AI-Based Prediction Model for Iliofemoral DVT Thrombolysis

Imaging-based Prediction of Stent-free Pharmaco-mechanical Thrombolysis in Patients With Extensive Acute Ilio-femoral Deep Vein Thrombosis

This prospective single-arm cohort study aims to develop an AI-powered prediction model for treatment outcomes in patients with acute extensive iliofemoral deep vein thrombosis (IF-DVT) undergoing stent-free pharmacomechanical thrombolysis. The study addresses the current lack of validated tools for patient selection and outcome prediction in catheter-directed interventions for proximal DVT.

Thirty consecutive adult patients with MRV-confirmed acute IF-DVT will undergo pharmacomechanical thrombolysis using the AngioJet ZelanteDVT system with adjunctive rtPA administration.

The primary objective is to develop a convolutional neural network (CNN) trained on serial MRV imaging data to predict three-month venous recanalization success. MRV acquisitions occur at baseline, predischarge, and three-month follow-up. Ground truth segmentation will be performed by an experienced radiologist using 3D Slicer, with semi-automated propagation across the dataset. Feature extraction will include geometric metrics, radiomic texture analysis, and morphological characteristics of both thrombus and vessel architecture.

Secondary endpoints include acute kidney injury incidence (a significant concern with rheolytic thrombectomy due to hemolysis-induced nephrotoxicity), post-thrombotic syndrome development assessed via Villalta scoring, and various safety outcomes including major bleeding per ISTH criteria.

The study protocol incorporates rigorous monitoring for AKI using KDIGO criteria, with systematic evaluation of renal function, hemolysis markers, and electrolyte balance. Hydration protocols and nephroprotective measures will be standardized, though specific strategies require clarification from the nephrology team.

This research addresses critical gaps in evidence-based patient selection for invasive DVT treatment, particularly following the mixed results of the ATTRACT trial. The AI prediction model could enable personalized treatment decisions, potentially improving the risk-benefit ratio of pharmacomechanical interventions while reducing unnecessary procedures in patients unlikely to benefit.

Study Overview

• Status: Active, not recruiting
• Conditions: Deep Vein Thrombosis of the Lower Extremities
• Intervention / Treatment: Device: Rheolytic thrombectomy

• Study Type: Observational
• Enrollment (Actual): 30

Contacts and Locations

Study Locations

• Iran
  • Tehran Province
    • Tehran, Tehran Province, Iran, 1995614331
      • Rajaie Cardiovascular Medical and Research Institute

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

The study population will be drawn from adult patients aged 18 years and older of both sexes presenting to the Rajaie Cardiovascular Medical and Research Institute, a tertiary referral cardiovascular center in Tehran, Iran, with acute symptomatic iliofemoral deep vein thrombosis.

Description

Inclusion Criteria:

• All consecutive adult (≥18 years) patients with an MRV-based diagnosis of acute IF- DVT
• Symptomatic patients with severe pain and\or leg swelling more than 5 cm
• Willing to participate in the study

Exclusion Criteria:

• Previous history of VTE
• Presence of DVT syndrome for more than 21 days
• Terminal systemic disease requiring palliative treatment
• Active bleeding
• History of hemorrhagic stroke
• Major fibrinolytic contraindication
• Any hereditary coagulopathy disorders
• Patients with baseline renal dysfunction with an estimated glomerular filtration rate (eGFR) of < 60 ml/min/1.73m2 due to Cockroft-Gault formula based on the creatinine level at the time of admission
• Having any underlying condition that makes the patient unsuitable for MRV and/or rheolytic thrombectomy procedure (e.g., allergy to contrast agent, claustrophobia)
• Having any underlying disabling condition that necessitates a prolonged complete bed rest prohibiting early ambulation
• Low-quality MRV imaging or motion artifact (exclusion criteria for the imaging sub-studies)

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Extensive iliofemoral DVT; Patients with extensive ioliofemoral DVT candidate for pharmaco-mechanical thrombectomy	Device: Rheolytic thrombectomy; Rheolytic thrombectomy via AngioJet ZelanteDVTTM Catheter (Boston Scientific Co., USA).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
During the procedure	The extent of venous recanalization after stent-free pharmacomechanical thrombolysis as assessed by magnetic resonance venography at three months post-procedure. Recanalization will be graded as: Grade 0 (no flow/complete occlusion), Grade 1 (minimal flow with ≤25% lumen patency), Grade 2 (partial flow with 26-75% patency), or Grade 3 (near-complete flow with >75% patency). Treatment success is defined as achieving Grade 2 or 3 recanalization.	3 months post-procedure

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
MRV-based Predischarge Venous Recanalization	The extent of venous recanalization in the acute phase after stent-free pharmacomechanical thrombolysis as measured by magnetic resonance venography, classified as complete (>90% clearance), nearly complete (50-90% clearance), or partial (<50% resolution)	At hospital discharge (typically 3-7 days post-procedure)
At hospital discharge (typically 3-7 days post-procedure)	Quantified thrombus volume reduction from baseline to three-month follow-up as measured by magnetic resonance venography, with meaningful reduction defined as ≥50% volume decrease	3 months post-procedure
MRV-based Predischarge Percentage Reduction in Thrombus Volume	Quantified thrombus volume reduction from baseline to hospital discharge as measured by magnetic resonance venography, with meaningful reduction defined as ≥50% volume decrease	At hospital discharge (typically 3-7 days post-procedure)
Postprocedural Acute Kidney Injury Occurrence	Development of acute kidney injury during hospitalization based on KDIGO criteria: ≥0.3 mg/dL increase in serum creatinine within 48 hours, ≥1.5x baseline creatinine increase, or urine output <0.5 mL/kg/h for 6 hours.	During index hospitalization (typically 3-7 days)
Need for New Renal Replacement Therapy	Requirement for initiation of any form of renal replacement therapy (hemodialysis, continuous veno-venous hemofiltration, peritoneal dialysis) due to acute kidney injury in patients without previous dialysis history.	During index hospitalization (typically 3-7 days)
Postprocedural Oliguria or Anuria	Development of oliguria (urine output <0.5 mL/kg/hour) or anuria (urine output <50 mL/day) during the index hospitalization period.	During index hospitalization (typically 3-7 days)
Postprocedural Hyperkalemia	Elevated serum potassium concentration above normal limits (>5.0-5.5 mEq/L) during the index hospitalization period.	During index hospitalization (typically 3-7 days)
Postprocedural Gross Hematuria	Presence of visible blood in urine detected by visual inspection or urine testing during the index hospitalization period.	During index hospitalization (typically 3-7 days)
Major Bleeding Events	Major bleeding according to International Society of Thrombosis and Haemostasis (ISTH) definition: fatal bleeding, bleeding in critical organs, or bleeding causing ≥2.0 g/dL hemoglobin decrease or requiring ≥2 units red blood cell transfusion.	During index hospitalization (typically 3-7 days)
Three-month Recurrent Venous Thromboembolism	Objectively confirmed recurrent symptomatic venous thromboembolism (deep vein thrombosis or pulmonary embolism) during the three-month follow-up period.	3 months post-procedure
Three-month Post-thrombotic Syndrome Incidence	Development of post-thrombotic syndrome defined as Villalta score ≥5, assessed through standardized evaluation of symptoms (pain, cramps, heaviness, paresthesia, pruritus) and clinical signs (edema, induration, hyperpigmentation, redness, venous ectasia, calf pain on compression).	3 months post-procedure
Three-month Post-thrombotic Syndrome Severity	Severity classification of post-thrombotic syndrome using Villalta score: mild (5-9), moderate (10-14), or severe (≥15 or venous ulceration).	3 months post-procedure
In-hospital All-cause Mortality	Death from any cause during the index hospitalization period.	During index hospitalization (typically 3-7 days)
Three-month All-cause Mortality	Death from any cause during the three-month follow-up period.	3 months post-procedure
Technical Success Rate	Successful placement of the AngioJet device catheter and initiation of the thrombectomy procedure as intended per protocol.	During the procedure

Collaborators and Investigators

• Sponsor: Rajaie Cardiovascular Medical and Research Center

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2024
• Primary Completion (Estimated): October 1, 2025
• Study Completion (Estimated): October 1, 2025

Study Registration Dates

• First Submitted: September 12, 2025
• First Submitted That Met QC Criteria: September 12, 2025
• First Posted (Estimated): September 18, 2025

Study Record Updates

• Last Update Posted (Estimated): September 18, 2025
• Last Update Submitted That Met QC Criteria: September 12, 2025
• Last Verified: September 1, 2025

More Information

Terms related to this study

• Keywords: Deep vein thrombosis; Acute kidney injury; Prediction model; Pharmacomechanical thrombolysis; Iliofemoral vein; Magnetic resonance venography
• Additional Relevant MeSH Terms: Urogenital Diseases; Vascular Diseases; Cardiovascular Diseases; Male Urogenital Diseases; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Embolism and Thrombosis; Renal Insufficiency; Thrombosis; Venous Thrombosis; Acute Kidney Injury
• Other Study ID Numbers: IR.RHC.REC.1403.013

Drug and device information, study documents

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