integrating-surgical-recovery-protocols-and-artificial-intelligence-may-support-resource-limited-hospitals
Integrating Surgical Recovery Protocols and Artificial Intelligence May Support Resource-Limited Hospitals

Integrating Surgical Recovery Protocols and Artificial Intelligence May Support Resource-Limited Hospitals

In a correspondence published in Patient Safety in Surgery, researcher Abdullahi Hassan Elmi argues that integrating Enhanced Recovery After Surgery pathways with artificial intelligence tools represents a promising strategy to mitigate preventable harm within resource-limited surgical environments. Across developing and low-resource healthcare systems, surgical patient safety remains compromised by systemic hurdles, including delayed diagnostic assessments, restricted postoperative monitoring capacity, severe workforce deficits, incomplete clinical documentation, and the inconsistent implementation of standardized perioperative protocols. Rather than viewing digital diagnostic innovations and clinical care bundles as separate, competing interventions, the author contends that artificial intelligence and structured surgical recovery pathways should be deployed as complementary components of a unified perioperative safety infrastructure. When coordinated effectively, this combined paradigm has the potential to enhance institutional reliability, facilitate earlier recognition of patient deterioration, and foster sustainable, continuous quality improvement across clinical environments that routinely operate under profound material constraints.

The operational realities confronting surgical teams in resource-constrained environments demonstrate that patient safety is inherently dependent on reliable and consistent systems before, during, and after an operative procedure. Clinicians practicing in underfunded hospitals must frequently navigate demanding conditions characterized by acute shortages of specialized surgical and nursing personnel, fragile and fragmented referral pathways, and inadequate physiological monitoring technology.

Enhanced Recovery After Surgery protocols provide a structured, evidence-based methodology designed to address these systemic vulnerabilities by optimizing perioperative care at every clinical phase. These standardized pathways consolidate diverse, high-value clinical interventions into a coordinated continuum of care, commencing with comprehensive preoperative patient counselling and thorough nutritional optimization prior to surgery. Crucially, evidence indicates that these recovery principles are not confined to elite tertiary care centers; formalized recommendations have been successfully modified for elective abdominal and pelvic surgical procedures within primary and secondary hospitals in low- and middle-income nations.

The empirical foundation supporting Enhanced Recovery After Surgery pathways has expanded considerably, demonstrating substantial clinical utility across varied socioeconomic and clinical contexts. A recent systematic meta-analysis highlighted in the correspondence confirmed that the rigorous application of enhanced recovery guidelines is statistically associated with notable improvements in objective surgical metrics, particularly shorter overall hospital lengths of stay and significant reductions in postoperative complications.

Artificial intelligence presents an additional, transformative layer of decision support that can reinforce perioperative safety alongside established clinical pathways. Within surgical departments, algorithmic tools can be trained to assist clinical teams with complex analytical tasks, beginning with automated preoperative risk stratification to isolate patients carrying disproportionately elevated hazards of adverse events. Machine learning models can also assist in predicting delayed physiological recovery, evaluating individual patient susceptibility to specific surgical complications, and assisting operating theater planning to optimize constrained theater schedules.

When combined with Enhanced Recovery After Surgery pathways, artificial intelligence capabilities provide surgical teams with dynamic operational visibility that addresses frequent points of pathway breakdown. In fast-paced, resource-scarce wards where clinicians must make rapid decisions for numerous complex patients, algorithmic tools can identify which specific individuals require intensified bedside monitoring and timely medical reassessment. Importantly, this unified architecture is not designed to displace trained surgical professionals or substitute autonomous technology for human clinical judgment, but rather to supply frontline clinicians with practical digital aids that support timely decision-making.

Despite the substantial promise of computational decision tools, the correspondence emphasizes that artificial intelligence must never be introduced before basic, foundational clinical safety systems are firmly established and consistently maintained. Foremost among these indispensable safeguards is the World Health Organization Surgical Safety Checklist, which represents one of the most widely validated and impactful instruments for curbing preventable surgical harm globally. Rigorous international assessments conducted across diverse high-income and low-income healthcare environments have repeatedly linked consistent checklist utilization to dramatic reductions in perioperative morbidity and surgical mortality rates. Consequently, digital technologies must be conceptualized as complementary enhancements that sit atop robust foundational systems rather than as remedial substitutes for core clinical discipline, multidisciplinary communication, and standardized operative safety routines.

Practical verification of the necessity for foundational safety mechanisms is illustrated by clinical audit research conducted within resource-constrained environments, including a notable closed-loop audit study from Somalia examining adherence to the World Health Organization Surgical Safety Checklist. That investigation underscored how iterative cycles of local audit, structured peer feedback, and systematic quality improvement initiatives can substantially elevate checklist compliance and solidify daily operating theater safety practices. The lessons derived from the Somali experience indicate that technological interventions achieve lasting clinical efficacy only when embedded within an organizational culture characterized by open interdisciplinary communication, mutual accountability, and dedicated teamwork. Artificial intelligence algorithms cannot rectify deep-seated communication dysfunctions; instead, their clinical value is realized only when deployed within teams that already respect systematic verification and transparent peer review.

The deployment of artificial intelligence tools in low-resource surgical ecosystems also introduces significant ethical, technical, and regulatory concerns that demand careful deliberation. A primary hazard arises when algorithms developed and trained predominantly on clinical data from well-resourced, high-income healthcare institutions are exported to low-resource hospitals without extensive local adaptation and validation. To prevent algorithmic harm, artificial intelligence applications in health must adhere to the World Health Organization’s governance principles emphasizing transparency, accountability, patient safety, algorithmic equity, and ethical oversight.

To navigate these multifaceted realities, the correspondence advocates a gradual, realistic, and phased implementation roadmap specifically tailored to the institutional constraints of resource-limited healthcare facilities. Under this pragmatic approach, hospitals in Somalia and analogous settings must first direct their primary efforts toward fortifying fundamental clinical practices, including core recovery principles, checklist compliance, meticulous clinical documentation, infection prevention standards, postoperative monitoring routines, and multidisciplinary teamwork. Once these core clinical processes operate reliably, healthcare institutions can judiciously integrate simple, affordable, and explainable artificial intelligence tools designed to execute specific, high-priority safety functions. Such digital applications might include automated risk assessment algorithms, complication alert dashboards, digital audit feedback summaries, and structured outpatient follow-up notification systems. Ultimately, by marrying resilient clinical care pathways with locally tested, ethically governed digital assistance, surgical systems in low-resource environments can build a sustainable, reliable perioperative safety model that systematically reduces preventable operative harm.

Subject of Research: Perioperative safety protocols and artificial intelligence in resource-limited surgical systems

Article Title: Challenges for implementation of “Enhanced Recovery After Surgery” (ERAS) protocols and artificial intelligence support tools in resource-limited countries

Article References: Elmi, A. H. (2026). Challenges for implementation of “Enhanced Recovery After Surgery” (ERAS) protocols and artificial intelligence support tools in resource-limited countries. Patient Safety in Surgery, 20(1), Article 24. https://doi.org/10.1186/s13037-026-00492-0

Image Credits: AI Generated

DOI: 10.1186/s13037-026-00492-0

Keywords: Patient Safety in Surgery, Enhanced Recovery After Surgery, ERAS protocols, artificial intelligence, perioperative care, resource-limited settings, surgical complications, WHO Surgical Safety Checklist, risk stratification, postoperative surveillance, audit feedback, clinical decision support, Somalia surgical audit, antibiotic stewardship, delayed recovery prediction, multidisciplinary surgical teams, local algorithm validation, low- and middle-income countries