MétaCan
Menu
Back to cohort
Record W4405098952 · doi:10.2196/58334

The Measurement of Vital Signs in Pediatric Patients by Lifelight Software in Comparison to the Standard of Care: Protocol for the VISION-Junior Observational Study

2024· article· en· W4405098952 on OpenAlexvenueno aff
Gauri Misra, Simon Wegerif, Louise Fairlie, Melissa Kapoor, James Fok, Gemma Salt, Jay Halbert, Ian Maconochie, Niall Mullen

Bibliographic record

VenueJMIR Research Protocols · 2024
Typearticle
Languageen
FieldEngineering
TopicNon-Invasive Vital Sign Monitoring
Canadian institutionsnot available
Fundersnot available
KeywordsObservational studyPreprintProtocol (science)Medical physicsVital signsMedicineComputer scienceAlternative medicineWorld Wide WebSurgeryPathology

Abstract

fetched live from OpenAlex

BACKGROUND: Measuring vital signs (VS) is important in potentially unwell children, as a change in VS may indicate a more serious infection than is clinically apparent or herald clinical deterioration. However, currently available methods are not suitable for regular measurement of VS in the home or community setting, and adherence can be poor. The COVID-19 pandemic highlighted a need for the contactless measurement of VS by nonclinical personnel, reinforced by the growing use of telemedicine. The Lifelight app is being developed as a medical device for the contactless measurement of VS using remote photoplethysmography via the camera on smart devices. The VISION-D (Measurement of Vital Signs by Lifelight Software in Comparison to the Standard of Care-Development) and -V (Validation) studies demonstrated the accuracy of the app compared with standard of care (SOC) measurement of blood pressure, pulse rate (PR), and respiratory rate (RR) in adults, supporting certification of Lifelight as a class I Conformité Européenne medical device. OBJECTIVE: To support the development of the Lifelight app for pediatric patients, the VISION-Junior study is collecting high-quality data that will be used to develop algorithms for the measurement of VS (PR, RR, and oxygen saturation) in pediatric patients. The accuracy of the app will be assessed against SOC measurements made simultaneously with app measurements. METHODS: The study is recruiting pediatric patients (younger than 18 years of age) attending the Sunderland Royal Hospital pediatric emergency department of the South Tyneside and Sunderland National Health Service Foundation Trust. High-resolution videos of the face (and torso in children younger than 5 years of age) and audio recordings (to explore the value of crying, wheezing, coughing, and other sounds in predicting illness) are made using the Lifelight Data Collect app. VS are measured simultaneously using SOC methods (finger clip sensor for PR and oxygen saturation; manual counting of RR). Feedback from patients, parents, carers, and nurses who use Lifelight is collected via questionnaires. Anticipated recruitment is 500 participants, with subtargets for age, sex, and skin tone distribution (Fitzpatrick 6-point scale). Early data will be used to refine the algorithms. A separate dataset will be retained to test the performance of the app against predefined targets. RESULTS: The study started on June 12, 2023, and reached its recruitment target (n=532) in April 2024 after extending the deadline. Algorithm refinement is in progress, after which the performance of Lifelight will be compared with the SOC measurement of VS. The analyses are expected to be completed by mid-August 2024. CONCLUSIONS: Data collected in this study will be used to develop and assess the accuracy of the app for the measurement of VS in pediatric patients of all ages. TRIAL REGISTRATION: ClinicalTrials.gov NCT05850013; https://clinicaltrials.gov/study/NCT05850013. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/58334.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Protocol · Consensus signal: Protocol
Teacher disagreement score0.550
Threshold uncertainty score0.387

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.229
GPT teacher head0.499
Teacher spread0.269 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreProtocol

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Research ProtocolsSame topicNon-Invasive Vital Sign MonitoringFrench-language works237,207