Artificial intelligence guidance systems for ultrasound may reduce the need for specialized ultrasound exams

ISRCTN	ISRCTN31827847
DOI	https://doi.org/10.1186/ISRCTN31827847
ClinicalTrials.gov (NCT)	Nil known
Clinical Trials Information System (CTIS)	Nil known
Protocol serial number	Nil known
Sponsor	ThinkSono GmbH
Funder	ThinkSono GmbH

Submission date: 08/11/2025
Registration date: 15/11/2025
Last edited: 14/11/2025

Recruitment status: No longer recruiting
Overall study status: Completed
Condition category: Circulatory System

Prospectively registered

Protocol

Statistical analysis plan

Results

Individual participant data

Plain English summary of protocol

Background and study aims
Deep vein thrombosis (DVT) is a term that describes blood clots (thrombi) that can form in the deep veins. The deep leg veins are commonly affected (such as the proximal veins: the femoral vein or the popliteal vein) or the deep veins of the pelvis. The standard approach to making a diagnosis involves an algorithm combining pre-test probability, a blood test called the D-dimer test, and the patient undergoing an ultrasound of the leg veins. Ultrasound is currently completed by a trained expert (e.g. sonographer or radiologist).

However, handheld ultrasound probes have recently become available and they have enabled ‘app-based’ ultrasonography to be performed. ThinkSono has developed a system (ThinkSono Guidance) allowing non-specialists to perform DVT ultrasound. Prior studies have established the effectiveness of this system. This study seeks to evaluate its real world clinical use in the emergency department.

Who can participate?
Patients aged 18 years and over, coming for a check to see if they have a DVT and have symptoms suggesting that they need an ultrasound scan

What does the study involve?
Participants undergo a compression ultrasound scan by a non-ultrasound trained staff member (e.g a nurse) using Thinksono Guidance, as well as a D-dimer blood test.

What are the possible benefits and risks of participating?
This study may allow participants to avoid waiting time for a sonographer-performed duplex ultrasound assessment. The results from this study will also improve knowledge of how Thinksono Guidance may be implemented to help detect blood clots accurately and quickly.
Ultrasound is a very safe method of confirming a DVT or not, and is already used as standard care in hospitals. There are no additional risks of taking part.

Where is the study run from?
Attikon University Hospital (Greece)

When is the study starting and how long is it expected to run for?
April 2021 to May 2022

Who is funding the study?
ThinkSono GmbH (Germany)

Who is the main contact?
Sven Mischkewitz, hello@thinksono.com

Contact information

Dr Giancarlo Speranza
Public, Scientific

August-Bebel-Straße 88
Potsdam
14482
Germany

Phone	+49 1724754848
Email	hello@thinksono.com

Dr Efthymios Avgerinos
Principal investigator

Rimini, Chaidari
Athens
124 62
Greece

Phone	+30 21 0583 1000
Email	hello@thinksono.com

Study information

Primary study design	Interventional
Study design	Single-center non-randomized prospective trial
Secondary study design	Non randomised study
Scientific title	Novel artificial intelligence guided non-expert compression ultrasound deep vein thrombosis diagnostic pathway may reduce vascular laboratory venous testing
Study objectives	ThinkSono Guidance is an artificial intelligence (AI) based software previously shown to aid non-experts without venous duplex ultrasound training in acquiring valid ultrasound images of venous compressions at the point of care that can be reviewed and interpreted by remote qualified clinicians. The present pilot study sought to evaluate its real world clinical use in the emergency department, sparing the need for sonographer-performed venous duplex ultrasound and potentially reducing patient waiting times.
Ethics approval(s)	Approved 07/04/2021, Attikon University Hospital Institutional Review Board (Rimini, Chaidari, Athens, 124 62, Greece; +30 21 0583 1000; politis@attikonhospital.gr), ref: C24/07-04-2021
Health condition(s) or problem(s) studied	Deep vein thrombosis (DVT)
Intervention	Patients with suspected DVT underwent an AI-guided proximal DVT compression examination by non-ultrasound-trained providers using ThinkSono Guidance and D-dimer testing. All patients assessed as compressible on ultrasound with negative D dimers were discharged. All other patients were sent for a venous duplex scan.
Intervention type	Device
Phase	Not Applicable
Drug / device / biological / vaccine name(s)	Thinksono Guidance
Primary outcome measure(s)	Thinksono Guidance image quality was measured using the American College of Emergency Physicians (ACEP) scale at the time of review
Key secondary outcome measure(s)	1. Sensitivity of AI-guided scans to detect proximal deep vein thrombosis (DVT) compared to duplex ultrasound, D dimer levels, or follow up, as appropriate, at the time of evaluation 2. Specificity of AI-guided scans to detect proximal DVT compared to duplex ultrasound, D dimer levels, or follow up, as appropriate, at the time of evaluation 3. Negative Predictive Value (NPV) of AI-guided scans to detect proximal DVT compared to duplex ultrasound, D dimer levels, or follow up, as appropriate, at the time of evaluation 4. Positive Predictive Value (PPV) of AI-guided scans to detect proximal DVT compared to duplex ultrasound, D dimer levels, or follow up, as appropriate, at the time of evaluation 5. Proportion of patients discharged without the need for a duplex ultrasound scan (DUS), recorded from patient records at the time of discharge 6. Time to diagnosis, defined as the duration from initiation of the AI-guided scan to completion of on-call radiologist review, recorded from patient records during the analysis phase of the study
Completion date	07/05/2022

Eligibility

Participant type(s)	Patient
Age group	Adult
Sex	All
Target sample size at registration	50
Total final enrolment	53
Key inclusion criteria	Patients suspected of having DVT
Key exclusion criteria	1. Patient withdrawal of consent 2. Incomplete scans
Date of first enrolment	10/05/2021
Date of final enrolment	05/05/2022

Locations

Countries of recruitment

Greece

Study participating centre

Attikon University Hospital

Rimini, Chaidari
Athens
124 62
Greece

Results and Publications

Individual participant data (IPD) Intention to share	Yes
IPD sharing plan summary	Available on request
IPD sharing plan	The anonymized ultrasound datasets generated during and/or analysed during the current study may be shared if a request is made to hello@thinksono.com. A statement about the use of the data must be made.

Study outputs

Output type	Details	Date created	Date added	Peer reviewed?	Patient-facing?
Results article		14/05/2025	10/11/2025	Yes	No

Editorial Notes

14/11/2025: Study's existence confirmed by the Scientific Council Bioethics Committee Aegean Region University General
Hospital.