ThinkSono System for Deep Vein Thrombosis

(DVT GUARD Trial)

Recruiting at 3 trial locations

Overseen By Fouad Al Noor

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: ThinkSono, Ltd.

Disqualifiers: Consent not given, Incomplete scan, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Approved in 1 Jurisdiction This treatment is already approved in other countries

Compensation: Varies

Number of Visits: Unknown

500 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the ThinkSono Guidance System treatment for deep vein thrombosis?

The ThinkSono Guidance System uses a deep learning approach to help non-specialists diagnose deep vein thrombosis (DVT) using ultrasound images. In a study, this method showed high accuracy, with a sensitivity (ability to correctly identify those with the condition) of up to 94% and a negative predictive value (likelihood that those identified as not having the condition truly don't have it) of up to 100%, making it a promising tool for diagnosing DVT. ^{1 2 3 4 5}

How does the ThinkSono Guidance System treatment for deep vein thrombosis differ from other treatments?

The ThinkSono Guidance System is unique because it uses machine learning to help non-specialists diagnose deep vein thrombosis (DVT) at the point of care by interpreting ultrasound images, potentially reducing the need for specialist referrals and long waiting times. ^{5 6 7 8 9}

What is the purpose of this trial?

The purpose of this study is to confirm the safety and efficacy of the ThinkSono Guidance System, 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 diagnose 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. The ThinkSono Guidance System 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.

Research Team

Glenn Jacobowitz, MD

Principal Investigator

Northwell Health

Eligibility Criteria

This trial is for individuals who may have blood clots in their veins, such as those with pulmonary embolism or deep vein thrombosis. It's open to patients where healthcare professionals suspect a clot and need an ultrasound diagnosis. Specific eligibility criteria are not provided, but typically include adults who consent to participate.

Inclusion Criteria

The diagnostic DVT algorithm indicates that an ultrasound is needed

The participant is willing to provide written informed consent to participate in this research

I am over 18 years old.

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

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Data Collection

Participants undergo ultrasound scans using the ThinkSono system and a comparison standard of care duplex ultrasound scan

8 months

Multiple visits as required for data collection

Follow-up

Participants are monitored for safety and effectiveness after data collection

4 weeks

Treatment Details

Interventions

• ThinkSono Guidance System

Trial Overview The ThinkSono System, a mobile app designed to guide healthcare providers through conducting ultrasounds for blood clot detection at the point of care, is being tested for its safety and effectiveness compared to traditional methods.

Participant Groups

Group I: Comparison Arm Experimental Treatment 1 Intervention

This arm of patients will undergo an ultrasound scan using the ThinkSono system and a comparison standard of care duplex ultrasound scan.

ThinkSono Guidance System is already approved in European Union for the following indications:

Approved in European Union as ThinkSono Guidance for:

• Detection of deep vein thrombosis (DVT)

Who Is Running the Clinical Trial?

ThinkSono, Ltd.

Lead Sponsor

Trials

1

Recruited

500+

NYU Langone Health

Collaborator

Trials

1,431

Recruited

838,000+

Temple Health

Collaborator

Trials

1

Recruited

500+

Allegheny Health Network

Collaborator

Trials

6

Recruited

1,100+

Allegheny Health Network

Collaborator

Trials

7

Recruited

1,700+

Findings from Research

Paper-based clinical decision support systems (CDSS) improved venous thromboembolism (VTE) prophylaxis rates, but their impact on actual VTE rates was not clearly established, indicating potential for further improvement.

Computer-based CDSS significantly enhanced the prescribing of appropriate prophylaxis and reduced VTE events, especially in medical patients, suggesting they are more effective than paper-based systems, although some hospitals may lack the necessary technology resources.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Clinical decision support systems to improve utilization of thromboprophylaxis: a review of the literature and experience with implementation of a computerized physician order entry program. Adams, P., Riggio, JM., Thomson, L., et al.[2012]

A survey of 15 hospitals in North West England revealed significant variability in the management of deep vein thrombosis (DVT), with some hospitals lacking any formal protocols or guidelines.

Only 36.4% of hospitals could arrange ultrasound imaging within four hours for suspected DVT cases, highlighting the need for a national program to standardize and improve DVT management practices across the NHS.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The early management of DVT in the North West of England: A nation-wide problem? Khanbhai, M., Hansrani, V., Burke, J., et al.[2015]

The implementation of practice guidelines for managing deep vein thrombosis in a Problem-Oriented Patient Management System led to more appropriate treatment suggestions compared to the decisions made by attending physicians.

A retrospective evaluation showed that the guideline-generated suggestions were significantly more appropriate than the management decisions of the physicians, indicating the potential effectiveness of using structured guidelines in clinical practice.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Implementation and evaluation of practice guidelines. Lam, SH.[2018]

Implementing a combination of a computer-based clinical decision support system and training seminars significantly increased the use of appropriate VTE prophylaxis from 46.2% to 57.9% among hospitalized patients, indicating improved adherence to guidelines.

The most notable improvements were seen in high-risk groups, such as cancer patients (from 18.1% to 44.1%) and patients with three or more risk factors (from 25.0% to 42.9%), highlighting the effectiveness of the intervention in protecting those who need it most.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A clinical decision support system for venous thromboembolism prophylaxis at a general hospital in a middle-income country. Fuzinatto, F., Waldemar, FS., Wajner, A., et al.[2021]

A deep learning algorithm trained on ultrasound videos from 255 volunteers demonstrated high sensitivity (82-94%) and excellent negative predictive value (99-100%) for detecting deep vein thrombosis (DVT), making it a promising tool for non-specialists in point-of-care settings.

Integrating this automated DVT diagnostic approach into clinical pathways could provide significant cost benefits, with a positive net monetary benefit projected for software-supported examinations costing between £72 to £175.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. Kainz, B., Heinrich, MP., Makropoulos, A., et al.[2023]

A wearable device combining electromyography (EMG) and accelerometer sensors can accurately classify human activity states, achieving over 95% accuracy in distinguishing between 'positive' (active) and 'negative' (inactive) states that affect blood flow in the legs.

The addition of the EMG sensor enhances the ability to differentiate between similar activity states, such as standing and sitting, by 30%, which is important for assessing the risk of developing Deep Vein Thrombosis (DVT).

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Activity Segmentation Using Wearable Sensors for DVT/PE Risk Detection. Gentry, A., Mongan, WM., Lee, B., et al.[2021]

Gradient recalled echo magnetic resonance imaging (MRI) demonstrated high accuracy in diagnosing deep venous thrombosis (DVT), with a sensitivity of 97%, specificity of 95%, and overall accuracy of 96% based on a study of 199 patients.

When considering cases with normal MRI results as true normals, the sensitivity, specificity, and accuracy improved to 97%, 98%, and 97%, respectively, indicating that this imaging technique is a reliable method for detecting acute DVT.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Detection of deep venous thrombosis by magnetic resonance imaging. Spritzer, CE., Norconk, JJ., Sostman, HD., et al.[2022]

In a study involving 141 complete observations of patients suspected of having deep vein thrombosis (DVT), the D-Dimer test showed a sensitivity range of 82% to 97%, indicating it is effective at identifying potential DVT cases.

However, the combination of the D-Dimer test with a clinical model did not enhance diagnostic accuracy, and none of the tests could definitively exclude DVT, highlighting the need for further evaluation methods.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

[D-Dimer determination combined with clinical probability for the diagnosis of leg venous thrombosis]. Arrivé, L., Monnier-Cholley, L., Serru, V., et al.[2014]

The study demonstrated that using an AI algorithm to analyze ultrasound images for diagnosing iliac vein compression syndrome (IVCS) resulted in higher treatment effectiveness compared to standard ultrasound imaging, with significant improvements in patient outcomes such as reduced venous swelling and increased pain relief (p < 0.005).

The AI imaging model showed superior performance in detecting and recognizing lower extremity vein lesions, with better precision and accuracy than traditional methods, indicating its potential as a reliable diagnostic tool for clinicians.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Effect of Interventional Therapy on Iliac Venous Compression Syndrome Evaluated and Diagnosed by Artificial Intelligence Algorithm-Based Ultrasound Images. Bai, Y., Bo, F., Ma, W., et al.[2022]

References

1. England pubmed.ncbi.nlm.nih.gov

Clinical decision support systems to improve utilization of thromboprophylaxis: a review of the literature and experience with implementation of a computerized physician order entry program. [2012]

2. United States pubmed.ncbi.nlm.nih.gov

The early management of DVT in the North West of England: A nation-wide problem? [2015]

3. United States pubmed.ncbi.nlm.nih.gov

Implementation and evaluation of practice guidelines. [2018]

4. Brazil pubmed.ncbi.nlm.nih.gov

A clinical decision support system for venous thromboembolism prophylaxis at a general hospital in a middle-income country. [2021]

5. England pubmed.ncbi.nlm.nih.gov

Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning. [2023]

6. United States pubmed.ncbi.nlm.nih.gov

Activity Segmentation Using Wearable Sensors for DVT/PE Risk Detection. [2021]

7. United States pubmed.ncbi.nlm.nih.gov

Detection of deep venous thrombosis by magnetic resonance imaging. [2022]

8. France pubmed.ncbi.nlm.nih.gov

[D-Dimer determination combined with clinical probability for the diagnosis of leg venous thrombosis]. [2014]

9. England pubmed.ncbi.nlm.nih.gov

Effect of Interventional Therapy on Iliac Venous Compression Syndrome Evaluated and Diagnosed by Artificial Intelligence Algorithm-Based Ultrasound Images. [2022]