OC 60.5 - Artificial Intelligence in the Prediction of Venous Thromboembolism: A Systematic Review and Pooled Analysis

Tuesday, July 12, 2022

3:45 PM – 4:00 PM

Location: ExCel Center, ICC Auditorium

Presentation Format: In-Person

Presenting Author(s)

Thita Chiasakul, MD

Physician
King Chulalongkorn Memorial Hospital
Arlington, Virginia, United States

Co-Author(s)

Barbara Lam, MD

Fellow
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
WR

William Robertson

Program Director
National Blood Clot Alliance
Philadelphia, Pennsylvania, United States
LL

Leslie Lake

President
National Blood Clot Alliance
Philadelphia, Pennsylvania, United States
RR

Rachel P. Rosovsky

Associate Professor
Massachusetts General Hospital
Boston, Massachusetts, United States
IV

Ioannis Vlachos

Assistant Professor
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
JZ

Jeffrey Zwicker, MD

Chief, Benign Hematology
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
RP

Rushad Patell, MD

Assistant Professor of Medicine
Division of Hematology and Hematologic Malignancies, Beth Israel Deaconess Medical Center, Boston, MA
Boston, Massachusetts, United States

Background: Accurate diagnostic and prognostic predictions of venous thromboembolism (VTE) are crucial for VTE management. Artificial intelligence (AI) enables autonomous identification of the most predictive patterns from large complex data. Evidence regarding its performance in VTE prediction are emerging. Systematic reviews of current evidence are lacking.

Aims: To systematically review the performance of AI in the diagnosis and prediction of VTE and compare it to clinical risk assessment models (RAMs) or logistic regression models.

Methods: A systematic literature search was performed using PubMed, MEDLINE, EMBASE, and Web of Science from inception to April 20, 2021. Search terms included ‘artificial intelligence’ and ‘venous thromboembolism’. Eligible criteria were original studies evaluating AI in the prediction of VTE in adults and reporting one of the following outcomes: sensitivity, specificity, positive predictive value, negative predictive value, area under receiver operating curve (AUC), or c-statistic. Studies assessing Natural Language Processing (NLP) accuracy to detect VTE from radiological reports or medical records were excluded. Risks of bias were assessed using the PROBAST tool. Unpaired t-test was performed to compare the mean AUC from AI versus conventional methods (RAMs or logistic regression models).

Results: A total of 20 studies were included (Fig. 1). Numbers of participants ranged from 31 to 111,888. The AI methods included machine learning (11 studies), artificial neural network (4 studies), NLP (2 studies), support vector machines (1 study), Bayesian methods (1 study), and genetic programming (1 study). Twelve studies (60%) had both training and testing cohorts. Most studies had high risk of bias due to missing data handling and outcome determination. Among 14 studies where AUCs were reported, the mean AUC for AI vs. conventional methods were 0.79 (95%CI 0.74-0.85) vs. 0.61 (95%CI 0.54-0.68), respectively (P <.001) (Fig. 2).

Conclusion(s): The use of AI appears to improve the accuracy of diagnostic and prognostic prediction of VTE.