Evaluation of the diagnostic value of YiDiXie™-SS, YiDiXie™-HS and YiDiXie™-D in lung tumors
Li, X.; Chen, W.; Wang, W.; Sun, C.; Zhou, H.; Wu, Y.; Ge, Z.; Li, Y.; Lin, S.; Zhang, P.; Chen, S.; Li, W.; Chen, H.; Ji, L.; Liu, J.; Lai, Y.
Show abstract
BackgroundLung cancer poses a serious threat to human health. Lung CT is widely used for lung tumor screening or initial diagnosis, while contrast-lung CT is extensively employed in lung tumor diagnosis. However, false-positive lung CT results can lead to misdiagnosis and incorrect surgery or treatment, while false-negative lung CT results 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 and false-positive rates of lung CT. The aim of this study was to evaluate the diagnostic value of YiDiXie-SS, YiDiXie-HS and YiDiXie-D, in lung cancer. Patients and methodsThis study finally included 1250 subjects (the malignant group, n=1078; the benign group, n=172). 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. Results: YiDiXie-SS has a sensitivity of 97.5% (96.4% - 98.3%) and its specificity is 66.9% (59.5% - 73.5%). This means that YiDiXie-SS has very high sensitivity and high specificity in lung tumors.YiDiXie-HS has a sensitivity of 85.3% (83.0% - 87.2%) and its specificity is 83.1% (76.8% - 88.0%). This means that YiDiXie-HS has high sensitivity and high specificity in lung tumors.YiDiXie-D has a sensitivity of 73.9% (71.2% - 76.5%) and its specificity is 92.4% (87.5% - 95.5%). This means that YiDiXie-D has high sensitivity and very high specificity in lung tumors.YiDiXie-SS has a sensitivity of 98.2% (95% CI: 96.8% - 99.0%) and a specificity of 66.0% (95% CI: 51.7% - 77.8%) in patients with CT-positive tumors. This means that the application of YiDiXie-SS reduces the CT false-positive rate by 66.0% (95% CI: 51.7% - 77.8%) with essentially no increase in malignancy underdiagnosis. The sensitivity of YiDiXie-HS in CT negative patients was 84.2% (95% CI: 80.6% - 87.2%) and its specificity was 82.4% (95% CI: 74.8% - 88.1%). This means that the application of YiDiXie -HS reduces the false-negative lung CT rate by 84.2% (95% CI: 80.6% - 87.2%). YiDiXie-D has a sensitivity of 73.7% (70.1% - 77.1%) and a specificity of 93.6% (82.8% - 97.8%) in CT-positive patients. This means that YiDiXie -D reduces the rate of CT false positives by 93.6% (82.8% - 97.8%). YiDiXie-D has a sensitivity of 74.2% (70.1% - 78.0%) and a specificity of 92.0% (85.9% - 95.6%) in patients with a negative CT. This means that YiDiXie-D reduces the CT false-negative rate by 74.2% (70.1% - 78.0%) while maintaining high specificity. ConclusionYiDiXie-SS provides extremely high sensitivity and high specificity in lung tumors. YiDiXie-HS provides high sensitivity and high specificity in lung tumors. yiDiXie-D provides high sensitivity and very high specificity in lung tumors. YiDiXie -SS significantly reduces the rate of lung CT false positives with essentially no increase in delayed treatment of malignant tumors. YiDiXie-HS significantly reduces the false-negative rate of lung CT. YiDiXie-D can significantly reduce the false-positive rate of lung CT or significantly reduce the false-negative rate while maintaining high specificity. the YiDiXie test has important diagnostic value in lung cancer and is expected to solve the problems of "too high false-positive rate" and "too high false-negative rate" of lung CT. Clinical trial numberChiCTR2200066840.
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Quantitative analysis of chest computed tomography of COVID-19 pneumonia using a software widely used in Japan 96%
- Accuracy of deep learning based computed tomography diagnostic system of COVID-19: a consecutive sampling external validation cohort study 96%
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 94%
Similar papers in this journal
- Passive Microwave Radiometry (MWR) for diagnostics of COVID-19 lung complications in Kyrgyzstan 94%
- Auto-detection of motion artifacts on CT pulmonary angiograms with a physician-trained AI algorithm 93%
- Detection, Isolation and Quantification of Myocardial Infarct with Four Different Histological Staining Techniques 93%
Similar papers in this journal
- High-Dimensional Multinomial Multiclass Severity Scoring of COVID-19 Pneumonia Using CT Radiomics Features and Machine Learning Algorithms 95%
- Toward Understanding COVID-19 Pneumonia: A Deep-learning-based Approach for Severity Analysis and Monitoring the Disease 93%
- A deep learning approach for Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images 93%
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 91%
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 95%
- Post mortem pathological findings in COVID-19 cases: A Systematic Review 93%
- Retrospective study on the clinicogenomic characteristics of EGFR mutant and wildtype NSCLC 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.