Implementation determinants of a planned machine learning-enabled surgical scheduling system in a high-volume orthopaedic centre in Canada: qualitative findings.

Clinical Snapshot

Key Findings

• P Value: Not applicable — qualitative study

• Effect Size: Not applicable — qualitative study; no quantitative effect sizes reported

• Primary Outcome: Three main qualitative themes identified: (1) System functionality — substantial inefficiencies in existing manual scheduling including outdated software and fragmented information systems; (2) Process-related factors — inconsistent communication and workflow fragmentation; (3) Resource constraints — staffing, time and infrastructure limitations. Broad but variable stakeholder support for the planned ML-enabled system was identified, with perceived benefits for duration prediction, scheduling data access and reporting.

• Nnt Or Sensitivity: Not applicable — qualitative description study; no diagnostic, therapeutic or prognostic metrics calculated. Key implementation determinants identified include: user-friendly design, interoperability with existing systems, responsive training, phased implementation strategy and ongoing feedback mechanisms.

• Confidence Interval: Not applicable — qualitative study

Clinical Application

The study does not evaluate the ML system itself but identifies the pre-conditions for successful implementation. Key feasibility considerations include: the need for robust change management and stakeholder engagement processes; investment in interoperable IT infrastructure; dedicated training resources; and a phased rollout approach rather than 'big bang' implementation. These requirements have significant resource implications for health systems operating under fiscal constraint. The findings suggest that stakeholder buy-in is achievable but contingent on system design quality and implementation process. Australian public hospitals face analogous elective surgery wait time pressures, with the Australian Institute of Health and Welfare (AIHW) reporting persistent challenges in meeting elective surgery category benchmarks, particularly post-COVID-19. The National Elective Surgery Urgency Categorisation system and state-based surgical access targets (e.g., NSW Surgical Access Strategy, Victorian Elective Surgery Action Plan) create a directly comparable policy environment to Ontario's benchmark system. Australian orthopaedic centres — particularly those operating under Activity Based Funding (ABF) models — would face similar scheduling inefficiencies to those described. The TGA does not currently have a specific regulatory pathway for ML-based scheduling tools (as distinct from Software as a Medical Device), but RACGP and relevant surgical colleges would need to be engaged in any implementation governance framework. The Australian Digital Health Agency's national digital health strategy provides a relevant policy context for interoperability requirements identified in this study. PBS and MBS implications are indirect but relevant: improved scheduling efficiency could reduce avoidable MBS item duplication and improve theatre utilisation metrics used in ABF calculations. Healthcare administrators, surgical schedulers, orthopaedic surgeons, anaesthetists, perioperative nurses and health system leaders involved in elective surgical scheduling at high-volume orthopaedic or general surgical centres. Findings are most directly applicable to tertiary-level public hospital settings with high elective surgical volumes and existing manual or semi-automated scheduling workflows.

Abstract

OBJECTIVES: Elective non-emergent surgical wait times have increased across countries such as Canada, straining operating room (OR) resources and affecting patient outcomes and healthcare spending. Manual scheduling systems in Ontario orthopaedic centres create wide variations in wait times, with recent declines in meeting benchmark targets despite increased procedure volumes. Challenges stem from fragmented referral processes, outdated scheduling methods and resource constraints. Artificial intelligence and machine learning (ML) offer potential solutions for optimising scheduling; however, their implementation remains inconsistent. This study aims to identify determinants affecting the rollout of a new ML-driven automated scheduling system at a high-volume elective orthopaedic surgery centre. DESIGN: A qualitative description approach supported by implementation science frameworks. SETTING: A high-volume elective orthopaedic surgery unit at a Canadian tertiary care centre. PARTICIPANTS: 17 individuals from clinical, administrative and leadership roles who were directly involved in surgical scheduling. INTERVENTIONS: A new ML-driven automated surgical scheduling system. OUTCOMES: Perceptions of the proposed new surgical scheduling system (barriers and enablers of implementation, recommendations for improvement). RESULTS: Three main themes were identified, capturing challenges and enablers in the existing scheduling system: system functionality, process-related factors and resource constraints.Participants described substantial inefficiencies in the existing manual scheduling system, including outdated software, fragmented information systems, inconsistent communication and resource constraints. Across interest-holder groups, there was broad but variable perceived support for a planned ML-enabled scheduling system, particularly for improving duration prediction, access to scheduling data and reporting, alongside concerns about system complexity, workflow fit, training and resource implications. Interest-holders emphasised the importance of user-friendly design, interoperability, responsive training, phased implementation and ongoing feedback. CONCLUSIONS: This pre-implementation qualitative study identified significant process and resource limitations in manual orthopaedic surgical scheduling, but interest-holder support for a well-designed ML-driven system is strong. While participants anticipated potential benefits for scheduling accuracy, throughput and resource allocation, these perceived advantages will require meaningful user engagement, robust training, phased rollout and evaluation in subsequent implementation and outcome studies.

References

1. 1.Herrington, I., Makarski, J., Mathura, D., Whyne, C. M., Khalil, E. B., Ravi, B., Abbas, A., Lex, J. R., & Kastner, M. (2026). Implementation determinants of a planned machine learning-enabled surgical scheduling system in a high-volume orthopaedic centre in Canada: qualitative findings. BMJ Open. https://doi.org/10.1136/bmjopen-2025-113560