Development and Preliminary Validation of Intelligent Video Laryngoscope for Emergency Use (MEASURE-ILD)
Development of an Intelligent Video Laryngoscope and Preliminary Verification for Emergency Application
The investigators are developing a video laryngoscope equipped with artificial intelligence technology to enable automatic identification of key airway anatomical structures and real-time guidance during intubation, with the aim of improving the success rate and efficiency of endotracheal intubation in emergency settings.
Studie Overzicht
Toestand
Interventie / Behandeling
Studietype
Inschrijving (Geschat)
Fase
- Niet toepasbaar
Contacten en locaties
Studiecontact
- Naam: Jintao Wei wei
- Telefoonnummer: 19560480512
- E-mail: weijintao@zju.edu.cn
Studie Locaties
-
-
Zhejiang
-
Hangzhou, Zhejiang, China
- Werving
- Second Affiliated Hospital, Zhejiang University, School of Medicine
-
Contact:
- Jintao Wei
- Telefoonnummer: +86 19560480512
- E-mail: weijintao@zju.edu.cn
-
Shaoxing, Zhejiang, China, 312000
- Werving
- Shaoxing Central Hospital
-
Contact:
- dongzhi liu
- E-mail: weijintao@zju.edu.cn
-
-
Deelname Criteria
Geschiktheidscriteria
Leeftijden die in aanmerking komen voor studie
Accepteert gezonde vrijwilligers
Geslachten die in aanmerking komen voor studie
Beschrijving
Inclusion Criteria:
- Patient inclusion criteria: Adult patients in critical condition requiring endotracheal intubation via laryngoscopy (age ≥ 18 years).
Exclusion Criteria:
- pregnant women, prisoners, recent history of airway surgery, oral or pharyngeal malformations, inability to perform randomization due to the need for emergency endotracheal intubation, or when the investigator deemed it necessary or contraindicated to use AIVL, VL, or DL during the first intubation attempt.
Studie plan
Hoe is de studie opgezet?
Ontwerpdetails
- Primair doel: Behandeling
- Toewijzing: Gerandomiseerd
- Interventioneel model: Parallelle opdracht
- Masker: Geen (open label)
Wapens en interventies
Deelnemersgroep / Arm |
Interventie / Behandeling |
|---|---|
|
Actieve vergelijker: Video Laryngoscope(VL)
Participants randomized to this arm (n=60) will undergo the first endotracheal intubation attempt using a conventional video laryngoscope (VL), without AI-assisted anatomical identification or intubation guidance. |
A conventional video laryngoscope will be used for the first endotracheal intubation attempt. The device displays the airway image without AI-assisted identification of anatomical structures or real-time AI intubation guidance. |
|
Experimenteel: AI-assisted Video Laryngoscope (AIVL)
Participants randomized to this arm (n=60) will undergo the first endotracheal intubation attempt using an AI-assisted video laryngoscope (AIVL), which provides real-time identification of airway anatomical structures and intubation guidance. Operators will receive standardized training on the device controls, guidance interface, and image display before use. Operators may decide whether to follow the AI guidance. |
When using the AIVL for the first attempt at laryngoscopy intubation, the operator shall receive pre-procedural training, which primarily covers the functional buttons, the prompt interface, and image display. |
Wat meet het onderzoek?
Primaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
First-pass intubation success rate
Tijdsspanne: The time from enrollment to completion of intubation (usually within 10 minutes).
|
Proportion of participants with successful endotracheal tube placement on the first laryngoscopic attempt, confirmed by end-tidal carbon dioxide monitoring. |
The time from enrollment to completion of intubation (usually within 10 minutes).
|
Secundaire uitkomstmaten
Uitkomstmaat |
Maatregel Beschrijving |
Tijdsspanne |
|---|---|---|
|
Intubation time
Tijdsspanne: The time from enrollment to completion of intubation (usually within 10 minutes).
|
Time in seconds from insertion of the laryngoscope into the oral cavity until the endotracheal tube passes through the glottis. |
The time from enrollment to completion of intubation (usually within 10 minutes).
|
|
Severe complications occurring within 2 minutes after intubation were defined as severe hypoxemia (peripheral SpO₂ <80%), severe hypotension (systolic blood pressure <65 mmHg), initiation of vasoactive agents, cardiac arrest, or death.
Tijdsspanne: From enrollment to the 2 minutes after intubation
|
From enrollment to the 2 minutes after intubation
|
|
|
AI recall
Tijdsspanne: The time from enrollment to completion of intubation (usually within 10 minutes).
|
True-positive anatomical detections divided by true-positive plus false-negative detections, assessed against reference annotations. |
The time from enrollment to completion of intubation (usually within 10 minutes).
|
|
Duration of mechanical ventilation
Tijdsspanne: From enrollment to the end of treatment at 8 weeks
|
Duration of mechanical ventilation, measured in days. |
From enrollment to the end of treatment at 8 weeks
|
|
28-day all-cause mortality
Tijdsspanne: From enrollment through day 28.
|
Proportion of participants who die from any cause within 28 days after enrollment. |
From enrollment through day 28.
|
|
ICU length of stay
Tijdsspanne: From enrollment through the end of treatment, up to 8 weeks.
|
Duration of intensive care unit stay, measured in days. |
From enrollment through the end of treatment, up to 8 weeks.
|
|
Total hospital length of stay
Tijdsspanne: From enrollment through the end of treatment, up to 8 weeks.
|
Total duration of hospitalization, measured in days. |
From enrollment through the end of treatment, up to 8 weeks.
|
|
AI precision
Tijdsspanne: Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
True-positive anatomical detections divided by true-positive plus false-positive detections, assessed against reference annotations. |
Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
|
AI specificity
Tijdsspanne: Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
True-negative assessments divided by true-negative plus false-positive assessments, assessed against reference annotations. |
Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
|
AI F1 score
Tijdsspanne: Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
Harmonic mean of precision and recall: 2 x precision x recall / (precision + recall). |
Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
|
Mean average precision (mAP)
Tijdsspanne: Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
Mean of average precision across the evaluated anatomical classes against reference annotations. |
Video acquired from enrollment to completion of intubation, usually within 10 minutes.
|
Medewerkers en onderzoekers
Studie record data
Bestudeer belangrijke data
Studie start (Geschat)
Primaire voltooiing (Geschat)
Studie voltooiing (Geschat)
Studieregistratiedata
Eerst ingediend
Eerst ingediend dat voldeed aan de QC-criteria
Eerst geplaatst (Werkelijk)
Updates van studierecords
Laatste update geplaatst (Werkelijk)
Laatste update ingediend die voldeed aan QC-criteria
Laatst geverifieerd
Meer informatie
Termen gerelateerd aan deze studie
Andere studie-ID-nummers
- 2026-0142
Plan Individuele Deelnemersgegevens (IPD)
Bent u van plan om gegevens van individuele deelnemers (IPD) te delen?
Informatie over medicijnen en apparaten, studiedocumenten
Bestudeert een door de Amerikaanse FDA gereguleerd geneesmiddel
Bestudeert een door de Amerikaanse FDA gereguleerd apparaatproduct
Deze informatie is zonder wijzigingen rechtstreeks van de website clinicaltrials.gov gehaald. Als u verzoeken heeft om uw onderzoeksgegevens te wijzigen, te verwijderen of bij te werken, neem dan contact op met register@clinicaltrials.gov. Zodra er een wijziging wordt doorgevoerd op clinicaltrials.gov, wordt deze ook automatisch bijgewerkt op onze website .