1Postgraduate trainee, Department of Oral Medicine and Radiology, Kalinga Institute of Dental Sciences, Kalinga Institute of Industrial Technology, Bhubaneswar, Odisha, India. Email: aanusikha.07@gmail.com
2Postgraduate Trainee, Dept of Public Health Dentistry, Institute of Dental Sciences, Siksha O Anusandhan University, Bhubaneswar, Odisha. Email: drshubhracsaha@gmail.com
3Postgraduate Trainee, Dept of Prosthodontics Crown Bridge and Implantology, Institute of Dental Sciences, Siksha 'O' Anusandhan University, Bhubaneswar, Odisha. Email: dr15nirali@gmail.com
4Postgraduate trainee, Department of Oral Medicine and Radiology, Kalinga Institute of Dental Sciences, Kalinga Institute of Industrial Technology, Bhubaneswar, Odisha, India. Email: dr.smrutie9@gmail.com
5Postgraduate Trainee, Dept of Public Health Dentistry, Institute of Dental Sciences, Siksha O Anusandhan University, Bhubaneswar, Odisha. Email: Shalini.sahoo14@gmail.com
6Postgraduate trainee, Department of Oral Medicine and Radiology, Kalinga Institute of Dental Sciences, Kalinga Institute of Industrial Technology, Bhubaneswar, Odisha, India. Email: srkaromr@gmail.com
Background: Chronic orofacial pain is a complex condition characterized by heterogeneous pathophysiology and variable response to conventional therapies. Neuromodulation has shown therapeutic potential; however, traditional open-loop stimulation protocols lack personalization. Integration of artificial intelligence (AI) may enhance treatment precision through real-time adaptive control.
Aim: To evaluate the clinical efficacy and feasibility of AI-guided closed-loop neuromodulation compared to conventional open-loop neuromodulation in patients with chronic orofacial pain.
Materials and Methods: This prospective randomized controlled trial included 100 participants diagnosed with chronic orofacial pain. Subjects were randomly allocated into Group A (AI-guided closed-loop neuromodulation; n=50) and Group B (conventional neuromodulation; n=50). Both groups received 12 sessions over 4 weeks. The AI system dynamically adjusted stimulation parameters based on real-time neurophysiological and physiological signals. Primary outcome was change in pain intensity measured by Visual Analog Scale (VAS). Secondary outcomes included Pain Disability Index (PDI), quality of life (SF-12), analgesic consumption, and AI performance metrics. Statistical analysis was performed using STATA, with significance set at p<0.05.
Results: Group A demonstrated significantly greater reduction in VAS scores at Week 4 compared to Group B (mean reduction 3.82 ± 1.04 vs. 2.14 ± 1.01; p<0.001). Significant improvements were also observed in PDI and SF-12 scores in the AI group (p<0.001). Regression analysis confirmed AI-guided intervention as an independent predictor of pain reduction. The AI model showed high predictive accuracy (ROC-AUC 0.91). No serious adverse events were reported.
Conclusion: AI-guided closed-loop neuromodulation is a safe and more effective approach than conventional stimulation, supporting its translational potential for precision management of chronic orofacial pain.
Keywords: Artificial intelligence, Chronic orofacial pain, Closed-loop neuromodulation, Machine learning, Precision pain management
How to cite this article: Anusikha A, Saha SC, Agarwal NJ, Mohapatra SP, Sahoo S, Kar SR; From bench to chairside: Transitional roadmap for AI-guided neuromodulation in orofacial pain...Int J Drug Deliv Technol. 2026;16 (13s): 34-41; DOI: 10.25258/ijddt.16.13s.3
Source of support: Nil.
Conflict of interest: Nil.