Machine Learning-Based Shear Wave Elastography Elastic Index (SWEEI) in Predicting Cervical Lymph Node Metastasis of Papillary Thyroid Microcarcinoma: A Comparative Analysis of Five Practical Prediction Models.
cervical lymph node metastasis
machine learning algorithm
papillary thyroid microcarcinoma
prediction model
shear wave elastography elastic index
Journal
Cancer management and research
ISSN: 1179-1322
Titre abrégé: Cancer Manag Res
Pays: New Zealand
ID NLM: 101512700
Informations de publication
Date de publication:
2022
2022
Historique:
received:
21
07
2022
accepted:
14
09
2022
entrez:
29
9
2022
pubmed:
30
9
2022
medline:
30
9
2022
Statut:
epublish
Résumé
Although many factors determine the prognosis of papillary thyroid carcinoma (PTC), cervical lymph node metastasis (CLNM) is one of the most terrible factors. In view of this, this study aimed to build a CLNM prediction model for papillary thyroid microcarcinoma (PTMC) with the help of machine learning algorithm. We retrospectively analyzed 387 PTMC patients hospitalized in the Department of Medical Oncology, Enshi Tujia and Miao Autonomous Prefecture Central Hospital from January 1, 2015, to January 31, 2022. Based on supervised learning algorithms, namely random forest classifier (RFC), artificial neural network(ANN), support vector machine(SVM), decision tree(DT), and extreme gradient boosting gradient(XGboost) algorithm, the LNM prediction model was constructed, and the prediction efficiency of ML-based model was evaluated via receiver operating characteristic curve(ROC) and decision curve analysis(DCA). Finally, a total of 24 baseline variables were included in the supervised learning algorithm. According to the iterative analysis results, the pulsatility index(PI), resistance index(RI), peak systolic blood flow velocity(PSBV), systolic acceleration time(SAT), and shear wave elastography elastic index(SWEEI), such as average value(Emean), maximum value(Emax), and minimum value(Emix) were candidate predictors. Among the five supervised learning models, RFC had the strongest prediction efficiency with area under curve(AUC) of 0.889 (95% CI: 0.838-0.940) and 0.878 (95% CI: 0.821-0.935) in the training set and testing set, respectively. While ANN, DT, SVM and XGboost had prediction efficiency between 0.767 (95% CI: 0.716-0.818) and 0.854 (95% CI: 0.803-0.905) in the training set, and ranged from 0.762 (95% CI: 0.705-0.819) to 0.861 (95% CI: 0.804-0.918) in the testing set. We have successfully constructed an ML-based prediction model, which can accurately classify the LNM risk of patients with PTMC. In particular, the RFC model can help tailor clinical decisions of treatment and surveillance.
Identifiants
pubmed: 36171862
doi: 10.2147/CMAR.S383152
pii: 383152
pmc: PMC9512413
doi:
Types de publication
Journal Article
Langues
eng
Pagination
2847-2858Informations de copyright
© 2022 Huang et al.
Déclaration de conflit d'intérêts
The authors declare that they have no conflicts of interest in this work.
Références
Stroke. 2019 May;50(5):1263-1265
pubmed: 30890116
Circulation. 2015 Nov 17;132(20):1920-30
pubmed: 26572668
J Multivar Anal. 2021 May;183:
pubmed: 33518826
Hepatology. 2018 Jan;67(1):260-272
pubmed: 28370257
Comput Intell Neurosci. 2021 Nov 24;2021:8592824
pubmed: 34868299
Surgery. 2013 Oct;154(4):697-701; discussion 701-3
pubmed: 24011674
BMC Surg. 2019 Apr 24;18(Suppl 1):110
pubmed: 31074400
Endocrinol Metab Clin North Am. 2019 Mar;48(1):199-213
pubmed: 30717902
BMC Med Inform Decis Mak. 2021 Mar 20;21(1):105
pubmed: 33743696
BMC Med Inform Decis Mak. 2019 May 30;19(1):104
pubmed: 31146749
Arch Surg. 2006 May;141(5):489-94; discussion 494-6
pubmed: 16702521
Arch Endocrinol Metab. 2016 Oct 10;60(5):492-499
pubmed: 27737333
Minerva Chir. 2013 Jun;68(3):321-8
pubmed: 23774098
J Bioinform Comput Biol. 2021 Oct;19(5):2150028
pubmed: 34693886
Ann Surg Oncol. 2011 Aug;18(8):2245-50
pubmed: 21327454
Am J Surg. 2018 Jul;216(1):135-139
pubmed: 28954712
BMC Med Imaging. 2022 May 2;22(1):82
pubmed: 35501717
Endocrine. 2013 Dec;44(3):616-22
pubmed: 23645523
N Engl J Med. 2016 Sep 15;375(11):1054-67
pubmed: 27626519
Nat Rev Endocrinol. 2016 Nov;12(11):646-653
pubmed: 27418023
Nat Commun. 2020 Sep 23;11(1):4807
pubmed: 32968067
Sci Rep. 2020 Mar 23;10(1):5245
pubmed: 32251324
Endocr Relat Cancer. 2017 Sep;24(9):485-493
pubmed: 28696209
Endocr Pathol. 2020 Sep;31(3):291-300
pubmed: 32468210
Clin Endocrinol (Oxf). 2014 Aug;81(2):282-8
pubmed: 24483297
Am Surg. 2004 Jul;70(7):576-80; discussion 580-2
pubmed: 15279178
Front Endocrinol (Lausanne). 2021 Jan 21;11:555243
pubmed: 33551989
J Chem Inf Model. 2020 Mar 23;60(3):1910
pubmed: 31975583
World J Surg. 1994 Jul-Aug;18(4):559-67; discussion 567-8
pubmed: 7725745
Laryngoscope. 2011 Mar;121(3):487-91
pubmed: 21344423
Cytopathology. 2020 Sep;31(5):432-444
pubmed: 32248583
Curr Biol. 2019 Apr 1;29(7):R231-R236
pubmed: 30939301
Thyroid. 2016 Jan;26(1):1-133
pubmed: 26462967
Lancet. 2016 Dec 3;388(10061):2783-2795
pubmed: 27240885
J Med Syst. 2019 May 15;43(7):180
pubmed: 31093787
Folia Biol (Praha). 2019;65(5-6):212-220
pubmed: 32362304
IEEE Trans Image Process. 2018 May 10;27(8):4012-4024
pubmed: 29993742
Sports Health. 2020 Jul/Aug;12(4):373-381
pubmed: 32003647
Surgery. 2020 Jan;167(1):46-55
pubmed: 31526581
Med Phys. 2018 Jul;45(7):3449-3459
pubmed: 29763967