Understanding pain and discomfort in preterm babies using artificial intelligence
| ISRCTN | ISRCTN11335900 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN11335900 |
| ClinicalTrials.gov (NCT) | Nil known |
| Clinical Trials Information System (CTIS) | Nil known |
| Integrated Research Application System (IRAS) | 299441 |
| Protocol serial number | IRAS 299441, CPMS 53578 |
| Sponsor | Newcastle upon Tyne Hospitals NHS Foundation Trust |
| Funder | Leverhulme Trust |
- Submission date
- 20/06/2022
- Registration date
- 19/07/2022
- Last edited
- 24/08/2022
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Neonatal Diseases
Plain English summary of protocol
Background and study aims
This study aims to explore whether a machine learning tool can better identfy whether babies born before their due date (preterm) who are being looked after in neonatal intensive care units are comfortable or not.
Who can participate?
Babies born at least 4 weeks before their due date (born before 36 weeks gestation) and who are medically stable with consent from their parents.
What does the study involve?
No changes to routine care are involved. Participating babies will undergo video and sound recordings during their normal neonatal care, and computer ratings are compared to the clinical team's assessment of whether the baby was comfortable or not. Machine learning will be used to develop the best algorithm to identify baby discomfort that could be used in the future to alert staff and parents that the baby is uncomfortable.
What are the possible benefits and risks of participating?
Participants will not gain from taking part. There are no risks expected as the researchers are only video recording infants during standard care.
Where is the study run from
Newcastle University and Newcastle upon Tyne Hospitals NHS Foundation Trust (UK)
When is the study starting and how long is it expected to run for?
January 2021 to August 2023
Who is funding the study?
The Lerverhulme Trust as part of the Newcastle University doctoral training programme in behaviour informatics (UK)
Who is the main contact?
Dr Janet Berrington, janet.berrington1@nhs.net
Contact information
Principal investigator
Ward 35
Royal Victoria Infirmary
Newcastle
NE1 4LP
United Kingdom
 ORCID ID |
0000-0002-6185-2843 |
|---|---|
| Phone | +44 (0)191 2825197 |
| janet.berrington1@nhs.net |
Study information
| Primary study design | Observational |
|---|---|
| Study design | Observational case series |
| Secondary study design | Case series |
| Study type | Participant information sheet |
| Scientific title | Preterm Enhanced Automated Capture Of Comfort Knowledge: the Peacock study |
| Study acronym | PEACOCK |
| Study objectives | Current observational informatics using state-of-the-art machine learning can better understand whether a newborn baby in an intensive care setting is comfortable or not. |
| Ethics approval(s) | Not provided at time of registration |
| Health condition(s) or problem(s) studied | Preterm infant discomfort during intensive care |
| Intervention | The study uses computer learning to evaluate a video of the baby during routine procedures and learns as more cases are observed. No changes to routine care are involved. Participating babies will have video and sound recordings during their normal neonatal care, and computer ratings are compared to the clinical teams' assessment of whether the baby was comfortable or not. Machine learning will be used to develop the best algorithm to identify baby discomfort that could be used in the future to alert staff and parents that the baby is uncomfortable. |
| Intervention type | Other |
| Primary outcome measure(s) |
How well the final learning model performs, assessed using machine learning metrics (confusion matrix, accuracy, precision, recall/sensitivity, F1 score, specificity and area under the curve) at the time of the video recording |
| Key secondary outcome measure(s) |
1. What signal or mixture of signals is most informative of preterm babies’ state (face, body, sound and physiological data) at the time of the video |
| Completion date | 01/08/2023 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Neonate |
| Sex | All |
| Target sample size at registration | 50 |
| Key inclusion criteria | 1. Born at <36 weeks gestation 2. Medically stable 3. Signed parental consent |
| Key exclusion criteria | 1. Infants with significant brain, spine or facial congenital abnormality 2. Parents unwilling to provide consent 3. Infants with postmenstrual age >36 weeks |
| Date of first enrolment | 01/08/2022 |
| Date of final enrolment | 31/07/2023 |
Locations
Countries of recruitment
- United Kingdom
- England
Study participating centre
Newcastle upon Tyne
TS1 4LP
United Kingdom
Results and Publications
| Individual participant data (IPD) Intention to share | No |
|---|---|
| IPD sharing plan summary | Not expected to be made available |
| IPD sharing plan | The researchers do not anticipate making data available routinely as it is complex video and audio and would breach patient confidentiality. |
Study outputs
| Output type | Details | Date created | Date added | Peer reviewed? | Patient-facing? |
|---|---|---|---|---|---|
| Participant information sheet | Participant information sheet | 11/11/2025 | 11/11/2025 | No | Yes |
Editorial Notes
24/08/2022: Internal review.
04/08/2022: Internal review.
21/06/2022: Trial's existence confirmed by the HRA.
