ClinicalTrials.gg
Not yet recruitingNCT06957587Updated Oct 27, 2026

Intelligent Classification of Intraoperative Hemodynamic Phenotypes Based on CADFlow Doppler Monitoring

An observational study in Ultrasound, Machine Learning and Intraoperative Hypotension, sponsored by Shanghai 6th People's Hospital. Not yet recruiting at 2 sites in China. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-10-27.

Sponsored by Shanghai 6th People's Hospital · Observational

How we know

Updated Oct 27, 2026Now Not yet recruitingStart date moved+7 moreGo to Updates ↓

Help build ClinicalTrials.gg — short surveys, remote interviews or testing, in your language. Take part →

Study type
Observational
Model
Cohort
Time perspective
Prospective
Enrollment
440
Ages
18 Years and older
Sex
All
01

Where this study stands

Counted across the records on this site · 2026-11-22

Among 59 studies in Hypotension with a site in China — 26 open to participants now, 29 under way, none of them phase 3. Hypotension · China.

Planned enrollment
9th of 19
440 · median 200
Started
2026
with 10 others
Observational
19 of 59
9 open now
Primary completion
2027-12
later than 26 of 28 live
Registered
42nd of 59
by date

Among the 59 studies in Hypotension with a site in China, this one is the 9th largest by planned enrollment of the 19 observational ones that give a count, is one of 11 that started in 2026, is one of 19 observational ones, reaches primary completion later than 26 of the 28 other live ones, and was the 42nd registered.

Hypotension

892 studies on the registry are indexed under Hypotension; 199 are open to participants now.

Browse Hypotension studies →

Open to participants now

26 of the 59 studies in Hypotension with a site in China are open now. Recruiting first, the newest first:

20 more — sign in →

All 26 open studies →

A study can be open while its sites in China have not opened yet or have stopped. Only those recruiting at a site in China →

Who these studies take

Of the 114 Hypotension studies recruiting now, 53 (46%) set no upper age limit and 36 (32%) stop at 75 or younger; 7 take children under 18; 16 take healthy volunteers.

This study: 18 Years and older · all sexes · no healthy volunteers.

The full table on the hub →

This tab as a report to print or save as PDF → With an account.

Was this useful?
Get alerts for this landscapeDownload CSVNarrow it in search →With an account: a weekly mail of what changed among 59 studies in Hypotension with a site in China, or all of them as a file.
02

Study summary

The goal of this observational study is to learn about intraoperative hemodynamic phenotypes in adult patients undergoing elective surgery under general anesthesia, using a new wearable ultrasound patch (CADFlow) that continuously monitors carotid and jugular blood flow. The main question it aims to answer is:

Can a machine learning model built solely on non-invasive carotid and jugular Doppler data accurately identify and classify a patient's hemodynamic phenotype in real time during surgery? Participants undergoing routine elective surgery who are monitored with the CADFlow device as part of standard care will be recorded continuously from after tracheal intubation until the end of surgery. The collected signals will be used to discover distinct hemodynamic phenotypes and to train a model that classifies each patient's phenotype in real time.

Read the detailed description

Accurate and continuous assessment of intraoperative hemodynamic status is fundamental to perioperative safety. Marked intraoperative hemodynamic instability is closely associated with postoperative complications and mortality, making precise hemodynamic management a central goal of perioperative medicine. Since the 1970s, hemodynamic profiling has relied primarily on parameters obtained from the pulmonary artery catheter (PAC); the four-quadrant framework built on pulmonary artery occlusion pressure (PAOP) and cardiac index (CI) - such as the Forrester-Diamond classification - distinguishes "warm-dry", "warm-wet", "cold-dry" and "cold-wet" phenotypes and remains a classic element of critical-care teaching. However, PAC placement is an invasive procedure carrying risks such as pulmonary-artery rupture and arrhythmias, which limits its routine use in surgical patients.

Machine learning (ML) has increasingly been explored for hemodynamic phenotype classification, and unsupervised methods have shown particular promise. Geri et al. identified five cardiovascular phenotypes in septic shock by combining clinical and echocardiographic data; Guinot et al. identified three congestion-related phenotypes in ICU patients using clinical, biomarker and Doppler data; and Kouz et al. and Jian et al. identified endotypes of intraoperative hypotension in surgical cohorts using hierarchical clustering and autoencoder-based deep clustering, respectively. Nevertheless, these studies share common limitations: most depend on invasive arterial or PAC-derived parameters; they capture arterial-side flow information only and lack venous indices needed to assess preload and right-heart function; and the complexity of ML "black-box" models raises the need to benchmark them against simpler, more cost-effective approaches.

CADFlow is a novel wireless, wearable Doppler-ultrasound patch that continuously and noninvasively monitors carotid artery and jugular vein hemodynamic parameters simultaneously. Its fully noninvasive design (a probe applied to the neck) avoids the risks of arterial puncture or PAC insertion, eliminates operator-dependent variability, and provides both carotid parameters (VTI, ccFT, peak systolic velocity Vs, dP/dt) and jugular parameters (Jvti, mean jugular flow jTAV, jugular pulsatility index jPI, jugular filling index JVI). This dual arterial-and-venous information is not available from arterial-only Doppler or invasive monitoring, and the resulting multimodal feature set is expected to improve the resolution, physiological interpretability and performance of unsupervised phenotype classification.

This study aims to apply CADFlow multimodal data and unsupervised learning to automatically discover intraoperative hemodynamic phenotypes and, on this basis, to develop a real-time phenotype classification model, thereby providing new tools and evidence for intelligent perioperative hemodynamic management

03

Conditions studied

  • Ultrasound
  • Machine Learning
  • Intraoperative Hypotension
  • Hemodynamic Monitoring
  • Hemodynamic Phenotype / Endotype

Browse trials for

04

Who can participate

The criteria were revised on the registry on Oct 27, 2026. See what changed

Ages eligible
18 Years and older
Sexes eligible
All
Accepts healthy volunteers
No
Sampling method
Probability sample

Study population

Adult patients scheduled for elective, supine, general-anaesthesia surgery.

Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.

Inclusion criteria

  • Provides written to participate in the study;
  • Age 18 years or older;
  • (BMI) between 18 and 30 kg/m2;
  • (ASA) physical status class I-III;
  • Scheduled for elective, supine, tracheal-intubation general-anaesthesia surgery

Exclusion criteria

Exclusion Criteria:

  • Severe cardiac arrhythmia (e.g., atrial fibrillation, frequent premature ventricular contractions) that compromises signal accuracy;
  • Pregnancy;
  • Anatomical abnormality of the carotid artery or jugular vein, or extremely poor ultrasound signal quality.
Terms in these criteria, in plain language(3)

Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.

Informed consent

Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorized to decide for you.

You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.

BMI (body mass index)

Weight in kilograms divided by height in metres squared. Example: 70 kg and 1.75 m gives 70 ÷ (1.75 × 1.75) ≈ 22.9.

What counts as overweight or obesity differs between countries (some use lower cut-offs), so go by the range the study states.

ASA physical status

The anaesthetists’ scale of health before surgery: I is healthy, II has a mild illness that is under control, III a severe one, IV a severe illness that is a constant threat to life. V and VI are used for the critically ill and for organ donors.

05

Study design

Observational model
Cohort
Time perspective
Prospective
Enrollment
440 participants (estimated)
Patient registry
No

Groups and cohorts

  • Adult patients scheduled for elective surgery

    Adult patients aged 18 years or older scheduled for elective, supine, tracheal-intubation general-anaesthesia surgery will be enrolled into a single observational cohort.

06

What researchers measure

Primary outcomes

  1. Real-time phenotype classification performance of the machine-learning model

    Using the phenotype labels derived from unsupervised clustering of intraoperative CADFlow multimodal data, a supervised learning model will be trained to classify the current intraoperative hemodynamic phenotype in real time. Performance will be assessed by accuracy, macro-averaged AUC and macro-averaged F1-score.

    Time frame: Intraoperatively, from completion of tracheal intubation to the end of surgery

Secondary outcomes

  1. Phenotype feature-profile characterisation

    Distribution of CADFlow parameters across the discovered phenotypes (box/ violin plots) to verify physiological interpretability

    Time frame: Intraoperative

  2. Stability and interpretability of the unsupervised clustering solution

    Stability and interpretability of the unsupervised clustering solution (Silhouette coefficient, Calinski-Harabasz index, Bootstrap stability) and the association between phenotypes and intraoperative events such as hypotension and vasopressor use.

    Time frame: Intraoperative

07

Study locations

2 sites
08

References and documents

Individual participant data

Plan to share: Undecided

No publications or documents are linked to this record.

09

Timeline

1 registry update since Sep 25, 2026
ElapsedEstimatedEstimated, not yet reachedDate before it movedWhere the date was before it movedSimilar studies: half by the dot; the band is the middle halfHalf of similar studies reached it by the dot; the band is the middle half, from a quarter to three quarters

Start is estimated for Nov 2026; primary completion for Dec 2027, 13 months later.

Of 149 non-industry observational studies under Hypotension, half reached primary completion within 12 months of starting (the median), counting those still running; a quarter within 5 and three quarters within 25. This study's planned 13 months is close to that.

Counting every sponsor, half of 154 studies reached it within 11 months; a quarter within 5 and three quarters within 25.

Since we started tracking on Sep 25, 2026, the dates moved once, on Oct 27, 2026: start Oct 2025 → Nov 2026, primary completion Jul 2027 → Dec 2027 and completion Aug 2027 → Jun 2028.

Earlier changes are on the record history on ClinicalTrials.gov ↗

How these figures are worked out, and which studies are left out of them.

Registered
Apr 26, 2025
First posted
May 4, 2025
StartEst.
Nov 1, 2026was Oct 2025
Primary completionEst.
Dec 31, 2027was Jul 2027
CompletionEst.
Jun 30, 2028was Aug 2027
Last update
Oct 27, 2026
What these dates mean
Start.
When the first participant enrolled; while estimated, when the study expects to open to recruitment.
Primary completion.
When the last participant was examined or treated to collect data for the study's main question, its primary outcome. A study that stopped early gives the date its data collection stopped.
Completion.
When the last participant's last visit took place, for every outcome, secondary ones and side effects included: the end of the study. Often later than primary completion, sometimes the same day.
Actual and Est.
Actual means the registry says the date has happened. Est. (estimated) is a date the sponsor plans or expects. It can still move, and the sponsor is expected to change it to actual once it has passed.
Status
Recruiting→Not yet recruiting
changed Oct 27, 2026
Start date
Oct 1, 2025→Nov 1, 2026
Oct 27, 2026
Primary completion
Jul 31, 2027→Dec 31, 2027
Oct 27, 2026
Study completion
Aug 31, 2027→Jun 30, 2028
Oct 27, 2026
Enrollment
800→440
Oct 27, 2026
Eligibility
Maximum age 75 Years→none; 2 inclusion criteria edited, 3 added, 2 removed; 3 exclusion criteria added, 5 removed
What changed in the criteria
Inclusion criteria
  • RemovedAgree to join this study and sign the informed consent form;
  • RemovedAge between 18 and 75 years old (inclusive);
  • AddedProvides written informed consent to participate in the study;
  • AddedAge 18 years or older;
  • EditedBMI (bodyBody mass index (BMI) is between 18 and 30 kg/m2;
  • EditedAmerican Society of Anesthesiologists (ASA) gradesphysical status class I-IIIII;
  • AddedScheduled for elective, supine, tracheal-intubation general-anaesthesia surgery
Exclusion criteria
  • RemovedPreoperative hemoglobin (Hb) <10g/dl
  • RemovedCardiac dysfunction (NYHA class III-IV), respiratory dysfunction (ATS class 2-4), history of liver and kidney dysfunction (such as transaminase / albumin / bilirubin abnormalities, hepatitis history, serum creatinine / urea nitrogen rise, etc.), nervous system abnormalities (those who cannot cooperate due to stroke or its sequelae, Alzheimer, etc.);
  • RemovedThe ultrasonic display of inferior vena cava, internal jugular vein, subclavian vein or common carotid artery is extremely poor, venous thrombosis or anatomical abnormalities;
  • RemovedMultiple injury with chest, abdomen or brain;
  • RemovedPregnant woman
  • AddedSevere cardiac arrhythmia (e.g., atrial fibrillation, frequent premature ventricular contractions) that compromises signal accuracy;
  • AddedPregnancy;
  • AddedAnatomical abnormality of the carotid artery or jugular vein, or extremely poor ultrasound signal quality.
Oct 27, 2026
Interventions
Arms added: Adult patients scheduled for elective surgery; arms removed: patients prepare to receive surgery
Oct 27, 2026
Primary outcomes
1 edited
What changed in the outcomes
  • ChangedBefore Quantitative estimation of blood volumeNow Real-time phenotype classification performance of the machine-learning modelTime frame: within 30mins before the surgery → Intraoperatively, from completion of tracheal intubation to the end of surgery
Oct 27, 2026
Secondary outcomes
2 added
What changed in the outcomes
  • AddedPhenotype feature-profile characterisationTime frame: Intraoperative
  • AddedStability and interpretability of the unsupervised clustering solutionTime frame: Intraoperative
Oct 27, 2026
Title
A Deep Learning Model for Blood Volume Estimation From Multi-modal Ultrasound→Intelligent Classification of Intraoperative Hemodynamic Phenotypes Based on CADFlow Doppler Monitoring
Oct 27, 2026
Show all 1 update
  1. Oct 27, 2026
    Recruiting→Not yet recruiting
    Start date Oct 1, 2025→Nov 1, 2026
    Primary completion Jul 31, 2027→Dec 31, 2027
    Study completion Aug 31, 2027→Jun 30, 2028
    Enrollment 800→440
    Eligibility Maximum age 75 Years→none; 2 inclusion criteria edited, 3 added, 2 removed; 3 exclusion criteria added, 5 removed
    What changed in the criteria
    Inclusion criteria
    • RemovedAgree to join this study and sign the informed consent form;
    • RemovedAge between 18 and 75 years old (inclusive);
    • AddedProvides written informed consent to participate in the study;
    • AddedAge 18 years or older;
    • EditedBMI (bodyBody mass index (BMI) is between 18 and 30 kg/m2;
    • EditedAmerican Society of Anesthesiologists (ASA) gradesphysical status class I-IIIII;
    • AddedScheduled for elective, supine, tracheal-intubation general-anaesthesia surgery
    Exclusion criteria
    • RemovedPreoperative hemoglobin (Hb) <10g/dl
    • RemovedCardiac dysfunction (NYHA class III-IV), respiratory dysfunction (ATS class 2-4), history of liver and kidney dysfunction (such as transaminase / albumin / bilirubin abnormalities, hepatitis history, serum creatinine / urea nitrogen rise, etc.), nervous system abnormalities (those who cannot cooperate due to stroke or its sequelae, Alzheimer, etc.);
    • RemovedThe ultrasonic display of inferior vena cava, internal jugular vein, subclavian vein or common carotid artery is extremely poor, venous thrombosis or anatomical abnormalities;
    • RemovedMultiple injury with chest, abdomen or brain;
    • RemovedPregnant woman
    • AddedSevere cardiac arrhythmia (e.g., atrial fibrillation, frequent premature ventricular contractions) that compromises signal accuracy;
    • AddedPregnancy;
    • AddedAnatomical abnormality of the carotid artery or jugular vein, or extremely poor ultrasound signal quality.
    Primary outcomes 1 edited
    What changed in the outcomes
    • ChangedBefore Quantitative estimation of blood volumeNow Real-time phenotype classification performance of the machine-learning modelTime frame: within 30mins before the surgery → Intraoperatively, from completion of tracheal intubation to the end of surgery
    Secondary outcomes 2 added
    What changed in the outcomes
    • AddedPhenotype feature-profile characterisationTime frame: Intraoperative
    • AddedStability and interpretability of the unsupervised clustering solutionTime frame: Intraoperative
    Interventions Arms added: Adult patients scheduled for elective surgery; arms removed: patients prepare to receive surgery
    Title A Deep Learning Model for Blood Volume Estimation From Multi-modal Ultrasound→Intelligent Classification of Intraoperative Hemodynamic Phenotypes Based on CADFlow Doppler Monitoring
    + 4 other changes: verification date, description, conditions and site details

From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗

10

Registry details

Key details

Study ID
NCT06957587
Lead sponsor
Shanghai 6th People's Hospital
Responsible party
Xiaofeng WANG (attending doctor, Shanghai 6th People's Hospital) — Principal investigator
First posted
May 4, 2025
Start date
Nov 1, 2026 (estimated)
Primary completion
Dec 31, 2027 (estimated)
Completion
Jun 30, 2028 (estimated)
Last update
Oct 27, 2026

Study contacts

xiuxiu sun, MD
Contact
liuyuanec@163.com
021-64369181 ext. 56428

Oversight

Data monitoring committee
No
FDA-regulated drug
No
FDA-regulated device
No
View the source record on ClinicalTrials.gov ↗

Not currently enrolling

This study is not yet recruiting, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.

Follow this study

Get an email when the registry record changes — status, dates, results — or when someone posts here.

Sign in to follow

Discussion

Questions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.

Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.

Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.

Start the discussion