Track this trial free. DataLookout checks ClinicalTrials.gov daily and emails you which fields changed on NCT06957587 (status, enrollment, completion dates, endpoints, sites) when this record is updated. Free accounts track up to 5 trials.

Track this trial

A Deep Learning Model for Blood Volume Estimation From Multi-modal Ultrasound

StatusRecruiting
PhaseNot specified
Started
View on ClinicalTrials.gov ↗

Record History

  1. Trial status: Withdrawn to Recruiting Primary completion date: Dec 31, 2026 to Jul 31, 2027 · Enrollment target: 0 to 800 · Study sites: 1 to 2 · 3 morev6 Show 6 more changesShow less
    • Primary completion date: Dec 31, 2026 to Jul 31, 2027
    • Enrollment target: 0 to 800
    • Study sites: 1 to 2
    • Completion date: Dec 31, 2026 to Aug 31, 2027
    • Eligibility criteria expanded, about 3 words
    • Study title expanded, about 1 word

    See this version in full on ClinicalTrials.gov ↗

  2. Trial status: Recruiting to Withdrawn Sponsor's reason: The research protocol needs to be revised and resubmitted Enrollment target: estimated 254 to confirmed 0 · Start date: Jul 1, 2025 to Oct 1, 2025 · Study sites: 2 to 1v5 Show 3 more changesShow less
    • Enrollment target: estimated 254 to confirmed 0
    • Start date: Jul 1, 2025 to Oct 1, 2025
    • Study sites: 2 to 1
  3. Trial status: Not Yet Recruiting to Recruiting Enrollment target: 300 to 254 · Study sites: 1 to 2v4 Show 2 more changesShow less
    • Enrollment target: 300 to 254
    • Study sites: 1 to 2
  4. Start date: Jun 1, 2025 to Jul 1, 2025 Study sites: 0 to 1 · Primary completion date: Aug 31, 2026 to Dec 31, 2026v3 Show 2 more changesShow less
    • Study sites: 0 to 1
    • Primary completion date: Aug 31, 2026 to Dec 31, 2026
  5. Primary completion date: Dec 31, 2025 to Aug 31, 2026 Completion date: Dec 31, 2025 to Dec 31, 2026 · Eligibility criteria expanded, about 12 words · Study title shortened, about 2 wordsv2 Show 3 more changesShow less
    • Completion date: Dec 31, 2025 to Dec 31, 2026
    • Eligibility criteria expanded, about 12 words
    • Study title shortened, about 2 words

    See this version in full on ClinicalTrials.gov ↗

  6. Study First Submitted
  • Stopped: an ongoing trial was terminated, suspended or withdrawn.
  • Notable: the trial’s plan changed such as a big move in its timeline or size, a new primary endpoint, sponsor or phase, or recruiting opened or resumed.
  • Minor: routine progress and housekeeping, such as sites added or enrollment closed.
1. Background \& Rationale: Accurate assessment of a patient's blood volume (BV) status before surgery is critical for preventing perioperative complications. However, there is currently no clinically feasible, accurate, and non-invasive method for direct BV quantification. We hypothesize that dynamic ultrasound videos of major blood vessels contain rich, sub-visual spatiotemporal information about vascular compliance and filling that can be leveraged to estimate BV. 2. Objective: To develop and validate a deep learning model that integrates multi-modal ultrasound video data to achieve non-invasive, quantitative estimation of preoperative blood volume. 3. Study Design: A prospective, single-center, observational study. 4. Methods: Participants: Adult patients scheduled for surgery. Data Acquisition: Input (Features): Preoperative ultrasound video clips will be recorded in standardized views of four key vessels: the Internal Jugular Vein (IJV), Subclavian Vein (SCV), Inferior Vena Cava (IVC), and Common Carotid Artery (CA). Target (Label): The true Blood Volume (BV) will be calculated for each patient using the acute normovolemic hemodilution (ANH) method. The change in hemoglobin concentration before and after this process is used to calculate the total blood volume with high clinical reliability. Model Development: A hybrid deep learning architecture (e.g., CNN + LSTM/Transformer) will be trained to extract features from the ultrasound videos and learn the complex, non-linear mapping to the BV value derived from ANH. The model will be trained and internally validated using a k-fold cross-validation approach. 5. Expected Outcome \& Significance: We anticipate the development of a novel, end-to-end deep learning model capable of providing a quantitative BV estimate from routine ultrasound scans. This technology has the potential to revolutionize perioperative fluid management by offering a rapid, non-invasive, and accurate tool for objective volume status assessment, ultimately guiding personalized therapy and improving patient outcomes.
Trial Details
NCT Number NCT06957587
Lead Sponsor Shanghai 6th People's Hospital
Conditions Blood Volume Analysis, Ultrasound, Machine Learning
Enrollment 800 participants
Start Date
Primary Completion (estimated)
Study Completion (estimated)
Updated on ClinicalTrials.gov