Evaluation of the diagnostic value of YiDiXie™-HS, YiDiXie™-SS and YiDiXie™-D in liver tumors
Zhou, H.; Sun, C.; Chen, S.; Wu, Y.; Li, X.; Ge, Z.; Chen, W.; Li, Y.; Lin, S.; Zhang, P.; Wang, W.; Li, W.; Sun, X.; Ji, L.; Li, J.; Lai, Y.
Show abstract
BackgroundLiver cancer is one of the cancers that consistently ranks among the top five cancers in terms of incidence and mortality in many countries. However, false-positive results on enhanced CT can lead to misdiagnosis and incorrect surgery or treatment, while false-negative results on enhanced CT can lead to missed diagnosis and delayed treatment. There is an urgent need to find convenient, cost-effective and non-invasive diagnostic methods to reduce the false-positive rate of ultrasound and the false-negative and false-positive rates of enhanced CT for liver tumors. The purpose of this study is to evaluate the diagnostic value of YiDiXie-HS, YiDiXie-SS and YiDiXie-D in liver tumors. Patients and methodsThis study finally included 217 subjects (the malignant group, n=185; the benign group, n=32). Remaining serum samples from the subjects were collected and tested using the YiDiXie all-cancer detection kit, which was applied to assess the sensitivity and specificity of YiDiXie-SS, YiDiXie-HS and YiDiXie-D, respectively. ResultsThe sensitivity of YiDiXie-SS was 98.9% (96.1% - 99.8%) and its specificity was 68.8% (51.4% - 82.0%). This means that YiDiXie-SS has very high sensitivity and high specificity in liver tumors.YiDiXie-HS has a sensitivity of 88.1% (82.7% - 92.0%) and its specificity is 84.4% (68.2% - 93.1%). This means that YiDiXie-HS has high sensitivity and high specificity in liver tumors.YiDiXie-D has a sensitivity of 72.4% (65.6% - 78.4%) and its specificity is 93.8% (79.9% - 98.9%). This means that YiDiXie-D has high sensitivity and very high specificity in liver tumors.YiDiXie-SS has a sensitivity of 99.2% (95.8% - 100%) and a specificity of 66.7% (39.1% - 86.2%) in patients with positive enhanced CT. This means that the application of YiDiXie-SS reduces the false-positive rate of enhanced CT by 66.7% (39.1% - 86.2%) with essentially no increase in the leakage of malignant tumors.YiDiXie-HS has a sensitivity of 89.1% (95% CI: 78.2% - 94.9%) in patients with a negative enhanced CT, and its specificity is 85.0% (64.0% - 94.8%). This means that YiDiXie-HS reduces the false-negative rate of enhanced CT by 85.0% (64.0% - 94.8%). YiDiXie-D has a sensitivity of 73.1% (64.9% - 80.0%) and a specificity of 91.7% (64.6% - 99.6%) in patients with positive enhanced CT. This means that YiDiXie-D reduces the false-positive rate of enhanced CT by 91.7% (64.6% - 99.6%). YiDiXie-D has a sensitivity of 70.9% (95% CI: 57.9% - 81.2%) and a specificity of 95.0% (95% CI: 76.4% - 99.7%) in patients with negative enhanced CT. This means that YiDiXie -D reduces the false-negative rate of enhanced CT by 70.9% (95% CI: 57.9% - 81.2%) while maintaining high specificity. ConclusionYiDiXie-SS has very high sensitivity and high specificity in liver tumors. YiDiXie-HS has high sensitivity and high specificity in liver tumors. YiDiXie-D has high sensitivity and very high specificity in liver tumors. YiDiXie-SS significantly reduces the false positive rate of liver-enhanced CT with essentially no increase in delayed treatment of malignant tumors. YiDiXie-HS significantly reduces the false-negative rate of enhanced CT. YiDiXie-D can significantly reduce the false-positive rate of enhanced CT or significantly reduce the false-negative rate of enhanced CT while maintaining a high specificity. The YiDiXie test has significant diagnostic value in liver tumors, and is expected to solve the problems of "high false-positive rate" and "high false-negative rate" of enhanced CT in liver tumors. Clinical trial numberChiCTR2200066840.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 95%
- Accuracy of deep learning based computed tomography diagnostic system of COVID-19: a consecutive sampling external validation cohort study 95%
- Classification of early and late stage Liver Hepatocellular Carcinoma patients from their genomics and epigenomics profiles. 95%
Similar papers in this journal
- Detection, Isolation and Quantification of Myocardial Infarct with Four Different Histological Staining Techniques 94%
- Demarcation line determination for diagnosis of gastric cancer disease range using unsupervised machine learning in magnifying narrow-band imaging 94%
- Passive Microwave Radiometry (MWR) for diagnostics of COVID-19 lung complications in Kyrgyzstan 93%
Similar papers in this journal
- Prognostic Analysis of Histopathological Images Using Pre-Trained Convolutional Neural Networks 94%
- DNMT family induced down-regulation of NDRG1 via DNA methylation and clinicopathological significance in gastric cancer 93%
- Ursolic acid improves the bacterial community mapping of the intestinal tract in liver fibrosis mice 93%
Similar papers in this journal
- Combined DeRitis ratio and alkaline phosphatase on the Prediction of Portal Vein Tumor Thrombosis in Patients with Hepatocellular Carcinoma 95%
- A deep learning approach for Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images 94%
- Segmentation of Pancreatic Ductal Adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and Texture Descriptors 93%
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 96%
- Post mortem pathological findings in COVID-19 cases: A Systematic Review 94%
- The Impact of Fasting the Holy Month of Ramadan on Colorectal Cancer Patients and Two Tumor Biomarkers: A Tertiary-Care Hospital Experience 93%
"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.