A multi-variable predictive warning model for cervical cancer using clinical and SNPs data.

Area of Science:

• Oncology
• Genetics
• Biostatistics

Background:

• Cervical cancer is a significant global health concern, ranking as the fourth most common cancer in women worldwide.
• Early detection and intervention are critical for improving patient outcomes and survival rates.

Purpose of the Study:

• To develop an early predictive warning model for cervical cancer and precancerous lesions.
• To integrate clinical data with simple nucleotide polymorphisms (SNPs) for enhanced predictive accuracy.

Main Methods:

• Collected clinical data and germline SNPs from 472 participants.
• Employed logistic regression, LASSO, and stepwise regression for variable selection.
• Applied machine learning models including logistic regression (LR), SVM, RF, DT, XGBoost, and NN.
• Utilized ROC curves and decision curve analysis (DCA) for model evaluation.

Main Results:

• An optimal logistic regression (LR) model was identified, incorporating 6 SNPs and 2 clinical variables as independent risk factors.
• The LR model demonstrated good clinical applicability, as validated by DCA.

Conclusions:

• The developed predictive model accurately forecasts cervical cancer risk by combining clinical and SNP data.
• This tool facilitates timely interventions and refines clinical decision-making in cervical cancer management.