Evaluation of the MCED value of YiDiXie™-HS and YiDiXie™-SS
Sun, C.; Lu, C.; Zhang, Y.; Wang, L.; Ge, Z.; Wen, Z.; Chen, W.; Li, Y.; Wu, Y.; Lin, S.; Zhang, P.; Wang, W.; Chen, S.; Zhou, H.; Li, X.; Wang, S.; Xia, Y.; Li, W.; Lan, W.; Cai, Y.; Ji, L.; Wang, H.; Lai, Y.
Show abstract
BackgroundCancer is a serious threat to the whole of humanity. The Multi-Cancer Early Detection (MCED) test is expected to solve the problem of "Universal cancer screening". The purpose of this study is to evaluate the MCED value of two MCED tests, YiDiXie-HS and YiDiXie-SS, in multiple cancer types. Patients and methods11094 subjects were finally included in this study (the malignant tumor group, n = 4405; the normal control group, n = 6689). The malignant tumor group included all major solid and hematological malignant tumor types. The sensitivity and specificity of YiDiXie-HS and YiDiXie-SS were evaluated, respectively. ResultsThe overall sensitivity of YiDiXie-HS for different cancer types and stages was 90.1% (89.2% - 90.9%; 3971/4405), and its specificity was 89.7% (89.0% - 90.4%; 6002/6689). Its sensitivity increases with clinical stage: stage I, 85.6% (83.9% - 87.1%); stage II, 91.4% (89.6% - 93.0%); stage III, 93.9% (92.0% - 95.4%); and stage IV, 98.4% (96.9% - 99.2%). The overall sensitivity of YiDiXie-SS for different cancer types and stages was 99.1% (98.8% - 99.3%; 4365/4405), and its specificity was 65.2% (64.0% - 66.3%; 4358/6689). Its sensitivity was basically comparable in each clinical stage: stage I, 98.6% (98.0% - 99.1%); stage II, 99.5% (98.9% - 99.8%); stage III, 99.5% (98.6% - 99.8%); stage IV, 99.8% (98.9% - 100.0%). ConclusionYiDiXie-HS has a high sensitivity in all clinical stages of all cancer types. YiDiXie-SS has an extremely high sensitivity in all clinical stages of all cancer types. YiDiXie-HS and YiDiXie-SS can replace existing cancer screening tests and are expected to solve the world problem of "Universal cancer screening". Clinical trial numberChiCTR2200066840.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Machine learning based prediction of recurrence after curative resection for rectal cancer 95%
- Weakly supervised learning for multi-organ adenocarcinoma classification in whole slide images 95%
- Comprehensive analysis of prostate cancer life expectancy, loss of life expectancy, and healthcare expenditures: Taiwan national cohort study spanning 2008 to 2019 94%
Similar papers in this journal
- Comprehensive analysis of potential immunotherapy genomic biomarkers in 1,000 Chinese patients with cancer 94%
- Circulating serum miRNAs predict response to platinum chemotherapy in high-grade serous ovarian cancer 94%
- Downregulation of NCL attenuates tumor formation and growth in cervical cancer by targeting the PI3K/AKT pathway 93%
Similar papers in this journal
- Analytical performance of a highly sensitive system to detect gene variants using next-generation sequencing for lung cancer companion diagnostics 95%
- Identification of prognostic biomarkers for suppressing tumorigenesis and metastasis of Hepatocellular carcinoma through transcriptome analysis 92%
- Detection, Isolation and Quantification of Myocardial Infarct with Four Different Histological Staining Techniques 92%
Similar papers in this journal
- Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction 93%
- Stay-at-home and face mask policies intentions inconsistent with incidence and fatality during US COVID-19 pandemic 91%
- Evaluation of a clinical decision support system for detection of patients at risk after kidney transplantation 91%
Similar papers in this journal
"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.