Hybrid Natural Language Processing–Metadata Classification (HNLP–MC) Approach for Artificial Intelligence-Driven Categorization of Information Technology Service Desk Tickets in Healthcare Project Management Systems

Abstract

In healthcare project management systems, information technology (IT) service desk tickets play a vital role in ensuring the continuous operation of hospital information systems (HIS). However, manual handling of these requests often leads to duplication, misclassification, and delayed responses, reducing overall efficiency. To address these challenges, the current study proposes the hybrid NLP–metadata classification (HNLP–MC) model, an artificial intelligence-driven framework that integrates natural language processing (NLP) with structured metadata analysis for automated categorization of IT service tickets. Historical data from a healthcare project management system were analyzed using textual and metadata features. The textual content was represented using the term frequency–inverse document frequency (TF–IDF) technique to capture the significance of words in each request, while metadata attributes provided contextual information for improved classification. Several machine learning classifiers, including logistic regression (LR), support vector machine (SVM), random forest (RF), and gradient boosting (GB), achieving accuracies of 80.77%, 73.42%, 78.52%, and 82.96%, respectively, were evaluated to determine the most effective algorithm for predicting the appropriate category of new service desk tickets. Based on the comparative results, the GB classifier was selected as the core model of the HNLP–MC approach, demonstrating superior performance in terms of average classification accuracy. Experimental findings confirm that the proposed HNLP–MC method enhances classification precision and reduces response time compared to manual processing, highlighting its potential to optimize IT service workflows and improve operational efficiency in healthcare project management systems.

Keywords

• Artificial Intelligence
• Natural Language Processing
• Machine Learning
• Information Technology Service Desk
• Text Classification
• Hospital Information System

Sağlık Proje Yönetim Sistemlerinde Yapay Zekâ Tabanlı Bilgi Teknolojileri Yardım Masası Çağrılarının Sınıflandırılması için Hibrit Doğal Dil İşleme–Üstveri Sınıflandırma (HNLP–MC) Yaklaşımı

Abstract

Sağlık proje yönetim sistemlerinde bilgi teknolojileri (BT) yardım masası çağrıları, hastane bilgi yönetim sistemi (HBYS) kesintisiz çalışmasını sağlamak açısından kritik bir rol oynamaktadır. Ancak bu taleplerin manuel olarak yönetilmesi, çoğu zaman yinelenen kayıtların oluşmasına, yanlış sınıflandırmalara ve gecikmeli yanıtlara neden olarak genel verimliliği azaltmaktadır. Bu zorlukların üstesinden gelmek amacıyla, bu çalışmada doğal dil işleme (NLP) ile yapılandırılmış üstveri analizini bütünleştiren, yapay zekâ destekli hibrit bir çerçeve olan Hibrit Doğal Dil İşleme–Üstveri Sınıflandırma (HNLP–MC) modeli önerilmektedir. Bir sağlık proje yönetim sistemine ait geçmiş verilere, metin ve üstveri özellikleri birlikte kullanılarak analiz uygulanmıştır. Metin içerikleri, her bir talepteki kelimelerin önemini yakalamak için terim frekansı–ters belge frekansı (TF–IDF) tekniği ile temsil edilmiş; üstveri öznitelikleri ise sınıflandırma doğruluğunu artırmak amacıyla bağlamsal bilgi sağlamıştır. Lojistik regresyon (LR), destek vektör makinesi (SVM), rastgele orman (RF) ve gradyan artırma (GB) gibi çeşitli makine öğrenmesi sınıflandırıcıları sırasıyla %80,77, %73,42, %78,52 ve %82,96 doğruluk oranları ile değerlendirilmiştir. Bu karşılaştırmalı analiz sonucunda, HNLP–MC yaklaşımının temel modeli olarak GB sınıflandırıcısı seçilmiş ve ortalama sınıflandırma doğruluğu açısından üstün performans göstermiştir. Deneysel bulgular, önerilen HNLP–MC yönteminin manuel işleme kıyasla sınıflandırma hassasiyetini artırdığını ve yanıt süresini azalttığını ortaya koymaktadır. Bu sonuçlar, yöntemin BT hizmet süreçlerini optimize etme ve sağlık proje yönetim sistemlerinde operasyonel verimliliği artırma potansiyelini vurgulamaktadır.

Keywords

• Yapay Zekâ
• Doğal Dil İşleme
• Makine Öğrenmesi
• Bilgi Teknolojileri Hizmet Masası
• Metin Sınıflandırma
• Hastane Bilgi Yönetim Sistemi

References

1. P. Handayani, A. Hidayanto, A. Pinem, I. Hapsari, P. Sandhyaduhita, and I. Budi, “Acceptance model of a hospital information system”, International Journal of Medical Informatics, vol. 99, pp. 11–28, 2017. doi:10.1016/j.ijmedinf.2016.12.004.
2. S. Mohapatra and A. Roy, “A study on mediclaim processing in connected healthcare system”, in Trends in Wireless Communication and Information Security, M. Chakraborty, R. K. Jha, V. E. Balas, S. N. Sur, and D. Kandar, Eds. Singapore: Springer, 2021, vol. 740, Lecture Notes in Electrical Engineering, doi: 10.1007/978-981-33-6393-9_37.
3. A. Ramesh, C. Kambhampati, J. Monson, and P. Drew, “Artificial intelligence in medicine”, Annals of the Royal College of Surgeons of England, vol. 86, pp. 334–338, 2004, doi: 10.1308/147870804290.
4. K. R. Chowdhary, “Natural language processing”, in Fundamentals of Artificial Intelligence. New Delhi, India: Springer, 2020, pp. 603–649, doi: 10.1007/978-81-322-3972-7_19.
5. H. Habehh and S. Gohel, “Machine learning in healthcare”, Current Genomics, vol. 22, pp. 291–300, 2021, doi: 10.2174/1389202922666210705124359.
6. S. P. Paramesh, C. Ramya, and K. S. Shreedhara, “Classifying the unstructured IT service desk tickets using ensemble of classifiers”, in Proc. 3rd Int. Conf. Comput. Syst. Inf. Technol. Sustain. Solutions (CSITSS), Bengaluru, India, Dec. 20–22, 2018, pp. 221–227, doi: 10.1109/CSITSS.2018.8768734.
7. R. Bergquist, L. Rinaldi, and X. N. Zhou, “Artificial intelligence for healthcare: Restrained development despite impressive applications”, Infect. Dis. Poverty, vol. 14, p. 72, 2025, doi: 10.1186/s40249-025-01339-z.
8. M. X. Arias-Barahona, H. B. Arteaga-Arteaga, S. Orozco-Arias, J. C. Flórez-Ruíz, M. A. Valencia-Díaz, and R. Tabares-Soto, “Requests classification in the customer service area for software companies using machine learning and natural language processing”, PeerJ Comput. Sci., vol. 9, p. e1016, 2023, doi: 10.7717/peerj-cs.1016.

9. H. Sakai and S. S. Lam, “QUAD-LLM-MLTC: Large language models ensemble learning for healthcare text multi-label classification”, arXiv preprint arXiv:2502.14189, 2025, doi: 10.48550/arXiv.2502.14189.
10. R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An overview on the advancements of support vector machine models in healthcare applications: A review”, Information, vol. 15, p. 235, 2024, doi: 10.3390/info15040235.
11. T. C. T. Chen, H. C. Wu, and M. C. Chiu, “A deep neural network with modified random forest incremental interpretation approach for diagnosing diabetes in smart healthcare”, Applied Soft Computing, vol. 152, p. 111183, 2024, doi: 10.1016/j.asoc.2023.111183.
12. G. Ambrish, B. Ganesh, A. Ganesh, C. Srinivas, and K. Mensinkal, “Logistic regression technique for prediction of cardiovascular disease”, Global Transitions Proceedings, vol. 3, pp. 127–130, 2022, doi: 10.1016/j.gltp.2022.04.008.
13. W. Qiuqian, G. GaoMin, Z. KeZhu, and C. Chenchen, “A light gradient boosting machine learning-based approach for predicting clinical data breast cancer”, Multiscale Multidisciplinary Modeling, Experiments and Design, vol. 8, p. 75, 2025, doi: 10.1007/s41939-024-00662-6.
14. S. Jain, S. K. Jain, and S. Vasal, “An effective TF-IDF model to improve the text classification performance”, in Proc. 2024 IEEE 13th Int. Conf. on Communication Systems and Network Technologies (CSNT), Jabalpur, India, Apr. 6–7, 2024, pp. 1–4, doi: 10.1109/CSNT60213.2024.10545818.
15. F. Almeida and G. Xexéo, “Word embeddings: A survey”, arXiv preprint arXiv:1901.09069, 2019, doi: 10.48550/arXiv.1901.09069.
16. K. Denecke, R. May, and O. Rivera-Romero, “Transformer models in healthcare: A survey and thematic analysis of potentials, shortcomings and risks”, Journal of Medical Systems, vol. 48, p. 23, 2024, doi: 10.1007/s10916-024-02043-5.
17. N. K. Mustafa, R. Ibrahim, S. M. Aljunid, A. N. Aizuddin, and Z. Awang, “Critical success factors influencing the acceptance of a casemix-based hospital information system: Cross-sectional study”, Journal of Medical Internet Research, vol. 27, p. e74226, 2025, doi: 10.2196/74226.
18. A. H. Zamzam, K. Hasikin, and A. K. A. Wahab, “Integrated failure analysis using machine learning predictive system for smart management of medical equipment maintenance”, Engineering Applications of Artificial Intelligence, vol. 125, p. 106715, 2023, doi: 10.1016/j.engappai.2023.106715.
19. P. K. K. Gandla, R. K. Verma, C. R. Panigrahi, and B. Pati, “Ticket classification using machine learning”, in Proc. 7th Int. Conf. on Advance Computing and Intelligent Engineering (ICACIE 2022), B. Pati, C. R. Panigrahi, P. Mohapatra, and K. C. Li, Eds., vol. 1, Lecture Notes in Networks and Systems. Singapore: Springer, 2024, pp. 1–10, doi: 10.1007/978-981-99-5015-7_41.
20. H. Christian, A. M. Pramodana, and D. Suhartono, “Single document automatic text summarization using term frequency–inverse document frequency (TF–IDF)”, ComTech: Comput. Math. Eng. Appl., vol. 7, pp. 285–294, 2016, doi: 10.21512/comtech.v7i4.3746.
21. E. Bisong, “Logistic regression”, in Building Machine Learning and Deep Learning Models on Google Cloud Platform: A Comprehensive Guide for Beginners. Berlin/Heidelberg, Germany: Springer, 2019, pp. 243–250.
22. Y. Liu, Y. Wang, and J. Zhang, “New machine learning algorithm: Random forest”, in Lecture Notes in Computer Science: Proc. Int. Conf. on Information Computing and Applications (ICICA 2012), B. Liu, M. Ma, and J. Chang, Eds. Berlin/Heidelberg, Germany: Springer, 2012, vol. 7473. doi: 10.1007/978-3-642-34062-8_32.
23. D. A. Pisner and D. M. Schnyer, “Support vector machine”, in Machine Learning, New York, NY, USA: Academic, 2020, pp. 101–121, doi: 10.1016/B978-0-12-815739-8.00006-7.
24. A. Natekin and A. Knoll, “Gradient boosting machines, a tutorial”, Frontiers in Neurorobotics, vol. 7, p. 21, 2013, doi: 10.3389/fnbot.2013.00021.