Predicting Major Adverse Cardiovascular Events Following Carotid Endarterectomy Using Machine Learning

Predicting Outcomes Following Lower Extremity Endovascular Revascularization Using Machine Learning

BACKGROUND

Lower extremity endovascular revascularization for peripheral artery disease carries nonnegligible perioperative risks; however, outcome prediction tools remain limited. Using machine learning, we developed automated algorithms that predict 30-day outcomes following lower extremity endovascular revascularization.

METHODS AND RESULTS

The National Surgical Quality Improvement Program targeted vascular database was used to identify patients who underwent lower extremity endovascular revascularization (angioplasty, stent, or atherectomy) for peripheral artery disease between 2011 and 2021. Input features included 38 preoperative demographic/clinical variables. The primary outcome was 30-day postprocedural major adverse limb event (composite of major reintervention, untreated loss of patency, or major amputation) or death. Data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, 6 machine learning models were trained using preoperative features. The primary model evaluation metric was area under the receiver operating characteristic curve. Overall, 21 886 patients were included, and 30-day major adverse limb event/death occurred in 1964 (9.0%) individuals. The best performing model for predicting 30-day major adverse limb event/death was extreme gradient boosting, achieving an area under the receiver operating characteristic curve of 0.93 (95% CI, 0.92-0.94). In comparison, logistic regression had an area under the receiver operating characteristic curve of 0.72 (95% CI, 0.70-0.74). The calibration plot showed good agreement between predicted and observed event probabilities with a Brier score of 0.09. The top 3 predictive features in our algorithm were (1) chronic limb-threatening ischemia, (2) tibial intervention, and (3) congestive heart failure.

CONCLUSIONS

Our machine learning models accurately predict 30-day outcomes following lower extremity endovascular revascularization using preoperative data with good discrimination and calibration. Prospective validation is warranted to assess for generalizability and external validity.

Hospital and long-term results of carotid endarterectomy in patients with different severity of coronary artery lesion according to syntax score

AIM

Analysis of in-hospital and long-term results of carotid endarterectomy (CEE) in patients with different severity of coronary atherosclerosis.

MATERIAL AND METHODS

This comparative, retrospective, open study for the period from January 2013 to April 2020 included 1719 patients operated on for occlusive-stenotic lesions of the internal carotid arteries (ICA). Classical and eversion CEA were used as revascularization strategies. The criteria for inclusion in the study were: 1. Presence of coronary angiography within six months before the present CEE; 2. A history of myocardial revascularization in patients with severe coronary lesions. Depending on the severity of coronary atherosclerosis, all patients were divided into 3 groups: Group 1-871 (50.7 %) patients - with the presence of hemodynamically significant stenosis of the coronary arteries (CA) with a history of myocardial revascularization; Group 2-496 (28.8 %) patients - with the presence of hemodynamically insignificant lesions of the coronary artery (up to 70 %, not inclusive, and the trunk of the left coronary artery, up to 50 %, not inclusive); Group 3-352 (20.5 %) patients - without signs of atherosclerotic lesions of the coronary artery. In group 1, the observation period was 56.8±23.2 months, in group 2-62.0±15.6 months, in group 3-58.1±20.4 months.

RESULTS

During the hospital observation period, there were no significant intergroup differences in the number of complications. All cardiovascular events were detected in isolated cases. The most common injury was damage to the cranial nerves, diagnosed in every fifth patient in the total sample. The combined endpoint (CET), including death + myocardial infarction (MI) + acute cerebrovascular accident/transient ischemic attack (stroke/TIA), was 0.75 % (n=13). In the long-term follow-up period, when comparing survival curves, group 3 revealed the largest number of ischemic strokes (p = 0.007), myocardial infarction (p = 0.03), and CCT (p = 0.005). There were no intergroup differences in the number of deaths (p=0.62).

CONCLUSION

The results of the study showed that there was no significant intergroup difference in the development of complications at the hospital postoperative stage. However, in the long-term follow-up period, a group of patients with isolated lesions of the ICA demonstrated a rapid increase in the number of MI, stroke/TIA, and a combined endpoint, which was apparently associated with low compliance and progression of atherosclerosis in previously unaffected arteries.