Preoperative Patient Sentiment Is Associated With Postoperative Outcomes in Adult Spinal Deformity Surgery
Ross J. Gore, David Mazur-Hart, Mohan K. Sunkara, Aaqib Ali, Qizar Ali, Christopher J. Lynch, Christopher AmesStudy Design:
Prospective observational pilot study of adult spinal deformity surgery patients.
Objective:
To determine whether preoperative patient sentiment, quantified using a 21-class valence scale extending the CARP paradigm implemented through an offline Large Language Model, predicts postoperative outcomes.
Summary of Background Data:
Predicting adult spinal deformity surgery outcomes remains challenging with traditional clinical and radiographic parameters alone. Although patient psychological factors and expectations significantly influence postoperative satisfaction and quality of life, systematic approaches to capture these factors are underdeveloped. Offline Large Language Models offer scalable, privacy-preserving psychological risk stratification.
Materials and Methods:
We prospectively enrolled 18 patients undergoing adult spinal deformity surgery. Seven structured open-ended interview questions administered preoperatively were analyzed using a 21-class sentiment framework (CARP paradigm, −1.0 to +1.0 scale) implemented through Qwen 2.5 32B. This on-premise approach ensures HIPAA compliance without transmitting patient data externally. We assessed 28 validated outcome measures (EQ-5D domains, Neck Disability Index [NDI], SRS-22 components) preoperatively and at 12-month follow-up. Pearson correlation analysis quantified relationships between preoperative sentiment scores and postoperative outcome changes.
Results:
Preoperative sentiment demonstrated strong predictive associations with postoperative outcomes. Daily life impact sentiment (Question 1) showed the strongest predictive power with 14 significant correlations (
Conclusions:
Preoperative patient sentiment quantified through offline LLM-driven CARP analysis provides a rapid, scalable, privacy-preserving screening tool for identifying psychological risk. The open-source implementation enables real-time risk stratification without cloud dependencies. Integration of systematic sentiment assessment into preoperative evaluation may improve patient selection, enable personalized counseling, and identify high-risk psychological phenotypes requiring intervention. Prospective external validation in larger, multicenter cohorts is needed.