Machine Learning Model for Diagnosing Intervertebral Disc Degeneration
Author Information
Author(s): Lin Maoqiang, Li Shaolong, Wang Yabin, Zheng Guan, Hu Fukang, Zhang Qiang, Song Pengjie, Zhou Haiyu
Primary Institution: The Second Hospital & Clinical Medical School, Lanzhou University
Hypothesis
The study aims to explore the role of lymphatics-associated genes in intervertebral disc degeneration and develop a diagnostic model using machine learning.
Conclusion
A diagnostic model based on lymphatics-associated genes was developed and validated, effectively identifying patients with intervertebral disc degeneration.
Supporting Evidence
- Fifteen differentially expressed lymphatics-associated genes were identified.
- The diagnostic model achieved an AUC value of 0.938 in the training set.
- The model was validated with an AUC value of 0.772 in an external dataset.
- Machine learning algorithms were used to select key genes for the diagnostic model.
- Potential therapeutic drugs were identified based on the model genes.
Takeaway
Researchers created a computer program that helps doctors figure out if someone has a back problem by looking at specific genes.
Methodology
The study used datasets from the GEO database, identified differentially expressed lymphatics-associated genes, and applied four machine learning algorithms to construct and validate a diagnostic model.
Potential Biases
The relatively small sample size may lead to overfitting of the model.
Limitations
The sample size was small, which may affect the generalizability of the results, and detailed clinical characteristics were lacking.
Participant Demographics
The training set included 30 samples, with a mix of patients with intervertebral disc degeneration and normal controls.
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