Description

This observational study investigates the impact of passive plate therapy using an automated, artificial intelligence (AI)-driven design workflow on presurgical cleft size in infants with unilateral cleft lip and palate. Cleft lip and palate represent one of the most common congenital craniofacial anomalies, and early presurgical interventions such as passive plates aim to reduce the cleft size, support feeding, and facilitate better surgical outcomes. However, access to such interventions is often limited by the need for specialized staff, complex workflows, and reliance on intraoral impressions.

Recent technological advancements have enabled the integration of digital workflows and AI into presurgical cleft care. In particular, a pipeline has been developed that uses intraoral scanning, and AI-assisted modeling to design individualized passive plates. These plates are manufactured via 3D printing and do not require invasive impressions nor extensive laboratory work making them potentially safer and more scalable in low or medium resource settings.

This study specifically evaluates the clinical effectiveness of such AI-designed passive plates compared to standard care without any presurgical orthopedic therapy. Infants are enrolled from two sites in India (Chennai and Hyderabad), where clinical practices differ with respect to the use of passive plates. As this is a non-randomized, observational study, group assignment is based on local standard of care at each site.

The primary objective is to assess the percentage reduction in cleft width from birth to the time of primary surgery (typically around 4 months of age) in infants treated with AI-designed passive plates. The secondary objective is to compare cleft width at the time of surgery between infants who received the plates and those who did not, offering insight into the relative anatomical outcomes of the intervention.

All participating infants will undergo standardized intraoral scans at baseline (within the first two weeks of life) and again just prior to primary surgical repair. The scans are used to measure the anterior-posterior cleft width and calculate percentage change over time. Cleft measurements are obtained digitally from 3D scan data using validated image processing software.

The AI-assisted design of the passive plates is performed using a custom plugin within Blender software, which automatically detects anatomical landmarks and generates the plate geometry with minimal user input. The digital files are subsequently exported for 3D printing using biocompatible materials. Infants in the intervention group will wear the plate continuously from the time of fitting until primary surgery, under the supervision of trained clinical teams.

Data from the two cohorts (plate vs. no plate) will be compared using appropriate statistical methods to assess differences in cleft size reduction and absolute cleft width at surgery. This study does not include randomization or blinding, as the intervention is assigned based on institutional practice. However, efforts will be made to ensure consistency in scanning methods, measurement protocols, and outcome assessment across both sites.

This study is part of a larger initiative to evaluate the generalizability and effectiveness of AI-based digital workflows in cleft care across diverse healthcare settings. The findings are expected to inform future integration of automated design technologies in presurgical treatment planning, especially in regions where access to skilled cleft teams is limited.

No additional interventions, medications, or behavioral changes are introduced as part of this study. Participation involves routine procedures and follow-up through the standard cleft treatment timeline.