James Policy

All Publications

• Artificial Intelligence-Based Large Language Models Can Facilitate Patient Education. Journal of the Pediatric Orthopaedic Society of North America Bryson, X., Albarran, M., Pham, N., Salunga, A., Johnson, T., Hogue, G. D., Brooks, J. T., Tileston, K. R., Louer, C. R., El-Hawary, R., Imrie, M. N., Policy, J. F., Bouton, D., Hariharan, A. R., Van Nortwick, S., Upasani, V. V., Bauer, J. M., Tice, A., Vorhies, J. S. 2025; 12: 100196

  Abstract

  Background: Artificial intelligence (AI) large language models (LLMs) are becoming increasingly popular, with patients and families more likely to utilize LLM when conducting internet-based research about scoliosis. For this reason, it is vital to understand the abilities and limitations of this technology in disseminating accurate medical information. We used an expert panel to compare LLM-generated and professional society-authored answers to frequently asked questions about pediatric scoliosis.Methods: We used three publicly available LLMs to generate answers to 15 frequently asked questions (FAQs) regarding pediatric scoliosis. The FAQs were derived from the Scoliosis Research Society, the American Academy of Orthopaedic Surgeons, and the Pediatric Spine Foundation. We gave minimal training to the LLM other than specifying the response length and requesting answers at a 5th-grade reading level. A 15-question survey was distributed to an expert panel composed of pediatric spine surgeons. To determine readability, responses were inputted into an open-source calculator. The panel members were presented with an AI and a physician-generated response to a FAQ and asked to select which they preferred. They were then asked to individually grade the accuracy of responses on a Likert scale.Results: The panel members had a mean of 8.9 years of experience post-fellowship (range: 3-23 years). The panel reported nearly equivalent agreement between AI-generated and physician-generated answers. The expert panel favored professional society-written responses for 40% of questions, AI for 40%, ranked responses equally good for 13%, and saw a tie between AI and "equally good" for 7%. For two professional society-generated and three AI-generated responses, the error bars of the expert panel mean score for accuracy and appropriateness fell below neutral, indicating a lack of consensus and mixed opinions with the response.Conclusions: Based on the expert panel review, AI delivered accurate and appropriate answers as frequently as professional society-authored FAQ answers from professional society websites. AI and professional society websites were equally likely to generate answers with which the expert panel disagreed.Key Concepts: (1)Large language models (LLMs) are increasingly used for generating medical information online, necessitating an evaluation of their accuracy and effectiveness compared with traditional sources.(2)An expert panel of physicians compared artificial intelligence (AI)-generated answers with professional society-authored answers to pediatric scoliosis frequently asked questions, finding that both types of answers were equally favored in terms of accuracy and appropriateness.(3)The panel reported a similar rate of disagreement with AI-generated and professional society-generated answers, indicating that both had areas of controversy.(4)Over half of the expert panel members felt they could distinguish between AI-generated and professional society-generated answers but this did not relate to their preferences.(5)While AI can support medical information dissemination, further research and improvements are needed to address its limitations and ensure high-quality, accessible patient education.Levels of Evidence: IV.

  View details for DOI 10.1016/j.jposna.2025.100196

  View details for PubMedID 40791971

• Innovative technique for early-onset scoliosis casting using Jackson table. Spine deformity Montgomery, B. K., Tileston, K., Kaur, J., Kym, D., Segovia, N. A., Imrie, M., Policy, J., Rinsky, L., Vorhies, J. 2022

  Abstract

  PURPOSE: Early-onset scoliosis (EOS) can have harmful effects on pulmonary function. Serial elongation, derotation, and flexion (EDF) casting can cure EOS or delay surgical intervention. Most described casting techniques call for specialized tables, which are not available at many institutions. We describe an innovative technique for EDF casting utilizing a modified Jackson table (MJ) and compare results to a Risser frame (RF).METHODS: All patients who underwent EDF casting at our institution between January 2015 and January 2019 were identified and retrospectively reviewed. Patients were stratified by type of table used and clinical and radiographic outcomes were compared. Standard descriptive statistics were calculated.RESULTS: We identified 25 patients who underwent 77 casting events, 11 on an MJ table and 14 on a RF. Mean follow-up was 32months (range 11-61months). 28% of patients had idiopathic scoliosis. There was no significant difference in age at initiation of casting (P=0.3), initial Cobb angle (equivalence, P=0.009), or rate of idiopathic scoliosis between the MJ and RF groups. There was no significant difference in initial coronal Cobb angle percent correction (equivalence, P=0.045) or percent correction at 1-year follow-up (equivalence, P=0.010) between the two groups. There was no difference in cast related complications. There was a significant difference in surgical time, with the MJ group 11min shorter than the RF (P=0.005).CONCLUSION: The MJ table is a safe and effective alternative for applying EDF casts under traction without the need for a specialized table.LEVEL OF EVIDENCE: III.

  View details for DOI 10.1007/s43390-022-00526-4

  View details for PubMedID 35776363

• Moving toward patients being pain- and spasm-free after pediatric scoliosis surgery by using bilateral surgically-placed erector spinae plane catheters. Canadian journal of anaesthesia = Journal canadien d'anesthesie Tsui, B. C., Esfahanian, M. n., Lin, C. n., Policy, J. n., Vorhies, J. n. 2019

  View details for DOI 10.1007/s12630-019-01543-0

  View details for PubMedID 31776896