Machine Learning-Based Algorithm for the Early Prediction of Postoperative Hypocalcemia Risk After Thyroidectomy

We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk. Postoperative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia coul...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Annals of surgery Jg. 280; H. 5; S. 835
Hauptverfasser:	Muller, Olivier, Bauvin, Pierre, Bacoeur, Ophélie, Michailos, Théo, Bertoni, Maria-Vittoria, Demory, Charles, Marciniak, Camille, Chetboun, Mikael, Baud, Grégory, Raffaelli, Marco, Caiazzo, Robert, Pattou, Francois
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States 01.11.2024
Schlagworte:	Adult Aged Algorithms Female Humans Hypocalcemia - blood Hypocalcemia - diagnosis Hypocalcemia - etiology Machine Learning Male Middle Aged Postoperative Complications - blood Postoperative Complications - diagnosis Postoperative Complications - epidemiology Postoperative Complications - etiology Predictive Value of Tests Retrospective Studies Risk Assessment - methods Risk Factors Thyroidectomy - adverse effects
ISSN:	1528-1140, 1528-1140
Online-Zugang:	Weitere Angaben
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk. Postoperative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia could guide the selective prescription of calcium supplementation only to patients most likely to present with hypocalcemia after total thyroidectomy. This retrospective study enrolled all patients undergoing total thyroidectomy in a single referral center between November 2019 and March 2022 (derivation cohort) and April 2022 and September 2022 (validation cohort). The primary study outcome was postoperative hypocalcemia (serum calcium under 80 mg/L). Exposures were multiple clinical and biological variables prospectively collected and analyzed with various machine learning methods to develop and validate a multivariable prediction algorithm. Among 610/118 participants in the derivation/validation cohorts, 100 (16.4%)/26 (22%) presented postoperative hypocalcemia. The most accurate prediction algorithm was obtained with random forest and combined intraoperative parathyroid hormone measurements with 3 clinical variables (age, sex, and body mass index) to calculate a postoperative hypocalcemia risk for each patient. After multiple cross-validation, the area under the receiver operative characteristic curve was 0.902 (0.829-0.970) in the derivation cohort, and 0.928 (95% CI: 0.86; 0.97) in the validation cohort. Postoperative hypocalcemia risk values of 7% (low threshold) and 20% (high threshold) had, respectively, a sensitivity of 92%, a negative likelihood ratio of 0.11, a specificity of 90%, and a positive of 7.6 for the prediction of postoperative hypocalcemia. Using machine learning, we developed and validated a simple multivariable model that allowed the accurate prediction of postoperative hypocalcemia. The resulting algorithm could be used at the point of care to guide clinical management after total thyroidectomy.
AbstractList	We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk.OBJECTIVEWe used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk.Postoperative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia could guide the selective prescription of calcium supplementation only to patients most likely to present with hypocalcemia after total thyroidectomy.BACKGROUNDPostoperative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia could guide the selective prescription of calcium supplementation only to patients most likely to present with hypocalcemia after total thyroidectomy.This retrospective study enrolled all patients undergoing total thyroidectomy in a single referral center between November 2019 and March 2022 (derivation cohort) and April 2022 and September 2022 (validation cohort). The primary study outcome was postoperative hypocalcemia (serum calcium under 80 mg/L). Exposures were multiple clinical and biological variables prospectively collected and analyzed with various machine learning methods to develop and validate a multivariable prediction algorithm.METHODSThis retrospective study enrolled all patients undergoing total thyroidectomy in a single referral center between November 2019 and March 2022 (derivation cohort) and April 2022 and September 2022 (validation cohort). The primary study outcome was postoperative hypocalcemia (serum calcium under 80 mg/L). Exposures were multiple clinical and biological variables prospectively collected and analyzed with various machine learning methods to develop and validate a multivariable prediction algorithm.Among 610/118 participants in the derivation/validation cohorts, 100 (16.4%)/26 (22%) presented postoperative hypocalcemia. The most accurate prediction algorithm was obtained with random forest and combined intraoperative parathyroid hormone measurements with 3 clinical variables (age, sex, and body mass index) to calculate a postoperative hypocalcemia risk for each patient. After multiple cross-validation, the area under the receiver operative characteristic curve was 0.902 (0.829-0.970) in the derivation cohort, and 0.928 (95% CI: 0.86; 0.97) in the validation cohort. Postoperative hypocalcemia risk values of 7% (low threshold) and 20% (high threshold) had, respectively, a sensitivity of 92%, a negative likelihood ratio of 0.11, a specificity of 90%, and a positive of 7.6 for the prediction of postoperative hypocalcemia.RESULTSAmong 610/118 participants in the derivation/validation cohorts, 100 (16.4%)/26 (22%) presented postoperative hypocalcemia. The most accurate prediction algorithm was obtained with random forest and combined intraoperative parathyroid hormone measurements with 3 clinical variables (age, sex, and body mass index) to calculate a postoperative hypocalcemia risk for each patient. After multiple cross-validation, the area under the receiver operative characteristic curve was 0.902 (0.829-0.970) in the derivation cohort, and 0.928 (95% CI: 0.86; 0.97) in the validation cohort. Postoperative hypocalcemia risk values of 7% (low threshold) and 20% (high threshold) had, respectively, a sensitivity of 92%, a negative likelihood ratio of 0.11, a specificity of 90%, and a positive of 7.6 for the prediction of postoperative hypocalcemia.Using machine learning, we developed and validated a simple multivariable model that allowed the accurate prediction of postoperative hypocalcemia. The resulting algorithm could be used at the point of care to guide clinical management after total thyroidectomy.CONCLUSIONSUsing machine learning, we developed and validated a simple multivariable model that allowed the accurate prediction of postoperative hypocalcemia. The resulting algorithm could be used at the point of care to guide clinical management after total thyroidectomy. We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk. Postoperative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia could guide the selective prescription of calcium supplementation only to patients most likely to present with hypocalcemia after total thyroidectomy. This retrospective study enrolled all patients undergoing total thyroidectomy in a single referral center between November 2019 and March 2022 (derivation cohort) and April 2022 and September 2022 (validation cohort). The primary study outcome was postoperative hypocalcemia (serum calcium under 80 mg/L). Exposures were multiple clinical and biological variables prospectively collected and analyzed with various machine learning methods to develop and validate a multivariable prediction algorithm. Among 610/118 participants in the derivation/validation cohorts, 100 (16.4%)/26 (22%) presented postoperative hypocalcemia. The most accurate prediction algorithm was obtained with random forest and combined intraoperative parathyroid hormone measurements with 3 clinical variables (age, sex, and body mass index) to calculate a postoperative hypocalcemia risk for each patient. After multiple cross-validation, the area under the receiver operative characteristic curve was 0.902 (0.829-0.970) in the derivation cohort, and 0.928 (95% CI: 0.86; 0.97) in the validation cohort. Postoperative hypocalcemia risk values of 7% (low threshold) and 20% (high threshold) had, respectively, a sensitivity of 92%, a negative likelihood ratio of 0.11, a specificity of 90%, and a positive of 7.6 for the prediction of postoperative hypocalcemia. Using machine learning, we developed and validated a simple multivariable model that allowed the accurate prediction of postoperative hypocalcemia. The resulting algorithm could be used at the point of care to guide clinical management after total thyroidectomy.
Author	Caiazzo, Robert Muller, Olivier Demory, Charles Marciniak, Camille Pattou, Francois Bacoeur, Ophélie Michailos, Théo Baud, Grégory Raffaelli, Marco Bauvin, Pierre Bertoni, Maria-Vittoria Chetboun, Mikael
Author_xml	– sequence: 1 givenname: Olivier surname: Muller fullname: Muller, Olivier organization: Department of General and Endocrine Surgery, CHU Lille, Lille, France – sequence: 2 givenname: Pierre surname: Bauvin fullname: Bauvin, Pierre organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France – sequence: 3 givenname: Ophélie surname: Bacoeur fullname: Bacoeur, Ophélie organization: Department of General and Endocrine Surgery, CHU Lille, Lille, France – sequence: 4 givenname: Théo surname: Michailos fullname: Michailos, Théo organization: Department of General and Endocrine Surgery, CHU Lille, Lille, France – sequence: 5 givenname: Maria-Vittoria surname: Bertoni fullname: Bertoni, Maria-Vittoria organization: Department of General and Endocrine Surgery, CHU Lille, Lille, France – sequence: 6 givenname: Charles surname: Demory fullname: Demory, Charles organization: Department of General and Endocrine Surgery, CHU Lille, Lille, France – sequence: 7 givenname: Camille surname: Marciniak fullname: Marciniak, Camille organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France – sequence: 8 givenname: Mikael surname: Chetboun fullname: Chetboun, Mikael organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France – sequence: 9 givenname: Grégory surname: Baud fullname: Baud, Grégory organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France – sequence: 10 givenname: Marco surname: Raffaelli fullname: Raffaelli, Marco organization: Endocrine Surgery, Department of Surgery, Universita Cattolica dela Sacro Cuore, Roma, Italy – sequence: 11 givenname: Robert surname: Caiazzo fullname: Caiazzo, Robert organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France – sequence: 12 givenname: Francois surname: Pattou fullname: Pattou, Francois organization: Univ Lille, Inserm, Institut Pasteur de Lille, CHU Lille, Lille, France
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/39109425$$D View this record in MEDLINE/PubMed
BookMark	eNpNkE9LwzAchoNM3B_9BiI5eulM0rRpj3NMJ1QcunvJ0l_WaNvUJBP67R04Ye_lfQ8Pz-GdolFnO0DolpI5Jbl4-CgWc3KWlGfkAk1owrKIUk5GZ3uMpt5_EkKPjLhC4zg_KjhLJqh_lao2HeACpOtMt48epYcKL5q9dSbULdbW4VADXknXDHjjoDIqGNthq_HG-mB7cDKYH8DrobdKNgpaI_G78V94oQM4vK0HZ00FKth2uEaXWjYebk49Q9un1Xa5joq355floogUzxmJMqmBJVABEVxnaSp1JWkKOU80BZayHd0JyhLFhSapUloRIFTxmAtJhQQ2Q_d_2t7Z7wP4ULbGK2ga2YE9-DImWZ5lLE7EEb07oYddC1XZO9NKN5T_J7Ff1YptMg
CitedBy_id	crossref_primary_10_1007_s12020_025_04357_x crossref_primary_10_1007_s12020_025_04378_6
ContentType	Journal Article
Copyright	Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.
Copyright_xml	– notice: Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.
DBID	CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1097/SLA.0000000000006480
DatabaseName	Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic MEDLINE
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	no_fulltext_linktorsrc
EISSN	1528-1140
ExternalDocumentID	39109425
Genre	Journal Article
GroupedDBID	--- .-D .XZ .Z2 01R 0R~ 1J1 23M 354 40H 4Q1 4Q2 4Q3 53G 5GY 5VS 6J9 71W 77Y 7O~ AAAAV AAAXR AAGIX AAHPQ AAIQE AAJCS AAMOA AAMTA AAQKA AARTV AASCR AASOK AASXQ AAUEB AAXQO ABASU ABBUW ABDIG ABJNI ABOCM ABPMR ABPPZ ABPXF ABVCZ ABXVJ ABXYN ABZAD ABZZY ACDDN ACDOF ACEWG ACGFO ACGFS ACILI ACLDA ACOAL ACWDW ACWRI ACXJB ACXNZ ACZKN ADGGA ADHPY AE6 AEBDS AENEX AFBFQ AFCHL AFDTB AFEXH AFMBP AFNMH AFSOK AFUWQ AGINI AHJKT AHOMT AHQNM AHQVU AHVBC AIJEX AINUH AJCLO AJIOK AJNWD AJZMW AKCTQ AKULP ALKUP ALMA_UNASSIGNED_HOLDINGS ALMTX AMJPA AMKUR AMNEI AOHHW AOQMC ASPBG AVWKF AZFZN BOYCO BQLVK BYPQX C45 CGR CS3 CUY CVF DIWNM E.X EBS ECM EEVPB EIF ERAAH EX3 F2K F2L F2M F2N F5P FCALG FL- GNXGY GQDEL H0~ HLJTE HZ~ IH2 IKREB IKYAY IN~ IPNFZ J5H JF7 JK3 JK8 K-A K-F K8S KD2 KMI L-C L7B N9A NPM N~7 N~B O9- OAG OAH OBH OCB ODMTH OGEVE OHH OHYEH OL1 OLB OLG OLH OLU OLV OLY OLZ OPUJH OVD OVDNE OVIDH OVLEI OVOZU OWBYB OWU OWV OWW OWX OWY OWZ OXXIT P2P RIG RLZ RPM RXW S4R S4S TAF TEORI TSPGW UQX V2I VVN W3M WH7 WOQ WOW X3V X3W XXN XYM YFH YOC ZFV ZY1 ~H1 7X8 ADKSD ADSXY
ID	FETCH-LOGICAL-c4920-8afe25ede074f866afda16e945f1e262b1b7125c47f06ccfc0e01c4347a17ae2
IEDL.DBID	7X8
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001328598200005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1528-1140
IngestDate	Mon Sep 08 14:59:10 EDT 2025 Mon Jul 21 05:43:02 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	5
Language	English
License	Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c4920-8afe25ede074f866afda16e945f1e262b1b7125c47f06ccfc0e01c4347a17ae2
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://pubmed.ncbi.nlm.nih.gov/PMC11446540
PMID	39109425
PQID	3089882357
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_3089882357 pubmed_primary_39109425
PublicationCentury	2000
PublicationDate	2024-November
PublicationDateYYYYMMDD	2024-11-01
PublicationDate_xml	– month: 11 year: 2024 text: 2024-November
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	Annals of surgery
PublicationTitleAlternate	Ann Surg
PublicationYear	2024
SSID	ssj0014807
Score	2.4863446
Snippet	We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk.... We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia...
SourceID	proquest pubmed
SourceType	Aggregation Database Index Database
StartPage	835
SubjectTerms	Adult Aged Algorithms Female Humans Hypocalcemia - blood Hypocalcemia - diagnosis Hypocalcemia - etiology Machine Learning Male Middle Aged Postoperative Complications - blood Postoperative Complications - diagnosis Postoperative Complications - epidemiology Postoperative Complications - etiology Predictive Value of Tests Retrospective Studies Risk Assessment - methods Risk Factors Thyroidectomy - adverse effects
Title	Machine Learning-Based Algorithm for the Early Prediction of Postoperative Hypocalcemia Risk After Thyroidectomy
URI	https://www.ncbi.nlm.nih.gov/pubmed/39109425 https://www.proquest.com/docview/3089882357
Volume	280
WOSCitedRecordID	wos001328598200005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings	1
isFullTextHit
isPrint
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAMrDwEK_ykpFYo-bh2MmEAgJ1oFUFHbpFjh9tBE1CU5D67zknrjohIZEhW6zobN_3nc93H0J3gkNQwH3hADZnDmGhUQOEjRdLyjggtBAia8Qm2HAYTSbxyB641fZa5donNo5alsKckfcCN4qBDQYhu68-HaMaZbKrVkJjG3UCoDJmY7LJJotgy6UBoiBSgkhiXToXs97bS9K2LrQPJZH7O8lswOb54L-_eYj2Lc3ESbsujtCWKo5RNWhuTipsm6pOnQfAMImTjykMsZzNMTBYDIwQN22P8Whhsjhm5nCpsZH1LSvVdgrH_VVlUFCoec7xa16_48SojePxbLUoc2lyAfPVCRo_P40f-45VXHAEiSGOjLhWfqikAmKhI0q5ltyjKiah9pRP_czLGDAiQZh2qRBauMr1BAkI4x7jyj9FO0VZqHOEFQ0AGrUXaRmAaXlmPAeRmkWxopywLrpd2y-FBW2yFLxQ5VedbizYRWftJKRV23kjhSmGcNQPL_7w9SXa84GAtHWDV6ijYTura7Qrvpd5vbhpVgq8h6PBD8b-yKc
linkProvider	ProQuest
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-Based+Algorithm+for+the+Early+Prediction+of+Postoperative+Hypocalcemia+Risk+After+Thyroidectomy&rft.jtitle=Annals+of+surgery&rft.au=Muller%2C+Olivier&rft.au=Bauvin%2C+Pierre&rft.au=Bacoeur%2C+Oph%C3%A9lie&rft.au=Michailos%2C+Th%C3%A9o&rft.date=2024-11-01&rft.eissn=1528-1140&rft.volume=280&rft.issue=5&rft.spage=835&rft_id=info:doi/10.1097%2FSLA.0000000000006480&rft_id=info%3Apmid%2F39109425&rft_id=info%3Apmid%2F39109425&rft.externalDocID=39109425
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1528-1140&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1528-1140&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1528-1140&client=summon