pAIn-sense: Unveiling Physiological and Psychosocial Pain Components With an Artificial Intelligence Based Telemonitoring Tool
Study Details
Study Description
Brief Summary
The pAIn-sense study aims to revolutionize the monitoring and treatment of chronic pain, a major health concern that significantly impacts psychological well-being and quality of life. Traditional approaches to pain management face challenges like unspecific drug use and high healthcare costs, and they often leave patients dissatisfied. PAIn-sense aims at comprehensively understanding pain from both physical and emotional perspectives. To accomplish this, the study will employ advanced Artificial Intelligence (AI) techniques and wearable sensing technology. The study aims to monitor patients continuously, during both day and night activities, to gather a multidimensional set of data on their physiological, psychosocial, and pain conditions.
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Detailed Description
Chronic pain has long been known as one of the major health concerns, impacting psychological health, functioning, and quality of life. However, its treatment is complex and is challenged by a complex interplay between biological, psychological, and social factors. Common pain treatments present significant medical and technological limitations, reflected in unspecific drug usage and an extremely high number of medical examinations that patients face regularly, with a huge cost burden on the healthcare system. Furthermore, the overall efficacy of pain management is often limited (73% dissatisfaction with treatment), leaving the patient in poor life conditions. Designing individualized targeted therapies requires understanding each subject's multidimensional pain experience, taking into consideration both the physical and emotional aspects involved. However, today, the golden standard measurement for pain is self-reports, which inherently suffer from subjective differences in perception and reporting. Healthcare systems advocate for the discovery of biomarkers and reliable clinical trial endpoints for pain to foster diagnosis, monitor pain progression, assess new treatments, and personalized therapeutic response. Nevertheless, most of the evidence today comes from inpatient settings or controlled laboratory environments. The pAIn-sense study aims at providing a radically novel approach in the monitoring and treatment of pain patients: a novel telemonitoring system allowing to understand the real nature of the pain (emotional vs physical), leveraging the use of advanced Artificial Intelligence techniques and wearable sensing technology collecting biometric data, therefore enabling efficient personalized treatments.
To achieve this goal, the investigators will combine real patient data both from a physical and emotional perspective, to characterize the pain nature of patients and provide a tailored continuum-of-care.
The system will include:
-
Robotic wearable sensors (Hardware): wearable technology for physiological monitoring (e.g., skin conductance, blood volume pressure and heart rate, activity)
-
Digital platform (Software): a customized application that collects psychological assessments, psychological status, medication, subjective pain level and sleep quality.
-
AI-based engine: advanced AI models take all the previous physical and psychological information and model it to provide an outline of what is the nature of the pain level of the subject.
The system will be used to monitor the patient during normal activities (day and night) while collecting physiological, psychosocial, and pain information.
Study Design
Arms and Interventions
Arm | Intervention/Treatment |
---|---|
Pain Patients suffering from acute/chronic nociceptive and neuropathic pain |
Other: No intervention
Observational study with no intervention - Monitoring
|
Control Healthy controls |
Other: No intervention
Observational study with no intervention - Monitoring
|
Outcome Measures
Primary Outcome Measures
- Pain level [Up to one month]
Reported trough a digital health platform by the patients. The level and its dynamic are monitored daily. The pain level is recorded through a score from 1 to 10 that is reported trough a digital health platform by the patients.
- Psychosocial components of pain experience through questionnaires [Up to one month]
Monitored using the wearable technology and software digital platforms. Questionnaires will be presented to the patients and will include anxiety, depression, fatigue, pain catastrophizing, sleep, awareness, pain efficacy, treatment expectation
- Physiological components of pain and pain attacks in the physiological signals [Up to one month]
Measured and extracted from wearable technology worn continuously. Physiological biomarkers will include Skin Conductance (SC), blood volume pulse (BVP), Heart rate (HR), Brain signals (functional magnetic resonance imaging, electroencephalogram), movements (accelerometer, IMU), temperature.
- Psychological and clinical factors affecting pain [Up to one month]
Identified using questionnaires. Scales are usually represented with values from 0 to 10 with 0 best outcome and 10 worst outcome.
- Medication intake (rate and times per day) [Up to one month]
As described in each patient's constant pain therapy or reported by the patient on request using the platform. Medication will be measure in terms of rate of medications and changes during the protocols, times per day of intake, number of times a on-request medication is taken.
Secondary Outcome Measures
- Rehabilitation, physiotherapy and their effect [Up to one month]
Correlation between rehabilitation or physiotherapy attendance and pain
- Sleep, activity and other daily factors and their correlation with pain [Up to one month]
Correlation between sleep, activity and other daily factors with pain (measured both from wearable technology and from patients report)
- Predictors of chronification from acute phase [Up to one month]
Identification and classification of physiological and psychosocial markers, that characterize transition between acute pain and chronic pain
- Quality of Life and pain interference [Up to one month]
QoL index done through questioners and how much pain interfere with the overall quality of life. Scales from 0 to 10, with 10 better outcome and 0 worst outcome.
- Responsiveness to medication [Up to one month]
Changes in physiological biomarkers and pain perception following the intake of medication
Eligibility Criteria
Criteria
Inclusion Criteria:
-
Ongoing nociceptive pain after an injury or Neuropathic pain (acute or chronic)
-
Familiar with using electronic devices
Exclusion Criteria:
-
Inability to follow the procedures of the study, e.g. due to language problems, psychological disorders, dementia, etc.
-
Unable or not willing to give informed consent
Contacts and Locations
Locations
Site | City | State | Country | Postal Code | |
---|---|---|---|---|---|
1 | Neuroengineering Lab | Zürich | Zurich | Switzerland | 8001 |
2 | Balgrist University Hospital | Zurich | Switzerland | 8008 |
Sponsors and Collaborators
- ETH Zurich
- Balgrist University Hospital
Investigators
- Principal Investigator: Stanisa Raspopovic, PhD, ETH Zurich
Study Documents (Full-Text)
None provided.More Information
Publications
- 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.
- Davis KD, Aghaeepour N, Ahn AH, Angst MS, Borsook D, Brenton A, Burczynski ME, Crean C, Edwards R, Gaudilliere B, Hergenroeder GW, Iadarola MJ, Iyengar S, Jiang Y, Kong JT, Mackey S, Saab CY, Sang CN, Scholz J, Segerdahl M, Tracey I, Veasley C, Wang J, Wager TD, Wasan AD, Pelleymounter MA. Discovery and validation of biomarkers to aid the development of safe and effective pain therapeutics: challenges and opportunities. Nat Rev Neurol. 2020 Jul;16(7):381-400. doi: 10.1038/s41582-020-0362-2. Epub 2020 Jun 15.
- Kratz AL, Ehde DM, Bombardier CH, Kalpakjian CZ, Hanks RA. Pain Acceptance Decouples the Momentary Associations Between Pain, Pain Interference, and Physical Activity in the Daily Lives of People With Chronic Pain and Spinal Cord Injury. J Pain. 2017 Mar;18(3):319-331. doi: 10.1016/j.jpain.2016.11.006. Epub 2016 Dec 2.
- Lotsch J, Ultsch A. Machine learning in pain research. Pain. 2018 Apr;159(4):623-630. doi: 10.1097/j.pain.0000000000001118. No abstract available.
- May M, Junghaenel DU, Ono M, Stone AA, Schneider S. Ecological Momentary Assessment Methodology in Chronic Pain Research: A Systematic Review. J Pain. 2018 Jul;19(7):699-716. doi: 10.1016/j.jpain.2018.01.006. Epub 2018 Jan 31.
- Tracey I, Woolf CJ, Andrews NA. Composite Pain Biomarker Signatures for Objective Assessment and Effective Treatment. Neuron. 2019 Mar 6;101(5):783-800. doi: 10.1016/j.neuron.2019.02.019.
- Volkow ND, McLellan AT. Opioid Abuse in Chronic Pain--Misconceptions and Mitigation Strategies. N Engl J Med. 2016 Mar 31;374(13):1253-63. doi: 10.1056/NEJMra1507771. No abstract available.
- 2021-01814