Ignite Creation Date:
2025-12-25 @ 2:27 AM
Ignite Modification Date:
2026-01-01 @ 5:46 AM
Study NCT ID:
NCT07038434
Status:
RECRUITING
Last Update Posted:
2025-06-26
First Post:
2025-05-19
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Refining mUltiple Artificial intelliGence strateGies for Automatic Pain Assessment Investigations: RUGGI Study
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D059350', 'term': 'Chronic Pain'}, {'id': 'D000072716', 'term': 'Cancer Pain'}, {'id': 'D009437', 'term': 'Neuralgia'}], 'ancestors': [{'id': 'D010146', 'term': 'Pain'}, {'id': 'D009461', 'term': 'Neurologic Manifestations'}, {'id': 'D012816', 'term': 'Signs and Symptoms'}, {'id': 'D013568', 'term': 'Pathological Conditions, Signs and Symptoms'}, {'id': 'D010523', 'term': 'Peripheral Nervous System Diseases'}, {'id': 'D009468', 'term': 'Neuromuscular Diseases'}, {'id': 'D009422', 'term': 'Nervous System Diseases'}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'NA', 'maskingInfo': {'masking': 'NONE'}, 'primaryPurpose': 'DIAGNOSTIC', 'interventionModel': 'SINGLE_GROUP', 'interventionModelDescription': '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.'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 200}}, 'statusModule': {'overallStatus': 'RECRUITING', 'startDateStruct': {'date': '2025-05-06', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-06', 'completionDateStruct': {'date': '2026-01', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2025-06-17', 'studyFirstSubmitDate': '2025-05-19', 'studyFirstSubmitQcDate': '2025-06-17', 'lastUpdatePostDateStruct': {'date': '2025-06-26', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2025-06-26', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-12', 'type': 'ESTIMATED'}}, 'outcomesModule': {'otherOutcomes': [{'measure': 'Creation of a structured multimodal dataset for AI-based pain research', 'timeFrame': 'From Day 0 to Day 30', 'description': 'A standardized and anonymized dataset will be developed from collected multimodal inputs (biosignals, thermography, facial videos, linguistic data, questionnaires) to enable future research.\n\nUnit of measure: Dataset availability (Yes/No)'}], 'primaryOutcomes': [{'measure': 'Accuracy of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 (baseline) to Day 30 (follow-up)', 'description': '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).'}, {'measure': 'Sensitivity of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 to Day 30', 'description': "Sensitivity (true positive rate) will be computed to determine the model's ability to correctly identify patients experiencing chronic pain.\n\nUnit of measure: Sensitivity (%)"}, {'measure': 'Specificity of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 to Day 30', 'description': "Specificity (true negative rate) will be computed to assess the model's ability to correctly identify patients who are not experiencing chronic pain.\n\nUnit of measure: Specificity (%)"}, {'measure': 'Precision of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 to Day 30', 'description': 'Precision (positive predictive value) will be calculated to assess the proportion of correct positive predictions among all positive classifications.\n\nUnit of measure: Precision (%)'}, {'measure': 'F1-score of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 to Day 30', 'description': 'F1-score, the harmonic mean of precision and sensitivity, will be used to assess overall model performance, especially in the presence of class imbalance.\n\nUnit of measure: F1-score (numeric value)'}, {'measure': 'AUC-ROC of AI models in classifying chronic pain', 'timeFrame': 'From Day 0 to Day 30', 'description': "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.\n\nUnit of measure: AUC-ROC (numeric value from 0 to 1)"}], 'secondaryOutcomes': [{'measure': 'Change in Patient Global Impression of Change (PGIC) score', 'timeFrame': 'From Day 0 to Day 30', 'description': "This outcome will measure patients' perceived improvement in their condition using the PGIC scale.\n\nUnit of measure: Score on a 7-point Likert scale (1 = No change to 7 = Very much improved)"}, {'measure': 'Change in Brief Pain Inventory (BPI) interference score', 'timeFrame': 'From Day 0 to Day 30', 'description': 'This outcome will measure how much pain interferes with daily functioning, using the BPI interference subscale.\n\nUnit of measure: Score from 0 (no interference) to 10 (complete interference)'}, {'measure': 'Correlation between analgesic treatments and pain intensity (NRS)', 'timeFrame': 'From Day 0 to Day 30', 'description': 'The outcome will assess the correlation between the type and frequency of analgesic treatments and changes in pain intensity, measured with the Numeric Rating Scale (NRS).\n\nUnit of measure: Pearson correlation coefficient (r), NRS scores from 0 to 10'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Artificial Intelligence', 'Machine Learning', 'Deep Learning', 'Automatic Pain Assessment', 'Facial Expression Analysis', 'Natural Language Processing', 'Stroop Test', 'Bio-signals', 'Chronic Pain'], 'conditions': ['Chronic Pain', 'Cancer Pain', 'Neuropathic Pain', 'Pain Assessment']}, 'referencesModule': {'references': [{'pmid': '30586067', 'type': 'BACKGROUND', 'citation': "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': '39097739', 'type': 'BACKGROUND', 'citation': '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': '37799520', 'type': 'BACKGROUND', 'citation': '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': '39116379', 'type': 'BACKGROUND', 'citation': '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': '36348668', 'type': 'BACKGROUND', 'citation': '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': '37416623', 'type': 'BACKGROUND', 'citation': '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': '36252231', 'type': 'BACKGROUND', 'citation': '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': '36926544', 'type': 'BACKGROUND', 'citation': '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': '34051102', 'type': 'BACKGROUND', 'citation': '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': '38755449', 'type': 'BACKGROUND', 'citation': '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': '39107083', 'type': 'BACKGROUND', 'citation': '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': '34062143', 'type': 'BACKGROUND', 'citation': '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': '38132273', 'type': 'BACKGROUND', 'citation': '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': '35027516', 'type': 'BACKGROUND', 'citation': '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.'}]}, 'descriptionModule': {'briefSummary': '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.\n\nThe 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.\n\nAll 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.', 'detailedDescription': 'This study, titled "Refining mUltiple artificial intelliGence strateGies for automatic pain assessment Investigations" (RUGGI), explores the integration of AI in chronic pain evaluation. Pain is a multidimensional and subjective experience, and conventional assessment methods often rely solely on self-reported scales. This introduces the risk of over- or under-treatment. To overcome this limitation, the study leverages multimodal data-including physiological signals, facial expressions, and linguistic analysis-to build models capable of objectively assessing pain intensity and characteristics.\n\nThe primary aim is to calibrate predictive models (e.g., Support Vector Machines, Random Forest, Convolutional Neural Networks, YOLO architectures, and MLPs) that can recognize pain patterns using supervised and unsupervised learning. Bio-signals (EEG, HRV, GSR, EMG), infrared thermography (HIRA system), and prosodic-linguistic features will be analyzed. Data will be collected during structured timepoints: baseline (rest), Stroop test execution, and follow-up.\n\nPatients are recruited based on chronic pain diagnosis per IASP and ICD-11 criteria. Inclusion criteria include age ≥18 and informed consent. The study foresees a target enrollment of approximately 200 patients within 6 months. Data will be processed following a rigorous AI pipeline, including preprocessing, feature extraction, dimensionality reduction, and cross-validation (k-fold with grid search optimization). Outcome measures include the Area Under the Curve (AUC), sensitivity, specificity, F1 score, and model explainability (via SHAP, LIME).\n\nSecondary outcomes include assessing patient-reported quality of life, evaluating analgesic strategies, and generating a public-use APA dataset. All procedures are compliant with Good Clinical Practice (GCP), GDPR, and EU Artificial Intelligence Act (Reg. 2024/1689). The study is conducted at the University Hospital "San Giovanni di Dio e Ruggi d\'Aragona" in Salerno, Italy.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* 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.\n* Diagnosed with either:\n* Chronic primary pain (e.g., fibromyalgia, irritable bowel syndrome, chronic headaches)\n* Chronic secondary non-cancer pain (e.g., low back pain, osteoarthritis, post-surgical pain)\n* Chronic cancer-related pain (due to cancer or its treatment)\n* Ability to understand the study procedures and provide written informed consent.\n\nExclusion Criteria:\n\n* Current treatment with psychotropic drugs or presence of active psychiatric disorders (e.g., psychosis, major depression).\n* Known history of alcohol or substance abuse.\n* Pregnancy or breastfeeding.\n* Age under 18 years.\n* Inability to provide informed consent (e.g., due to cognitive impairment).'}, 'identificationModule': {'nctId': 'NCT07038434', 'acronym': 'RUGGI', 'briefTitle': 'Refining mUltiple Artificial intelliGence strateGies for Automatic Pain Assessment Investigations: RUGGI Study', 'organization': {'class': 'OTHER', 'fullName': "Azienda Ospedaliera OO.RR. S. Giovanni di Dio e Ruggi D'Aragona"}, 'officialTitle': 'Refining mUltiple Artificial intelliGence strateGies for Automatic Pain Assessment Investigations: RUGGI Study', 'orgStudyIdInfo': {'id': 'AOURUGGI-0012506-2025'}}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'AI-Based Pain Assessment in Chronic Pain Patients', 'description': '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.', 'interventionNames': ['Diagnostic Test: Multimodal AI-Based Pain Assessment']}], 'interventions': [{'name': 'Multimodal AI-Based Pain Assessment', 'type': 'DIAGNOSTIC_TEST', 'otherNames': ['Automatic Pain Assessment', 'AI Pain Evaluation'], 'description': '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.', 'armGroupLabels': ['AI-Based Pain Assessment in Chronic Pain Patients']}]}, 'contactsLocationsModule': {'locations': [{'zip': '84131', 'city': 'Salerno', 'state': 'Italy', 'status': 'RECRUITING', 'country': 'Italy', 'contacts': [{'name': 'Marco Cascella, MD, PhD', 'role': 'CONTACT', 'email': 'mcascella@unisa.it', 'phone': '+39 089672428'}, {'name': 'Valentina Cerrone, RN, MSc', 'role': 'CONTACT', 'email': 'valentina.cerrone@sangiovannieruggi.it'}, {'name': 'Marco Cascella, MD, PhD', 'role': 'PRINCIPAL_INVESTIGATOR'}, {'name': 'Valentina Cerrone', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Giuseppe Polese', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Ornella Piazza', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Francesco Amato', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Maria Romano', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Alfonso Maria Ponsiglione', 'role': 'SUB_INVESTIGATOR'}, {'name': 'Francesco Di Salle', 'role': 'SUB_INVESTIGATOR'}], 'facility': "Azienda Ospedaliera Universitaria San Giovanni di Dio e Ruggi d'Aragona", 'geoPoint': {'lat': 40.67545, 'lon': 14.79328}}], 'centralContacts': [{'name': 'Marco Cascella, MD, PhD', 'role': 'CONTACT', 'email': 'mcascella@unisa.it', 'phone': '+39 089 672428'}, {'name': 'Valentina Cerrone, RN, MSc', 'role': 'CONTACT', 'email': 'valentina.cerrone@sangiovannieruggi.it'}], 'overallOfficials': [{'name': 'Marco Cascella, MD, PhD', 'role': 'PRINCIPAL_INVESTIGATOR', 'affiliation': 'University of Salerno'}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO', 'description': 'Individual participant data (IPD) will not be shared due to the sensitive nature of biometric and video-derived data, including facial thermography and audio recordings. Although all data are anonymized, there remains a potential risk of re-identification through multimodal signals. Additionally, no specific provisions for data sharing were included in the original informed consent approved by the ethics committee.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'Valentina Cerrone', 'class': 'OTHER'}, 'collaborators': [{'name': 'University of Salerno, Italy', 'class': 'UNKNOWN'}, {'name': 'Federico II University', 'class': 'OTHER'}], 'responsibleParty': {'type': 'SPONSOR_INVESTIGATOR', 'investigatorTitle': 'Study Coordinator', 'investigatorFullName': 'Valentina Cerrone', 'investigatorAffiliation': "Azienda Ospedaliera OO.RR. S. Giovanni di Dio e Ruggi D'Aragona"}}}}