Comparing surgical thoroughness and recurrence in thyroid cancer patients across race/ethnicity

Investigating potential disparities by exploring time to surgical thyroid cancer treatment

(1) Delays in initial treatment have been a frequently used metric for assessing disparities in medicine; however, there has been sparse literature on treatment delays in thyroid cancer. We therefore aimed to assess disparities by investigating the association between race/ethnicity, insurance type, and socioeconomic status and time to surgical treatment of thyroid cancer. (2) A retrospective chart review was conducted to collect demographic and clinical data from 443 surgical thyroid cancer patients at Mount Sinai Hospital in 2018-2019. We investigated the time between thyroid cancer diagnosis and surgery by race/ethnicity, insurance, and income groups. (3) Univariate analysis showed that race/ethnicity, insurance type, and SES alone were not statistically significant predictors of earlier time to treatment (p = 0.766, 0.339, 0.435, respectively). On multivariable linear regression, time between diagnosis and surgical treatment was not significantly different for racial minorities compared to non-Hispanic White patients, patients with Medicare/Medicaid compared to private insurance, and patients with lowest income quartile (<$54,585) compared to those with the highest (≥$116,560). (4) Present study showed no significant delays in treatment for different racial/ethnic, insurance, and income groups.

Parathyroidectomy outcomes for Asians in the United States: Implications for resident surgical education

Introduction

Outcomes for Asian patients in the United States are often overlooked in the surgical literature. Surgical education includes little emphasis on reporting outcomes for Asian patients in the United States. Our null hypothesis (H0) is that there is no difference in surgical complications following parathyroid surgery between Asians and all other ethnicities in the United States. Our alternate hypothesis (H1) is that Asians have more incidences of certain complications (possibly due to culture and language barriers).

Methods

Data from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) was queried for parathyroidectomy and patient race. Complications within 30 days of surgery were extracted.

Results

Among, White, Black, Asian, Pacific Islanders, Native Americans, and Hispanic patients of the United States the Asians (p = 0.018) and Blacks (p = 0.003) had increased operative time for parathyroid surgery compared to other groups. Hispanics had the most surgical complications (p = 0.025). Blacks had statistically significant longer hospital stay (p < 0.0001).

Discussion/conclusion

United States Asian patient data is not typically analyzed separately for complications. We found that in the United States Asians have increased operative time for parathyroidectomy. Future studies of healthcare inequities should include analysis of data for Asian surgical data in the United States as this may help prevent future surgical complications.

A Predictive Model for the 10-year Overall Survival Status of Patients With Distant Metastases From Differentiated Thyroid Cancer Using XGBoost Algorithm-A Population-Based Analysis

Purpose: To explore clinical and non-clinical characteristics affecting the prognosis of patients with differentiated thyroid cancer with distant metastasis (DTCDM) and establish an accurate overall survival (OS) prognostic model.

Patients and methods: Study subjects and related information were obtained from the National Cancer Institute’s surveillance, epidemiology, and results database (SEER). Kaplan‐Meier analysis, log-rank test, and univariate and multivariate Cox analysis were used to screen for factors influencing the OS of patients with DTCDM. Nine variables were introduced to build a machine learning (ML) model, receiver operating characteristic (ROC) was used to evaluate the recognition ability of the model, calibration plots were used to obtain prediction accuracy, and decision curve analysis (DCA) was used to estimate clinical benefit.

Results: After applying the inclusion and exclusion criteria, a total of 3,060 patients with DTCDM were included in the survival analysis from 2004 to 2017. A machine learning prediction model was developed with nine variables: age at diagnosis, gender, race, tumor size, histology, regional lymph node metastasis, primary site surgery, radiotherapy, and chemotherapy. After excluding patients who survived <120 months, variables were sub-coded and machine learning was used to model OS prognosis in patients with DTCDM. Patients 6–50 years of age had the highest scores in the model. Other variables with high scores included small tumor size, male sex, and age 51–76. The AUC and calibration curves confirm that the XGBoost model has good performance. DCA shows that our model can be used to support clinical decision-making in a 10-years overall survival model.

Conclusion: An artificial intelligence model was constructed using the XGBoost algorithms to predict the 10-years overall survival rate of patients with DTCDM. After model validation and evaluation, the model had good discriminative ability and high clinical value. This model could serve as a clinical tool to help inform treatment decisions for patients with DTCDM.