Major adverse events associated with inducible cardiac ischemia during treadmill exercise testing for peripheral artery disease

Characteristics of ulcerated and non‐ulcerated necrobiosis lipoidica

BACKGROUND

Necrobiosis lipoidica (NL) is complicated by ulceration in up to 35% of cases.

METHODS

Retrospective study of patients with NL seen at our institution between January 1, 1992, and May 25, 2021, was conducted. Ulcerated NL (UNL, n = 83) and non-ulcerated NL (NUNL, n = 233) groups were compared.

RESULTS

Twenty-six percent (83/316) of patients with NL experienced ulceration. UNL was significantly more likely to be painful (52% vs. 36%, P = 0.01), was more likely to have a lesion-associated cutaneous malignancy (7% vs. 0%, P < 0.001), and had a larger median size (7 vs. 5 cm, P = 0.004) compared to NUNL. Vascular studies were performed on a subset of patients and revealed transcutaneous oxygen pressure (TcPO2) < 40 mm Hg in 53% and venous insufficiency in 62% with no significant differences between UNL and NUNL groups. In patients with unilateral ulceration, mean TcPO2 values (39.7 vs. 46.6 mm Hg), regional perfusion index <0.6 (29% vs. 14%), and TcPO2 < 40 mm Hg (43% vs. 14%) were worse in the ulcerated leg compared to the non-ulcerated leg, but these differences were not statistically significant.

CONCLUSIONS

UNL was more likely to be painful, develop lesion-associated malignancy, and be larger in size compared to NUNL. There were no statistically significant differences in venous insufficiency, arterial Doppler/ankle brachial index, or TcPO2 values between UNL and NUNL patients, however, a significant portion of the cohort demonstrated abnormal vascular studies, particularly on TcPO2 and venous insufficiency testing.

Artificial intelligence for the evaluation of peripheral artery disease using arterial Doppler waveforms to predict abnormal ankle-brachial index

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 (4/1/2015 - 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.