Purpose
This study aimed to leverage Shapley additive explanation (SHAP)-based feature engineering to predict appendix cancer. Traditional models often lack transparency, hindering clinical adoption. We propose a framework that integrates SHAP for feature selection, construction, and weighting to enhance accuracy and clinical relevance.
Methods
Data from the Kaggle Appendix Cancer Prediction dataset (260,000 samples, 21 features) were used in this prediction study conducted from January through March 2025, in accordance with TRIPOD-AI guidelines. Preprocessing involved label encoding, SMOTE (synthetic minority over-sampling technique) to address class imbalance, and an 80:20 train-test split. Baseline models (random forest, XGBoost, LightGBM) were compared; LightGBM was selected for its superior performance (accuracy=0.8794). SHAP analysis identified key features and guided 3 engineering steps: selection of the top 15 features, construction of interaction-based features (e.g., chronic severity), and feature weighting based on SHAP values. Performance was evaluated using accuracy, precision, recall, and F1-score.
Results
Four LightGBM model configurations were evaluated: baseline (accuracy=0.8794, F1-score=0.8691), feature selection (accuracy=0.8968, F1-score=0.8860), feature construction (accuracy=0.8980, F1-score=0.8872), and feature weighting (accuracy=0.8986, F1-score=0.8877). SHAP-based engineering yielded performance improvements, with feature weighting achieving the highest precision (0.9940). Key features (e.g., red blood cell count and chronic severity) contributed to predictions while maintaining interpretability.
Conclusion
The SHAP-based framework substantially improved the accuracy and transparency of appendix cancer predictions using LightGBM (F1-score=0.8877). This approach bridges the gap between predictive power and clinical interpretability, offering a scalable model for rare disease prediction. Future validation with real-world data is recommended to ensure generalizability.

Objectives

Primary biliary cirrhosis (PBC) is a chronic cholestatic liver disease that may progress to end stage liver cirrhosis. Benefits of ursodeoxycholic acid (UDCA) treatment has been investigated through large clinical studies. However, most of the studies were done in western countries and recent increase in prevalence of this relatively uncommon chronic liver disease draws attention in Korea. As early UDCA treatment effectively prevent the grave consequences of PBC progression, early diagnosis and lifelong management with UDCA is important. This study was designed to investigate the clinical features of PBC and response rates of UDCA treatments in Ewha Womans University Medical Center.

Methods

Clinical data of PBC patients diagnosed between 2001 and 2014 at Ewha Womans University Medical Center were analyzed retrospectively.

Results

A total of 35 patients with mean follow-up duration of 42 months were enrolled. At the diagnosis, 72.7% of the patients were asymptomatic, 5.7% had decompensated liver cirrhosis. The mean serum alkaline phosphate (ALP) level was 2.65 times upper limit of normal. UDCA was prescribed in 91.4% of the patients (n=32), among which 77.4% exhibited biochemical responses defined as serum ALP less than 2 upper limit of normal at 6 months (Mayo criteria).

Conclusion

Most PBC patients were asymptomatic at the time of diagnosis and the average biochemical responses rate to UDCA treatment were ranged from 60.0% to 78.9% according to various response criteria. To elucidate the clinical features and courses of Korean PBC patients in detail, larger scale investigations and longer clinical follow up studies are warranted.