Risk-stratified papillary thyroid microcarcinoma: post-operative management and treatment outcome in a single center

Artificial neural network prediction of postoperative complications in papillary thyroid microcarcinoma based on preoperative ultrasonographic features

OBJECTIVE

To predict post-thyroidectomy complications in papillary thyroid microcarcinoma (PTMC) patients using a deep learning model based on preoperative ultrasonographic features. This study addresses the global rise in PTMC incidence and the challenges in treatment decision-making with high-resolution ultrasonography.

METHOD

This study enrolled 1638 patients with clinically staged cN0 PTMC who received surgical treatment from 1997 to 2019 at Beijing Friendship Hospital. Deep learning model was developed using fully connected neural network. Feature selection included 1000 iterations of Bootstrap sampling and Recursive Feature Elimination (RFE) to identify the top 10 features. Data preprocessing involved normalization and imputation for missing values. SMOTE addressed class imbalance. The model was trained and tested on random data split, with performance metrics including Accuracy (ACC), Area Under the Curve (AUC), Sensitivity (SEN), and Specificity (SPE), visualized through a ROC curve and confusion matrix.

RESULTS

The fully connected deep neural network model demonstrated high accuracy (ACC 0.81), Area Under the Curve (AUC 0.74), sensitivity (SEN 0.65), and specificity (SPE 0.83) and visualized by ROC curve and confusion matrix. These results highlight the model's reliability and potential as an effective tool in predicting postoperative complications and assisting in clinical decision-making for PTMC patients.

CONCLUSION

This study highlights the potential of deep learning in enhancing medical predictions and personalized healthcare. Despite promising results, limitations include a single-center data source and unconsidered factors like lifestyle and genetics. Future research should expand data sources, include more influencing factors, and refine algorithms to improve accuracy and applicability in thyroid cancer treatment.

Mortality rate and causes of death in papillary thyroid microcarcinoma

PURPOSE

Papillary thyroid microcarcinoma (PTMC) has an excellent prognosis; however, some PTMCs exhibit poor outcomes. Cancer-specific death from PTMC has been rarely reported, so we aimed to evaluate mortality rates and causes of death in patients who died with PTMC.

METHODS

We retrospectively reviewed 8969 PTMC patients treated at Samsung Medical Center from 1994 to 2017. Mortality rate and causes of death in PTMC patients were evaluated and compared with those of 7873 patients with papillary thyroid carcinoma (PTC) > 1 cm. In addition, we reviewed previous publications reporting cancer-specific deaths from PTMC.

RESULTS

Among the 8969 PTMC patients, 107 (1.2%) patients died. Only two (0.02%) patients have died of PTMC, which was less than the cancer-specific deaths from PTC > 1 cm (0.71%). Among the deceased PTMC patients, 63 (58.9%) died of other malignancies, three (2.8%) died of cardiovascular diseases, and five (4.7%) died of other diseases. Compared with PTC > 1 cm, cancer-specific deaths was less (1.9% vs. 15.1%, P < 0.001), and deaths from other malignancies were higher in deceased PTMC patients (58.9% vs. 30.5%, P < 0.001). According to 18 studies, PTMC-specific mortality rates ranged from 0.05% to 14.3%, and 336 cancer-specific deaths (0.43%) occurred among 78,770 PTMC patients.

CONCLUSION

The cancer-specific mortality rate of PTMC patients was extremely low (0.02%). More than half of deceased PTMC patients died of other malignancies, which was significantly more than those with PTC > 1 cm. These results support that active surveillance can be selected as a therapeutic option for PTMC.

Risk Stratification of Differentiated Thyroid Cancer at King Abdullah Specialized Children's Hospital Endocrinology Clinic in Riyadh, Saudi Arabia

Background Papillary thyroid cancer (PTC), a well-differentiated form of cancer, accounts for the majority of thyroid malignancies, and the incidence of PTC is on the rise. While the rate of PTC recurrence is considered to be low, there are broad spectrums of clinical and biological behavior that can lead to disease recurrence. The American Thyroid Association (ATA) risk stratification system for differentiated thyroid cancer is used as a prognostic tool to guide decision-making and management strategies most likely to achieve a favorable outcome. Aim This study aimed to estimate the prevalence of PTC recurrence in each category of the ATA risk stratification system and determine the appropriate iodine dose to be administered at the King Abdulaziz Medical City Endocrinology Clinic in Riyadh, Saudi Arabia. Methods A cross-sectional retrospective chart review was conducted on adult patients with PTC who underwent thyroidectomy procedures at the King Abdullah Specialized Children's Hospital (KASCH) Endocrinology Clinic in Riyadh between 2015 and 2023. IBM SPSS (Statistical Package for the Social Sciences) version 25 (IBM Corp., Armonk, NY) was used for data analysis. Results Of the 697 patients included in the study, 82.4% were females. About 5% had suffered from PTC recurrence, and 54.4% had low-risk stratification. In addition, more than half (52.1%) had received radioactive iodine (RAI). The recurrence of PTC was significantly associated with age (P = 0.019), ATA risk stratification (P = 0.0001), RAI therapy (P = 0.001), and iodine dosage (P = 0.013). Conclusion Both low PTC recurrence rates and low-risk stratification were observed among the PTC patients. The risk factors relating to PTC recurrence included high-risk stratification, advanced age, RAI therapy, and the dosage of RAI administered.

Transoral endoscopic and robotic thyroidectomy for thyroid cancer: the mid-term oncological outcome

BACKGROUND

Traditional open thyroidectomy is the surgical standard for thyroid cancer; however, it inevitably leaves a visible scar on the neck and affects the patient's quality of life. Therefore, to avoid making a neck incision, the transoral endoscopic thyroidectomy vestibular approach (TOETVA) and transoral robotic thyroidectomy (TORT) have been developed recently, and the surgical outcomes of these techniques are as favorable as open surgery for benign disease. Additionally, positive short-term surgical outcomes have also been achieved in a few patients with thyroid cancer. However, no data on the mid-to-long-term recurrence and survival rates of transoral thyroidectomy in thyroid cancer are available. Therefore, in this study, we analyzed the surgical outcomes and mid-term oncological results of the TOETVA and TORT in patients with thyroid cancer.

METHODS

We reviewed patients who had received TOETVA or TORT between July 2017 and November 2021 and followed up on their oncological outcomes until December 2022. Perioperative surgical and mid-term oncological outcomes were analyzed.

RESULTS

The 115 patients underwent 122 operations (57 TOETVAs and 65 TORTs), including seven complete thyroidectomies for differentiated thyroid cancer (DTC), Stage I-II, including T1-T3, N0-N1a, and initial low- to high-risk groups. There was no conversion from transoral to open surgery. TORT required a longer operating time (median [interquartile range]) than TOETVA (lobectomy: 279 [250, 318] vs. 196 [173, 253] min, p < 0.001; bilateral total thyroidectomy: 375 [309, 433] vs. 279 [238, 312] min, p < 0.001); however, no difference was found between the two groups regarding perioperative complications. Complete thyroidectomy with a second transoral approach was safe. TOETVA and TORT achieved favorable oncological outcomes with 100% survival and 98.2% acceptable response (excellent and indeterminate response) during a mean 37.88 ± 12.42 months mid-term follow-up.

CONCLUSIONS

Transoral endoscopic and robotic thyroidectomy was safe and achieved favorable mid-term oncological outcomes in a selected cohort of patients with early-stage DTC.