UMIN-CTR Clinical Trial

Unique ID issued by UMIN UMIN000044894
Receipt number R000051274
Scientific Title Creation of a deep learning model to predict hypotension after induction of general anesthesia using a biometric screen during awakening - A prospective observational study
Date of disclosure of the study information 2021/07/20
Last modified on 2022/01/04 09:24:59

* This page includes information on clinical trials registered in UMIN clinical trial registed system.
* We don't aim to advertise certain products or treatments


Basic information

Public title

Creation of a deep learning model to predict hypotension after induction of general anesthesia using a biometric screen during awakening - A prospective observational study

Acronym

Creation of a deep learning model to predict hypotension after induction of general anesthesia using a biometric screen during awakening - A prospective observational study

Scientific Title

Creation of a deep learning model to predict hypotension after induction of general anesthesia using a biometric screen during awakening - A prospective observational study

Scientific Title:Acronym

Creation of a deep learning model to predict hypotension after induction of general anesthesia using a biometric screen during awakening - A prospective observational study

Region

Japan


Condition

Condition

Surgical cases undergoing general anesthesia

Classification by specialty

Anesthesiology

Classification by malignancy

Others

Genomic information

NO


Objectives

Narrative objectives1

The purpose of this study is to predict perioperative hypotension by using deep learning with image information. If we can intuitively predict hypotension after induction of general anesthesia by analyzing visual information obtained from images with deep learning, we may be able to prevent perioperative complications and also respond quickly.

Basic objectives2

Efficacy

Basic objectives -Others


Trial characteristics_1


Trial characteristics_2


Developmental phase



Assessment

Primary outcomes

Accuracy of Deep Learning Model Using Biometric Images Before General Anesthesia Induction for Predicting Blood Pressure Decline after General Anesthesia Induction

Key secondary outcomes



Base

Study type

Observational


Study design

Basic design


Randomization


Randomization unit


Blinding


Control


Stratification


Dynamic allocation


Institution consideration


Blocking


Concealment



Intervention

No. of arms


Purpose of intervention


Type of intervention


Interventions/Control_1


Interventions/Control_2


Interventions/Control_3


Interventions/Control_4


Interventions/Control_5


Interventions/Control_6


Interventions/Control_7


Interventions/Control_8


Interventions/Control_9


Interventions/Control_10



Eligibility

Age-lower limit

20 years-old <=

Age-upper limit

80 years-old >=

Gender

Male and Female

Key inclusion criteria

Surgical cases undergoing general anesthesia in the operating room of Yamagata University Hospital will be included. Among them, cases in which arterial pressure measurement is performed prior to induction of general anesthesia will be considered eligible cases.

Key exclusion criteria

Patients who have been sedated prior to induction of general anesthesia.
Patients undergoing tracheal intubation prior to induction of general anesthesia.
Patients with contraindications to propofol or remimazolam.
Patients who did not give their consent to participate in the study.
Patients with aortic aneurysms or cerebral aneurysms that require management to prevent excessive blood pressure fluctuations.

Target sample size

100


Research contact person

Name of lead principal investigator

1st name kaneyuki
Middle name
Last name kawamae

Organization

Yamagata University Medical School Hospital

Division name

Department of Anesthesia

Zip code

9909585

Address

2-2-2, Iida-Nishi, Yamagata City

TEL

0236331122

Email

yarimizu.kenya@gmail.com


Public contact

Name of contact person

1st name kenya
Middle name
Last name yarimizu

Organization

Yamagata University Medical School Hospital

Division name

Department of Anesthesia

Zip code

9909585

Address

2-2-2, Iida-Nishi, Yamagata City

TEL

0236331122

Homepage URL


Email

yarimizu.kenya@gmail.com


Sponsor or person

Institute

Yamagata University

Institute

Department

Personal name



Funding Source

Organization

Department of Anesthesiology, Yamagata University Medical School Hospital

Organization

Division

Category of Funding Organization

Self funding

Nationality of Funding Organization



Other related organizations

Co-sponsor


Name of secondary funder(s)



IRB Contact (For public release)

Organization

Yamagata University Medical School Hospital

Address

2-2-2, Iida-Nishi, Yamagata City

Tel

0236331122

Email

yarimizu.kenya@gmail.com


Secondary IDs

Secondary IDs

NO

Study ID_1


Org. issuing International ID_1


Study ID_2


Org. issuing International ID_2


IND to MHLW



Institutions

Institutions



Other administrative information

Date of disclosure of the study information

2021 Year 07 Month 20 Day


Related information

URL releasing protocol


Publication of results

Unpublished


Result

URL related to results and publications


Number of participants that the trial has enrolled


Results


Results date posted


Results Delayed


Results Delay Reason


Date of the first journal publication of results


Baseline Characteristics


Participant flow


Adverse events


Outcome measures


Plan to share IPD


IPD sharing Plan description



Progress

Recruitment status

Enrolling by invitation

Date of protocol fixation

2021 Year 07 Month 07 Day

Date of IRB

2021 Year 07 Month 07 Day

Anticipated trial start date

2021 Year 07 Month 21 Day

Last follow-up date

2023 Year 03 Month 31 Day

Date of closure to data entry


Date trial data considered complete


Date analysis concluded



Other

Other related information

After entering the operating room, non-schematic arterial pressure measurement, schematic arterial pressure measurement, transcutaneous oxygen saturation measurement, and electrocardiogram measurement should be performed, and vitals should be measured continuously until the patient leaves the operating room.
Administer propofol 1-2 mg/kg or remimazolam 12 mg/kg/hr.
Biometric images (arterial pressure, electrocardiogram, transcutaneous oxygen saturation, capnograph) from the anesthesia recorder (ORSYS, PHILIPS) will be extracted every 20-30 seconds until about 30 minutes after securing the arterial pressure line, and saved to USB with password.
The extracted images will be classified according to the following time course: T1: from before induction of general anesthesia to preoxygenation, T2: from the start of preoxygenation to the start of anesthetic administration, T3: from the start of anesthetic administration to muscle relaxation administration, T4: from muscle relaxation administration to tracheal intubation, and T5: from tracheal intubation to about 15 minutes later (about 30 minutes after securing the arterial pressure line by observation). After induction of general anesthesia (T4)
The imaging data will be categorized as positive if hypotension is observed after induction of general anesthesia (T5) and negative if hypotension is not observed. (There are two patterns each from T1 to T5, for a total of 10 patterns.)
The AI model is created using positive and negative data, with 80% of the total data used as train data. Using 20% of the total data as test data, draw ROC curve and calculate AUC.


Management information

Registered date

2021 Year 07 Month 18 Day

Last modified on

2022 Year 01 Month 04 Day



Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000051274


Research Plan
Registered date File name

Research case data specifications
Registered date File name

Research case data
Registered date File name