Artificial intelligence in perfusion is often discussed in terms of prediction accuracy and physiologic targets. In a new editorial, Ignazio Condello and Youssef El Dsouki argue that its value should also be judged by how well it supports the people managing cardiopulmonary bypass (CPB). Their proposed expansion of the MAMBO framework connects oxygen delivery, cognitive workload, and sustainable operating-room workflows.
What is the MAMBO framework?
MAMBO stands for Modern Advanced Management of Blood Oxygenation. The authors describe five organizing principles: monitoring, adaptation, management, balance, and optimization. Their central proposal is to extend these principles beyond patient physiology to include clinician workload, communication, and the interaction between perfusionists and digital systems.
This publication is an editorial perspective. It presents a conceptual direction for practice and research, rather than a validated treatment protocol, a clinical trial, or a study demonstrating improved patient outcomes.
Five principles with a broader purpose
Monitoring
The proposed model combines physiologic surveillance with attention to workload and situational awareness. The authors discuss digital biomarkers and cognitive-load monitoring as possible ways to recognize excessive demands on perfusionists. The editorial does not itself test these measures or establish thresholds for intervention.
Adaptation
AI-assisted systems could prioritize relevant information as conditions change, potentially helping clinicians recognize deterioration and manage competing demands. Here, predictive alerts and adaptive displays are proposed support mechanisms; their effects on fatigue and decision-making are not measured.
Management
The framework treats communication, alarm handling, and multidisciplinary coordination as part of perfusion management. A technically capable system still needs to fit the sequence of work and the responsibilities of the team using it.
Balance
The authors use balance in two senses: matching oxygen delivery to metabolic demand and supporting the professional managing that physiology. Prolonged vigilance, information overload, and occupational stress are presented as reasons to incorporate human factors into technology and workflow design.
Optimization
Optimization extends beyond selecting physiologic targets. In the proposed model, it also includes simplifying workflows, reducing avoidable stressors, and improving communication and organizational sustainability.
AI as support for clinical judgment
The editorial envisions perfusionists working as physiologic strategists who interpret integrated data and evaluate predictive information. That evolution would require skills in understanding algorithms, recognizing their limitations, and incorporating their outputs into clinical reasoning.
The authors explicitly preserve the central role of human expertise. AI is presented as a way to support interpretation and prioritization, rather than replace the perfusionist’s judgment. The practical research question is whether a digital system helps the team make better decisions without creating additional cognitive demands.
What the paper does—and does not—establish
The article offers a useful conceptual link between precision perfusion and human-centered system design. It does not report a patient cohort, a comparison group, an implemented AI intervention, or quantitative measures of workload, alarm burden, staff retention, or clinical outcomes.
Consequently, reductions in cognitive overload, improved workflow efficiency, and safer care should be read as proposed benefits requiring evaluation. The editorial also does not provide an operational implementation package, validated decision thresholds, or evidence that the expanded MAMBO framework outperforms existing approaches.
Its narrative discussion draws on a small set of references rather than a systematic evidence assessment. Readers should consult the underlying studies before treating broad statements about AI, workload, or oxygen delivery as established effects of this framework.
Relevance for perfusion teams
The main educational contribution is a broader definition of successful perfusion technology: useful information, manageable workload, effective communication, and preserved clinical oversight alongside physiologic performance. For teams considering new digital tools, the framework provides questions to investigate rather than a ready-made standard of care.
Future evaluations would need to measure both clinical and human-factors outcomes, including how systems perform during critical transitions and unexpected events. The editorial’s vision is promising as a discussion framework, but its benefits remain to be demonstrated.
Source: Condello I, El Dsouki Y. The MAMBO Framework and the Future of Modern Perfusion: Artificial Intelligence, Cognitive Ergonomics, and Sustainable Workflow Integration. Cureus. 2026;18(6):e110501. Published June 8, 2026. doi:10.7759/cureus.110501.
Funding and disclosures: Both authors disclose employment with Spectrum Medical Ltd. and state that the work was conducted independently as part of their academic activity. They report no financial support for the submitted work. The original article is distributed under CC BY 4.0. This IPA educational summary is independently paraphrased; the source PDF is unchanged.
