Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence
Background Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary. Aim Our objective was to develop a prediction model for ve...
Gespeichert in:
Veröffentlicht in: | International journal of clinical pharmacy 2024-08, Vol.46 (4), p.899-909 |
---|---|
Hauptverfasser: | , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 909 |
---|---|
container_issue | 4 |
container_start_page | 899 |
container_title | International journal of clinical pharmacy |
container_volume | 46 |
creator | Chang, Luyao Hao, Xin Yu, Jing Zhang, Jinyuan Liu, Yimeng Ye, Xuxiao Yu, Ze Gao, Fei Pang, Xiaolu Zhou, Chunhua |
description | Background
Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary.
Aim
Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques.
Method
Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations.
Results
A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (
R
2
= 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value.
Conclusion
The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice. |
doi_str_mv | 10.1007/s11096-024-01724-y |
format | Article |
fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_miscellaneous_3055892699</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A803123580</galeid><sourcerecordid>A803123580</sourcerecordid><originalsourceid>FETCH-LOGICAL-c393t-3d35bc238efc0a60d49e17b17a11b9a401d207a57a1f7ad1faabbb40d526f0563</originalsourceid><addsrcrecordid>eNp9ktuO1SAUhonROJPtvIAXpok33nTkUErr3WR01GQSb_SaUFhsmVDYQru1z-BLS6fjeIgREg6L7_8Di4XQU4LPCcbiZSYE922NaVNjIsq4PECnlBJcC0HIw_s1ZifoLOcbXFrTUsKbx-iEdYIzLNpT9P01HMHHgwv7SlWj0p9dgMqDSmENjdGAr2xM1SGBcXpag0cIXln1bSVVCR2hcA6mpdIxaAhTUpOL4VUxTDClmA-wUXmazVLNeTVJoHz9NSZvKjg6A0X4BD2yymc4u5t36NPVm4-X7-rrD2_fX15c15r1bKqZYXzQlHVgNVYtNk0PRAxEKEKGXjWYGIqF4mVvhTLEKjUMQ4MNp63FvGU79GLzPaT4ZYY8ydFlDd6rAHHOkmHOu562fV_Q53-hN3FOodyuUB0XHLfdb9ReeZAu2FhSoFdTedFhRijjZdqh839QpRsYXckcWFfifwjoJtAlhzmBlYfkRpUWSbBci0BuRSBLEcjbIpBLET27u_E8jGDuJT-_vABsA3I5CntIv570H9sfXV--Tw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3085750689</pqid></control><display><type>article</type><title>Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence</title><source>SpringerLink Journals - AutoHoldings</source><creator>Chang, Luyao ; Hao, Xin ; Yu, Jing ; Zhang, Jinyuan ; Liu, Yimeng ; Ye, Xuxiao ; Yu, Ze ; Gao, Fei ; Pang, Xiaolu ; Zhou, Chunhua</creator><creatorcontrib>Chang, Luyao ; Hao, Xin ; Yu, Jing ; Zhang, Jinyuan ; Liu, Yimeng ; Ye, Xuxiao ; Yu, Ze ; Gao, Fei ; Pang, Xiaolu ; Zhou, Chunhua</creatorcontrib><description>Background
Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary.
Aim
Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques.
Method
Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations.
Results
A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (
R
2
= 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value.
Conclusion
The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice.</description><identifier>ISSN: 2210-7703</identifier><identifier>ISSN: 2210-7711</identifier><identifier>EISSN: 2210-7711</identifier><identifier>DOI: 10.1007/s11096-024-01724-y</identifier><identifier>PMID: 38753076</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Adenosine deaminase ; Algorithms ; Analysis ; Antidepressants ; Blood levels ; Data mining ; Deep learning ; Evidence-based medicine ; Health aspects ; Hyperlipidemia ; Internal Medicine ; Learning algorithms ; Machine learning ; Medicine ; Medicine & Public Health ; Patients ; Pharmacy ; Prediction models ; Research Article ; Venlafaxine</subject><ispartof>International journal of clinical pharmacy, 2024-08, Vol.46 (4), p.899-909</ispartof><rights>The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><rights>2024. The Author(s), under exclusive licence to Springer Nature Switzerland AG.</rights><rights>COPYRIGHT 2024 Springer</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c393t-3d35bc238efc0a60d49e17b17a11b9a401d207a57a1f7ad1faabbb40d526f0563</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11096-024-01724-y$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11096-024-01724-y$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38753076$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Chang, Luyao</creatorcontrib><creatorcontrib>Hao, Xin</creatorcontrib><creatorcontrib>Yu, Jing</creatorcontrib><creatorcontrib>Zhang, Jinyuan</creatorcontrib><creatorcontrib>Liu, Yimeng</creatorcontrib><creatorcontrib>Ye, Xuxiao</creatorcontrib><creatorcontrib>Yu, Ze</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><creatorcontrib>Pang, Xiaolu</creatorcontrib><creatorcontrib>Zhou, Chunhua</creatorcontrib><title>Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence</title><title>International journal of clinical pharmacy</title><addtitle>Int J Clin Pharm</addtitle><addtitle>Int J Clin Pharm</addtitle><description>Background
Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary.
Aim
Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques.
Method
Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations.
Results
A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (
R
2
= 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value.
Conclusion
The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice.</description><subject>Adenosine deaminase</subject><subject>Algorithms</subject><subject>Analysis</subject><subject>Antidepressants</subject><subject>Blood levels</subject><subject>Data mining</subject><subject>Deep learning</subject><subject>Evidence-based medicine</subject><subject>Health aspects</subject><subject>Hyperlipidemia</subject><subject>Internal Medicine</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Patients</subject><subject>Pharmacy</subject><subject>Prediction models</subject><subject>Research Article</subject><subject>Venlafaxine</subject><issn>2210-7703</issn><issn>2210-7711</issn><issn>2210-7711</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9ktuO1SAUhonROJPtvIAXpok33nTkUErr3WR01GQSb_SaUFhsmVDYQru1z-BLS6fjeIgREg6L7_8Di4XQU4LPCcbiZSYE922NaVNjIsq4PECnlBJcC0HIw_s1ZifoLOcbXFrTUsKbx-iEdYIzLNpT9P01HMHHgwv7SlWj0p9dgMqDSmENjdGAr2xM1SGBcXpag0cIXln1bSVVCR2hcA6mpdIxaAhTUpOL4VUxTDClmA-wUXmazVLNeTVJoHz9NSZvKjg6A0X4BD2yymc4u5t36NPVm4-X7-rrD2_fX15c15r1bKqZYXzQlHVgNVYtNk0PRAxEKEKGXjWYGIqF4mVvhTLEKjUMQ4MNp63FvGU79GLzPaT4ZYY8ydFlDd6rAHHOkmHOu562fV_Q53-hN3FOodyuUB0XHLfdb9ReeZAu2FhSoFdTedFhRijjZdqh839QpRsYXckcWFfifwjoJtAlhzmBlYfkRpUWSbBci0BuRSBLEcjbIpBLET27u_E8jGDuJT-_vABsA3I5CntIv570H9sfXV--Tw</recordid><startdate>20240801</startdate><enddate>20240801</enddate><creator>Chang, Luyao</creator><creator>Hao, Xin</creator><creator>Yu, Jing</creator><creator>Zhang, Jinyuan</creator><creator>Liu, Yimeng</creator><creator>Ye, Xuxiao</creator><creator>Yu, Ze</creator><creator>Gao, Fei</creator><creator>Pang, Xiaolu</creator><creator>Zhou, Chunhua</creator><general>Springer International Publishing</general><general>Springer</general><general>Springer Nature B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7T5</scope><scope>7U9</scope><scope>H94</scope><scope>K9.</scope><scope>NAPCQ</scope><scope>7X8</scope></search><sort><creationdate>20240801</creationdate><title>Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence</title><author>Chang, Luyao ; Hao, Xin ; Yu, Jing ; Zhang, Jinyuan ; Liu, Yimeng ; Ye, Xuxiao ; Yu, Ze ; Gao, Fei ; Pang, Xiaolu ; Zhou, Chunhua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c393t-3d35bc238efc0a60d49e17b17a11b9a401d207a57a1f7ad1faabbb40d526f0563</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adenosine deaminase</topic><topic>Algorithms</topic><topic>Analysis</topic><topic>Antidepressants</topic><topic>Blood levels</topic><topic>Data mining</topic><topic>Deep learning</topic><topic>Evidence-based medicine</topic><topic>Health aspects</topic><topic>Hyperlipidemia</topic><topic>Internal Medicine</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Patients</topic><topic>Pharmacy</topic><topic>Prediction models</topic><topic>Research Article</topic><topic>Venlafaxine</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chang, Luyao</creatorcontrib><creatorcontrib>Hao, Xin</creatorcontrib><creatorcontrib>Yu, Jing</creatorcontrib><creatorcontrib>Zhang, Jinyuan</creatorcontrib><creatorcontrib>Liu, Yimeng</creatorcontrib><creatorcontrib>Ye, Xuxiao</creatorcontrib><creatorcontrib>Yu, Ze</creatorcontrib><creatorcontrib>Gao, Fei</creatorcontrib><creatorcontrib>Pang, Xiaolu</creatorcontrib><creatorcontrib>Zhou, Chunhua</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>Immunology Abstracts</collection><collection>Virology and AIDS Abstracts</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Nursing & Allied Health Premium</collection><collection>MEDLINE - Academic</collection><jtitle>International journal of clinical pharmacy</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chang, Luyao</au><au>Hao, Xin</au><au>Yu, Jing</au><au>Zhang, Jinyuan</au><au>Liu, Yimeng</au><au>Ye, Xuxiao</au><au>Yu, Ze</au><au>Gao, Fei</au><au>Pang, Xiaolu</au><au>Zhou, Chunhua</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence</atitle><jtitle>International journal of clinical pharmacy</jtitle><stitle>Int J Clin Pharm</stitle><addtitle>Int J Clin Pharm</addtitle><date>2024-08-01</date><risdate>2024</risdate><volume>46</volume><issue>4</issue><spage>899</spage><epage>909</epage><pages>899-909</pages><issn>2210-7703</issn><issn>2210-7711</issn><eissn>2210-7711</eissn><abstract>Background
Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary.
Aim
Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques.
Method
Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations.
Results
A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (
R
2
= 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value.
Conclusion
The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><pmid>38753076</pmid><doi>10.1007/s11096-024-01724-y</doi><tpages>11</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2210-7703 |
ispartof | International journal of clinical pharmacy, 2024-08, Vol.46 (4), p.899-909 |
issn | 2210-7703 2210-7711 2210-7711 |
language | eng |
recordid | cdi_proquest_miscellaneous_3055892699 |
source | SpringerLink Journals - AutoHoldings |
subjects | Adenosine deaminase Algorithms Analysis Antidepressants Blood levels Data mining Deep learning Evidence-based medicine Health aspects Hyperlipidemia Internal Medicine Learning algorithms Machine learning Medicine Medicine & Public Health Patients Pharmacy Prediction models Research Article Venlafaxine |
title | Developing a machine learning model for predicting venlafaxine active moiety concentration: a retrospective study using real-world evidence |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T15%3A02%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Developing%20a%20machine%20learning%20model%20for%20predicting%20venlafaxine%20active%20moiety%20concentration:%20a%20retrospective%20study%20using%20real-world%20evidence&rft.jtitle=International%20journal%20of%20clinical%20pharmacy&rft.au=Chang,%20Luyao&rft.date=2024-08-01&rft.volume=46&rft.issue=4&rft.spage=899&rft.epage=909&rft.pages=899-909&rft.issn=2210-7703&rft.eissn=2210-7711&rft_id=info:doi/10.1007/s11096-024-01724-y&rft_dat=%3Cgale_proqu%3EA803123580%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3085750689&rft_id=info:pmid/38753076&rft_galeid=A803123580&rfr_iscdi=true |