Reassessing adult surfactant replacement therapy with mechanics-informed reinforcement learning

Philippe Meliga, Gregor Roncin, Alejandro Yepes Peñaranda and Elie Hachem

PLOS Computational Biology, 2026, vol. 22, issue 8, 1-45

Abstract: Surfactant replacement therapy (SRT) remains clinically limited to neonatal applications, in part because the mechanical feasibility of achieving efficient delivery in adult lungs is poorly understood. Previous computational studies have largely been descriptive or based on parameter sweeps, providing limited guidance on how to design efficient adult protocols under anatomical constraints. Here, we introduce a computational framework that integrates mechanistic modeling of surfactant propagation in anatomically motivated airway trees with deep reinforcement learning (DRL) to identify efficient delivery strategies across scales and airway geometries. The approach leverages a reduced-order model of plug transport and redistribution that captures the key mechanics of surfactant coating in complex airway networks while remaining lightweight enough for large-scale optimization. A custom DRL agent autonomously explores delivery parameters—including aliquot volume, flow rate, patient posture, and surfactant properties—to optimize protocol-level performance across diverse anatomical and physiological conditions. Under the branch-level coverage-based reward adopted here, systematic optimization of delivery parameters improves distal delivery at both pediatric and adult scales, while clarifying how these gains depend on prescribed volume, airway asymmetry, and control complexity. Increasing the number of aliquots improves access to distal regions and, in favorable geometries, shifts the onset of high-coverage regimes toward lower prescribed volumes, whereas posture becomes especially informative in asymmetric trees. Extending the control space to include surfactant rheology provides an additional lever, particularly in constrained adult settings, but does not overcome the structural limitations imposed by strong geometric asymmetry. Overall, these results establish a physics-based framework for AI-assisted optimization of intrapulmonary liquid delivery and clarify the respective roles of dose partitioning, posture, and formulation tuning. They also show that the interpretation of delivery success depends strongly on the evaluation metric: branch-level coverage provides a functionally oriented measure across heterogeneous airway trees, whereas stricter homogeneity metrics yield substantially more pessimistic assessments, especially in adult asymmetric geometries. These findings do not predict clinical efficacy; rather, they provide a controlled mechanistic feasibility benchmark and testable design hypotheses within physiologically realistic bounds.Author summary: Surfactant replacement therapy (SRT), in which a liquid surfactant is delivered directly into the lungs, is highly effective in premature infants but has repeatedly failed in adults with acute respiratory distress syndrome. One common explanation is that the adult lung is simply too large and too irregular for the liquid to spread efficiently. We tested this idea using a computer model that simulates how surfactant plugs move, split, and coat the airways, combined with an artificial-intelligence method that learns which delivery protocols work best. We examined how adjustable factors such as dose splitting, instillation flow rate, body position, and surfactant properties affect delivery in pediatric and adult airway trees. Our results show that delivery performance depends strongly on airway geometry and on how success is measured. In particular, some classical global uniformity measures can yield dramatically more pessimistic assessments of adult delivery, especially in asymmetric trees. By contrast, branch-level coverage provides a more functionally oriented picture of how broadly surfactant reaches the distal lung. Overall, the study identifies which protocol choices most improve delivery, where strong geometric limitations remain, and how mechanical strategy and formulation interact. These findings do not demonstrate clinical benefit and should not be read as candidate clinical protocols. Nonetheless, they suggest that some assumed mechanical constraints on adult SRT deserve re-examination, and provide computational design hypotheses to guide targeted experimental studies in controlled settings.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1014629 (text/html)
https://journals.plos.org/ploscompbiol/article/fil ... 14629&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pcbi00:1014629

DOI: 10.1371/journal.pcbi.1014629

Access Statistics for this article

More articles in PLOS Computational Biology from Public Library of Science
Bibliographic data for series maintained by ploscompbiol ().