Large-Scale Comparative Analysis Reveals A Simple Model To Predict The Prevalence Of Thyroid Nodules

Nomogram Prediction Model of Thyroid Nodule in Healthcare Professionals: Based on Physical and Psychological Risk Factors

Background

Thyroid nodules are a common condition with a 7-15% likelihood of developing thyroid cancer. The prevalence of thyroid nodules in healthcare professionals is poorly understood, and how psychosomatic factors affect the occurrence of thyroid nodules is an interesting question. Therefore, the aims of this study are to explore the physiological and psychological aspects associated of thyroid nodules in healthcare professionals and establish a prediction model to provide a supportive basis for the primary prevention of thyroid nodules.

Methods

A total of 738 healthcare professionals in a tertiary general hospital were selected by convenience sampling to complete an online psychological questionnaire and physical examination (biochemical indicators, ultrasound, etc.) from February to May 2023. Logistic regression was used to analyze risk factors, and the prediction model was established by nomogram.

Results

A total of 406 of 738 healthcare professionals had thyroid nodules, the detection rate was 55.0%, among those detected, 24.1% were male and 75.9% were female. Multivariate logistic regression analysis showed: compared with ≤40 years old, aged 41-50 years old, or >50 years old were risk factors for thyroid nodules (OR=2.071/8.034); female (OR=1.873) was also risk factor for thyroid nodules relative to male; in addition, anxiety (OR=1.105), perceived stress (OR=1.045), fatty liver (OR=2.716), TSH abnormality (OR=1.944), and ALT abnormality (OR=2.252) were also risk factors. Based on the above seven influencing factors, a nomogram was drawn and verified internally. The results showed that the area AUC under the ROC curve of the model was 0.713, and the calibration curve indicated that the model consistency was acceptable.

Conclusion

The detection rate of thyroid nodules is higher in healthcare professionals. A combination of psychological and physiological factors in TNs has a significant impact on thyroid nodules. Identifying risk factors for thyroid nodules and managing them promptly is important for the complete health of healthcare professionals.

Diagnostic Performance of Ultrasound Computer-Aided Diagnosis Software Compared with That of Radiologists with Different Levels of Expertise for Thyroid Malignancy: A Multicenter Prospective Study

The aim of the work described here was to evaluate the diagnostic performance of ultrasound thyroid computer-aided diagnosis (CAD) software. This multicenter prospective study included 494 patients (565 thyroid nodules) who underwent surgery or biopsy after ultrasonography at four hospitals from January 2019 to September 2019. The diagnostic performance metrics of different readers were calculated and compared with the pathologic results. The sensitivity of CAD was outstanding and was equivalent to that of a senior radiologist (90.51% vs. 88.47%, p > 0.05). The area under the curve of CAD was equivalent to that of a junior radiologist (0.748 vs. 0.739, p > 0.05). However, the specificity was only 49.63%, which was lower than those of the three radiologists (75.56%, 85.93% and 90.37% for the junior, intermediate and senior radiologists, respectively). The diagnostic performance of the junior radiologist was significantly improved with the aid of CAD (junior + CAD). The sensitivity and area under the curve of junior + CAD were improved from 72.20% to 89.93% and from 0.739 to 0.816, respectively (both p values <0.05), and the positive predictive value, negative predictive value and κ coefficient improved from 76.3% to 78.6%, 82.0% to 86.8% and 0.394 to 0.511, respectively. Though specificity slightly decreased from 75.56% to 73.33%, the difference was not statistically significant (p > 0.05). In general, the clinical application value of CAD is promising, and its instrumental value for junior radiologists is significant.