UMIN-CTR Clinical Trial

Public title

Artificial Intelligence-assisted Measurement of Cardiac Output via Non-invasive Image Technology During Passive Leg Raising Testing (AI-MONITOR): A Prospective Observational Study

Acronym

AI-MONITOR study

Scientific Title

Artificial Intelligence-assisted Measurement of Cardiac Output via Non-invasive Image Technology During Passive Leg Raising Testing (AI-MONITOR): A Prospective Observational Study

Scientific Title:Acronym

AI-MONITOR study

Region

Japan

Condition

Patients admitted to the intensive care unit (ICU) of Fukushima Medical University Hospital who were monitored with the FloTrac system and underwent passive leg raising (PLR) testing.

Classification by specialty

Anesthesiology

Intensive care medicine

Classification by malignancy

Others

Genomic information

NO

Narrative objectives1

The purpose of this study is to validate an artificial intelligence (AI)-based method for geometrically extracting arterial pressure waveform area ratios from photographs of physiological monitor screens acquired using a smartphone. Specifically, the study aims to determine how accurately stroke volume (SV) and cardiac output (CO) changes derived from these area ratios reflect hemodynamic changes induced by passive leg raising (PLR).

The FloTrac system, a continuous cardiac output monitoring device, will be used as the reference method. This study will evaluate the accuracy and feasibility of the proposed approach as a novel hemodynamic assessment tool that does not require specialized equipment and can be applied in a real-world intensive care unit (ICU) setting.

Basic objectives2

Efficacy

Basic objectives -Others

Trial characteristics_1

Trial characteristics_2

Developmental phase

Primary outcomes

Agreement and error (Bland Altman analysis) between changes in stroke volume (delta SV) derived from ChatGPT based analysis of arterial pressure waveform area ratios (AI method) and delta SV measured by the FloTrac system (FT method) during passive leg raising (PLR).

Key secondary outcomes

a) Comparison of the percent changes in SV and CO calculated by the AI method and the FT method during the transition from the head-down to the head-up position (Bland-Altman analysis)

b) Sensitivity, specificity, and area under the curve (AUC) using delta SV calculated by the AI method as a continuous variable, defining fluid responsiveness (gold standard) as a more than 10% increase in delta SV measured by the FT method

c) Trend concordance rate of delta SV and delta CO between the AI and FT methods during two sequential postural changes (head-up to head-down to head-up), assessed by four-quadrant plot analysis

d) Feasibility (analysis success rate) of the proposed method (smartphone recording and AI image analysis) and classification of reasons for unanalyzable cases (e.g., light reflection, extreme camera shake, AI recognition errors, and waveform irregularities due to arrhythmias)

The following will be performed as exploratory analyses:

e) Comparison of delta SV and delta CO calculated using As/Ad and Pmd extracted by three different prompts in the AI method

f) Similar evaluation of the above using Gemini, and comparison of the results between ChatGPT and Gemini

Study type

Observational

Basic design

Randomization

Randomization unit

Blinding

Control

Stratification

Dynamic allocation

Institution consideration

Blocking

Concealment

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

Age-lower limit

18

years-old

<=

Age-upper limit

100

years-old

>=

Gender

Male and Female

Key inclusion criteria

Patients aged 18 years or older who meet either of the following criteria will be eligible for inclusion:
Patients admitted to the intensive care unit (ICU) of Fukushima Medical University Hospital between Aug 2026 and December 2028 who were monitored with the FloTrac system and underwent passive leg raising (PLR) testing.

Key exclusion criteria

Data from patients or time points meeting any of the following criteria will be excluded:

1. Passive leg raising (PLR) tests performed in the presence of cardiac arrhythmias.

2. Patients receiving mechanical circulatory support (e.g., extracorporeal membrane oxygenation [ECMO]).

3. Patients in whom interpretation of the PLR test is considered difficult, or in whom the reliability of hemodynamic measurements obtained from the FloTrac system or pulmonary artery catheter (PAC) is considered inadequate.

Target sample size

84

Name of lead principal investigator

1st name	Keisuke
Middle name
Last name	Yoshida

Organization

Fukushima Medical University

Division name

Department of Anesthesiology

Zip code

9601295

Address

1-Hikarigaoka, Fukushima, Fukushima, Japan

TEL

0245471342

Email

kei-y7of@fmu.ac.jp

Name of contact person

1st name	Keisuke
Middle name
Last name	Yoshida

Organization

Fukushima Medical University

Division name

Department of Anesthesiology

Zip code

9601295

Address

1, Hikarigaoka, Fukushima, Fuksuhima, Japan

TEL

0245471342

Homepage URL

Email

kei-y7of@fmu.ac.jp

Institute

Fukushima Medical University

Institute

Department

Personal name

Organization

JSPS KAKENHI

Organization

Division

Category of Funding Organization

Japanese Governmental office

Nationality of Funding Organization

Co-sponsor

Name of secondary funder(s)

Organization

Ethics Committee of Fukushima Medical University

Address

1, Hikarigaoka, Fukushima, Fukushima, Japan

Tel

0245471825

Email

rs@fmu.ac.jp

Secondary IDs

NO

Study ID_1

Org. issuing International ID_1

Study ID_2

Org. issuing International ID_2

IND to MHLW

Institutions

Date of disclosure of the study information

2026

Year

08

Month

26

Day

URL releasing protocol

Publication of results

Unpublished

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

Recruitment status

Preinitiation

Date of protocol fixation

2026

Year

07

Month

11

Day

Date of IRB

2026

Year

08

Month

24

Day

Anticipated trial start date

2026

Year

09

Month

01

Day

Last follow-up date

2029

Year

03

Month

31

Day

Date of closure to data entry

Date trial data considered complete

Date analysis concluded

Other related information

ICU management will be performed according to the standard practice at our institution. Upon ICU admission, all patients are routinely monitored using standard monitoring devices including an arterial catheter. Among them, patients for whom continuous cardiac output monitoring is considered clinically appropriate will be monitored using the FloTrac system (for postoperative patients, the system is typically initiated in the operating room).

During ICU stay, the following data will be collected and analyzed:

- Patient characteristics: age, sex, height, weight, diagnosis (or surgical procedure in postoperative patients), comorbidities, and use of vasoactive agents.
- Severity of illness: Sequential Organ Failure Assessment (SOFA) score and Acute Physiology and Chronic Health Evaluation II (APACHE II) score.
- Details of each passive leg raising (PLR) test, including date, time, vasoactive medications, and fluid administration status.
- FloTrac system data obtained during PLR testing: stroke volume (SV), cardiac output (CO), stroke volume variation (SVV), systemic vascular resistance (SVR), and central venous pressure (CVP), when available.
- Photographs of the physiological monitor obtained using a smartphone before and after PLR testing, including blood pressure, heart rate, and CVP when available.

Registered date

2026

Year

08

Month

04

Day

Last modified on

2026

Year

08

Month

26

Day

Link to view the page

Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000070674