Refining mUltiple Artificial intelliGence strateGies for Automatic Pain Assessment Investigations: RUGGI Study

NCT07038434 | Recruiting

• 1 other identifier: AOURUGGI-0012506-2025
• Study Type: interventional
• Target: 200
• Locations: 1 country
• Sites: 1

Brief Summary

This single-center, non-profit, observational-interventional study aims to develop artificial intelligence (AI) models for the automatic assessment of chronic pain (APA - Automatic Pain Assessment). The study will enroll adult patients with chronic pain of various origins (oncologic and non-oncologic). Participants will undergo multidimensional evaluations that include clinical assessments, self-report questionnaires, bio-signal collection (e.g., EEG, EDA, HRV, GSR, PPG), and facial expression analysis via infrared thermography and video recordings. The primary objective is to calibrate and test machine learning and deep learning models to recognize and predict the presence and severity of pain using multimodal data inputs. Secondary objectives include evaluating the effectiveness of pain treatments, assessing quality of life, and developing a standardized APA dataset for future research. All data collection procedures are non-invasive and safe, and include tools like wearable sensors and standardized neurocognitive tests. The study is approved by the Italian Ethics Committee (Comitato Etico Territoriale Campania 2) and complies with GDPR and EU AI regulations.

Conditions

Chronic Pain; Cancer Pain; Neuropathic Pain; Pain Assessment

Keywords

Artificial Intelligence; Machine Learning; Deep Learning; Automatic Pain Assessment; Facial Expression Analysis; Natural Language Processing; Stroop Test; Bio-signals; Chronic Pain

Outcome Measures

Primary Outcomes (6)

• Accuracy of AI models in classifying chronic pain

  Accuracy will be calculated to evaluate how well supervised machine learning and deep learning models can correctly classify the presence of chronic pain using multimodal data (e.g., biosignals, facial thermography, video, and audio).

  From Day 0 (baseline) to Day 30 (follow-up)

• Sensitivity of AI models in classifying chronic pain

  Sensitivity (true positive rate) will be computed to determine the model's ability to correctly identify patients experiencing chronic pain. Unit of measure: Sensitivity (%)

  From Day 0 to Day 30

• Specificity of AI models in classifying chronic pain

  Specificity (true negative rate) will be computed to assess the model's ability to correctly identify patients who are not experiencing chronic pain. Unit of measure: Specificity (%)

  From Day 0 to Day 30

• Precision of AI models in classifying chronic pain

  Precision (positive predictive value) will be calculated to assess the proportion of correct positive predictions among all positive classifications. Unit of measure: Precision (%)

  From Day 0 to Day 30

• F1-score of AI models in classifying chronic pain

  F1-score, the harmonic mean of precision and sensitivity, will be used to assess overall model performance, especially in the presence of class imbalance. Unit of measure: F1-score (numeric value)

  From Day 0 to Day 30

• AUC-ROC of AI models in classifying chronic pain

  The area under the receiver operating characteristic curve (AUC-ROC) will be used to evaluate the model's ability to discriminate between pain and no-pain conditions across thresholds. Unit of measure: AUC-ROC (numeric value from 0 to 1)

  From Day 0 to Day 30

Secondary Outcomes (3)

• Change in Patient Global Impression of Change (PGIC) score

  From Day 0 to Day 30

• Change in Brief Pain Inventory (BPI) interference score

  From Day 0 to Day 30

• Correlation between analgesic treatments and pain intensity (NRS)

  From Day 0 to Day 30

Other Outcomes (1)

• Creation of a structured multimodal dataset for AI-based pain research

  From Day 0 to Day 30

Study Arms (1)

AI-Based Pain Assessment in Chronic Pain Patients

EXPERIMENTAL

Participants with chronic pain will undergo a multimodal, non-invasive diagnostic assessment including self-reported pain questionnaires (NRS, DN-4, BPI), wearable biosignal acquisition (EEG, EMG, EDA, HRV), facial thermography using the HIRA system, video-based facial expression analysis, linguistic evaluation, and the Stroop Test. These data will be used to develop and validate machine learning models for automatic pain assessment.

Diagnostic Test: Multimodal AI-Based Pain Assessment

Interventions

Multimodal AI-Based Pain Assessment DIAGNOSTIC_TEST

A non-invasive, multimodal diagnostic procedure combining self-reported pain scales (NRS, DN-4, BPI), wearable biosignal acquisition (EDA, EMG, HRV, EEG), facial thermography (HIRA system), video-based facial expression analysis, linguistic interview, and the Stroop Test. Data are used to train and validate machine learning models for automatic pain assessment in chronic pain patients.

Also known as: Automatic Pain Assessment, AI Pain Evaluation

AI-Based Pain Assessment in Chronic Pain Patients

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Adults (≥18 years old) with chronic pain, defined according to IASP and ICD-11 as pain that persists or recurs for more than three months.
• Diagnosed with either:
• Chronic primary pain (e.g., fibromyalgia, irritable bowel syndrome, chronic headaches)
• Chronic secondary non-cancer pain (e.g., low back pain, osteoarthritis, post-surgical pain)
• Chronic cancer-related pain (due to cancer or its treatment)
• Ability to understand the study procedures and provide written informed consent.

You may not qualify if:

• Current treatment with psychotropic drugs or presence of active psychiatric disorders (e.g., psychosis, major depression).
• Known history of alcohol or substance abuse.
• Pregnancy or breastfeeding.
• Age under 18 years.
• Inability to provide informed consent (e.g., due to cognitive impairment).

Sponsors & Collaborators

• Valentina Cerrone: lead
• University of Salerno, Italy: collaborator
• Federico II University: collaborator

Study Sites (1)

Azienda Ospedaliera Universitaria San Giovanni di Dio e Ruggi d'Aragona

Salerno, Italy, 84131, Italy

RECRUITING

Related Publications (14)

• Treede RD, Rief W, Barke A, Aziz Q, Bennett MI, Benoliel R, Cohen M, Evers S, Finnerup NB, First MB, Giamberardino MA, Kaasa S, Korwisi B, Kosek E, Lavand'homme P, Nicholas M, Perrot S, Scholz J, Schug S, Smith BH, Svensson P, Vlaeyen JWS, Wang SJ. Chronic pain as a symptom or a disease: the IASP Classification of Chronic Pain for the International Classification of Diseases (ICD-11). Pain. 2019 Jan;160(1):19-27. doi: 10.1097/j.pain.0000000000001384.

  PMID: 30586067 BACKGROUND

• Cascella M, Di Gennaro P, Crispo A, Vittori A, Petrucci E, Sciorio F, Marinangeli F, Ponsiglione AM, Romano M, Ovetta C, Ottaiano A, Sabbatino F, Perri F, Piazza O, Coluccia S. Advancing the integration of biosignal-based automated pain assessment methods into a comprehensive model for addressing cancer pain. BMC Palliat Care. 2024 Aug 3;23(1):198. doi: 10.1186/s12904-024-01526-z.

  PMID: 39097739 BACKGROUND

• Machova K, Szaboova M, Paralic J, Micko J. Detection of emotion by text analysis using machine learning. Front Psychol. 2023 Sep 20;14:1190326. doi: 10.3389/fpsyg.2023.1190326. eCollection 2023.

  PMID: 37799520 BACKGROUND

• Albashayreh A, Bandyopadhyay A, Zeinali N, Zhang M, Fan W, Gilbertson White S. Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives. JCO Clin Cancer Inform. 2024 Aug;8:e2300235. doi: 10.1200/CCI.23.00235.

  PMID: 39116379 BACKGROUND

• Lotsch J, Ultsch A, Mayer B, Kringel D. Artificial intelligence and machine learning in pain research: a data scientometric analysis. Pain Rep. 2022 Nov 3;7(6):e1044. doi: 10.1097/PR9.0000000000001044. eCollection 2022 Nov-Dec.

  PMID: 36348668 BACKGROUND

• Cascella M, Schiavo D, Cuomo A, Ottaiano A, Perri F, Patrone R, Migliarelli S, Bignami EG, Vittori A, Cutugno F. Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives. Pain Res Manag. 2023 Jun 28;2023:6018736. doi: 10.1155/2023/6018736. eCollection 2023.

  PMID: 37416623 BACKGROUND

• Nicholas MK. The biopsychosocial model of pain 40 years on: time for a reappraisal? Pain. 2022 Nov 1;163(Suppl 1):S3-S14. doi: 10.1097/j.pain.0000000000002654. No abstract available.

  PMID: 36252231 BACKGROUND

• Kutafina E, Becker S, Namer B. Measuring pain and nociception: Through the glasses of a computational scientist. Transdisciplinary overview of methods. Front Netw Physiol. 2023 Feb 10;3:1099282. doi: 10.3389/fnetp.2023.1099282. eCollection 2023.

  PMID: 36926544 BACKGROUND

• Lang VA, Lundh T, Ortiz-Catalan M. Mathematical and Computational Models for Pain: A Systematic Review. Pain Med. 2021 Dec 11;22(12):2806-2817. doi: 10.1093/pm/pnab177.

  PMID: 34051102 BACKGROUND

• Kaplan CM, Kelleher E, Irani A, Schrepf A, Clauw DJ, Harte SE. Deciphering nociplastic pain: clinical features, risk factors and potential mechanisms. Nat Rev Neurol. 2024 Jun;20(6):347-363. doi: 10.1038/s41582-024-00966-8. Epub 2024 May 16.

  PMID: 38755449 BACKGROUND

• Clauw DJ. From fibrositis to fibromyalgia to nociplastic pain: how rheumatology helped get us here and where do we go from here? Ann Rheum Dis. 2024 Oct 21;83(11):1421-1427. doi: 10.1136/ard-2023-225327.

  PMID: 39107083 BACKGROUND

• Cohen SP, Vase L, Hooten WM. Chronic pain: an update on burden, best practices, and new advances. Lancet. 2021 May 29;397(10289):2082-2097. doi: 10.1016/S0140-6736(21)00393-7.

  PMID: 34062143 BACKGROUND

• Rahman S, Kidwai A, Rakhamimova E, Elias M, Caldwell W, Bergese SD. Clinical Diagnosis and Treatment of Chronic Pain. Diagnostics (Basel). 2023 Dec 18;13(24):3689. doi: 10.3390/diagnostics13243689.

  PMID: 38132273 BACKGROUND

• Zimmer Z, Fraser K, Grol-Prokopczyk H, Zajacova A. A global study of pain prevalence across 52 countries: examining the role of country-level contextual factors. Pain. 2022 Sep 1;163(9):1740-1750. doi: 10.1097/j.pain.0000000000002557. Epub 2021 Dec 15.

  PMID: 35027516 BACKGROUND

MeSH Terms

Conditions

Chronic Pain; Cancer Pain; Neuralgia

Condition Hierarchy (Ancestors)

Pain; Neurologic Manifestations; Signs and Symptoms; Pathological Conditions, Signs and Symptoms; Peripheral Nervous System Diseases; Neuromuscular Diseases; Nervous System Diseases

Study Officials

• Marco Cascella, MD, PhD

  University of Salerno

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Marco Cascella, MD, PhD

CONTACT

+39 089 672428; mcascella@unisa.it

Valentina Cerrone, RN, MSc

CONTACT

valentina.cerrone@sangiovannieruggi.it

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: NA
• Masking: NONE
• Purpose: DIAGNOSTIC
• Intervention Model: SINGLE GROUP
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Study Coordinator

Model Details: All participants receive the same diagnostic evaluation protocol, including clinical pain assessment, wearable bio-signal monitoring, neurocognitive testing, facial expression analysis, and language processing. The study is designed as a single-arm exploratory diagnostic protocol.

Study Record Dates

• First Submitted: May 19, 2025
• First Posted: June 26, 2025
• Study Start: May 6, 2025
• Primary Completion: December 1, 2025
• Study Completion: January 1, 2026
• Last Updated: June 26, 2025

Record last verified: 2025-06

Data Sharing

• IPD Sharing: Will not share

Locations

IT (1)