Abstract
Background: Delphian lymph node (DLN) has been considered to be a gate that predicts widespread lymph node involvement, higher recurrence and mortality rates of head and neck cancer.
Objective: This study aimed to establish a preoperative ultrasonography integrated machine learning prediction model to predict Delphian lymph node metastasis (DLNM) in patients with diagnosed papillary thyroid carcinoma (PTC).
Methods: Ultrasonographic and clinicopathologic variables of PTC patients from 2014 to 2021 were retrospectively analyzed. The risk factors associated with DLNM were identified and validated through a developed random forest (RF) algorithm model based on machine learning and a logistic regression (LR) model.
Results: A total of 316 patients with 402 thyroid lesions were enrolled for the training dataset and 280 patients with 341 lesions for the validation dataset, with 170 (28.52%) patients developed DLNM. The elastography score of ultrasonography, central lymph node metastasis, lateral lymph node metastasis, and serum calcitonin were predictive factors for DLNM in both models. The RF model has better predictive performance in the training dataset and validation dataset (AUC: 0.957 vs. 0.890) than that in the LR model (AUC: 0.908 vs. 0.833).
Conclusion: The preoperative ultrasonography integrated RF model constructed in this study could accurately predict DLNM in PTC patients, which may provide clinicians with more personalized clinical decision-making recommendations preoperatively. Machine learning technology has the potential to improve the development of DLNM prediction models in PTC patients.
Graphical Abstract
[http://dx.doi.org/10.1097/SLA.0b013e31815efdc4] [PMID: 18376193]
[http://dx.doi.org/10.1097/SLA.0b013e31821219ca] [PMID: 21372688]
[http://dx.doi.org/10.1007/s00268-013-2406-x] [PMID: 24366273]
[http://dx.doi.org/10.1111/ajco.12480] [PMID: 26990889]
[http://dx.doi.org/10.2147/CMAR.S232884] [PMID: 32110106]
[http://dx.doi.org/10.1111/ans.15458] [PMID: 31566299]
[http://dx.doi.org/10.1177/030089168507100407] [PMID: 4049538]
[http://dx.doi.org/10.4158/EP-2020-0129] [PMID: 33471728]
[http://dx.doi.org/10.1210/js.2017-00333] [PMID: 29308446]
[http://dx.doi.org/10.1038/s41467-020-18497-3] [PMID: 32968067]
[http://dx.doi.org/10.3389/fonc.2021.792347] [PMID: 35004316]
[http://dx.doi.org/10.7863/jum.2003.22.10.1126] [PMID: 14606572]
[http://dx.doi.org/10.1016/j.ultrasmedbio.2015.03.009] [PMID: 25805059]
[http://dx.doi.org/10.1016/j.jacr.2017.01.046] [PMID: 28372962]
[http://dx.doi.org/10.3389/fendo.2021.591015] [PMID: 33841323]
[http://dx.doi.org/10.1002/lary.29426] [PMID: 33493364]
[http://dx.doi.org/10.1288/00005537-198709000-00007] [PMID: 3626727]
[http://dx.doi.org/10.1186/s40463-019-0362-7] [PMID: 31470907]
[http://dx.doi.org/10.1007/s00268-013-2157-8] [PMID: 23877804]
[http://dx.doi.org/10.18632/oncotarget.19047] [PMID: 28915656]
[http://dx.doi.org/10.1186/1477-7819-10-226] [PMID: 23110552]
[PMID: 32377069]
[http://dx.doi.org/10.1016/j.ejrad.2019.01.006] [PMID: 30777203]
[http://dx.doi.org/10.1016/j.ultrasmedbio.2015.07.010] [PMID: 26306431]
[http://dx.doi.org/10.1016/j.ultrasmedbio.2019.06.421] [PMID: 31371128]
[PMID: 5012366]
[http://dx.doi.org/10.1007/978-0-387-69219-7_5] [PMID: 17953408]
[http://dx.doi.org/10.1097/01.sla.0000250445.92336.2a] [PMID: 17435543]
[http://dx.doi.org/10.1007/s00268-006-0864-0] [PMID: 17308849]
[http://dx.doi.org/10.1210/jc.2009-2368] [PMID: 20339026]
[http://dx.doi.org/10.1002/jcla.23278] [PMID: 32141647]