โก Quick Summary
The development of CASPER, a specialty-specific AI clinical decision support system for craniofacial surgery, marks a significant advancement in surgical practice. Utilizing a knowledge base of 8,561 open-access articles, CASPER demonstrates expert-level reasoning with a mean semantic evaluation score of 0.89.
๐ Key Details
- ๐ Knowledge Base: 8,561 open-access craniofacial surgery articles (2000-2025)
- โ๏ธ Technology: Retrieval-augmented generation (RAG) with RAPTOR hierarchical architecture
- ๐งฉ Capabilities: Text and image analysis for clinical decision support
- ๐ Performance: Mean SEM-eval score of 0.89, integrating an average of 7.8 sources per query
๐ Key Takeaways
- ๐ก CASPER is the first citation-enabled AI system specifically designed for craniofacial surgery.
- ๐ High performance was noted in pediatric airway, facial trauma, and oncologic surgery.
- ๐ Top scores achieved for specific queries like Pierre-Robin mandibular distraction (0.96).
- ๐ Lower scores were observed in complex domains such as Le Fort III contraindications (0.81).
- โ Manual reviews confirmed high content coverage and citation accuracy.
- ๐ Potential impact on surgical planning and decision-making consistency.
- ๐ Enhances knowledge translation in clinical practice and surgical education.
๐ Background
Craniofacial surgery is a complex field that requires the integration of multidisciplinary knowledge. However, there has been a notable lack of specialty-specific decision support tools. The advent of artificial intelligence and retrieval-augmented generation technology presents an opportunity to create transparent, evidence-based systems that can significantly aid surgical practice.
๐๏ธ Study
The authors developed CASPER, a domain-specific multimodal RAG system, to address the need for specialized decision support in craniofacial surgery. The system was built using a comprehensive knowledge base and was evaluated against 25 clinical questions across various craniofacial subspecialties, focusing on its ability to retrieve and synthesize relevant literature.
๐ Results
CASPER achieved a mean semantic evaluation score of 0.89, indicating strong alignment with supporting literature. The system integrated an average of 7.8 sources per query, with the highest performance observed in pediatric airway management (0.93) and oncologic surgery (0.95). Notably, specific queries like orbital floor fracture management also received high scores (0.95).
๐ Impact and Implications
The introduction of CASPER has the potential to revolutionize craniofacial surgery by providing transparent, evidence-grounded recommendations. This system can enhance surgical planning, improve decision-making consistency, and facilitate knowledge translation in both clinical practice and surgical education, ultimately leading to better patient outcomes.
๐ฎ Conclusion
CASPER represents a groundbreaking advancement in the integration of AI within craniofacial surgery. By delivering expert-comparable reasoning and evidence-based recommendations, this system is poised to significantly improve surgical practices. The future of surgical decision-making looks promising with the continued development of such innovative technologies.
๐ฌ Your comments
What are your thoughts on the development of CASPER and its implications for craniofacial surgery? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
Specialty-Specific Citation-Enabled AI Clinical Decision Support System for Craniofacial Surgery: Development of CASPER.
Abstract
BACKGROUND: Craniofacial surgery requires synthesis of complex, multidisciplinary knowledge, yet specialty-specific decision support tools are lacking. Retrieval-augmented generation (RAG) offers an opportunity to create transparent, evidence-based artificial intelligence (AI) systems tailored to surgical practice.
METHODS: The authors developed CASPER, a domain-specific, multimodal RAG system with text and image analysis capabilities, built with RAPTOR hierarchical architecture and a knowledge base of 8561 open-access craniofacial surgery articles (2000-2025). The system retrieved and synthesized peer-reviewed literature in response to 25 clinical questions spanning craniofacial subspecialties. Performance was evaluated using semantic similarity (SEM-eval) to retrieved documents, manual content coverage review, and manual citation accuracy verification.
RESULTS: CASPER achieved strong alignment with supporting literature (mean SEM-eval 0.89ยฑ0.04; range: 0.81-0.96), integrating an average of 7.8 sources per query. Highest performance was observed in pediatric airway (0.93), facial trauma (0.93), and oncologic surgery (0.95), with top scores for Pierre-Robin mandibular distraction (0.96) and orbital floor fracture management (0.95). Lower scores occurred in complex or emerging domains such as Le Fort III contraindications (0.81) and facial feminization planning (0.81). Manual review confirmed that CASPER maintained high content coverage across scenarios, with citations consistently accurate and directly supportive of system outputs.
CONCLUSIONS: CASPER is the first citation-enabled AI system for craniofacial surgery and demonstrates expert-comparable reasoning across diverse clinical scenarios. By delivering transparent, evidence-grounded recommendations, CASPER has the potential to enhance surgical planning, improve decision-making consistency, and accelerate knowledge translation in both clinical practice and surgical education.
Author: [‘Ozmen BB’, ‘Singh N’, ‘Shah K’, ‘Berber I’, ‘Pinsky E’, ‘Schwarz GS’]
Journal: J Craniofac Surg
Citation: Ozmen BB, et al. Specialty-Specific Citation-Enabled AI Clinical Decision Support System for Craniofacial Surgery: Development of CASPER. Specialty-Specific Citation-Enabled AI Clinical Decision Support System for Craniofacial Surgery: Development of CASPER. 2025; (unknown volume):(unknown pages). doi: 10.1097/SCS.0000000000012279