Loading…

Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)

•Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative cli...

Full description

Saved in:
Bibliographic Details
Published in:European journal of radiology 2024-07, Vol.176, p.111508, Article 111508
Main Authors: Zou, Xugong, Cui, Ning, Ma, Qiang, Lin, Zhipeng, Zhang, Jian, Li, Xiaoqun
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c354t-4d69197c69cd570fec7b673b02b4a18761b68cde302d158b376df4841fcff8883
container_end_page
container_issue
container_start_page 111508
container_title European journal of radiology
container_volume 176
creator Zou, Xugong
Cui, Ning
Ma, Qiang
Lin, Zhipeng
Zhang, Jian
Li, Xiaoqun
description •Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care. This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP). Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71–0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort. The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.
doi_str_mv 10.1016/j.ejrad.2024.111508
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3056670373</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0720048X24002249</els_id><sourcerecordid>3056670373</sourcerecordid><originalsourceid>FETCH-LOGICAL-c354t-4d69197c69cd570fec7b673b02b4a18761b68cde302d158b376df4841fcff8883</originalsourceid><addsrcrecordid>eNp9kEFO3DAYha0KVAbaEyBVXsIigx07trNggaC0lZDYtFJ3lmP_Lh4SO7UzCI7APThZT0KmAyxZPenXe__T-xA6pGRJCRUnqyWssnHLmtR8SSltiPqAFlTJupKyljtoQWRNKsLV7z20X8qKENLwtv6I9piSTdtwtkDjBdxBn8YB4oSTxwYPxt6ECLgHk2OIf_CQHPTYp4zHDC7YaXMcI6yHNN2kbO5xDuUWh4htMvfB9LNmwBHA9YC7kMbygI_-PT4xbIfjT2jXm77A5xc9QL8uv_48_15dXX_7cX52VVnW8KniTrS0lVa01jWSeLCyE5J1pO64mTcK2gllHTBSO9qojknhPFeceuu9UoodoKPt3zGnv2sokx5CsdD3JkJaF81II4QkTLLZyrZWm1MpGbwecxhMftCU6A1qvdL_UesNar1FPae-vBSsuwHcW-aV7Ww43RpgnnkXIOtiA0Q7M8xgJ-1SeLfgGSHpkc0</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3056670373</pqid></control><display><type>article</type><title>Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)</title><source>Elsevier</source><creator>Zou, Xugong ; Cui, Ning ; Ma, Qiang ; Lin, Zhipeng ; Zhang, Jian ; Li, Xiaoqun</creator><creatorcontrib>Zou, Xugong ; Cui, Ning ; Ma, Qiang ; Lin, Zhipeng ; Zhang, Jian ; Li, Xiaoqun</creatorcontrib><description>•Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care. This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP). Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71–0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort. The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.</description><identifier>ISSN: 0720-048X</identifier><identifier>ISSN: 1872-7727</identifier><identifier>EISSN: 1872-7727</identifier><identifier>DOI: 10.1016/j.ejrad.2024.111508</identifier><identifier>PMID: 38759543</identifier><language>eng</language><publisher>Ireland: Elsevier B.V</publisher><subject>Adult ; Aged ; Biopsy, Large-Core Needle ; Coaxial core needle lung biopsy (CCNB) ; Female ; Humans ; Image-Guided Biopsy ; Lung Neoplasms - diagnostic imaging ; Lung Neoplasms - pathology ; Machine Learning ; Machine learning (ML) ; Male ; Middle Aged ; Pneumothorax ; Pneumothorax - diagnostic imaging ; Pneumothorax - etiology ; Prediction model ; Retrospective Studies ; Risk Assessment ; Risk factor ; Risk Factors ; Sensitivity and Specificity</subject><ispartof>European journal of radiology, 2024-07, Vol.176, p.111508, Article 111508</ispartof><rights>2024</rights><rights>Copyright © 2024. Published by Elsevier B.V.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c354t-4d69197c69cd570fec7b673b02b4a18761b68cde302d158b376df4841fcff8883</cites><orcidid>0000-0001-6247-2554</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,27905,27906</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/38759543$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zou, Xugong</creatorcontrib><creatorcontrib>Cui, Ning</creatorcontrib><creatorcontrib>Ma, Qiang</creatorcontrib><creatorcontrib>Lin, Zhipeng</creatorcontrib><creatorcontrib>Zhang, Jian</creatorcontrib><creatorcontrib>Li, Xiaoqun</creatorcontrib><title>Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)</title><title>European journal of radiology</title><addtitle>Eur J Radiol</addtitle><description>•Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care. This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP). Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71–0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort. The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.</description><subject>Adult</subject><subject>Aged</subject><subject>Biopsy, Large-Core Needle</subject><subject>Coaxial core needle lung biopsy (CCNB)</subject><subject>Female</subject><subject>Humans</subject><subject>Image-Guided Biopsy</subject><subject>Lung Neoplasms - diagnostic imaging</subject><subject>Lung Neoplasms - pathology</subject><subject>Machine Learning</subject><subject>Machine learning (ML)</subject><subject>Male</subject><subject>Middle Aged</subject><subject>Pneumothorax</subject><subject>Pneumothorax - diagnostic imaging</subject><subject>Pneumothorax - etiology</subject><subject>Prediction model</subject><subject>Retrospective Studies</subject><subject>Risk Assessment</subject><subject>Risk factor</subject><subject>Risk Factors</subject><subject>Sensitivity and Specificity</subject><issn>0720-048X</issn><issn>1872-7727</issn><issn>1872-7727</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kEFO3DAYha0KVAbaEyBVXsIigx07trNggaC0lZDYtFJ3lmP_Lh4SO7UzCI7APThZT0KmAyxZPenXe__T-xA6pGRJCRUnqyWssnHLmtR8SSltiPqAFlTJupKyljtoQWRNKsLV7z20X8qKENLwtv6I9piSTdtwtkDjBdxBn8YB4oSTxwYPxt6ECLgHk2OIf_CQHPTYp4zHDC7YaXMcI6yHNN2kbO5xDuUWh4htMvfB9LNmwBHA9YC7kMbygI_-PT4xbIfjT2jXm77A5xc9QL8uv_48_15dXX_7cX52VVnW8KniTrS0lVa01jWSeLCyE5J1pO64mTcK2gllHTBSO9qojknhPFeceuu9UoodoKPt3zGnv2sokx5CsdD3JkJaF81II4QkTLLZyrZWm1MpGbwecxhMftCU6A1qvdL_UesNar1FPae-vBSsuwHcW-aV7Ww43RpgnnkXIOtiA0Q7M8xgJ-1SeLfgGSHpkc0</recordid><startdate>202407</startdate><enddate>202407</enddate><creator>Zou, Xugong</creator><creator>Cui, Ning</creator><creator>Ma, Qiang</creator><creator>Lin, Zhipeng</creator><creator>Zhang, Jian</creator><creator>Li, Xiaoqun</creator><general>Elsevier B.V</general><scope>6I.</scope><scope>AAFTH</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0001-6247-2554</orcidid></search><sort><creationdate>202407</creationdate><title>Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)</title><author>Zou, Xugong ; Cui, Ning ; Ma, Qiang ; Lin, Zhipeng ; Zhang, Jian ; Li, Xiaoqun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c354t-4d69197c69cd570fec7b673b02b4a18761b68cde302d158b376df4841fcff8883</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Adult</topic><topic>Aged</topic><topic>Biopsy, Large-Core Needle</topic><topic>Coaxial core needle lung biopsy (CCNB)</topic><topic>Female</topic><topic>Humans</topic><topic>Image-Guided Biopsy</topic><topic>Lung Neoplasms - diagnostic imaging</topic><topic>Lung Neoplasms - pathology</topic><topic>Machine Learning</topic><topic>Machine learning (ML)</topic><topic>Male</topic><topic>Middle Aged</topic><topic>Pneumothorax</topic><topic>Pneumothorax - diagnostic imaging</topic><topic>Pneumothorax - etiology</topic><topic>Prediction model</topic><topic>Retrospective Studies</topic><topic>Risk Assessment</topic><topic>Risk factor</topic><topic>Risk Factors</topic><topic>Sensitivity and Specificity</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zou, Xugong</creatorcontrib><creatorcontrib>Cui, Ning</creatorcontrib><creatorcontrib>Ma, Qiang</creatorcontrib><creatorcontrib>Lin, Zhipeng</creatorcontrib><creatorcontrib>Zhang, Jian</creatorcontrib><creatorcontrib>Li, Xiaoqun</creatorcontrib><collection>ScienceDirect Open Access Titles</collection><collection>Elsevier:ScienceDirect:Open Access</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>European journal of radiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zou, Xugong</au><au>Cui, Ning</au><au>Ma, Qiang</au><au>Lin, Zhipeng</au><au>Zhang, Jian</au><au>Li, Xiaoqun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)</atitle><jtitle>European journal of radiology</jtitle><addtitle>Eur J Radiol</addtitle><date>2024-07</date><risdate>2024</risdate><volume>176</volume><spage>111508</spage><pages>111508-</pages><artnum>111508</artnum><issn>0720-048X</issn><issn>1872-7727</issn><eissn>1872-7727</eissn><abstract>•Developed ML model to predict post-CCNB pneumothorax risk.•Collected data on ≤3 cm lung nodules.•Gaussian Naive Bayes classifier achieved an AUC of 0.82.•Algorithm enhances perioperative care and clinical decision-making. The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care. This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP). Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71–0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort. The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.</abstract><cop>Ireland</cop><pub>Elsevier B.V</pub><pmid>38759543</pmid><doi>10.1016/j.ejrad.2024.111508</doi><orcidid>https://orcid.org/0000-0001-6247-2554</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0720-048X
ispartof European journal of radiology, 2024-07, Vol.176, p.111508, Article 111508
issn 0720-048X
1872-7727
1872-7727
language eng
recordid cdi_proquest_miscellaneous_3056670373
source Elsevier
subjects Adult
Aged
Biopsy, Large-Core Needle
Coaxial core needle lung biopsy (CCNB)
Female
Humans
Image-Guided Biopsy
Lung Neoplasms - diagnostic imaging
Lung Neoplasms - pathology
Machine Learning
Machine learning (ML)
Male
Middle Aged
Pneumothorax
Pneumothorax - diagnostic imaging
Pneumothorax - etiology
Prediction model
Retrospective Studies
Risk Assessment
Risk factor
Risk Factors
Sensitivity and Specificity
title Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T15%3A28%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Development%20of%20a%20machine%20learning%20model%20for%20predicting%20pneumothorax%20risk%20in%20coaxial%20core%20needle%20biopsy%20(%E2%89%A43%20cm)&rft.jtitle=European%20journal%20of%20radiology&rft.au=Zou,%20Xugong&rft.date=2024-07&rft.volume=176&rft.spage=111508&rft.pages=111508-&rft.artnum=111508&rft.issn=0720-048X&rft.eissn=1872-7727&rft_id=info:doi/10.1016/j.ejrad.2024.111508&rft_dat=%3Cproquest_cross%3E3056670373%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c354t-4d69197c69cd570fec7b673b02b4a18761b68cde302d158b376df4841fcff8883%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3056670373&rft_id=info:pmid/38759543&rfr_iscdi=true