Improving Detection Accuracy of Lung Cancer Serum Proteomic Profiling via Two-Stage Training Process
Author Information
Author(s): Hsu Pei-Sung, Wang Yu-Shan, Huang Su-Chen, Lin Yi-Hsien, Chang Chih-Chia, Tsang Yuk-Wah, Jiang Jiunn-Song, Kao Shang-Jyh, Uen Wu-Ching, Chi Kwan-Hwa
Primary Institution: Shin Kong Wu Ho-Su Memorial Hospital, Taipei, Taiwan
Hypothesis
This study aimed to improve the detection accuracy of lung cancer by SELDI in mixed individuals, those who are healthy and those with inflammatory disease.
Conclusion
Using a two-stage training process will improve the specificity and accuracy of detecting lung cancer.
Supporting Evidence
- The two-stage method had statistically higher specificity (80%) and accuracy (74.7%) compared to the one-stage method.
- The predominant protein peak at 11480 Da was identified as a key factor in distinguishing lung cancer from other conditions.
- Inflammatory disease can severely interfere with the detection accuracy of SELDI profiles for lung cancer.
Takeaway
Researchers found a better way to tell if someone has lung cancer by using a two-step process that looks at their blood, which helps avoid confusion with other illnesses.
Methodology
Sera from 118 lung cancer patients, 72 healthy individuals, and 31 patients with inflammatory disease were analyzed using a two-stage SELDI-TOF-MS process.
Potential Biases
Potential bias due to the inclusion of patients with inflammatory diseases that may affect biomarker detection.
Limitations
The study may not account for all variables affecting detection accuracy, and the reproducibility in different laboratories remains a challenge.
Participant Demographics
The study included 118 lung cancer patients (80 males, 38 females), 72 healthy individuals (39 males, 33 females), and 31 patients with inflammatory diseases (23 males, 8 females).
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website