International Journal of Drug Delivery Technology
Volume 16, Issue 3, 2026

Deep Learning-Driven Smart Telemedicine Queue Management System for Time-Critical Patient Care

Shunmugapriya S1*, Sathya K2, Mohan Kumar S3, Sudha P4, Brindha R5

1*PG and Research Department of Mathematics, Rajah Serfoji Government College (Autonomous), (Affiliated to Bharathidasan University), Thanjavur-613006, Tamil Nadu, India. Email: sspriya1969@gmail.com

2Department of Mathematics, Adaikalamatha College, (Affiliated to Bharathidasan University), Thanjavur-613403, Tamil Nadu, India. Email: ksathyaswaminathan@gmail.com

3Department of Mathematics, SRM TRP Engineering College (Autonomous), Tiruchirappalli-621105, Tamil Nadu, India. Email: mohansaara@gmail.com

4Department of Mathematics, Excel Engineering College (Autonomous), Namakkal-637303, Tamil Nadu, India. Email: sudhamathsecet@gmail.com

5Department of Mathematics, Velalar College of Engineering and Technology, Erode-638012, Tamil Nadu, India. Email: brindhaaramasamy@gmail.com

Received: 15th Dec, 2025; Revised: 9th Feb 2026; Accepted: 13th Feb, 2026; Available Online: 30th March, 2026

ABSTRACT

Telemedicine systems are increasingly using real time patient data to aid in the provision of remote healthcare. Nonetheless, traditional queue management methods are insufficient in prioritising time-important consultations. This manuscript proposes a deep learning - driven, intelligent telemedicine queue management system, in which patients are given dynamic priority on a basis of predicted clinical urgency. Multi-variate physiological time-series data and patient-reported symptoms are analysed using deep-learning based models to estimate the urgency scores. Long Short--Term Memory (LSTM) networks are used to obtain temporal patterns of health and severity trends. The predicted urgency scores are then used to reproduce the order of the consultation queues, and thus to provide timely access to clinicians for high risk patients. Empirical results show substantial reductions in waiting time for critical cases as well as system efficiency compared to first-come-first-served and rule-based scheduling paradigms. The proposed framework therefore provides a scalable and intelligent approach for time critical telemedicine settings.

Keywords: Telemedicine, Deep Learning, Queue Management, Time-Critical Care, LSTM, Smart Healthcare.

How to cite this article: Shunmugapriya S, Sathya K, Kumar SM, Sudha P, Brindha R. Deep Learning-Driven Smart Telemedicine Queue Management System for Time-Critical Patient Care. Int J Drug Deliv Technol. 2026;16(3): 121-131. DOI: 10.25258/ijddt.16.3.16

Source of support: Nil.

Conflict of interest: None