TY - JOUR
T1 - Artificial intelligence for the evaluation of peripheral artery disease using arterial Doppler waveforms to predict abnormal ankle-brachial index
AU - McBane, Robert D.
AU - Murphree, Dennis H.
AU - Liedl, David
AU - Lopez-Jimenez, Francisco
AU - Attia, Itzhak Zachi
AU - Arruda-Olson, Adelaide
AU - Scott, Christopher G.
AU - Prodduturi, Naresh
AU - Nowakowski, Steve E.
AU - Rooke, Thom W.
AU - Casanegra, Ana I.
AU - Wysokinski, Waldemar E.
AU - Swanson, Keith E.
AU - Houghton, Damon E.
AU - Bjarnason, Haraldur
AU - Wennberg, Paul W.
N1 - Publisher Copyright:
© The Author(s) 2022.
PY - 2022/8
Y1 - 2022/8
N2 - Background: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. Methods: Consecutive patients (4/8/2015 – 12/31/2020) undergoing rest and postexercise ankle–brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 – 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. Results: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92–0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91–0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). Conclusion: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.
AB - Background: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. Methods: Consecutive patients (4/8/2015 – 12/31/2020) undergoing rest and postexercise ankle–brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 – 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. Results: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92–0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91–0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). Conclusion: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.
KW - Doppler waveforms
KW - ankle-brachial index (ABI)
KW - artificial intelligence
KW - exercise testing
KW - peripheral artery disease (PAD)
UR - http://www.scopus.com/inward/record.url?scp=85130221007&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130221007&partnerID=8YFLogxK
U2 - 10.1177/1358863X221094082
DO - 10.1177/1358863X221094082
M3 - Article
C2 - 35535982
AN - SCOPUS:85130221007
SN - 1358-863X
VL - 27
SP - 333
EP - 342
JO - Vascular Medicine (United Kingdom)
JF - Vascular Medicine (United Kingdom)
IS - 4
ER -