Related Experiment Video
Updated: Jul 17, 2026
09:16
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
[Detecting biomarkers from serum in nephroblastoma patients with support vector machine]
Jia-xiang Wang1, Jiao Zhang, Qiu-liang Liu
1Department of Surgery, First Affiliated Hospital, Zhengzhou University, Zhengzhou, 450052, China. wjiaxiang@zzu.edu.cn
Zhonghua Yi Xue Za Zhi
|February 10, 2007
Summary
This study identified novel protein biomarkers for nephroblastoma detection. The developed serum protein fingerprint model shows high accuracy for early diagnosis and screening of this childhood cancer.
Area of Science:
- Biochemistry
- Proteomics
- Bioinformatics
Context:
- Nephroblastoma is a significant childhood cancer requiring improved early detection methods.
- Current diagnostic approaches may lack the sensitivity and specificity for timely intervention.
Purpose:
- To identify novel serum protein biomarkers for nephroblastoma.
- To develop a diagnostic model for early detection and classification of nephroblastoma using SELDI-TOF-MS and bioinformatics.
Summary:
- Surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS) analyzed serum samples from nephroblastoma patients, healthy children, and children with other abdominal tumors.
- Four potential protein biomarkers (m/z 6984.5, 6455.5, 6914.0, 3256.7) were identified.
- A diagnostic model using two biomarkers achieved 100% sensitivity and specificity in distinguishing nephroblastoma from healthy controls, and 93.3% sensitivity and 100% specificity against other pediatric abdominal tumors.
Impact:
- The findings suggest a highly sensitive and specific proteomic approach for early nephroblastoma diagnosis.
- This method holds promise for identifying new tumor biomarkers and improving pediatric cancer diagnostics.
