The machine learning-based model for lateral lymph node metastasis of thyroid medullary carcinoma improved the prediction ability of occult metastasis.

BACKGROUND: For medullary thyroid carcinoma (MTC) with no positive findings in the lateral neck before surgery, whether prophylactic lateral neck dissection (LND) is needed remains controversial. A better way to predict occult metastasis in the lateral neck is needed. METHODS: From January 2010 to January 2022, patients who were diagnosed with MTC and underwent primary surgery at our hospital were retrospectively reviewed. We collected the patients' baseline characteristics, surgical procedure, and rescored the ultrasound images of the primary lesions using American College of Radiology (ACR) Thyroid Imaging, Reporting and Data System (TI-RADS). Regularized logistic regression, 5-fold cross-validation and decision curve analysis was applied for lateral lymph node metastasis (LLNM) model's development and validation. Then, we tested the predictive ability of the LLNM model for occult LLNM in cN0-1a patients. RESULTS: A total of 218 patients were enrolled. Five baseline characteristics and two TI-RADS features were identified as high-risk factors for LLNM: gender, baseline calcitonin (Ctn), tumor size, multifocality, and central lymph node (CLN) status, as well as TI-RADS margin and level. A LLNM model was developed and showed a good discrimination with 5-fold cross-validation mean area under curve (AUC) = 0.92 ± 0.03 in the test dataset. Among cN0-1a patients, our LLNM model achieved an AUC of 0.91 (95% CI, 0.88-0.94) for predicting occult LLNM, which was significantly higher than the AUCs of baseline Ctn (0.83) and CLN status (0.64). CONCLUSIONS: We developed a LLNM prediction model for MTC using machine learning based on clinical baseline characteristics and TI-RADS. Our model can predict occult LLNM for cN0-1a patients more accurately, then benefit the decision of prophylactic LND.

A nomogram to predict lateral lymph node metastases in lateral neck in patients with medullary thyroid cancer.

Background: Medullary thyroid cancer (MTC) can only be cured by surgery, but the management of lateral lymph nodes is controversial, especially for patients with cN0+cN1a. To address this challenge, we developed a multivariate logistic regression model to predict lateral lymph node metastases (LNM). Methods: We retrospectively collected clinical data from 124 consecutive MTC patients who underwent initial surgery at our institution. The data of 82 patients (from 2010 to 2018) and 42 patients (from January 2019 to November 2019) were used as the training set for building the model and as the test set for validating the model, respectively. Results: In the training group, the multivariate analyses indicated that male and MTC patients with higher preoperative basal calcitonin levels were more likely to have lateral LNM (P = 0.007 and 0.005, respectively). Multifocal lesions and suspected lateral LNM in preoperative ultrasound (US) were independent risk factors (P = 0.032 and 0.002, respectively). The identified risk factors were incorporated into a multivariate logistic regression model to generate the nomogram, which showed good discrimination (C-index = 0.963, 95% confidence interval [CI]: 0.9286-0.9972). Our model was validated with an excellent result in the test set and even superior to the training set (C-index = 0.964, 95% CI: 0.9121-1.000). Conclusion: Higher preoperative basal calcitonin level, male sex, multifocal lesions, and lateral lymph node involvement suspicion on US are risk factors for lateral LNM. Our model and nomogram will objectively and accurately predict lateral LNM in patients with MTC.

Diagnostic yield and clinical impact of exome sequencing in early-onset scoliosis (EOS).

BACKGROUND: Early-onset scoliosis (EOS), defined by an onset age of scoliosis less than 10 years, conveys significant health risk to affected children. Identification of the molecular aetiology underlying patients with EOS could provide valuable information for both clinical management and prenatal screening. METHODS: In this study, we consecutively recruited a cohort of 447 Chinese patients with operative EOS. We performed exome sequencing (ES) screening on these individuals and their available family members (totaling 670 subjects). Another cohort of 13 patients with idiopathic early-onset scoliosis (IEOS) from the USA who underwent ES was also recruited. RESULTS: After ES data processing and variant interpretation, we detected molecular diagnostic variants in 92 out of 447 (20.6%) Chinese patients with EOS, including 8 patients with molecular confirmation of their clinical diagnosis and 84 patients with molecular diagnoses of previously unrecognised diseases underlying scoliosis. One out of 13 patients with IEOS from the US cohort was molecularly diagnosed. The age at presentation, the number of organ systems involved and the Cobb angle were the three top features predictive of a molecular diagnosis. CONCLUSION: ES enabled the molecular diagnosis/classification of patients with EOS. Specific clinical features/feature pairs are able to indicate the likelihood of gaining a molecular diagnosis through ES.