Optimizing Healthcare Inventory Management: A Machine Learning Approach for Efficient Classification of Basic Materials

Durmuş A., Aydın Ö., Dalkılıç F.

OPSEARCH, cilt.62, sa.2, 2025 (ESCI)

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 62 Sayı: 2
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s12597-025-00238
  • Dergi Adı: OPSEARCH
  • Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, ABI/INFORM, INSPEC, zbMATH
  • Manisa Celal Bayar Üniversitesi Adresli: Evet

Özet

Purpose: Healthcare facilities play a critical role in providing medical services to communities, yet deficiencies in their inventory management systems can hinder their ability to meet community needs. This study aims to address these challenges by proposing a strategy to optimize inventory management through the application of classification methods.

Methods: A system utilizing machine learning techniques was developed for classifying inventory in healthcare facilities. Data from the facility were analyzed using various machine learning algorithms including Naive Bayes, Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbors (KNN), Neural Network, XGBoost, and Support Vector Machine (SVM). Python programming language was employed for implementation, utilizing Google Colab for the computational environment.

Results: The performance of different machine learning techniques in classifying basic materials inventory was evaluated. Results indicate that Decision Tree, Random Forest, KNN, and XGBoost algorithms demonstrate high performance in classification tasks.

Conclusions: Efficient inventory management is crucial for healthcare facilities to meet community needs effectively. The utilization of machine learning techniques, particularly Decision Tree, Random Forest, KNN, and XGBoost can significantly improve inventory classification processes, leading to a more organized and efficient system for healthcare facilities.