Mohit Kharbanda, Arshi Husain, Virendra P. Vishwakarma

DOI: https://doi.org/10.5281/zenodo.21912213

This study investigate whether evolutionary hyperparameter search can meaningfully improve classifier performance for gallstone disease (GSD) diagnosis. Working from a cohort of 319 patients described by 38 clinical and demographic variables, we split the data into training (80%) and testing (20%) partitions using stratified sampling, and standardized features using statistics computed solely from the training partition to avoid information leakage. A Genetic Algorithm (GA) then searched the hyperparameter space of six classifiers– Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Decision Tree (DT), K-Nearest Neighbors (KNN), and Logistic Regression (LR) with each candidate configuration scored by 5-fold stratified cross-validation restricted to the training partition. Tuned models were refit on the full training set and evaluated once, on the held-out test partition, using accuracy, precision, recall, F1-score, and confusion-matrix analysis. XGBoost led every metric at 90.62%, with a ROC-AUC of 93.46%, RF and SVM tied at 79.69% accuracy, LR reached 78.12%, KNN 67.19%, and DT62.50%. The margin between XGBoost and the remaining classifiers indicates that, for this dataset, pairing gradient boosting with evolutionary tuning offers a genuine advantage over the alternatives tested.

Gallstone disease, Machine learning, Genetic Algorithm, Synthetic resampling, XGBoost, Ensembles, Decision support systems

Webuilt a GA-optimized classification pipeline for gallstone disease using 38 clinical and demographic variables from 319 patients, with hyperparameter search, cross-validation, and model comparison all kept strictly within the training partition until final evaluation. Across the six classifiers tested, XGBoost was the clear winner: 90.62% on accuracy, precision, recall, and F1-score, correctly classifying 58 of the 64 held-out test cases. RF and SVM followed at 79.69% accuracy, LR at 78.12%, and KNN and DT trailed at 67.19% and 62.50% respectively. The implication from this analysis can be straightforward: the use of evolutionary tuning combined with a gradient boost ing classifier appears to be a powerful combination for this type of structured-data GSD classification problem. However, the dataset under consideration is small in size 319 samples which means that the following natural question is how this advantage would manifest itself in larger, more diverse cohorts of patients

[1] L. Deng, S. Wang, D. Wan, Q. Zhang, W. Shen, X. Liu,
and Y. Zhang, “Relative fat mass and physical indices as
predictors of gallstone formation: Insights from machine
learning and logistic regression,” International Journal of
General Medicine, pp. 509–527, 2025.
[2] Y. Ma, P. Yue, J. Zhang, J. Yuan, Z. Liu, Z. Chen, H.
Zhang, C. Zhang, Y. Zhang, C. Dong et al., “Early pre
diction of acute gallstone pancreatitis severity: A novel
machine learning model based on CT features and open
access online prediction platform,” Annals of Medicine,
vol. 56, no. 1, p. 2357354, 2024.
[3] C. Hong, I. Zafar, M. M. Ayaz, R. Kanwal, F. Kanwal,
M. Dauelbait, M. Bourhia, and Y. A. B. Jardan, “Analysis
of machine learning algorithms for real-time gallbladder
stone identification from ultrasound images in clinical
decision support systems,” International Journal of Com
putational Intelligence Systems, vol. 18, no. 1, pp. 1–28,
2025.
[4] A. Bozdag, M. Yildirim, M. Karaduman, H. B. Mutlu,
G. Karaduman, and A. Aksoy, “Detection of gallbladder
disease types using a feature engineering-based developed
“Construction and evaluation of a nomogram to predict
gallstone disease based on body composition,” Inter
national Journal of General Medicine, pp. 5947–5956,
2022.
[6] A. Veena and S. Gowrishankar, “Context based health
care informatics system to detect gallstones using deep
learning methods,” International Journal of Advanced
Technology and Engineering Exploration, vol. 9, no. 96,
p. 1661, 2022.
[7] N. M. Salem, K. M. Jack, H. Gu, A. Kumar, M. Garcia,
P. Yang, and V. Dinu, “Machine and deep learning iden
tified metabolites and clinical features associated with
gallstone disease,” Computer Methods and Programs in
Biomedicine Update, vol. 3, p. 100106, 2023.
[8] I. Esen, H. Arslan, S. Aktürk Esen, M. Gül¸sen, N. Kül
tekin, and O. Özdemir, “Early prediction of gallstone
disease with a machine learning-based method from
bioimpedance and laboratory data,” Medicine, vol. 103,
no. 8, p. e37258, 2024.
[9] P. Sarker, J. J. Tiang, and A. A. Nahid, “Gallstone classifi
cation using random forest optimized by Sand Cat Swarm
Optimization algorithm with SHAP and DiCE-based in
terpretability,” Sensors, vol. 25, no. 17, p. 5489, 2025.
[10] D. Kumar, M. A. Mehta, K. Kotecha, and A. Kulkarni,
“Computer-aided cholelithiasis diagnosis using explain
able convolutional neural network,” Scientific Reports,
vol. 15, p. 4249, 2025.
[11] A. M. Obaid, A. Turki, H. Bellaaj, and M. Ksantini, “Di
agnosis of gallbladder disease using artificial intelligence:
A comparative study,” International Journal of Computer
Intelligence Systems, vol. 17, p. 46, 2024.
[12] K. Kanwal, I. Batool, I. Naz, A. Shabbir, M. Fatima,
and H. Batool Gill, “Automated detection of gallstone
disease using machine learning techniques: A data-driven
approach,” JSCIR, vol. 7, no. 2, pp. 157–176, 2025.
[13] X. Wang, H. Zhang, Z. Bai, X. Xie, and Y. Feng, “Current
status of artificial intelligence analysis for the diagnosis
of gallbladder diseases using ultrasonography: A scoping
review,” Translational Gastroenterology and Hepatology,
vol. 10, 2024.
[14] C. Ge, J. Jang, P. Svrcek, V. Fleming, and Y. H. Kim, “Ex
ploring deep learning applications using ultrasound single
view cines in acute gallbladder pathologies: Preliminary
results,” Academic Radiology, vol. 32, no. 2, pp. 770–775,
2025.
6
CBIR system,” Diagnostics, vol. 15, no. 5, p. 552, 2025.
[15] R. A. Putra, G. A. Pradipta, and P. D. W. Ayu, “Gallblad
der disease classification from ultrasound images using
CNN feature extraction and machine learning optimiza
tion,” Journal of Electronic, Electromedical, and Medical
Informatics, vol. 7, no. 4, pp. 1089–1111, 2025.
[16] M.Indirani, S. Sudheer, R. Mahaveerakannan et al., “Gall
stone disease prediction using clinical and biochemical
features through ensemble learning techniques,” Interna
tional Journal of Computational Intelligence Systems, vol.
19, p. 19, 2026.
[17] S. B. Akben and H. Yumruta¸s, “A new ensemble learning
approach for non-invasive gallstone risk prediction,” in
2025 16th International Conference on Electrical and
Electronics Engineering (ELECO), Bursa, Türkiye, 2025,
pp. 1–6.
[18] E. Zeqo and E. Naka, “A metaheuristic and machine
learning-based algorithm for predicting gallstone dis
ease,” in 2025 International Conference on Big Data,
Knowledge and Control Systems Engineering (BdKCSE),
Bankya, Bulgaria, 2025, pp. 1–8.
[19] M. T. Meyer, J. Wasserthal, J. Cyriac et al., “Automated
detection of gallbladder stones using a deep learning al
gorithm on computed tomography scans,” Abdominal Ra
diology, 2026.

Mohit Kharbanda, Arshi Husain, Virendra P. Vishwakarma (2026). Evolutionary Hyperparameter Optimization of Machine Learning Classifiers for Gallstone Disease Prediction. International Journal of Computer Techniques, 13(4), 211–217. ISSN: 2394-2231. DOI: https://doi.org/10.5281/zenodo.21912213