Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis

Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divide...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of personalized medicine 2022-11, Vol.12 (11), p.1930
Hauptverfasser: Yu, Chenyan, Li, Yao, Yin, Minyue, Gao, Jingwen, Xi, Liting, Lin, Jiaxi, Liu, Lu, Zhang, Huixian, Wu, Airong, Xu, Chunfang, Liu, Xiaolin, Wang, Yue, Zhu, Jinzhou
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 11
container_start_page 1930
container_title Journal of personalized medicine
container_volume 12
creator Yu, Chenyan
Li, Yao
Yin, Minyue
Gao, Jingwen
Xi, Liting
Lin, Jiaxi
Liu, Lu
Zhang, Huixian
Wu, Airong
Xu, Chunfang
Liu, Xiaolin
Wang, Yue
Zhu, Jinzhou
description Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.
doi_str_mv 10.3390/jpm12111930
format Article
fullrecord <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9693570</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2748294783</sourcerecordid><originalsourceid>FETCH-LOGICAL-c386t-76b6cac4481a2b9406bdaa9f5d4d035b0662d51362440d12f222446c974fc7513</originalsourceid><addsrcrecordid>eNpdkctKxTAQhoMoKurKFyi4EaSaW9NmI8jxCsfLQtchTVKbQ5sck1Q5b2-8IOoQmJn8Hz8zDAD7CB4TwuHJYjkijBDiBK6BbQzrqqQUs_Vf9RbYi3EBczQVxgxugi3CKMYIVttAn03JjzIZXdxK1VtnirmRwVn3XFhXPASjrUofHYHluVwVtz4kOdi0-pRlssalWLzZ1Bd33pWz3g8mpvyvipkNoffRxl2w0ckhmr3vvAOeLi8eZ9fl_P7qZnY2LxVpWCpr1jIlFaUNkrjlFLJWS8m7SlMNSdVCxrCuEGGYUqgR7jDOFVO8pp2qs7ADTr98l1M7Gq3yaEEOYhnsKMNKeGnFX8XZXjz7V8EZJ1UNs8Hht0HwL1PeQ4w2KjMM0hk_RYFrwvNrapzRg3_owk_B5fUyRRvMad2QTB19USr4GIPpfoZBUHwcUPw6IHkH3mSL3w</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2748294783</pqid></control><display><type>article</type><title>Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central</source><source>PubMed Central Open Access</source><creator>Yu, Chenyan ; Li, Yao ; Yin, Minyue ; Gao, Jingwen ; Xi, Liting ; Lin, Jiaxi ; Liu, Lu ; Zhang, Huixian ; Wu, Airong ; Xu, Chunfang ; Liu, Xiaolin ; Wang, Yue ; Zhu, Jinzhou</creator><creatorcontrib>Yu, Chenyan ; Li, Yao ; Yin, Minyue ; Gao, Jingwen ; Xi, Liting ; Lin, Jiaxi ; Liu, Lu ; Zhang, Huixian ; Wu, Airong ; Xu, Chunfang ; Liu, Xiaolin ; Wang, Yue ; Zhu, Jinzhou</creatorcontrib><description>Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.</description><identifier>ISSN: 2075-4426</identifier><identifier>EISSN: 2075-4426</identifier><identifier>DOI: 10.3390/jpm12111930</identifier><identifier>PMID: 36422105</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Algorithms ; Ascites ; Automation ; Bilirubin ; Cholangitis ; Cholesterol ; Cirrhosis ; Creatinine ; Datasets ; Deep learning ; Gallbladder diseases ; Hepatitis ; High density lipoprotein ; Hospitals ; Laboratories ; Learning algorithms ; Liver cirrhosis ; Liver diseases ; Machine learning ; Medical prognosis ; Mortality ; Patients ; Precision medicine ; Regression analysis ; Trends ; Variables</subject><ispartof>Journal of personalized medicine, 2022-11, Vol.12 (11), p.1930</ispartof><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2022 by the authors. 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c386t-76b6cac4481a2b9406bdaa9f5d4d035b0662d51362440d12f222446c974fc7513</citedby><cites>FETCH-LOGICAL-c386t-76b6cac4481a2b9406bdaa9f5d4d035b0662d51362440d12f222446c974fc7513</cites><orcidid>0000-0003-4171-7457 ; 0000-0002-9772-4608 ; 0000-0003-0544-9248 ; 0000-0002-3724-5744</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9693570/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC9693570/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,314,723,776,780,881,27901,27902,53766,53768</link.rule.ids></links><search><creatorcontrib>Yu, Chenyan</creatorcontrib><creatorcontrib>Li, Yao</creatorcontrib><creatorcontrib>Yin, Minyue</creatorcontrib><creatorcontrib>Gao, Jingwen</creatorcontrib><creatorcontrib>Xi, Liting</creatorcontrib><creatorcontrib>Lin, Jiaxi</creatorcontrib><creatorcontrib>Liu, Lu</creatorcontrib><creatorcontrib>Zhang, Huixian</creatorcontrib><creatorcontrib>Wu, Airong</creatorcontrib><creatorcontrib>Xu, Chunfang</creatorcontrib><creatorcontrib>Liu, Xiaolin</creatorcontrib><creatorcontrib>Wang, Yue</creatorcontrib><creatorcontrib>Zhu, Jinzhou</creatorcontrib><title>Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis</title><title>Journal of personalized medicine</title><description>Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.</description><subject>Algorithms</subject><subject>Ascites</subject><subject>Automation</subject><subject>Bilirubin</subject><subject>Cholangitis</subject><subject>Cholesterol</subject><subject>Cirrhosis</subject><subject>Creatinine</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Gallbladder diseases</subject><subject>Hepatitis</subject><subject>High density lipoprotein</subject><subject>Hospitals</subject><subject>Laboratories</subject><subject>Learning algorithms</subject><subject>Liver cirrhosis</subject><subject>Liver diseases</subject><subject>Machine learning</subject><subject>Medical prognosis</subject><subject>Mortality</subject><subject>Patients</subject><subject>Precision medicine</subject><subject>Regression analysis</subject><subject>Trends</subject><subject>Variables</subject><issn>2075-4426</issn><issn>2075-4426</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpdkctKxTAQhoMoKurKFyi4EaSaW9NmI8jxCsfLQtchTVKbQ5sck1Q5b2-8IOoQmJn8Hz8zDAD7CB4TwuHJYjkijBDiBK6BbQzrqqQUs_Vf9RbYi3EBczQVxgxugi3CKMYIVttAn03JjzIZXdxK1VtnirmRwVn3XFhXPASjrUofHYHluVwVtz4kOdi0-pRlssalWLzZ1Bd33pWz3g8mpvyvipkNoffRxl2w0ckhmr3vvAOeLi8eZ9fl_P7qZnY2LxVpWCpr1jIlFaUNkrjlFLJWS8m7SlMNSdVCxrCuEGGYUqgR7jDOFVO8pp2qs7ADTr98l1M7Gq3yaEEOYhnsKMNKeGnFX8XZXjz7V8EZJ1UNs8Hht0HwL1PeQ4w2KjMM0hk_RYFrwvNrapzRg3_owk_B5fUyRRvMad2QTB19USr4GIPpfoZBUHwcUPw6IHkH3mSL3w</recordid><startdate>20221119</startdate><enddate>20221119</enddate><creator>Yu, Chenyan</creator><creator>Li, Yao</creator><creator>Yin, Minyue</creator><creator>Gao, Jingwen</creator><creator>Xi, Liting</creator><creator>Lin, Jiaxi</creator><creator>Liu, Lu</creator><creator>Zhang, Huixian</creator><creator>Wu, Airong</creator><creator>Xu, Chunfang</creator><creator>Liu, Xiaolin</creator><creator>Wang, Yue</creator><creator>Zhu, Jinzhou</creator><general>MDPI AG</general><general>MDPI</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FH</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BBNVY</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>LK8</scope><scope>M7P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-4171-7457</orcidid><orcidid>https://orcid.org/0000-0002-9772-4608</orcidid><orcidid>https://orcid.org/0000-0003-0544-9248</orcidid><orcidid>https://orcid.org/0000-0002-3724-5744</orcidid></search><sort><creationdate>20221119</creationdate><title>Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis</title><author>Yu, Chenyan ; Li, Yao ; Yin, Minyue ; Gao, Jingwen ; Xi, Liting ; Lin, Jiaxi ; Liu, Lu ; Zhang, Huixian ; Wu, Airong ; Xu, Chunfang ; Liu, Xiaolin ; Wang, Yue ; Zhu, Jinzhou</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c386t-76b6cac4481a2b9406bdaa9f5d4d035b0662d51362440d12f222446c974fc7513</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Ascites</topic><topic>Automation</topic><topic>Bilirubin</topic><topic>Cholangitis</topic><topic>Cholesterol</topic><topic>Cirrhosis</topic><topic>Creatinine</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Gallbladder diseases</topic><topic>Hepatitis</topic><topic>High density lipoprotein</topic><topic>Hospitals</topic><topic>Laboratories</topic><topic>Learning algorithms</topic><topic>Liver cirrhosis</topic><topic>Liver diseases</topic><topic>Machine learning</topic><topic>Medical prognosis</topic><topic>Mortality</topic><topic>Patients</topic><topic>Precision medicine</topic><topic>Regression analysis</topic><topic>Trends</topic><topic>Variables</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yu, Chenyan</creatorcontrib><creatorcontrib>Li, Yao</creatorcontrib><creatorcontrib>Yin, Minyue</creatorcontrib><creatorcontrib>Gao, Jingwen</creatorcontrib><creatorcontrib>Xi, Liting</creatorcontrib><creatorcontrib>Lin, Jiaxi</creatorcontrib><creatorcontrib>Liu, Lu</creatorcontrib><creatorcontrib>Zhang, Huixian</creatorcontrib><creatorcontrib>Wu, Airong</creatorcontrib><creatorcontrib>Xu, Chunfang</creatorcontrib><creatorcontrib>Liu, Xiaolin</creatorcontrib><creatorcontrib>Wang, Yue</creatorcontrib><creatorcontrib>Zhu, Jinzhou</creatorcontrib><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Natural Science Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>Biological Science Collection</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Biological Science Collection</collection><collection>Biological Science Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Journal of personalized medicine</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Chenyan</au><au>Li, Yao</au><au>Yin, Minyue</au><au>Gao, Jingwen</au><au>Xi, Liting</au><au>Lin, Jiaxi</au><au>Liu, Lu</au><au>Zhang, Huixian</au><au>Wu, Airong</au><au>Xu, Chunfang</au><au>Liu, Xiaolin</au><au>Wang, Yue</au><au>Zhu, Jinzhou</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis</atitle><jtitle>Journal of personalized medicine</jtitle><date>2022-11-19</date><risdate>2022</risdate><volume>12</volume><issue>11</issue><spage>1930</spage><pages>1930-</pages><issn>2075-4426</issn><eissn>2075-4426</eissn><abstract>Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.</abstract><cop>Basel</cop><pub>MDPI AG</pub><pmid>36422105</pmid><doi>10.3390/jpm12111930</doi><orcidid>https://orcid.org/0000-0003-4171-7457</orcidid><orcidid>https://orcid.org/0000-0002-9772-4608</orcidid><orcidid>https://orcid.org/0000-0003-0544-9248</orcidid><orcidid>https://orcid.org/0000-0002-3724-5744</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2075-4426
ispartof Journal of personalized medicine, 2022-11, Vol.12 (11), p.1930
issn 2075-4426
2075-4426
language eng
recordid cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9693570
source MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central; PubMed Central Open Access
subjects Algorithms
Ascites
Automation
Bilirubin
Cholangitis
Cholesterol
Cirrhosis
Creatinine
Datasets
Deep learning
Gallbladder diseases
Hepatitis
High density lipoprotein
Hospitals
Laboratories
Learning algorithms
Liver cirrhosis
Liver diseases
Machine learning
Medical prognosis
Mortality
Patients
Precision medicine
Regression analysis
Trends
Variables
title Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T20%3A31%3A16IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automated%20Machine%20Learning%20in%20Predicting%2030-Day%20Mortality%20in%20Patients%20with%20Non-Cholestatic%20Cirrhosis&rft.jtitle=Journal%20of%20personalized%20medicine&rft.au=Yu,%20Chenyan&rft.date=2022-11-19&rft.volume=12&rft.issue=11&rft.spage=1930&rft.pages=1930-&rft.issn=2075-4426&rft.eissn=2075-4426&rft_id=info:doi/10.3390/jpm12111930&rft_dat=%3Cproquest_pubme%3E2748294783%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2748294783&rft_id=info:pmid/36422105&rfr_iscdi=true