IntubationDOLPHINNCT07922434
AI-assisted Tracheal Intubation in Children
An observational study of Intubation, run by Insel Gruppe AG, University Hospital Bern at 1 site in Switzerland.
Trial summary
The aim of this study is to investigate whether the use of larynGuide™ provides accurate and reliable information regarding the position of the endotracheal tube following an intubation attempt in children. Read more about this study
- Who is it for?
- Ages 6 months to 6 years
- Conditions the study is for
- Intubation
- What is being tested?
- LarynGuide
- Type of treatment
- Medical device
- How many people
- 110 participants
- Where
- 1 siteSwitzerland
- Study dates
- Nov 2026to 30 Apr 2028
- How long will I take part?
- 1 Day
- Phase
- Observational
- 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 6 months to 6 years
- All sexes
- No healthy volunteers
- Child
Study population: Pediatric patients aged 6 months to 6 years with German-speaking parents classified American Society of Anesthesiologists (ASA) I, II or III undergoing surgery (except intracranial surgery) in general anaesthesia with tracheal intubation without contraindication for intubation with C-MAC video laryngoscope (KARL STORZ, Tuttlingen, Germany) or indication for impossible mask ventilation and high aspiration risk with given informend consent
Who may be able to join
- male or female pediatric patients ≥ 6 months to ≤ 6 years,
- American Society of Anesthesiologists (ASA) class I to III
- undergoing elective surgery in general anaesthesia with tracheal intubation.
Who cannot join
- Contraindication for intubation with C-MAC video laryngoscope (Karl Storz, Tuttlingen, Germany)
- Patients < 6 months or > 6 years
- No proper trained personnel for the device at the study site
- Expected impossible mask ventilation.
- High risk of aspiration (requiring rapid sequence induction and intubation)
- Intracranial surgery
- Limited knowledge of German language or refusing informed consent.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
Switzerland1 site
Inselspital
Bern, Canton of Bern, 3010
Alexander Fuchs, PD Dr. med., +41 31 632 23 84, alexander.fuchs@insel.ch
About this study
Official title: DiagnOstic Accuracy of LarynGuide™ for Paediatric AI-assisted tracHeal Intubation (DOLPHIN)
The aim of this study is to investigate whether the use of larynGuide™ provides accurate and reliable information regarding the position of the endotracheal tube following an intubation attempt in children. larynGuide™ is a software tool that runs on a video laryngoscope platform to assist with laryngoscopy and intubation.
Read the detailed description
Eligible patients will be prepared for intubation according to the local Standard Operating Procedures (SOPs) of the anaesthesia departments. Mandatory monitoring: saturation of peripheral oxygen (SpO₂), heart rate (HR), non-invasive blood pressure (NIBP), end-tidal carbon dioxide (EtCO₂).
The larynGuide™ software system (consisting of 2 displays, one regular C-MAC video laryngoscope monitor (KARL STORZ, Tuttlingen, Germany) which will be used by the board-certified anaesthesiologist for intubation and the other one for the study team displaying the software which is not to be seen from the anaesthetist perspective) is being taken to the induction room making sure that display is not to be seen from the anaesthesiologist point of view.
Induction of anaesthesia: If feasible, all children included in this protocol will be pre oxygenated before induction of anaesthesia for one minute through face-mask with Fraction of inspired oxygen (FiO₂) 1.0 and flow rates of 6-10L/min. The induction of anaesthesia for tracheal intubation will be performed using a combination of sedative/hypnotic drugs, opioids and non-depolarizing muscle relaxant. The following medications will be mandatory as per protocol:
- One or more of the following hypnotic agents (Thiopentone 4-7 mg/kg, Ketamine 0.5-2 mg/kg, Propofol 1-4 mg/kg, Midazolam 0.5-1 mg/kg, Sevoflurane up to 8%).
- An opioid drug and anticholinergic can be chosen and administered at the discretion of the anaesthetist in charge.
- A neuromuscular blocking agent (NMBA): Rocuronium 0.5-1 mg/kg, Cis Atracurium 0.2-0.5 mg/kg, Atracurium 0,5 mg/kg, Vecuronium 0.1 mg/kg, Mivacurium 0.2 - 0.3 mg/kg or Succinylcholine 2 mg/kg.
Before intubation: After induction of anaesthesia and the administration of a NMBA, bag-mask ventilation with FiO₂ 1.0 (flow rates of 6-10 L/min) will be performed for 60 seconds until apnea sets in. Thereafter bag-mask ventilation will be stopped and apnoeic oxygenation (1l/kgBW) will be started. Video laryngoscopy will be performed with a C-MAC video laryngoscope and the patient's trachea will be intubated. Once the intubation attempt is completed, the software displays a green light for the correct tube position or the words "Bad intubation" on the monitor (which is only seen by the study personnel). The anaesthesiologist in charge (board certified) performs checks to assess the correctness of the tracheal tube position by visual check and by attaching the patient to the ventilator and measuring the endtidal carbon dioxide (CO₂) (Gold standard to rule out oesophageal intubation in anaesthesia). After the board-certified anaesthesiologist communicated to have completed the intubation attempt, the research staff will look if the software displays a green light or the words "Bad intubation" on the monitor.
- Conditions
- Intubation
- Being tested
- LarynGuide
- Keywords
- Artificial Intelligence, Tracheal video intubation, larynGuide, Airway management
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
LarynGuideDevice
Artificial Intelligence assisted tracheal video intubation in children
| Study group | Role | What they receive |
|---|---|---|
| Pediatric patients (≥ 6 months to ≤ 6 years) undergoing elective surgery | Pediatric patients (≥ 6 months to ≤ 6 years) undergoing elective surgery surgery in general anaesthesia with tracheal intubation Receives: Device: LarynGuide |
What is being measured
The primary outcome is the main question the study is designed to answer.
Rate of correct assessment given by larynGuide™
Correctness of the advice measured by accuracy of the LarynGuide™, a software for artificial intelligence assisted tracheal intubation (aiEndoscopic, Zürich, Switzerland) on tube position given at the end of an intubation attempt
Measured: 5 minutes
Secondary outcomes (7)
Overall success rate
Overall success rate under assistance with larynGuide™
Measured: 5 minutes
first-attempt success rate
First-attempt oro-tracheal intubation success rate confirmed with waveform capnography in percentage
Measured: 10 minutes
Number of attempts
number of attempts until correct intubation
Measured: 5 minutes
Number of incidents of technical problems of larynGuide™
Number of the occurrence of any technical problem of the larynGuide™, a software for artificial intelligence assisted tracheal intubation (aiEndoscopic, Zürich, Switzerland)
Measured: 10 minutes
Percentage of glottic opening (POGO)
Best percentage of glottic opening (POGO)
Measured: 2 minutes
Rate of Cormack & Lehane Score from 1 to 4
Cormack-Lehane classification is used to describe laryngeal view during direct laryngoscopy and can be divided into 4 grades of which 1 is the best (all of the glottis can be seen - so the best view) and 4 is the worste (not even the epiglottis is visible - worst view). The occurrence of these grades will be recorded.
Measured: 2 minutes
Occurrence rate of airway management complications
Complications during and after airway management such oral/airway injury with bleeding, difficult bag-mask ventilation, emesis, aspiration of gastric contents, hypotension necessitating treatment, hypoxia causing bradycardia requiring chest compressions, pneumothorax and the administration of resuscitation drugs
Measured: 5 minutes
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted6 Nov 2026
- Study startNov 2026 (estimated)
- Primary completion31 Oct 2027 (estimated)
- Study completion30 Apr 2028 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Publications (1)Papers the sponsor has linked to this study.
- Other trials for IntubationStudies of the same condition, open and under way.
- More trials run by Insel Gruppe AG, University Hospital BernThe sponsor's other registered studies.
- 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
- Observational
- Observational model
- Case only
- Time perspective
- Prospective
- Enrolment
- 110 participants (estimated)
- Target duration
- 1 Day
Sponsor and investigators
- Lead sponsor
- Insel Gruppe AG, University Hospital Bern
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07922434
- Sponsor's protocol ID
- DOLPHIN_FuchsRiva2026
- Acronym
- DOLPHIN
- Status last verified
- Oct 2026
- First submitted
- 2 Nov 2026
- Last updated
- 6 Nov 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No
Publications
Fuchs A, Raeber A, Lippuner R, Weber L, Borysenko Y, Huber M, Greif R, Riva T. Artificial intelligence-assisted tracheal intubation in humans: a prospective observational study of diagnostic accuracy. Anaesthesia. 2026 Mar;81(3):343-350. doi: 10.1111/anae.70063. Epub 2025 Nov 17.
PubMed 41243690
Study at a glance
From the registry record, last updated by the sponsor on 6 Nov 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- DiagnOstic Accuracy of LarynGuide™ for Paediatric AI-assisted tracHeal Intubation (DOLPHIN)
- ClinicalTrials.gov ID
- NCT07922434
- Acronym / sponsor ID
- DOLPHIN / DOLPHIN_FuchsRiva2026
- Conditions
- Intubation
- Keywords
- Artificial Intelligence, Tracheal video intubation, larynGuide, Airway management
- Study type
- Observational
- Recruitment status
- Not yet recruiting
- Enrolment
- 110 participants (estimated)
- Lead sponsor
- Insel Gruppe AG, University Hospital BernUniversity, hospital or other
- Study start
- Nov 2026 (estimated)
- Primary completion
- 31 Oct 2027 (estimated)
- Study completion
- 30 Apr 2028 (estimated)
- First posted
- 6 Nov 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 aim of this study is to investigate whether the use of larynGuide™ provides accurate and reliable information regarding the position of the endotracheal tube following an intubation attempt in children. larynGuide™ is a software tool that runs on a video laryngoscope platform to assist with laryngoscopy and intubation.
Detailed description
Eligible patients will be prepared for intubation according to the local Standard Operating Procedures (SOPs) of the anaesthesia departments. Mandatory monitoring: saturation of peripheral oxygen (SpO₂), heart rate (HR), non-invasive blood pressure (NIBP), end-tidal carbon dioxide (EtCO₂).
The larynGuide™ software system (consisting of 2 displays, one regular C-MAC video laryngoscope monitor (KARL STORZ, Tuttlingen, Germany) which will be used by the board-certified anaesthesiologist for intubation and the other one for the study team displaying the software which is not to be seen from the anaesthetist perspective) is being taken to the induction room making sure that display is not to be seen from the anaesthesiologist point of view.
Induction of anaesthesia: If feasible, all children included in this protocol will be pre oxygenated before induction of anaesthesia for one minute through face-mask with Fraction of inspired oxygen (FiO₂) 1.0 and flow rates of 6-10L/min. The induction of anaesthesia for tracheal intubation will be performed using a combination of sedative/hypnotic drugs, opioids and non-depolarizing muscle relaxant. The following medications will be mandatory as per protocol:
- One or more of the following hypnotic agents (Thiopentone 4-7 mg/kg, Ketamine 0.5-2 mg/kg, Propofol 1-4 mg/kg, Midazolam 0.5-1 mg/kg, Sevoflurane up to 8%).
- An opioid drug and anticholinergic can be chosen and administered at the discretion of the anaesthetist in charge.
- A neuromuscular blocking agent (NMBA): Rocuronium 0.5-1 mg/kg, Cis Atracurium 0.2-0.5 mg/kg, Atracurium 0,5 mg/kg, Vecuronium 0.1 mg/kg, Mivacurium 0.2 - 0.3 mg/kg or Succinylcholine 2 mg/kg.
Before intubation: After induction of anaesthesia and the administration of a NMBA, bag-mask ventilation with FiO₂ 1.0 (flow rates of 6-10 L/min) will be performed for 60 seconds until apnea sets in. Thereafter bag-mask ventilation will be stopped and apnoeic oxygenation (1l/kgBW) will be started. Video laryngoscopy will be performed with a C-MAC video laryngoscope and the patient's trachea will be intubated. Once the intubation attempt is completed, the software displays a green light for the correct tube position or the words "Bad intubation" on the monitor (which is only seen by the study personnel). The anaesthesiologist in charge (board certified) performs checks to assess the correctness of the tracheal tube position by visual check and by attaching the patient to the ventilator and measuring the endtidal carbon dioxide (CO₂) (Gold standard to rule out oesophageal intubation in anaesthesia). After the board-certified anaesthesiologist communicated to have completed the intubation attempt, the research staff will look if the software displays a green light or the words "Bad intubation" on the monitor.
Study design
- Observational model
- Case only
- Time perspective
- Prospective
- Target follow-up
- 1 Day
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Pediatric patients (≥ 6 months to ≤ 6 years) undergoing elective surgery | – | Device: LarynGuidePediatric patients (≥ 6 months to ≤ 6 years) undergoing elective surgery surgery in general anaesthesia with tracheal intubation |
Who may qualify
- Ages
- 6 months to 6 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Child
- Study population
- Pediatric patients aged 6 months to 6 years with German-speaking parents classified American Society of Anesthesiologists (ASA) I, II or III undergoing surgery (except intracranial surgery) in general anaesthesia with tracheal intubation without contraindication for intubation with C-MAC video laryngoscope (KARL STORZ, Tuttlingen, Germany) or indication for impossible mask ventilation and high aspiration risk with given informend consent
Key inclusion criteria (3 listed)
- male or female pediatric patients ≥ 6 months to ≤ 6 years,
- American Society of Anesthesiologists (ASA) class I to III
- undergoing elective surgery in general anaesthesia with tracheal intubation.
Key exclusion criteria (7 listed)
- Contraindication for intubation with C-MAC video laryngoscope (Karl Storz, Tuttlingen, Germany)
- Patients < 6 months or > 6 years
- No proper trained personnel for the device at the study site
- Expected impossible mask ventilation.
- High risk of aspiration (requiring rapid sequence induction and intubation)
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 |
|---|---|---|
| LarynGuideArtificial Intelligence assisted tracheal video intubation in children | Device | Pediatric patients (≥ 6 months to ≤ 6 years) undergoing elective surgery |
Primary outcome
Rate of correct assessment given by larynGuide™
Time frame: 5 minutes
Correctness of the advice measured by accuracy of the LarynGuide™, a software for artificial intelligence assisted tracheal intubation (aiEndoscopic, Zürich, Switzerland) on tube position given at the end of an intubation attempt
7 secondary outcomes
Overall success rate
Time frame: 5 minutes
first-attempt success rate
Time frame: 10 minutes
Number of attempts
Time frame: 5 minutes
Number of incidents of technical problems of larynGuide™
Time frame: 10 minutes
Percentage of glottic opening (POGO)
Time frame: 2 minutes
Rate of Cormack & Lehane Score from 1 to 4
Time frame: 2 minutes
Occurrence rate of airway management complications
Time frame: 5 minutes
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 6 Nov 2026.
- Background: PubMed 41243690Fuchs A, Raeber A, Lippuner R, Weber L, Borysenko Y, Huber M, Greif R, Riva T. Artificial intelligence-assisted tracheal intubation in humans: a prospective observational study of diagnostic accuracy. Anaesthesia. 2026 Mar;81(3):343-350. doi: 10.1111/anae.70063. Epub 2025 Nov 17.
- Individual participant dataSharing planned: No
Related trials for Intubation
Not yet recruiting
AI Smart Glasses Feedback for Intubation Training in Medical Students
Intubation, Intratracheal, Medical Education
Recruiting
Development and Preliminary Validation of Intelligent Video Laryngoscope for Emergency Use
Critically Ill Patients Requiring Mechanical Ventilation
Recruiting
Vagal Stimulator to Reduce Nasogastric Tube Use
Nasogastric Tube Intubation
Enrolling by invitation
Pediatric Intubation Simulations With Bougie
Difficult Airway Intubation
Not yet recruitingObservational study
Sniper Intubation for Training of Undergraduate Medical Student
Intubation;Difficult
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.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Intubation, run by Insel Gruppe AG, University Hospital Bern at 1 site in Switzerland.
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 3 inclusion and 7 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: opening soon, as of the sponsor's last update on 6 Nov 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in Switzerland. 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 Alexander Fuchs, PD Dr. med. (+41 31 632 23 84, alexander.fuchs@insel.ch), or a site near the patient. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Rate of correct assessment given by larynGuide™ (time frame: 5 minutes). 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 NCT07922434, which also lists 1 linked publication.
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 6 Nov 2026.