Determining the Validity of ThinkSono Guidance for Ultrasound Image Acquisition and Remote Detection (DVT GUARD)

The purpose of this study is to confirm the safety and efficacy of ThinkSono Guidance, a software data collection and communication tool designed to collect ultrasound data to help detect blood clots in veins. The ThinkSono system is CE Mark approved in the European Union and in clinical use in Europe. Usually, when an ultrasound is conducted to detect blood clots in veins, a sonographer (trained technologist who conducts ultrasounds) and/or radiologist will conduct the procedure, including a compression ultrasound exam, and the scan may require a bulky cart and ultrasound equipment. ThinkSono Guidance is a mobile software application that enables other healthcare professionals such as nurses, non-radiologist physicians including general practitioners, and other allied healthcare professionals to perform the ultrasound at the point of care using guidance from the software app. This is a multi-site non-randomized, double-blinded, prospective cohort pivotal study.

Study Overview

• Status: Completed
• Conditions: Deep Vein Thrombosis; Deep Vein Thrombosis, Pulmonary Embolus
• Intervention / Treatment: Device: ThinkSono System

Detailed Description

Deep vein thrombosis (DVT) is well recognized to cause significant morbidity and mortality both at the time of diagnosis and post-diagnosis. With an estimated incidence of 1- 2 per 1,000 people, over to 300,000 people in the US will be diagnosed with venous thromboembolism (VTE) per annum and two-thirds of these will be DVT. However, positive cases only represent 12-25% of the total number of patients who present with suspected DVT. In other words, between 75-88% of suspected DVT cases, when fully investigated, are negative. Estimates have placed the yearly cost of VTE to the US healthcare system at up to $10 billion.

It is notoriously difficult to diagnose a DVT by clinical acumen alone. The standard approach to making a diagnosis of proximal DVT currently involves an algorithm combining pre-test probability assessment through the Wells score, and compression ultrasonography. Handheld ultrasound probes have recently become available. These probes have enabled 'app-based' compression ultrasonography to be performed without the need for bulky cart or laptop-based ultrasound machines. These new machines have a small form factor, meaning only the ultrasound probe is required for diagnostic purposes in conjunction with a smartphone or tablet.

At present, although the new handheld probes are smaller and are better suited for point of care diagnosis, they still require an experienced radiologist or sonographer to perform the compression exam. This means that these devices can only be used wherever sonographers/radiologists are based most often i.e. hospital radiology departments. However, due to recent advances in "machine learning", software is now being developed for these 'app-based' probes that can assist non-radiology specialist healthcare professionals (e.g. nurses, non-radiologist physicians, general practitioners and other allied healthcare professionals) to carry out the compression ultrasound exam with minimal training.

ThinkSono Guidance is a guidance software expected to help non-radiology specialist healthcare professionals produce compression ultrasound image data that meet or exceed the minimal image quality criteria for a remote diagnosis by an expert (e.g. radiologist). The ThinkSono system is CE Mark approved in the European Union and in clinical use in Europe.

This study is a multi-site non-randomized, double-blinded, prospective cohort pivotal study. The purpose of this study is to confirm the safety and efficacy of ThinkSono Guidance as per the intended use defined as:

ThinkSono Guidance is a guidance, data acquisition and communication tool that guides non-ultrasound-trained healthcare staff to collect point of care compression ultrasound data in the proximal deep venous system of the lower extremity for interpretation by qualified clinicians.

• Study Type: Interventional
• Enrollment (Actual): 634
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • New York
    • New York, New York, United States, 10016
      • NYU Langone Health
  • Pennsylvania
    • Philadelphia, Pennsylvania, United States, 19140
      • Temple Health
    • Pittsburgh, Pennsylvania, United States, 15212
      • Allegheny Health Network
  • Texas
    • San Antonio, Texas, United States, 78229
      • South Texas Veterans Health System
  • Wisconsin
    • Madison, Wisconsin, United States, 53792
      • University of Wisconsin-Madison

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• The participant is willing to provide written informed consent to participate in this research.
• The participant is over the age of 18
• The participant has symptoms suggestive of a deep venous thrombosis (DVT)
• The diagnostic DVT algorithm indicates that an ultrasound is needed

Exclusion Criteria:

• Patient consent not given or retracted during the study.
• Local imaging specialists fail to scan the patient or fail to produce a conclusive imaging diagnosis.
• Incomplete ThinkSono Guidance scan due to logistical or other issues such as pain, lack of patient cooperation, barriers such as a cast or other physical limitations.
• Pregnant women
• Patients who undergo a local imaging scan and initiation of new treatment for DVT (e.g. lytic agents, therapeutic anticoagulation, or intervention after the local imaging scan) before a ThinkSono scan can be performed.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Other: Single Arm; This arm of patients will undergo an ultrasound scan using the ThinkSono system and a comparison standard of care duplex ultrasound scan.	Device: ThinkSono System; The ThinkSono Guidance System is a guidance software expected to help non-radiology specialist healthcare professionals produce compression ultrasound image data that meet or exceed the minimal image quality criteria for a remote diagnosis by an expert (e.g. radiologist).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Image Quality Adequacy	ThinkSono Guidance achieves adequate image quality with an American College of Emergency Physicians (ACEP) score equal to or greater than 3 in at least 60% of scans to show that non-ultrasound-trained operators can acquire relevant cine-loops (an expectation ≥75%, lower CI ≥60%). The ACEP score is a score on a scale of 1-5 assessing utilized as the national standard for image quality evaluation. Further information is available at: https://www.acep.org/siteassets/uploads/uploaded-files/acep/clinical-and-practice-management/policy-statements/information-papers/emergency-ultrasound-standard-reporting-guidelines---2018.pdf.	Measured during ThinkSono Guidance scanning (median scan time of 5.4 minutes).
Triage Sensitivity	The sensitivity for overall triage performance for proximal DVT is at least 85%.	Measured during ThinkSono Guidance scanning (median scan time of 5.4 minutes).
Triage Specificity	The specificity for overall triage performance for proximal DVT is at least 30%.	Measured during ThinkSono Guidance scanning (median scan time of 5.4 minutes).
Prioritization Specificity	Prioritization specificity quantifies how reliably the system identifies patients who merit high-urgency imaging specialist assessment based on their ThinkSono scans. A high prioritization specificity means that there are very few false-positive scans that lead to patients being prioritized unnecessarily. Further details are available in the trial protocol and statistical analysis plan. ThinkSono Guidance achieves specificity for prioritizing patients of at least 93%. This means that at least 93% of scans without proximal lower extremity DVT were not labeled as false positives by reviewers of ThinkSono Guidance scans.	Measured during ThinkSono Guidance scanning (median scan time of 5.4 minutes).

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Predictive Values	To observe the negative-predictive-value and positive-predictive-value of ThinkSono Guidance triage performance.	Measured during ThinkSono Guidance scanning (median scan time of 5.4 minutes).

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Serial Ultrasound Sensitivity	Clinical practice guidelines for proximal compression ultrasound recommend a repeat scan within a week if the initial scan is negative, in order to identify any progression of initially undetectable thrombi. Repeat scans were unfeasible and not clinically indicated for subjects in this study, and this outcome measure was simulated. Further details are available in the trial protocol and statistical analysis plan. This figure represents the estimated sensitivity of a repeated ThinkSono Guidance scan for lower extremity proximal DVT 1 week after the initial scan, as per clinical guidelines.	Measured at the time of ThinkSono Guidance scanning, during scan review by qualified clinicians, and during simulation of serial ultrasound scanning.

Collaborators and Investigators

• Sponsor: ThinkSono, Ltd.
• Collaborators: NYU Langone Health; University of Wisconsin, Madison; Allegheny Health Network; South Texas Veterans Health Care System; Temple Health
• Investigators: Principal Investigator: Glenn Jacobowitz, MD, Northwell Health

Publications and helpful links

General Publications

• Prandoni P, Kahn SR. Post-thrombotic syndrome: prevalence, prognostication and need for progress. Br J Haematol. 2009 May;145(3):286-95. doi: 10.1111/j.1365-2141.2009.07601.x. Epub 2009 Feb 13.
• Poulikidis KP, Gasparis AP, Labropoulos N. Prospective analysis of incidence, extent and chronicity of lower extremity venous thrombosis. Phlebology. 2014 Feb;29(1):37-42. doi: 10.1258/phleb.2012.012086. Epub 2013 May 6.
• Grosse SD, Nelson RE, Nyarko KA, Richardson LC, Raskob GE. The economic burden of incident venous thromboembolism in the United States: A review of estimated attributable healthcare costs. Thromb Res. 2016 Jan;137:3-10. doi: 10.1016/j.thromres.2015.11.033. Epub 2015 Nov 24.
• Roberts LN, Patel RK, Donaldson N, Bonner L, Arya R. Post-thrombotic syndrome is an independent determinant of health-related quality of life following both first proximal and distal deep vein thrombosis. Haematologica. 2014 Mar;99(3):e41-3. doi: 10.3324/haematol.2013.089870. Epub 2014 Jan 17. No abstract available.
• Kainz B, Heinrich MP, Makropoulos A, Oppenheimer J, Mandegaran R, Sankar S, Deane C, Mischkewitz S, Al-Noor F, Rawdin AC, Ruttloff A, Stevenson MD, Klein-Weigel P, Curry N. Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. NPJ Digit Med. 2021 Sep 15;4(1):137. doi: 10.1038/s41746-021-00503-7.
• Oppenheimer J, Mandegaran R, Staabs F, Adler A, Singohl S, Kainz B, Heinrich M, Geroulakos G, Spiliopoulos S, Avgerinos E. Remote Expert DVT Triaging of Novice-User Compression Sonography with AI-Guidance. Ann Vasc Surg. 2024 Feb;99:272-279. doi: 10.1016/j.avsg.2023.08.022. Epub 2023 Oct 10.
• Nothnagel K, Aslam MF. Evaluating the benefits of machine learning for diagnosing deep vein thrombosis compared with gold standard ultrasound: a feasibility study. BJGP Open. 2025 Jan 2;8(4):BJGPO.2024.0057. doi: 10.3399/BJGPO.2024.0057. Print 2024 Dec.
• Kearon C, Julian JA, Newman TE, Ginsberg JS. Noninvasive diagnosis of deep venous thrombosis. McMaster Diagnostic Imaging Practice Guidelines Initiative. Ann Intern Med. 1998 Apr 15;128(8):663-77. doi: 10.7326/0003-4819-128-8-199804150-00011.

Helpful Links

• Study sponsor website

Study record dates

Study Major Dates

• Study Start (Actual): November 8, 2023
• Primary Completion (Actual): December 8, 2025
• Study Completion (Actual): December 8, 2025

Study Registration Dates

• First Submitted: October 12, 2024
• First Submitted That Met QC Criteria: October 19, 2024
• First Posted (Actual): October 22, 2024

Study Record Updates

• Last Update Posted (Actual): March 25, 2026
• Last Update Submitted That Met QC Criteria: March 5, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Keywords: Ultrasound; Deep vein thrombosis; Artificial intelligence; Machine learning
• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Respiratory Tract Diseases; Lung Diseases; Embolism and Thrombosis; Embolism; Thrombosis; Pulmonary Embolism; Venous Thrombosis
• Other Study ID Numbers: 012023

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No