A Fast Algorithm for Maximal Propensity Score Matching

Prognostication of Outcomes in Spontaneous Intracerebral Hemorrhage: A Propensity Score-Matched Analysis with Support Vector Machine

OBJECTIVE

The role of surgery in spontaneous intracerebral hemorrhage (SICH) remains controversial. We aimed to use explainable machine learning (ML) combined with propensity-score matching to investigate the effects of surgery and identify subgroups of patients with SICH who may benefit from surgery in an interpretable fashion.

METHODS

We conducted a retrospective study of a cohort of 282 patients aged ≥21 years with SICH. ML models were developed to separately predict for surgery and surgical evacuation. SHapley Additive exPlanations (SHAP) values were calculated to interpret the predictions made by ML models. Propensity-score matching was performed to estimate the effect of surgery and surgical evacuation on 90-day poor functional outcomes (PFO).

RESULTS

Ninety-two patients (32.6%) underwent surgery, and 57 patients (20.2%) underwent surgical evacuation. A total of 177 patients (62.8%) had 90-day PFO. The support vector machine achieved a c-statistic of 0.915 when predicting 90-day PFO for patients who underwent surgery and a c-statistic of 0.981 for patients who underwent surgical evacuation. The SHAP scores for the top 5 features were Glasgow Coma Scale score (0.367), age (0.214), volume of hematoma (0.258), location of hematoma (0.195), and ventricular extension (0.164). Surgery, but not surgical evacuation of the hematoma, was significantly associated with improved mortality at 90-day follow-up (odds ratio, 0.26; 95% confidence interval, 0.10-0.67; P = 0.006).

CONCLUSIONS

Explainable ML approaches could elucidate how ML models predict outcomes in SICH and identify subgroups of patients who respond to surgery. Future research in SICH should focus on an explainable ML-based approach that can identify subgroups of patients who may benefit functionally from surgical intervention.

Bypass Versus Interwoven Nitinol Stents for Long Femoro-Popliteal Occlusions: A Propensity Matched Analysis

PURPOSE

To compare femoro-popliteal bypass and interwoven nitinol stenting for long occlusions of the femoro-popliteal segment.

MATERIALS AND METHODS

Single center retrospective propensity matching analysis of the symptomatic patients with long occlusion of the femoro-popliteal segment (> 20 cm), who underwent stenting with interwoven nitinol stent or femoro-popliteal bypass from 2012 to 2020.

PRIMARY ENDPOINTS

primary patency, primary-assisted patency, secondary patency. Secondary endpoints: major adverse cardiovascular events, major adverse limb events, primary sustained clinical improvement, survival.

RESULTS

A total of 437 patients were enrolled: 294 in the bypass group and 143 in the endovascular therapy (EVT) group. After propensity score matching, 264 and 113 patients remained in the groups, respectively. A median occlusion length was 250 mm. One-year and two-year primary and secondary patency rates were comparable in both groups (two-year primary patency: 68.5% for bypass vs. 68.9% for EVT, p = 1.00). In the "above the knee" subgroup analysis, two-year secondary patency was higher in the EVT group than in the bypass group (90.9% vs. 77.5%, p = 0.048). In "below-the-knee" subgroup analysis, primary and primary assisted patency were statistically significantly higher in the EVT group than in artificial bypass subgroup (66.7% vs. 42.4%, p = .046 and 76.7% vs. 45.5%, p = .011, respectively). However, compared to autovenous bypass, the EVT group showed lower primary patency rates, although the differences are not significant.

CONCLUSION

A nonselective endovascular strategy can allow for regular successful treatment of femoro-popliteal lesions longer than 25 cm.

The effect of the stented iliac lesions TASC-II C, D on the femoropopliteal bypass patency: Propensity score-matched observational study

INTRODUCTION

Concurrent stenting of complex iliac lesions during infrainguinal bypasses can increase the complexity of a case and impact outcomes.

OBJECTIVE

Our aim was to evaluate the effect of inflow stenting of TASC-II C, D iliac lesions on femoropopliteal bypass patency.

METHODS

A retrospective observational cohort study of patients who underwent femoropopliteal bypass with TASC-II C, D iliac artery stenting (hybrid group) or without inflow lesions (non-hybrid group) was conducted. After propensity score matching, 120 patients were included in the non-hybrid group and 60 patients in the hybrid one. The median follow-up was 432 (193; 1313) days in the hybrid group and 472 (196; 1376) days in the non-hybrid group (p = 0.94).

RESULTS

No significant differences were found between the groups in 30-day morbidity and serious adverse events. At 3 years, primary and secondary bypass patency for the hybrid group and non-hybrid group were 62.2% versus 59.9% (p = 0.36) and 63.7% versus 64.3% (p = 0.077), respectively. The primary patency of the iliac stents in patients of the hybrid group was 95% at 3 years. The estimated hazard ratio for primary patency for hybrid versus non-hybrid was 0.77, with 90% CI: 0.50-1.21; the noninferiority upper bound being 1.31, which corresponds to a 10% additive noninferiority margin for probabilities. The 3 years of freedom from amputation in patients with chronic limb-threatening ischemia was 94.1% and 75.0% in the hybrid and non-hybrid groups, respectively (p = 0.09).

CONCLUSION

The outcomes of the femoropopliteal bypass in hybrid surgery supplemented with stenting of TASC-II C, D iliac lesions was similar to femoropopliteal bypass with intact inflow arteries.

Comparative Analysis of Carotid Artery Stenting and Carotid Endarterectomy in Clinical Practice

The objective of the study was to describe immediate and long-term results of carotid endarterectomy (CEA) versus carotid stenting (CAS) with embolic protection in patients with severe carotid artery stenosis in clinical practice.

MATERIALS AND METHODS

This is a retrospective cohort study, conducted between 2009 and 2017. During the analyzed period, 2132 operations (2006 patients) were performed: 1215 (57%) CEA and 917 (43%) CAS. 278 patients (13.8% of 2006) were not contactable during the follow-up period (>30 days) leaving 1791 cases (1728 patients) for inclusion in the analysis. Propensity score matching was used to compare the treatment results of groups (561 cases were matched out of 1791). The results of 615 CEA (316 eversion, 299 "classic" with patch) and 615 CAS (using a variety of carotid stents) were compared.

RESULTS

In the asymptomatic subgroup (n = 455), the 30-day rate of stroke was not significantly different between the CEA group and the CAS group (1.5% versus 2.4%, P = .48). The 5-year rate of stroke was not significantly higher for CAS than for CEA (4.6% versus 3.3%, P = .3). In the symptomatic subgroup (n = 160), the 30-day rate of stroke was significantly higher in the CAS group than in the CEA group (7.5% versus 2.5%, P = .04). The 5-year rate of stroke was 13% for CAS and 8.7% for CEA (P = .2).

CONCLUSIONS

In the symptomatic subgroup, the 30-day rate of stroke was significantly higher in the CAS group than in the CEA group, therefore the use of CAS for symptomatic patients in routine practice should be limited. Our study demonstrates that the rates of stroke and survival after CEA and CAS in patients aged 80 years or younger with asymptomatic or symptomatic severe carotid stenosis did not differ significantly over a period of 5 years.