Swanson, Keith E

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.

Abstract Background The objective of this study was to characterize clinical features and outcomes among patients with calf deep vein thrombosis (DVT) limited to the muscular veins compared with axial veins. Methods Consecutive patients with ultrasound confirmed acute DVT involving the calf veins (January 1, 2016–August 1, 2018) were identified from the Gonda Vascular Center ultrasound database. Patients were divided into axial or muscular groups based on thrombus location. Demographics, management, and outcomes were compared. Results Over the study period, there were 647 patients with calf DVT equally distributed between axial (n = 321) and muscular (n = 326) locations. Within these groups, peroneal and soleal veins were most commonly involved. Nearly all cases were provoked (97%). Synchronous pulmonary embolism (PE) were more common for axial (30.8%) compared to muscular groups (20.2%; p = 0.001); nearly one-third had no pulmonary symptoms. Anticoagulation for a median of 3 months was initiated for 85.5% of both groups. Venous thromboembolism (VTE) recurrence was more common in the axial group (15.9% vs. 7.1%, p = 0.0015) including more frequent DVT propagation (9.4% vs. 3.1%; p = 0.0017) and PE (3.4% vs. 0.6%; p = 0.0168). Major bleeding, clinically relevant nonmajor bleeding, and mortality rates did not differ between groups. Withholding anticoagulation led to more frequent thrombus propagation in the axial group (3.4% vs. 0.9%; p = 0.029). Conclusion Several important features distinguish muscular from axial DVT. Axial DVT are more likely to have an associated PE and are more likely to experience recurrent VTE, particularly if anticoagulation is withheld.