EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Healthcare Appointment Scheduling with No-Show Analysis and Dynamic Slot Optimization

Subhendu Sekhar Sahoo Subhendu Sekhar Sahoo, Rasmiranjan Rout Rasmiranjan Rout, Bharat Ranjan Prusty Bharat Ranjan Prusty

International Journal of Science, Strategic Management and Technology · 06.06.2026 · 02 (06) · 1-12

DOI: 10.55041/ijsmt.v2i6.059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Science, Strategic Management and Technology, online erschienen am 06.06.2026. Verfasst von Subhendu Sekhar Sahoo Subhendu Sekhar Sahoo und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In contemporary healthcare administration, operational inefficiencies primarily stem from high patient no-show rates and static, inflexible appointment scheduling frameworks. These bottlenecks lead to underutilized clinical resources, inflated operational overhead, and degraded patient care access. To mitigate these challenges, this paper presents an intelligent, decentralized, and AI-driven smart healthcare appointment scheduling architecture. The proposed framework leverages advanced machine learning methodologies to engineer a dual-optimization engine: predictive no-show forecasting and dynamic time-slot re-allocation. By ingesting multi-dimensional datasets—encompassing historical patient demographics, clinical micro-histories, temporal scheduling patterns, environmental weather metrics, and real-time localized traffic variables—the predictive module utilizes gradient-boosted decision trees (LightGBM) and ensemble voting classifiers to accurately calculate individual patient default probabilities prior to the scheduled encounter. Crucially, the system moves beyond passive prediction by feeding these risk coefficients into a real-time dynamic optimization layer. This engine employs constrained Markov Decision Processes (MDP) and reinforcement learning heuristics to dynamically adjust slot durations, orchestrate intelligent overbooking strategies without escalating provider burnout, and automatically fast-track waitlisted patients via an automated, latency-aware notification pipeline. Simulations conducted on simulated and open-source clinical operational data demonstrate that the integrated model achieves a predictive accuracy ($F_1\text{-score} = 0.91$) for no-show occurrences, yields a $24\%$ reduction in idle clinic downtime, and improves overall patient throughput by $18\%$. Ultimately, this research provides a scalable, privacy-preserving, and computationally efficient paradigm for transitioning traditional healthcare workflows into adaptive, demand-responsive ecosystems.

Zitieren

APA

Sahoo, S. S. S. S. S., Rout, R. R. R., & Prusty, B. R. P. B. R. (2026). AI-Driven Healthcare Appointment Scheduling with No-Show Analysis and Dynamic Slot Optimization. International Journal of Science, Strategic Management and Technology, 02(06), 1-12. https://doi.org/10.55041/ijsmt.v2i6.059

Vancouver

Sahoo SSSSS, Rout RRR, Prusty BRPBR. AI-Driven Healthcare Appointment Scheduling with No-Show Analysis and Dynamic Slot Optimization. International Journal of Science, Strategic Management and Technology. 2026;02(06):1-12. doi:10.55041/ijsmt.v2i6.059

BibTeX
@article{Sahoo2026,
  author = {Sahoo, Subhendu Sekhar Sahoo Subhendu Sekhar and Rout, Rasmiranjan Rout Rasmiranjan and Prusty, Bharat Ranjan Prusty Bharat Ranjan},
  title = {AI-Driven Healthcare Appointment Scheduling with No-Show Analysis and Dynamic Slot Optimization},
  journal = {International Journal of Science, Strategic Management and Technology},
  year = {2026},
  volume = {02},
  number = {06},
  pages = {1--12},
  doi = {10.55041/ijsmt.v2i6.059}
}
Kostenlos starten →