primary_10_1016_j_pan_2024_02_003 crossref_primary_10_3389_fmed_2022_811890 crossref_primary_10_1186_s12911_024_02758_y crossref_primary_10_3390_jcm12041499 crossref_primary_10_1016_j_ajodo_2023_01_017 crossref_primary_10_1016_j_imu_2024_101562 crossref_primary_10_1016_j_heliyon_2023_e18758 crossref_primary_10_3390_antibiotics11030304 crossref_primary_10_1016_j_compbiomed_2025_110028 crossref_primary_10_3389_fpubh_2021_793801 crossref_primary_10_1038_s41598_024_73837_3 crossref_primary_10_1093_biomtc_ujaf019 crossref_primary_10_1002_advs_202400595 crossref_primary_10_2147_JMDH_S416943 crossref_primary_10_1007_s13755_025_00364_4 crossref_primary_10_1109_ACCESS_2024_3409152 crossref_primary_10_3390_s24092721 crossref_primary_10_3389_fneur_2023_1251944 crossref_primary_10_2147_IJGM_S515170 crossref_primary_10_1186_s12967_022_03364_0 crossref_primary_10_3389_fmed_2024_1398565 crossref_primary_10_1038_s41598_024_65128_8 crossref_primary_10_1186_s40537_023_00720_9 crossref_primary_10_1038_s41598_023_32160_z |
| Cites_doi | 10.1186/s12967-020-02620-5 10.1136/bmj.g7594 10.1097/CCM.0b013e31827c086f 10.1016/j.jfma.2017.09.014 10.1038/s41591-018-0213-5 10.1097/CCM.0b013e318298a139 10.1016/j.jvs.2019.12.026 10.1016/j.ijmedinf.2020.104176 10.1097/01.mlr.0000182534.19832.83 10.1016/j.medine.2018.07.019 10.1093/biomet/63.3.581 10.1038/sdata.2016.35 10.21203/rs.2.24188/v1 10.1186/s12916-019-1466-7 10.15537/smj.2015.6.11204 10.1109/JBHI.2014.2371533 10.15537/smj.2019.8.24447 |
| ContentType | Journal Article |
| Copyright | 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. Copyright © 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu. Copyright © 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu. 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu |
| Copyright_xml | – notice: 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: Copyright © 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu. – notice: Copyright © 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu. 2021 Zhu, Zhang, Wang, Yao, Ren, Chen, Jin, Guo, Liu, Zheng, Chen, Guo, Li, Du, Xi, Li, Huang, Li and Yu |
| DBID | AAYXX CITATION 3V. 7X7 7XB 88E 8C1 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3389/fmed.2021.662340 |
| DatabaseName | CrossRef ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Public Health Database ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC ProQuest Central ProQuest One ProQuest Central Proquest Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) ProQuest Health & Medical Collection Medical Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) Directory of Open Access Journals (DOAJ) |
| DatabaseTitle | CrossRef Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest Public Health ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | CrossRef MEDLINE - Academic Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2296-858X |
| ExternalDocumentID | oai_doaj_org_article_7da53c912c904474b1f0e469cc972c04 PMC8280779 10_3389_fmed_2021_662340 |
| GroupedDBID | 53G 5VS 9T4 AAFWJ AAYXX ACGFS ADBBV ADRAZ AFPKN ALMA_UNASSIGNED_HOLDINGS AOIJS BAWUL BCNDV CITATION DIK GROUPED_DOAJ HYE KQ8 M48 M~E OK1 PGMZT RPM 3V. 7X7 7XB 88E 8C1 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA K9. M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM |
| ID | FETCH-LOGICAL-c467t-662b94a70697c262cd8dcb371e112c05f79efcc855d7986d2a3368f4d58830833 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 39 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000673699100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2296-858X |
| IngestDate | Fri Oct 03 12:49:22 EDT 2025 Tue Sep 30 16:26:57 EDT 2025 Thu Oct 02 06:10:49 EDT 2025 Wed Nov 19 00:20:58 EST 2025 Sat Nov 29 04:29:38 EST 2025 Tue Nov 18 21:00:42 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c467t-662b94a70697c262cd8dcb371e112c05f79efcc855d7986d2a3368f4d58830833 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 These authors have contributed equally to this work Edited by: Rahul Kashyap, Mayo Clinic, United States This article was submitted to Intensive Care Medicine and Anesthesiology, a section of the journal Frontiers in Medicine Reviewed by: Mack Sheraton, Trinity Health System, United States; Tarun Singh, Mayo Clinic, United States |
| OpenAccessLink | https://doaj.org/article/7da53c912c904474b1f0e469cc972c04 |
| PMID | 34277655 |
| PQID | 3272679219 |
| PQPubID | 7426803 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_7da53c912c904474b1f0e469cc972c04 pubmedcentral_primary_oai_pubmedcentral_nih_gov_8280779 proquest_miscellaneous_2553242471 proquest_journals_3272679219 crossref_citationtrail_10_3389_fmed_2021_662340 crossref_primary_10_3389_fmed_2021_662340 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-07-01 |
| PublicationDateYYYYMMDD | 2021-07-01 |
| PublicationDate_xml | – month: 07 year: 2021 text: 2021-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Lausanne |
| PublicationPlace_xml | – name: Lausanne |
| PublicationTitle | Frontiers in medicine |
| PublicationYear | 2021 |
| Publisher | Frontiers Media SA Frontiers Media S.A |
| Publisher_xml | – name: Frontiers Media SA – name: Frontiers Media S.A |
| References | Collins (B12) 2015; 350 Hou (B10) 2020; 18 Yao (B16) 2020; 7 Rubin (B14) 1976; 63 Al-Omari (B4) 2015; 36 Ismaeil (B15) 2019; 40 Hung (B2) 2018; 117 Van Calster (B17) 2019; 17 Wunsch (B1) 2013; 41 Herring (B3) 2013; 41 Raffort (B9) 2020; 72 Johnson (B11) 2016; 3 Quan (B13) 2005; 43 García-Gallo (B5) 2020; 44 Komorowski (B6) 2018; 24 Yuan (B7) 2020; 141 Bighamian (B8) 2016; 20 |
| References_xml | – volume: 18 start-page: 462 year: 2020 ident: B10 article-title: Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost publication-title: J Transl Med. doi: 10.1186/s12967-020-02620-5 – volume: 350 start-page: g7594 year: 2015 ident: B12 article-title: Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement publication-title: BMJ. doi: 10.1136/bmj.g7594 – volume: 41 start-page: 1197 year: 2013 ident: B3 article-title: Increasing critical care admissions from U.S. emergency departments, 2001-2009 publication-title: Crit Care Med. doi: 10.1097/CCM.0b013e31827c086f – volume: 117 start-page: 798 year: 2018 ident: B2 article-title: Clinical characteristics and survival outcomes of terminally ill patients undergoing withdrawal of mechanical ventilation publication-title: J Formos Med Assoc. doi: 10.1016/j.jfma.2017.09.014 – volume: 24 start-page: 1716 year: 2018 ident: B6 article-title: The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care publication-title: Nat Med. doi: 10.1038/s41591-018-0213-5 – volume: 41 start-page: 2712 year: 2013 ident: B1 article-title: ICU occupancy and mechanical ventilator use in the United States publication-title: Crit Care Med. doi: 10.1097/CCM.0b013e318298a139 – volume: 72 start-page: 321 year: 2020 ident: B9 article-title: Artificial intelligence in abdominal aortic aneurysm publication-title: J Vasc Surg. doi: 10.1016/j.jvs.2019.12.026 – volume: 141 start-page: 104176 year: 2020 ident: B7 article-title: The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit publication-title: Int J Med Inform. doi: 10.1016/j.ijmedinf.2020.104176 – volume: 43 start-page: 1130 year: 2005 ident: B13 article-title: Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data publication-title: Med Care. doi: 10.1097/01.mlr.0000182534.19832.83 – volume: 44 start-page: 160 year: 2020 ident: B5 article-title: A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis publication-title: Med Intensiva. doi: 10.1016/j.medine.2018.07.019 – volume: 63 start-page: 581 year: 1976 ident: B14 article-title: Inference and missing data publication-title: Biometrika. doi: 10.1093/biomet/63.3.581 – volume: 3 start-page: 160035 year: 2016 ident: B11 article-title: MIMIC-III, a freely accessible critical care database publication-title: Sci Data. doi: 10.1038/sdata.2016.35 – volume: 7 start-page: 445 year: 2020 ident: B16 article-title: A machine learning-based prediction of hospital mortality in patients with postoperative sepsis publication-title: Front Med (Lausanne). doi: 10.21203/rs.2.24188/v1 – volume: 17 start-page: 230 year: 2019 ident: B17 article-title: Topic Group ‘Evaluating diagnostic tests and prediction models' of the STRATOS initiative. Calibration: the Achilles heel of predictive analytics publication-title: BMC Med doi: 10.1186/s12916-019-1466-7 – volume: 36 start-page: 759 year: 2015 ident: B4 article-title: Critical care service in Saudi Arabia publication-title: Saudi Med J. doi: 10.15537/smj.2015.6.11204 – volume: 20 start-page: 416 year: 2016 ident: B8 article-title: Prediction of hemodynamic response to epinephrine via model-based system identification publication-title: IEEE J Biomed Health Inform. doi: 10.1109/JBHI.2014.2371533 – volume: 40 start-page: 781 year: 2019 ident: B15 article-title: Survival of mechanically ventilated patients admitted to intensive care units. Results from a tertiary care center between 2016-2018 publication-title: Saudi Med J. doi: 10.15537/smj.2019.8.24447 |
| SSID | ssj0001325413 |
| Score | 2.411362 |
| Snippet | Background:
Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the... Background: Mechanically ventilated patients in the intensive care unit (ICU) have high mortality rates. There are multiple prediction scores, such as the... |
| SourceID | doaj pubmedcentral proquest crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database |
| StartPage | 662340 |
| SubjectTerms | Blood diseases Blood pressure Creatinine death Diabetes Glucose Heart failure Hemoglobin Hypertension Hypothyroidism Intensive care intensive care unit Kidney diseases Liver diseases Machine learning mechanical ventilation Medical history Medicine Metabolism Metastasis Mortality Nervous system prediction model Respiratory failure Sepsis Software Stroke Structured Query Language-SQL Ventilators Vital signs |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwEB3BFiEufCMCBRmJC4fQJHZimwuipRV72NUKAerNij9SKlZJ2WyR-PfMJN5t99IL19hR7DyP_cYevwF4y7WqvW3KtLDa05WcLLWByxSdDZuFXAetmiHZhJzP1empXsQNtz6GVW7mxGGi9p2jPfIDXsiikhoN7OPF75SyRtHpakyhcRv2SKlMTGDv8Hi--Hq1y8LRAcr5eD6J3phGuAIJhBb5-wpXftrzuLYeDbL9O1xzN1Ly2tJz8uB_G_0Q7kfSyT6No-QR3ArtY7g7i8fqT-DXbAipDCyqrZ6xxYoKCTRG2dKWPUNyy2aB7gkTrMu_7AfFGS2Rqnq2GMVZ-w9s1DgJPesahtSSzXBuPEqn0yn7XK9rWjKfwveT429HX9KYhSF1OImuU_xNVotaZpWWrqgK55V3lss8IFVzWdlIHRrnVFl6qVXli5rzSjXCl0pxJHj8GUzarg3PgcngJPo7zhWqFsg1bFV5rZ0SubVlLWUCBxssjIsS5ZQpY2nQVSH0DKFnCD0zopfAu-0bF6M8xw11DwnebT0S1h4edKszE-3USF-X3Gnsmc6EkMLmTRZEpZ3TEnsrEtjfIG2itffmCuYE3myL0U7p8KVuQ3fZG3TdiLsiF0hA7gyqnQbtlrTnPwfFb0WaRVK_uPnjL-EedXcMJt6HyXp1GV7BHfdnfd6vXkfT-AdMDRjO priority: 102 providerName: ProQuest |
| Title | Machine Learning Prediction Models for Mechanically Ventilated Patients: Analyses of the MIMIC-III Database |
| URI | https://www.proquest.com/docview/3272679219 https://www.proquest.com/docview/2553242471 https://pubmed.ncbi.nlm.nih.gov/PMC8280779 https://doaj.org/article/7da53c912c904474b1f0e469cc972c04 |
| Volume | 8 |
| WOSCitedRecordID | wos000673699100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: DOA dateStart: 20140101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: M~E dateStart: 20140101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: 7X7 dateStart: 20190101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: BENPR dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Public Health Database customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: 8C1 dateStart: 20190101 isFulltext: true titleUrlDefault: https://search.proquest.com/publichealth providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2296-858X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001325413 issn: 2296-858X databaseCode: PIMPY dateStart: 20190101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nj9MwELVgQYgL4lNkWSojceEQNrGTjM2NLbuih1QRAlROVmI7sKJKUdNdiX_PTJytmgtcuFhK7EjxjO15Y4_fMPZaalW7ps1j0WhHV3KSuPESYnQ2msSn2mvVDskmYLlUq5WuDlJ9UUxYoAcOgjsFV-fS6lRYnWQZZE3aJh59Oms1CBuYQBH1HDhTw-6KRMcnleFcEr0wjWryRAwq0rcFWnza6ziwQwNd_wRjTiMkD0zOxUP2YMSK_H34x0fslu8es3vleBr-hP0sh0hIz0eS1O-82lIlyZpTkrN1zxGT8tLT9V7Sxvo3_0rhQWtEmI5XgVO1f8cDNYnv-abliAh5iUvaPF4sFvxDvavJ0j1lXy7OP88_xmPyhNji2reLsZeNzmpICg1WFMI65WwjIfWIsGySt6B9a63KcwdaFU7UUhaqzVyulERcJp-xo27T-eeMg7eAboq1QtUZQoSmKJzWVmVp0-Q1QMROb0Rp7MgsTgku1gY9DBK-IeEbEr4Jwo_Ym_0XvwKrxl_anpF29u2ID3t4gaPEjKPE_GuUROzkRrdmnKS9kQJEARrX7Ii92lfj9KIzk7rzm6veoMdFkBNNeMRgMiYmPzSt6S5_DETdiqiGQB__jx68YPdJKCFS-IQd7bZX_iW7a693l_12xm7DCoZSYanm6YzdOTtfVp9mw7zAp2pRVt_-AInPDpQ |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VLQIufCMWChgJDhxCkziJbSSEoKVq1Ga1h4LKySS2UypWSdlsQf1T_EZm8rHtXnrrgWucxHH8PH5jj98AvOJK5rYoYy8slKUjOb5XOC48dDYK3wXKKVm2ySbEZCIPD9V0Df4OZ2EorHKwia2htrWhNfJNHoowEQoH2IeTXx5ljaLd1SGFRgeLPXf2B1225n26jf37Ogx3Ph9s7Xp9VgHPoFFYeEmCnxXlwk-UMGESGiutKbgIHFIP48elUK40RsaxFUomNsw5T2QZ2VhKjoSF43uvwXqEYJcjWJ-m2fTb-aoOR4cr4N1-KHp_CuHhSJA0DN5ixZzWWC7Mf22agBVuuxqZeWGq27nzv_2ku3C7J9XsYzcK7sGaq-7DjawPG3gAP7M2ZNSxXk32iE3nVEigZJQNbtYwJO8sc3QOmmA7O2NfKY5qhlTcsmknPtu8Y52Gi2tYXTKkzixD27_lpWnKtvNFTpTgIXy5kqY-glFVV-4xMOGMQH_OmFDmEXKpIkmsUkZGQVHEuRBj2Bz6Xptegp0ygcw0umKEFk1o0YQW3aFlDG-WT5x08iOX3PuJ4LS8j4TD2wv1_Ej3dkgLm8fcKGyZ8qNIREVQ-i5KlDFKYGujMWwMyNK9NWv0OazG8HJZjHaINpfyytWnjUbXlLg5cp0xiBUQr3zQakl1_KNVNJekySTUk8srfwE3dw-yfb2fTvaewi1qehc4vQGjxfzUPYPr5vfiuJk_74clg-9XDfJ_I91zxg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Machine+Learning+Prediction+Models+for+Mechanically+Ventilated+Patients%3A+Analyses+of+the+MIMIC-III+Database&rft.jtitle=Frontiers+in+medicine&rft.au=Zhu%2C+Yibing&rft.au=Zhang%2C+Jin&rft.au=Wang%2C+Guowei&rft.au=Yao%2C+Renqi&rft.date=2021-07-01&rft.pub=Frontiers+Media+S.A&rft.eissn=2296-858X&rft.volume=8&rft_id=info:doi/10.3389%2Ffmed.2021.662340&rft_id=info%3Apmid%2F34277655&rft.externalDocID=PMC8280779 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2296-858X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2296-858X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2296-858X&client=summon |