Quantifying pain in persistent spinal pain syndrome: a pilot protocol using spectrogram analysis and PROMIS score correlation

Persistent spinal pain syndrome (PSPS) is a debilitating condition that affects millions of individuals and presents unique challenges for effective assessment and management. Pain is often evaluated using self-report measures, which can be influenced by psychological, social, and contextual factors. Objective biomarkers of pain are critically needed to support more consistent and reproducible assessment. Spectrogram analysis of vocal signals has emerged as a promising method to detect physiological changes associated with pain through acoustic features such as pitch, loudness, and jitter. This pilot study will evaluate the feasibility of using spectrogram analysis to quantify pain and explore its relationship with scores from the Patient-Reported Outcomes Measurement Information System (PROMIS), a validated instrument for assessing physical, mental, and social health across chronic conditions. This single-site observational case-control feasibility study will enroll 80 participants, including 40 individuals diagnosed with PSPS and 40 healthy controls without spinal pain. Participants will complete the PROMIS-29 Profile v2.1 questionnaire and provide voice recordings under structured conditions. Spectrogram features will be extracted from the audio data using acoustic signal processing techniques and analyzed using machine learning models. Primary outcomes include recruitment rate, participant retention rate, PROMIS-29 completion rate, voice recording completion rate, adherence to data collection procedures, overall data completeness, and preliminary classification performance of the spectrogram analysis which will be used to evaluate the feasibility of conducting larger-scale validation studies. This pilot study will determine the feasibility of using spectrogram analysis of voice as a noninvasive and objective method to support pain assessment in individuals with PSPS. Results will provide foundational data to inform future large-scale validation studies and may contribute to the development of more precise and scalable tools for pain evaluation. This observational case-control feasibility study was not registered because no intervention was administered and the study was determined to be exempt/non-human subjects research by the institutional review board.