PTSD - Post Traumatic Stress DisorderCAUD-PINNCT07851480
Validation of an Algorithm for Predicting Awakenings Associated With Trauma-related Nightmares, Based on the Analysis of Physiological Patterns in Military and Former Military Patients Suffering From Post-traumatic Stress Disorder
A study testing CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakenings in people with PTSD - Post Traumatic Stress Disorder and Trauma-related Nightmares, run by Direction Centrale du Service de Santé des Armées at 3 sites in France.
Trial summary
The goal of this clinical trial is to validate an artificial intelligence algorithm called CAUD-PIN (CAUchemar Detection on INdividualized Parameters) to predict nightmare-related awakenings in military personnel and veterans suffering from post-traumatic stress disorder (PTSD). Read more about this study
- Who is it for?
- Ages 18 to 65 years
- Conditions the study is for
- PTSD - Post Traumatic Stress Disorder, Trauma-related Nightmares
- What is being tested?
- CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakenings
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 27 participants
- Where
- 3 sitesFrance
- Study dates
- 30 Apr 2026to Oct 2027
- Phase
- Interventional
- Are there results?
- Not yet: the study is under way
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 65 years
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Age between 18 and 65 years (age limit related to military status)
- Active military personnel or veterans
- Receiving psychiatric care in a military hospital (HNIA Bégin, HNIA Percy, or HRIA Brest) for PTSD related to combat trauma (exposure to death or life-threatening situations)
- PCL-5 score > 33
- Written informed consent obtained
- Trauma-related nightmares occurring ≥ 4 times per week
Who cannot join
- Pre-existing progressive psychiatric disorder prior to trauma (condition requiring long-term treatment > 1 year)
- Sleep disorder affecting sleep architecture (obstructive sleep apnea syndrome, narcolepsy)
- Neurological disorder (acute confusional state, severe traumatic brain injury) Inability to provide informed consent
- Persons under legal protection measures (guardianship, curatorship, or equivalent judicial protection)
- Persons not affiliated with a social security scheme
Trial locations and contacts
3 sites in 1 country. Contact the study team or a site near you to ask about taking part.
France3 sites, 3 recruiting
- Recruiting
Clermont Tonnerre Regional Military Teaching Hospital, psychiatry department
Brest, 29200
Julia SALOMÉ, MD, PHD
- Not yet recruiting
Percy National Military Teaching Hospital, Department of Psychiatry
Clamart, 92190
Gilles SIPAHIMALANI, MD, PhD
- Recruiting
Bégin National Military Teaching Hospital
Saint-Mandé, Île-de-France Region, 94160
Emeric SAGUIN, MD, PhD, +33 01 43 98 54 40, emeric.saguin@intradef.gouv.fr
Dorone FEINGOLD, Msc, +33 06 51 11 19 56, dorone.feingol@gmail.com
About this study
The goal of this clinical trial is to validate an artificial intelligence algorithm called CAUD-PIN (CAUchemar Detection on INdividualized Parameters) to predict nightmare-related awakenings in military personnel and veterans suffering from post-traumatic stress disorder (PTSD). The main question it aim to answer is :
- Can the CAUD-PIN algorithm detect physiological patterns preceding trauma-related nightmare awakenings with a sensitivity greater than 80%?
- What physiological signals best predict the occurrence of a trauma-related nightmare awakening?
Read more
Participants will:
Wear two non-invasive devices at home - an EEG headband and a wrist-worn sensor bracelet - for 15 consecutive nights Press a button on the bracelet each time they wake up from a nightmare Complete sleep and daytime diaries every evening and morning Attend two clinical assessments (at enrollment and at the end of the study, one month later) at one of the three participating military hospitals
The algorithm will be applied to the recorded data after collection and does not intervene in real time or affect participants' standard medical care in any way.
- Being tested
- CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakenings
- Keywords
- Post-Traumatic Stress Disorder (PTSD), Trauma-related nightmares, Sleep disorders, Artificial Intelligence, Machine Learning, Wearable Devices, Physiological Monitoring, Physiological signal processing, Sleep Recording, Military Personnel, Veterans, Ecological Momentary Assessment (EMA), Predictive Algorithm, Translational Research
- Medical subject headings
- Combat Disorders, Stress Disorders, Post-Traumatic, Sleep Wake Disorders
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakeningsDiagnostic test
CAUD-PIN (CAUchemar Detection on INdividualized Parameters) is a non-invasive, AI-based predictive algorithm developed by the VIFASOM research team (UMR 7330, Université Paris Cité / French Military Health Service) from the SOMMEPT clinical project. It analyzes multimodal physiological signals recorded during home sleep to identify patterns preceding Trauma-related nightmare awakenings in military patients with PTSD. Data are collected using two wearable devices: an EEG headband (Hypnodyne Zmax Lite) measuring brain activity and sleep stages, and a wrist-worn multisensor bracelet (Empatica EmbracePlus) measuring heart rate, electrodermal activity, skin temperature, and motor activity. The algorithm is applied exclusively post-hoc to pseudonymized recordings, with no real-time intervention and no impact on participants' standard medical care.
| Study group | Role | What they receive |
|---|---|---|
| CAUD-PIN Validation Group | Experimental | French Military personnel and/or veterans with PTSD wear two non-invasive wearable devices at home - an EEG headband (Hypnodyne Zmax Lite) and a multisensor bracelet (Empatica EmbracePlus) - for 15 consecutive nights. Participants press a button on the bracelet to report each nightmare-related awakening. Physiological data are analyzed post-hoc by the CAUD-PIN algorithm to validate its ability to predict trauma-related nightmare awakenings. Two clinical assessments are conducted at enrollment and at study completion. Receives: Diagnostic Test: CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakenings |
What is being measured
The primary outcome is the main question the study is designed to answer.
Sensitivity of the CAUD-PIN algorithm in predicting Trauma-related nightmare awakenings
Sensitivity will be calculated as the number of Trauma-related nightmare awakenings correctly identified by the CAUD-PIN algorithm divided by the total number of confirmed trauma-related nightmare awakenings, multiplied by 100.
Unit of Measure: Percentage
Measured: During the 15 consecutive nights of home sleep recording
Secondary outcomes (34)
Specificity of the CAUD-PIN algorithm for predicting Trauma-related nightmare awakenings
Specificity will be calculated as the number of events correctly classified as not being trauma-related nightmare awakenings divided by the total number of confirmed non-nightmare events, multiplied by 100.
Unit of Measure: Percentage
Measured: During the 15 consecutive nights of home sleep recording
Positive predictive value of the CAUD-PIN algorithm
Positive predictive value will be calculated as the number of correctly predicted trauma-related nightmare awakenings divided by the total number of trauma-related nightmare awakenings predicted by the CAUD-PIN algorithm, multiplied by 100.
Unit of Measure: Percentage
Measured: During the 15 consecutive nights of home sleep recording
Negative predictive value of the CAUD-PIN algorithm
Negative predictive value will be calculated as the number of events correctly predicted as not being trauma-related nightmare awakenings divided by the total number of events predicted as not being trauma-related nightmare awakenings, multiplied by 100.
Unit of Measure: Percentage
Measured: During the 15 consecutive nights of home sleep recording
Prediction lead time before trauma-related nightmare awakening
Mean time (in seconds) between the physiological predictive pattern detected by the CAUD-PIN algorithm and the participant's button press indicating a trauma-related nightmare awakening.
Unit of Measure: Seconds
Measured: Through 15 nights of recording
Intra- and inter-individual variability in heart rate preceding trauma-related nightmare awakenings
Intra- and inter-individual variability in heart rate (beats per minute, bpm) preceding trauma-related nightmare awakenings.
Variability will be quantified using:
- Within-subject standard deviation (SD)
- Between-subject variance estimated using mixed-effects models
Measured: During the 15 consecutive nights of home sleep recording
Intra- and inter-individual variability in electrodermal activity preceding trauma-related nightmare awakenings
Intra- and inter-individual variability in electrodermal activity (microsiemens, µS) preceding trauma-related nightmare awakenings.
Variability will be quantified using:
- Within-subject standard deviation (SD)
- Between-subject variance estimated using mixed-effects models
Measured: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Intra- and inter-individual variability in skin temperature preceding trauma-related nightmare awakenings
Intra- and inter-individual variability in skin temperature (°C) preceding trauma-related nightmare awakenings.
Variability will be quantified using:
- Within-subject standard deviation (SD)
- Between-subject variance estimated using mixed-effects models
Measured: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Intra- and inter-individual variability in motor activity preceding trauma-related nightmare awakenings
Intra- and inter-individual variability in motor activity (activity counts) preceding trauma-related nightmare awakenings.
Variability will be quantified using:
- Within-subject standard deviation (SD)
- Between-subject variance estimated using mixed-effects models
Measured: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Area Under the Curve (AUC) of the CAUD-PIN algorithm on combined dataset
Area Under the Receiver Operating Characteristic Curve (AUC, unitless) of the CAUD-PIN algorithm when trained and evaluated on the CAUD-PIN dataset alone compared to the combined dataset (SOMMEPT + CAUD-PIN).
Measured: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
F1-score of the CAUD-PIN algorithm on combined dataset
F1-score (unitless) of the CAUD-PIN algorithm when trained and evaluated on the CAUD-PIN dataset alone compared to the combined dataset (SOMMEPT + CAUD-PIN).
Measured: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Correlation between PCL-5 total score and percentage of trauma-related nightmare nights
PTSD severity will be assessed at T1 using the PTSD Checklist for DSM-5 (PCL-5) total score, ranging from 0 to 80 points. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score and percentage of trauma-related nightmare nights
Depression severity will be assessed at T1 using the Beck Depression Inventory (BDI) total score, ranging from 0 to 63 points. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between WHOQOL-BREF score and percentage of trauma-related nightmare nights
Quality of life will be assessed at T1 using the World Health Organization Quality of Life-BREF (WHOQOL-BREF) [specify total or domain score and range]. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score and percentage of trauma-related nightmare nights
Nightmare severity will be assessed at T1 using the Nightmare Severity Index (NSI) total score. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between mean number of trauma-related nightmare awakenings per night and percentage of trauma-related nightmare nights
The mean number of trauma-related nightmare awakenings per night will be calculated as the total number of participant-confirmed trauma-related nightmare awakenings divided by the number of valid recording nights. The percentage of trauma-related nightmare nights will be calculated as the percentage of valid recording nights containing at least one confirmed awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: During the 15 consecutive nights of home sleep recording
Correlation between mean heart rate and percentage of trauma-related nightmare nights
Heart rate will be measured in beats per minute using Empatica EmbracePLUS. For each participant, mean heart rate will be calculated across sleep period preceeding trauma-ralated awakeking across 15 nights. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: During the 15 consecutive nights of home sleep recording
Correlation between mean electrodermal activity and percentage of trauma-related nightmare nights
Electrodermal activity will be measured in microsiemens (µS) using Empatica EmbracePLUS. For each participant, mean electrodermal activity will be calculated across across sleep period preceeding trauma-ralated awakeking across across sleep period preceeding trauma-ralated awakeking across 15 nights. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: During the 15 consecutive nights of home sleep recording
Correlation between mean skin temperature and percentage of trauma-related nightmare nights
Skin temperature will be measured in degrees Celsius using Empatica EmbracePLUS. For each participant, mean skin temperature will be calculated across across sleep period preceeding trauma-ralated awakeking across 15 nights. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: During the 15 consecutive nights of home sleep recording
Correlation between mean motor activity and percentage of trauma-related nightmare nights
Motor activity will be measured in activity counts using Empatica EmbracePLUS. For each participant, mean motor activity will be calculated across across sleep period preceeding trauma-ralated awakeking across 15 nights. Trauma-related nightmare frequency will be calculated as the percentage of valid recording nights containing at least one participant-confirmed trauma-related nightmare awakening. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: During the 15 consecutive nights of home sleep recording
Correlation between trauma-related nightmare awakening frequency and change in PCL-5 total score between T1 and T2
Trauma-related nightmare frequency will be calculated as the total number of participant-confirmed trauma-related nightmare awakenings divided by the number of valid recording nights, expressed as awakenings per night. PTSD severity will be assessed at T1 and T2 using the PCL-5 total score, ranging from 0 to 80 points. Change will be calculated as the difference between the PCL-5 total scores obtained at T1 and T2. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between trauma-related nightmare awakening frequency and change in Beck Depression Inventory total score between T1 and T2
Trauma-related nightmare frequency will be calculated as the total number of participant-confirmed trauma-related nightmare awakenings divided by the number of valid recording nights, expressed as awakenings per night. Depression severity will be assessed at T1 and T2 using the Beck Depression Inventory total score, ranging from 0 to 63 points. Change will be calculated as the difference between the BDI total scores obtained at T1 and T2. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between trauma-related nightmare awakening frequency and change in WHOQOL-BREF score between T1 and T2
Trauma-related nightmare frequency will be calculated as the total number of participant-confirmed trauma-related nightmare awakenings divided by the number of valid recording nights, expressed as awakenings per night. Quality of life will be assessed at T1 and T2 using the WHOQOL-BREF [specify total or domain score and range]. Change will be calculated as the difference between the WHOQOL-BREF scores obtained at T1 and T2. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between PCL-5 total score at T1 and PSQI total score
PTSD severity will be assessed at T1 using the PCL-5 total score, ranging from 0 to 80 points. Subjective sleep quality will be assessed using the Pittsburgh Sleep Quality Index (PSQI) total score, ranging from 0 to 21 points, with higher scores indicating poorer sleep quality. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean total sleep time
PTSD severity will be assessed at T1 using the PCL-5 total score, ranging from 0 to 80 points. Total sleep time will be measured in minutes usingHypnodyne Zmax Lite device and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean sleep efficiency
PTSD severity will be assessed at T1 using the PCL-5 total score, ranging from 0 to 80 points. Sleep efficiency will be measured usingHypnodyne Zmax Lite device and PSQI questionnary, calculated as total sleep time divided by time in bed and multiplied by 100, and averaged across valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean wake after sleep onset
PTSD severity will be assessed at T1 using the PCL-5 total score, ranging from 0 to 80 points. Wake after sleep onset will be measured in minutes using Hypnodyne Zmax Lite device and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and PSQI total score
Depression severity will be assessed at T1 using the Beck Depression Inventory total score, ranging from 0 to 63 points. Subjective sleep quality will be assessed using the PSQI total score, ranging from 0 to 21 points, with higher scores indicating poorer sleep quality. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean total sleep time
Depression severity will be assessed at T1 using the Beck Depression Inventory total score, ranging from 0 to 63 points. Total sleep time will be measured in minutes using Hypnodyne Zmax Lite device and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean sleep efficiency
Depression severity will be assessed at T1 using the Beck Depression Inventory total score, ranging from 0 to 63 points. Sleep efficiency will be measured using Hypnodyne Zmax Lite device and PSQI questionnary, calculated as total sleep time divided by time in bed and multiplied by 100, and averaged across valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean wake after sleep onset
Depression severity will be assessed at T1 using the Beck Depression Inventory total score, ranging from 0 to 63 points. Wake after sleep onset will be measured in minutes using using Hypnodyne Zmax Lite device and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and PSQI total score
Nightmare severity will be assessed at T1 using the Nightmare Severity Index total score.. Subjective sleep quality will be assessed using the PSQI total score, ranging from 0 to 21 points, with higher scores indicating poorer sleep quality. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean total sleep time
Nightmare severity will be assessed at T1 using the Nightmare Severity Index total score.. Total sleep time will be measured in minutes using Hypnodyne Zmax Lite and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean sleep efficiency
Nightmare severity will be assessed at T1 using the Nightmare Severity Index total score.. Sleep efficiency will be measured using Hypnodyne Zmax Lite and PSQI questionnary, calculated as total sleep time divided by time in bed and multiplied by 100, and averaged across valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean wake after sleep onset
Nightmare severity will be assessed at T1 using the Nightmare Severity Index total score.. Wake after sleep onset will be measured in minutes using Hypnodyne Zmax Lite and PSQI questionnary and averaged across all valid recording nights. A single Pearson or Spearman correlation coefficient will be reported. Unit of Measure: Correlation coefficient (r).
Measured: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted1 Oct 2026
- Study start30 Apr 2026
- Primary completionOct 2027 (estimated)
- Study completionOct 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (4)Papers the sponsor has linked to this study.
- Other trials for PTSD - Post Traumatic Stress DisorderStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Basic science
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Enrolment
- 27 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Direction Centrale du Service de Santé des Armées
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
- Investigators
- Emeric SAGUIN, MD, PhD, Principal investigator, Department of Psychiatry, Begin National Military Teaching Hospital, Saint-Mandé, 94160, France
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07851480
- Sponsor's protocol ID
- 2025PBMD01
- Acronym
- CAUD-PIN
- Status last verified
- Mar 2026
- First submitted
- 2 Apr 2026
- Last updated
- 1 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: Individual participant data will not be shared. This study involves military personnel and veterans with PTSD, whose physiological and psychological data are considered highly sensitive. Data are pseudonymized and managed in accordance with the French General Data Protection Regulation (GDPR, EU 2016/679) and the Reference Methodology MR-001. Access is restricted to authorized members of the research team. Only aggregated and de-identified results will be disseminated through scientific publications and conference presentations.
Publications
Feingold D, Roseau JB, Verdonk C, Richards A, Chennaoui M, Saguin E, Leger D. Trauma-related nightmares: A Comprehensive and Integrative review. Sleep Med Rev. 2026 Jun;87:102259. doi: 10.1016/j.smrv.2026.102259. Epub 2026 Feb 18.
PubMed 41886932Feingold D, Quiquempoix M, Remadi M, Sipahimalani G, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M, Saguin E. Physiological markers of Trauma-related nightmares among military personnel suffering from PTSD: A multicenter home-recording study. Psychiatry Clin Neurosci. 2026 May;80(5):398-408. doi: 10.1111/pcn.70038. Epub 2026 Feb 14.
PubMed 41689450Saguin E, Feingold D, Sipahimalani G, Quiquempoix M, Roseau JB, Remadi M, Annette S, Guillard M, Van Beers P, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M. PTSD Symptom Severity Associated With Sleep Disturbances in Military Personnel: Evidence From a Prospective Controlled Study With Ecological Recordings. Depress Anxiety. 2025 Apr 25;2025:8011375. doi: 10.1155/da/8011375. eCollection 2025.
PubMed 40370761Saguin E, Feingold D, Roseau JB, Quiquempoix M, Boussaud M, Izabelle C, Metlaine A, Guillard M, Van Beers P, Gheorghiev C, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M. An ecological approach to clinically assess nightmares in military service members with severe PTSD. Sleep Med. 2023 Mar;103:78-88. doi: 10.1016/j.sleep.2023.01.024. Epub 2023 Jan 28.
PubMed 36764045
Study at a glance
From the registry record, last updated by the sponsor on 1 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Validation of an Algorithm for Predicting Awakenings Associated With Trauma-related Nightmares, Based on the Analysis of Physiological Patterns in Military and Former Military Patients Suffering From Post-traumatic Stress Disorder
- ClinicalTrials.gov ID
- NCT07851480
- Acronym / sponsor ID
- CAUD-PIN / 2025PBMD01
- Keywords
- Post-Traumatic Stress Disorder (PTSD), Trauma-related nightmares, Sleep disorders, Artificial Intelligence, Machine Learning, Wearable Devices, Physiological Monitoring, Physiological signal processing
- Study type
- Interventional
- Recruitment status
- Recruiting
- Enrolment
- 27 participants (estimated)
- Lead sponsor
- Direction Centrale du Service de Santé des ArméesUniversity, hospital or other
- Study start
- 30 Apr 2026 (actual)
- Primary completion
- Oct 2027 (estimated)
- Study completion
- Oct 2027 (estimated)
- First posted
- 1 Oct 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The goal of this clinical trial is to validate an artificial intelligence algorithm called CAUD-PIN (CAUchemar Detection on INdividualized Parameters) to predict nightmare-related awakenings in military personnel and veterans suffering from post-traumatic stress disorder (PTSD). The main question it aim to answer is :
- Can the CAUD-PIN algorithm detect physiological patterns preceding trauma-related nightmare awakenings with a sensitivity greater than 80%?
- What physiological signals best predict the occurrence of a trauma-related nightmare awakening?
Participants will:
Wear two non-invasive devices at home - an EEG headband and a wrist-worn sensor bracelet - for 15 consecutive nights Press a button on the bracelet each time they wake up from a nightmare Complete sleep and daytime diaries every evening and morning Attend two clinical assessments (at enrollment and at the end of the study, one month later) at one of the three participating military hospitals
The algorithm will be applied to the recorded data after collection and does not intervene in real time or affect participants' standard medical care in any way.
Study design
- Primary purpose
- Basic science
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| CAUD-PIN Validation Group | Experimental | Diagnostic Test: CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakeningsFrench Military personnel and/or veterans with PTSD wear two non-invasive wearable devices at home - an EEG headband (Hypnodyne Zmax Lite) and a multisensor bracelet (Empatica EmbracePlus) - for 15 consecutive nights. Participants press a button on the bracelet to report each nightmare-related awakening. Physiological data are analyzed post-hoc by the CAUD-PIN algorithm to validate its ability to predict trauma-related nightmare awakenings. Two clinical assessments are conducted at enrollment and at study completion. |
Who may qualify
- Ages
- 18 to 65 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (6 listed)
- Age between 18 and 65 years (age limit related to military status)
- Active military personnel or veterans
- Receiving psychiatric care in a military hospital (HNIA Bégin, HNIA Percy, or HRIA Brest) for PTSD related to combat trauma (exposure to death or life-threatening situations)
- PCL-5 score > 33
- Written informed consent obtained
Key exclusion criteria (5 listed)
- Pre-existing progressive psychiatric disorder prior to trauma (condition requiring long-term treatment > 1 year)
- Sleep disorder affecting sleep architecture (obstructive sleep apnea syndrome, narcolepsy)
- Neurological disorder (acute confusional state, severe traumatic brain injury) Inability to provide informed consent
- Persons under legal protection measures (guardianship, curatorship, or equivalent judicial protection)
- Persons not affiliated with a social security scheme
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakeningsCAUD-PIN (CAUchemar Detection on INdividualized Parameters) is a non-invasive, AI-based predictive algorithm developed by the VIFASOM research team (UMR 7330, Université Paris Cité / French Military Health Service) from the SOMMEPT clinical project. It analyzes multimodal physiological signals recorded during home sleep to identify patterns preceding Trauma-related nightmare awakenings in military patients with PTSD. Data are collected using two wearable devices: an EEG headband (Hypnodyne Zmax Lite) measuring brain activity and sleep stages, and a wrist-worn multisensor bracelet (Empatica EmbracePlus) measuring heart rate, electrodermal activity, skin temperature, and motor activity. The algorithm is applied exclusively post-hoc to pseudonymized recordings, with no real-time intervention and no impact on participants' standard medical care. | Diagnostic test | CAUD-PIN Validation Group |
Primary outcome
Sensitivity of the CAUD-PIN algorithm in predicting Trauma-related nightmare awakenings
Time frame: During the 15 consecutive nights of home sleep recording
Sensitivity will be calculated as the number of Trauma-related nightmare awakenings correctly identified by the CAUD-PIN algorithm divided by the total number of confirmed trauma-related nightmare awakenings, multiplied by 100. Unit of Measure: Percentage
34 secondary outcomes
Specificity of the CAUD-PIN algorithm for predicting Trauma-related nightmare awakenings
Time frame: During the 15 consecutive nights of home sleep recording
Positive predictive value of the CAUD-PIN algorithm
Time frame: During the 15 consecutive nights of home sleep recording
Negative predictive value of the CAUD-PIN algorithm
Time frame: During the 15 consecutive nights of home sleep recording
Prediction lead time before trauma-related nightmare awakening
Time frame: Through 15 nights of recording
Intra- and inter-individual variability in heart rate preceding trauma-related nightmare awakenings
Time frame: During the 15 consecutive nights of home sleep recording
Intra- and inter-individual variability in electrodermal activity preceding trauma-related nightmare awakenings
Time frame: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Intra- and inter-individual variability in skin temperature preceding trauma-related nightmare awakenings
Time frame: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Intra- and inter-individual variability in motor activity preceding trauma-related nightmare awakenings
Time frame: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Area Under the Curve (AUC) of the CAUD-PIN algorithm on combined dataset
Time frame: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
F1-score of the CAUD-PIN algorithm on combined dataset
Time frame: After completion of all participant data collection, following the 15-night recording period for each participant (approximately 18 months after study start)
Correlation between PCL-5 total score and percentage of trauma-related nightmare nights
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score and percentage of trauma-related nightmare nights
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between WHOQOL-BREF score and percentage of trauma-related nightmare nights
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score and percentage of trauma-related nightmare nights
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between mean number of trauma-related nightmare awakenings per night and percentage of trauma-related nightmare nights
Time frame: During the 15 consecutive nights of home sleep recording
Correlation between mean heart rate and percentage of trauma-related nightmare nights
Time frame: During the 15 consecutive nights of home sleep recording
Correlation between mean electrodermal activity and percentage of trauma-related nightmare nights
Time frame: During the 15 consecutive nights of home sleep recording
Correlation between mean skin temperature and percentage of trauma-related nightmare nights
Time frame: During the 15 consecutive nights of home sleep recording
Correlation between mean motor activity and percentage of trauma-related nightmare nights
Time frame: During the 15 consecutive nights of home sleep recording
Correlation between trauma-related nightmare awakening frequency and change in PCL-5 total score between T1 and T2
Time frame: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between trauma-related nightmare awakening frequency and change in Beck Depression Inventory total score between T1 and T2
Time frame: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between trauma-related nightmare awakening frequency and change in WHOQOL-BREF score between T1 and T2
Time frame: From Visit 1 (baseline) to Visit 2 (end of study, Day 30 ± 5 days after inclusion)
Correlation between PCL-5 total score at T1 and PSQI total score
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean total sleep time
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean sleep efficiency
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between PCL-5 total score at T1 and mean wake after sleep onset
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and PSQI total score
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean total sleep time
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean sleep efficiency
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Beck Depression Inventory total score at T1 and mean wake after sleep onset
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and PSQI total score
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean total sleep time
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean sleep efficiency
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Correlation between Nightmare Severity Index score at T1 and mean wake after sleep onset
Time frame: At Visit 1 (baseline) and during the 15 consecutive nights of home sleep recording
Results and safety
This study is still under way. Results are not available in the source record yet.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 1 Oct 2026.
- Background: PubMed 41886932Feingold D, Roseau JB, Verdonk C, Richards A, Chennaoui M, Saguin E, Leger D. Trauma-related nightmares: A Comprehensive and Integrative review. Sleep Med Rev. 2026 Jun;87:102259. doi: 10.1016/j.smrv.2026.102259. Epub 2026 Feb 18.
- Background: PubMed 41689450Feingold D, Quiquempoix M, Remadi M, Sipahimalani G, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M, Saguin E. Physiological markers of Trauma-related nightmares among military personnel suffering from PTSD: A multicenter home-recording study. Psychiatry Clin Neurosci. 2026 May;80(5):398-408. doi: 10.1111/pcn.70038. Epub 2026 Feb 14.
- Background: PubMed 40370761Saguin E, Feingold D, Sipahimalani G, Quiquempoix M, Roseau JB, Remadi M, Annette S, Guillard M, Van Beers P, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M. PTSD Symptom Severity Associated With Sleep Disturbances in Military Personnel: Evidence From a Prospective Controlled Study With Ecological Recordings. Depress Anxiety. 2025 Apr 25;2025:8011375. doi: 10.1155/da/8011375. eCollection 2025.
- Background: PubMed 36764045Saguin E, Feingold D, Roseau JB, Quiquempoix M, Boussaud M, Izabelle C, Metlaine A, Guillard M, Van Beers P, Gheorghiev C, Lahutte B, Leger D, Gomez-Merino D, Chennaoui M. An ecological approach to clinically assess nightmares in military service members with severe PTSD. Sleep Med. 2023 Mar;103:78-88. doi: 10.1016/j.sleep.2023.01.024. Epub 2023 Jan 28.
- Individual participant dataSharing planned: No. Individual participant data will not be shared. This study involves military personnel and veterans with PTSD, whose physiological and psychological data are considered highly sensitive. Data are pseudonymized and managed in accordance with the French General Data Protection Regulation (GDPR, EU 2016/679) and the Reference Methodology MR-001. Access is restricted to authorized members of the research team. Only aggregated and de-identified results will be disseminated through scientific publications and conference presentations.
Related trials for PTSD - Post Traumatic Stress Disorder
RecruitingPhase 1
Open-Label Psilocybin Study in Transdiagnostic Population
Transdiagnostic, Depression - Major Depressive Disorder
Not yet recruitingPhase 2
Assessing of Behavioral Risk and Response to Electromagnetic and Psychedelic Therapies
PTSD, PTSD - Post Traumatic Stress Disorder
Active, not recruitingObservational study
Trauma-Related Attributions in Trauma Treatment: An Observational Study
PTSD
Not yet recruiting
Multimodal Intervention for Individuals With Posttraumatic Stress Disorder (PTSD) and Hazardous Alcohol Use
Post Traumatic Stress Disorder PTSD, Hazardous Alcohol Use
Recruiting
Early Intervention for Postpartum PTSD: Comparing Written Exposure and Capnometry-Guided Breathing Therapy
Written Exposure Therapy, Breathing Techniques
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part.
Emeric SAGUIN, MD, PhD principal investigator
Department of Psychiatry, Begin National Military Teaching Hospital, Saint-Mandé, 94160, France
3 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing CAUD-PIN (CAUchemar Detection on INdividualized Parameters) - AI-based predictive algorithm forTrauma-related nightmare awakenings in people with PTSD - Post Traumatic Stress Disorder and Trauma-related Nightmares, run by Direction Centrale du Service de Santé des Armées at 3 sites in France.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 6 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: looking for participants now, as of the sponsor's last update on 1 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 3 sites in France. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
This study is still under way. Results are not available in the source record yet.
How can a doctor refer a patient or contact the research team?
Contact Emeric SAGUIN, MD, PhD (+33 01 43 98 54 40, emeric.saguin@intradef.gouv.fr), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Sensitivity of the CAUD-PIN algorithm in predicting Trauma-related nightmare awakenings (time frame: During the 15 consecutive nights of home sleep recording). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT07851480, which also lists 4 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 1 Oct 2026.