UMIN-CTR Clinical Trial

Basic information
Public title	Development of a Deep Learning Model Using Spectroscopic Arterial Pressure Waveform to Predict Hypotension after General Anesthesia Induction - A Retrospective Observational Study-
Acronym	Development of a Deep Learning Model Using Spectroscopic Arterial Pressure Waveform to Predict Hypotension after General Anesthesia Induction - A Retrospective Observational Study-
Scientific Title	Development of a Deep Learning Model Using Spectroscopic Arterial Pressure Waveform to Predict Hypotension after General Anesthesia Induction - A Retrospective Observational Study-
Scientific Title:Acronym	Development of a Deep Learning Model Using Spectroscopic Arterial Pressure Waveform to Predict Hypotension after General Anesthesia Induction - A Retrospective Observational Study-
Region	Japan

Condition
Condition	Cases in which general anesthesia is performed
Classification by specialty	Anesthesiology
Classification by malignancy	Others
Genomic information	NO

Objectives
Narrative objectives1	The objective is to predict hypotension after induction of general anesthesia by using deep learning with image information.
Basic objectives2	Others
Basic objectives -Others	In addition to numerical values such as test results, anesthesiologists sometimes use information such as waveforms contained in biometric images to understand the patient's condition. However, there have been few reports on predicting changes in the patient's condition using biometric imaging information. Therefore, we will create a model for predicting hypotension after induction of general anesthesia by using deep learning of biometric images, including the spectroscopic arterial pressure waveform during wakefulness, which has not been explicitly documented.
Trial characteristics_1
Trial characteristics_2
Developmental phase

Assessment
Primary outcomes	Prediction of hypotension after induction of general anesthesia from angiographic arterial pressure waveform before induction of general anesthesia
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 in this study. From those cases, we will select those in which spectroscopic arterial pressure measurement was performed prior to the induction of general anesthesia.
Key exclusion criteria	Patients with general anesthesia administered before induction of general anesthesia Patients with tracheal intubation administered before induction of general anesthesia
Target sample size	200

Research contact person
Name of lead principal investigator	1st name Kaneyuki Middle name Last name Kawamae
Organization	Yamagata University Medical School Hospital
Division name	Anesthesiology
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	Anesthesiology
Zip code	9909585
Address	2-2-2, Iida-Nishi, Yamagata City
TEL	0236331122
Homepage URL
Email	yarimizu.kenya@gmail.com

Sponsor
Institute	Yamagata university
Institute
Department

Funding Source
Organization	Yamagata university
Organization
Division
Category of Funding Organization	Other
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 02 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 06 Month 02 Day
Date of IRB	2021 Year 06 Month 02 Day
Anticipated trial start date	2021 Year 07 Month 02 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

From the biometric images stored in the anesthesia recording system (ORSYS, PHILIPS), we will extract the observation arterial pressure ECG images for about 10 seconds before induction of general anesthesia to a USB with a password. We classified the image data into two groups: positive for those who showed a decrease in blood pressure after the induction of general anesthesia and negative for those who did not. Create an AI model using the positive and negative data, using 80% of the total data as train data. AUC was calculated by drawing ROC curve using 20% of the total data as test data. After induction of general anesthesia, arterial pressure and electrocardiographic images will be examined in the same way. This is to confirm the prediction accuracy for hypotension occurring in real time, and to evaluate whether AI can predict changes in arterial pressure waveform before and after the induction of general anesthesia. The following information will be obtained from the medical record. Preoperative information, Intraoperative information,Preoperative information and the amount of anesthetics will be compared between the two groups. Based on the obtained data, we will examine the correlation with the decrease in blood pressure after the induction of general anesthesia using deep learning.

Management information
Registered date	2021 Year 07 Month 01 Day
Last modified on	2021 Year 07 Month 18 Day

Link to view the page
URL(English)	https://upload.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000051088