Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism

To train and validate machine learning-derived clinical decision algorithm ( CDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who u...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:European radiology 2024-10
Hauptverfasser: Yeh, Randy, Kuo, Jennifer H, Huang, Bernice, Shobeiri, Parnian, Lee, James A, Tay, Yu-Kwang Donovan, Tabacco, Gaia, Bilezikian, John P, Dercle, Laurent
Format: Artikel
Sprache:eng
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title European radiology
container_volume
creator Yeh, Randy
Kuo, Jennifer H
Huang, Bernice
Shobeiri, Parnian
Lee, James A
Tay, Yu-Kwang Donovan
Tabacco, Gaia
Bilezikian, John P
Dercle, Laurent
description To train and validate machine learning-derived clinical decision algorithm ( CDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance ( CDA). The CDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of CDA was prospectively validated. Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an CDA using five probability categories for hyperfunctioning glands. The CDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94]. Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty. Question Can an CDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed CDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an CDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.
doi_str_mv 10.1007/s00330-024-11159-8
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_3122634902</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3122634902</sourcerecordid><originalsourceid>FETCH-LOGICAL-c184t-bf858a6cde05edb348da2378e5b30eee3fb047429f13efb2beb3e44ff5e8cb9f3</originalsourceid><addsrcrecordid>eNpNkctOHDEQRS1EBITwAyyQl2w6lB897V4iRB4SKJtkbflRnjbqtge7J2h-JV-bhplErKpUuueqpEPIJYPPDKC7qQBCQANcNoyxtm_UETljUvCGgZLH7_ZT8rHWJwDomexOyKnoZbeCVp2RP4_GDTEhHdGUFNO68Vjib_TUjTFFZ0bq0cUac6JmXOcS52GiIRc6D0h9NOuUa6w0BzrsNljCNrl5CS9NdGOKmYddydHT9WiSrzSm5TpHTHOlL0sV3ZQ4mbLbw--AWKdP5EMwY8WLwzwnv77c_7z71jz8-Pr97vahcUzJubFBtcqsnEdo0VshlTdcdApbKwARRbAgO8n7wAQGyy1agVKG0KJytg_inFzvezclP2-xznqK1eG4fIx5W7VgnK-E7IEvUb6PupJrLRj04X_NQL860XsnenGi35xotUBXh_6tndD_R_5JEH8BJNmN4g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3122634902</pqid></control><display><type>article</type><title>Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism</title><source>Springer Nature - Complete Springer Journals</source><creator>Yeh, Randy ; Kuo, Jennifer H ; Huang, Bernice ; Shobeiri, Parnian ; Lee, James A ; Tay, Yu-Kwang Donovan ; Tabacco, Gaia ; Bilezikian, John P ; Dercle, Laurent</creator><creatorcontrib>Yeh, Randy ; Kuo, Jennifer H ; Huang, Bernice ; Shobeiri, Parnian ; Lee, James A ; Tay, Yu-Kwang Donovan ; Tabacco, Gaia ; Bilezikian, John P ; Dercle, Laurent</creatorcontrib><description>To train and validate machine learning-derived clinical decision algorithm ( CDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance ( CDA). The CDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of CDA was prospectively validated. Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an CDA using five probability categories for hyperfunctioning glands. The CDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94]. Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty. Question Can an CDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed CDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an CDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.</description><identifier>ISSN: 1432-1084</identifier><identifier>EISSN: 1432-1084</identifier><identifier>DOI: 10.1007/s00330-024-11159-8</identifier><identifier>PMID: 39476058</identifier><language>eng</language><publisher>Germany</publisher><ispartof>European radiology, 2024-10</ispartof><rights>2024. The Author(s), under exclusive licence to European Society of Radiology.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c184t-bf858a6cde05edb348da2378e5b30eee3fb047429f13efb2beb3e44ff5e8cb9f3</cites><orcidid>0000-0003-2945-5546</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/39476058$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yeh, Randy</creatorcontrib><creatorcontrib>Kuo, Jennifer H</creatorcontrib><creatorcontrib>Huang, Bernice</creatorcontrib><creatorcontrib>Shobeiri, Parnian</creatorcontrib><creatorcontrib>Lee, James A</creatorcontrib><creatorcontrib>Tay, Yu-Kwang Donovan</creatorcontrib><creatorcontrib>Tabacco, Gaia</creatorcontrib><creatorcontrib>Bilezikian, John P</creatorcontrib><creatorcontrib>Dercle, Laurent</creatorcontrib><title>Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism</title><title>European radiology</title><addtitle>Eur Radiol</addtitle><description>To train and validate machine learning-derived clinical decision algorithm ( CDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance ( CDA). The CDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of CDA was prospectively validated. Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an CDA using five probability categories for hyperfunctioning glands. The CDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94]. Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty. Question Can an CDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed CDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an CDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.</description><issn>1432-1084</issn><issn>1432-1084</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNpNkctOHDEQRS1EBITwAyyQl2w6lB897V4iRB4SKJtkbflRnjbqtge7J2h-JV-bhplErKpUuueqpEPIJYPPDKC7qQBCQANcNoyxtm_UETljUvCGgZLH7_ZT8rHWJwDomexOyKnoZbeCVp2RP4_GDTEhHdGUFNO68Vjib_TUjTFFZ0bq0cUac6JmXOcS52GiIRc6D0h9NOuUa6w0BzrsNljCNrl5CS9NdGOKmYddydHT9WiSrzSm5TpHTHOlL0sV3ZQ4mbLbw--AWKdP5EMwY8WLwzwnv77c_7z71jz8-Pr97vahcUzJubFBtcqsnEdo0VshlTdcdApbKwARRbAgO8n7wAQGyy1agVKG0KJytg_inFzvezclP2-xznqK1eG4fIx5W7VgnK-E7IEvUb6PupJrLRj04X_NQL860XsnenGi35xotUBXh_6tndD_R_5JEH8BJNmN4g</recordid><startdate>20241030</startdate><enddate>20241030</enddate><creator>Yeh, Randy</creator><creator>Kuo, Jennifer H</creator><creator>Huang, Bernice</creator><creator>Shobeiri, Parnian</creator><creator>Lee, James A</creator><creator>Tay, Yu-Kwang Donovan</creator><creator>Tabacco, Gaia</creator><creator>Bilezikian, John P</creator><creator>Dercle, Laurent</creator><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><orcidid>https://orcid.org/0000-0003-2945-5546</orcidid></search><sort><creationdate>20241030</creationdate><title>Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism</title><author>Yeh, Randy ; Kuo, Jennifer H ; Huang, Bernice ; Shobeiri, Parnian ; Lee, James A ; Tay, Yu-Kwang Donovan ; Tabacco, Gaia ; Bilezikian, John P ; Dercle, Laurent</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c184t-bf858a6cde05edb348da2378e5b30eee3fb047429f13efb2beb3e44ff5e8cb9f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yeh, Randy</creatorcontrib><creatorcontrib>Kuo, Jennifer H</creatorcontrib><creatorcontrib>Huang, Bernice</creatorcontrib><creatorcontrib>Shobeiri, Parnian</creatorcontrib><creatorcontrib>Lee, James A</creatorcontrib><creatorcontrib>Tay, Yu-Kwang Donovan</creatorcontrib><creatorcontrib>Tabacco, Gaia</creatorcontrib><creatorcontrib>Bilezikian, John P</creatorcontrib><creatorcontrib>Dercle, Laurent</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>European radiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yeh, Randy</au><au>Kuo, Jennifer H</au><au>Huang, Bernice</au><au>Shobeiri, Parnian</au><au>Lee, James A</au><au>Tay, Yu-Kwang Donovan</au><au>Tabacco, Gaia</au><au>Bilezikian, John P</au><au>Dercle, Laurent</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism</atitle><jtitle>European radiology</jtitle><addtitle>Eur Radiol</addtitle><date>2024-10-30</date><risdate>2024</risdate><issn>1432-1084</issn><eissn>1432-1084</eissn><abstract>To train and validate machine learning-derived clinical decision algorithm ( CDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance ( CDA). The CDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of CDA was prospectively validated. Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an CDA using five probability categories for hyperfunctioning glands. The CDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94]. Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty. Question Can an CDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed CDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an CDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports for surgical planning.</abstract><cop>Germany</cop><pmid>39476058</pmid><doi>10.1007/s00330-024-11159-8</doi><orcidid>https://orcid.org/0000-0003-2945-5546</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1432-1084
ispartof European radiology, 2024-10
issn 1432-1084
1432-1084
language eng
recordid cdi_proquest_miscellaneous_3122634902
source Springer Nature - Complete Springer Journals
title Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-17T15%3A08%3A46IST&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=Machine%20learning-derived%20clinical%20decision%20algorithm%20for%20the%20diagnosis%20of%20hyperfunctioning%20parathyroid%20glands%20in%20patients%20with%20primary%20hyperparathyroidism&rft.jtitle=European%20radiology&rft.au=Yeh,%20Randy&rft.date=2024-10-30&rft.issn=1432-1084&rft.eissn=1432-1084&rft_id=info:doi/10.1007/s00330-024-11159-8&rft_dat=%3Cproquest_cross%3E3122634902%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3122634902&rft_id=info:pmid/39476058&rfr_iscdi=true