PB1489 - Clinician and informaticist perceptions on the potential for artificial intelligence to improve venous thromboembolism management

Tuesday, June 27, 2023

18:30 – 19:30 ET

Room: Exhibition

Presenting Author(s)

Barbara Lam, MD

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

Co-Author(s)

LD

Laura Dodge

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

Siddhant Datta

Hospitalist
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
Rachel Rosovsky, MD, MPH

Hematologist, Associate Professor of Medicine
Massachusetts General Hospital and Harvard Medical School
Newton, 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
NR

Nimia Reyes

Medical Officer
Centers for Disease Control and Prevention
Atlanta, Georgia, United States
AA

Alys Adamski

Epidemiologist
Division of Blood Disorders, National Center on Birth Defects and Developmental Disabilities, Centers for Disease Control and Prevention
Atlanta, Georgia, United States
KA

Karon Abe

Branch Chief
Centers for Disease Control and Prevention
Atlanta, Georgia, United States
SP

Samuel Panoff

Research Assistant
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
SZ

Sabrina Zerbey

Research Assistant
Beth Israel Deaconess Medical Center
Boston, Massachusetts, United States
PE

Pavania Elavalakanar

Research Coordinator
Division of Hematology and Hematologic Malignancies, Beth Israel Deaconess Medical Center, Boston, MA
Boston, Massachusetts, United States
IV

Ioannis Vlachos

Assistant Professor
Beth Israel Deaconess Medical Center
boston, Massachusetts, United States
Jeffrey I. Zwicker, MD

Chief of the Hematology Service
Department of Medicine, Hematology Service, Memorial Sloan Kettering Cancer Center, New York City, NY
New York, New York, United States
Rushad Patell, MD (he/him/his)

Assistant Professor of Medicine
Beth Israel Deaconess Medical Center, Boston, MA, USA
Boston, Massachusetts, United States

Background: Venous thromboembolism (VTE) is a leading cause of morbidity and mortality globally. The complexity of managing these patients makes artificial intelligence (AI) a promising potential solution. While there are AI tools being developed for VTE management, attitudes towards the use of AI in this area are unknown.

Aims: Explore clinician and informaticist views on the use of AI for VTE management.

Methods: We conducted two national surveys of 1) clinicians and 2) informaticists. Participants were recruited through social media, professional organizations, and program directors across the United States (US). We summarized data as proportions with 95% confidence intervals (CI).

Results: Of 607 respondents to the clinician survey, 70% were < 40 years of age, 56% female, and 68.2% white. Physicians made up 71% of respondents, of which 47% were trainees. Most respondents (70.1%, 95% CI: 66.6-73.6) believed that AI probably or definitely can help with VTE prophylaxis. The three most common concerns were: lack of transparency (30%), readiness for clinical use (30%), and accuracy (27%) (Table 1).
Of 101 respondents to the informaticist survey, 55% were ≥40 years of age, 38% female, and 70% white. The majority reported being sufficiently or very well informed (91%) about AI. Most agreed AI can be used to manage VTE (56%, 95% CI: 46.3-65.6). The three most commonly perceived barriers were: a lack of transparency (54%), clinician reluctance (39%), and liability concerns (28%) (Table 2).

Conclusion(s): The majority of clinicians and informaticists believe that AI can help with VTE management. Informaticists were concerned that clinicians would not want to use AI for VTE management, but a majority of clinicians agreed that AI would be helpful. Both groups reported that their biggest concern is lack of transparency. Results from these surveys can be used to address key barriers prior to deployment of AI in healthcare.