Evaluation of the diagnostic value of YiDiXie™-SS in thyroid ultrasound-positive patients
Zhou, H.; Wu, Y.; Li, X.; Sun, C.; Ge, Z.; Chen, W.; Li, Y.; Lin, S.; Zhang, P.; Wang, W.; Chen, S.; Li, W.; Hu, H.; Cui, Y.; He, J.; Lai, Y.
Show abstract
BackgroundThyroid tumor, as an endocrine tumor with increasing incidence, causes a heavy economic burden. Thyroid ultrasound is widely used for screening or diagnosis of thyroid tumors. However, false-positive thyroid ultrasound results can lead to misdiagnosis and wrong puncture biopsy, while false-negative thyroid ultrasound results can lead to missed diagnosis and delayed treatment. There is an urgent need to find a convenient, cost-effective and non-invasive diagnostic method to reduce the false-positive and false-negative rates of thyroid ultrasound. The aim of the present study was to evaluate the diagnostic value of YiDiXie-SS, YiDiXie-HS and YiDiXie-D in thyroid cancer. Patients and methods843 subjects (malignant group, n=820; benign group, n=23) were finally included in this study. The remaining serum samples were collected and tested by YiDiXie all-cancer detection kit. The sensitivity and specificity of YiDiXie-SS were evaluated respectively. ResultsThe sensitivity of YiDiXie-SS was 98.5% (95% CI: 97.5% - 99.2%) and its specificity was 65.2% (95% CI: 44.9% - 81.2%). This means that YiDiXie -SS has an extremely high sensitivity and relatively high specificity in thyroid tumors.YiDiXie-HS has a sensitivity of 84.3% (95% CI: 81.6% - 86.6%) and a specificity of 87.0% (95% CI: 67.9% - 95.5%). This means that YiDiXie-HS has high sensitivity and specificity in thyroid tumors.YiDiXie-D has a sensitivity of 75.5% (95% CI: 72.4% - 78.3%) and a specificity of 95.7% (95% CI: 79.0% - 99.8%). This means that YiDiXie-D has relatively high sensitivity and very high specificity in thyroid tumors.The sensitivity of YiDiXie-SS in patients with positive thyroid ultrasound was 98.4% (95% CI: 97.3% - 99.1%) and the specificity was 64.3% (95% CI: 38.8% - 83.7%). This means that the application of YiDiXie -SS reduced the false-positive thyroid ultrasound rate by 64.3% (95% CI: 38.8% - 83.7%) with essentially no increase in malignant tumor underdiagnosis.The sensitivity of YiDiXie-HS in thyroid ultrasound-negative patients was 90.0% (95% CI: 79.9% - 95.3%) and the specificity 88.9% (95% CI: 56.9%). (95% CI: 56.5% - 99.4%). This means that the application of YiDiXie-HS reduced the false negative rate of thyroid ultrasound by 90.0% (95% CI: 79.9% - 95.3%).YiDiXie -D has a sensitivity of 75.3% (95% CI: 72.1% - 78.2%) and a specificity of 92.9% (95% CI: 68.5% - 99.6%) in patients with positive thyroid ultrasound. This means that YiDiXie-D reduces the rate of false-positive thyroid ultrasounds by 92.9% (95% CI: 68.5% - 99.6%). YiDiXie-D has a sensitivity of 78.3% (95% CI: 66.4% - 86.9%) and a specificity of 100% (95% CI: 70.1% - 100%) in patients with negative thyroid ultrasounds. This means that YiDiXie-D reduces the false-negative rate of thyroid ultrasound by 78.3% (95% CI: 66.4% - 86.9%) while maintaining high specificity. ConclusionYiDiXie-SS has extremely high sensitivity and relatively high specificity in thyroid tumors.YiDiXie-HS has high sensitivity and high specificity in thyroid tumors.YiDiXie -D has relatively high sensitivity and extremely high specificity in thyroid tumors. YiDiXie-SS significantly reduces thyroid ultrasound false-positive rates with essentially no increase in delayed treatment for thyroid cancer.YiDiXie -HS significantly reduces thyroid ultrasound false-negative rates.YiDiXie-D significantly reduces thyroid ultrasound false-positive rates or significantly reduces its false-negative rates while maintaining high specificity. YiDiXie tests have vital diagnostic value in thyroid cancer, and are expected to solve the problems of "high false-positive rate" and "high false-negative rate" of thyroid ultrasound. Clinical trial numberChiCTR2200066840.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The Role of Carbon Nanoparticle in Lymph Node Detection and Parathyroid Gland Protection during Thyroidectomy - a Meta Analysis 96%
- Expression based biomarkers and models to classify early and late stage samples of Papillary Thyroid Carcinoma 95%
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 94%
Similar papers in this journal
- Effects of contrast-medium and vertebral measurement level on computed tomography-based body composition parameters of skeletal muscle and adipose tissue 92%
- Benchmarking Deep Learning-based Image Retrieval of Oral Tumor Histology 91%
- The Impact of Fasting the Holy Month of Ramadan on Colorectal Cancer Patients and Two Tumor Biomarkers: A Tertiary-Care Hospital Experience 91%
Similar papers in this journal
- Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides 92%
- Improving prognosis of surrogate assay for breast cancer patients by absolute quantitation of Ki67 protein levels using Quantitative Dot Blot (QDB) method 92%
- miR-100-5p downregulates mTOR to suppress the proliferation, migration and invasion of prostate cancer cells 91%
Similar papers in this journal
- Demarcation line determination for diagnosis of gastric cancer disease range using unsupervised machine learning in magnifying narrow-band imaging 92%
- Analytical performance of a highly sensitive system to detect gene variants using next-generation sequencing for lung cancer companion diagnostics 91%
- Detection, Isolation and Quantification of Myocardial Infarct with Four Different Histological Staining Techniques 91%
Similar papers in this journal
- DNMT family induced down-regulation of NDRG1 via DNA methylation and clinicopathological significance in gastric cancer 92%
- Prognostic Analysis of Histopathological Images Using Pre-Trained Convolutional Neural Networks 91%
- A machine learning approach for identification of gastrointestinal predictors for the risk of COVID-19 related hospitalization 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.