A Machine Learning Approach for Predicting Early Phase Postoperative Hypertension in Patients Undergoing Carotid Endarterectomy

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Shapely additive values can effectively visualize pertinent covariates in machine learning when predicting hypertension

Machine learning methods are widely used within the medical field to enhance prediction. However, little is known about the reliability and efficacy of these models to predict long-term medical outcomes such as blood pressure using lifestyle factors, such as diet. The authors assessed whether machine-learning techniques could accurately predict hypertension risk using nutritional information. A cross-sectional study using data from the National Health and Nutrition Examination Survey (NHANES) between January 2017 and March 2020. XGBoost was used as the machine-learning model of choice in this study due to its increased performance relative to other common methods within medical studies. Model prediction metrics (e.g., AUROC, Balanced Accuracy) were used to measure overall model efficacy, covariate Gain statistics (percentage each covariate contributes to the overall prediction) and SHapely Additive exPlanations (SHAP, method to visualize each covariate) were used to provide explanations to machine-learning output and increase the transparency of this otherwise cryptic method. Of a total of 9650 eligible patients, the mean age was 41.02 (SD = 22.16), 4792 (50%) males, 4858 (50%) female, 3407 (35%) White patients, 2567 (27%) Black patients, 2108 (22%) Hispanic patients, and 981 (10%) Asian patients. From evaluation of model gain statistics, age was found to be the single strongest predictor of hypertension, with a gain of 53.1%. Additionally, demographic factors such as poverty and Black race were also strong predictors of hypertension, with gain of 4.33% and 4.18%, respectively. Nutritional Covariates contributed 37% to the overall prediction: Sodium, Caffeine, Potassium, and Alcohol intake being significantly represented within the model. Machine Learning can be used to predict hypertension.

Using machine learning to predict outcomes following carotid endarterectomy

OBJECTIVE

Prediction of outcomes following carotid endarterectomy (CEA) remains challenging, with a lack of standardized tools to guide perioperative management. We used machine learning (ML) to develop automated algorithms that predict outcomes following CEA.

METHODS

The Vascular Quality Initiative (VQI) database was used to identify patients who underwent CEA between 2003 and 2022. We identified 71 potential predictor variables (features) from the index hospitalization (43 preoperative [demographic/clinical], 21 intraoperative [procedural], and 7 postoperative [in-hospital complications]). The primary outcome was stroke or death at 1 year following CEA. Our data were split into training (70%) and test (30%) sets. Using 10-fold cross-validation, we trained six ML models using preoperative features (Extreme Gradient Boosting [XGBoost], random forest, Naïve Bayes classifier, support vector machine, artificial neural network, and logistic regression). The primary model evaluation metric was area under the receiver operating characteristic curve (AUROC). After selecting the best performing algorithm, additional models were built using intra- and postoperative data. Model robustness was evaluated using calibration plots and Brier scores. Performance was assessed on subgroups based on age, sex, race, ethnicity, insurance status, symptom status, and urgency of surgery.

RESULTS

Overall, 166,369 patients underwent CEA during the study period. In total, 7749 patients (4.7%) had the primary outcome of stroke or death at 1 year. Patients with an outcome were older with more comorbidities, had poorer functional status, and demonstrated higher risk anatomic features. They were also more likely to undergo intraoperative surgical re-exploration and have in-hospital complications. Our best performing prediction model at the preoperative stage was XGBoost, achieving an AUROC of 0.90 (95% confidence interval [CI], 0.89-0.91). In comparison, logistic regression had an AUROC of 0.65 (95% CI, 0.63-0.67), and existing tools in the literature demonstrate AUROCs ranging from 0.58 to 0.74. Our XGBoost models maintained excellent performance at the intra- and postoperative stages, with AUROCs of 0.90 (95% CI, 0.89-0.91) and 0.94 (95% CI, 0.93-0.95), respectively. Calibration plots showed good agreement between predicted and observed event probabilities with Brier scores of 0.15 (preoperative), 0.14 (intraoperative), and 0.11 (postoperative). Of the top 10 predictors, eight were preoperative features, including comorbidities, functional status, and previous procedures. Model performance remained robust on all subgroup analyses.

CONCLUSIONS

We developed ML models that accurately predict outcomes following CEA. Our algorithms perform better than logistic regression and existing tools, and therefore, have potential for important utility in guiding perioperative risk mitigation strategies to prevent adverse outcomes.

Analysis of the anatomic eligibility for transcarotid artery revascularization in Chinese patients who underwent carotid endarterectomy and transfemoral carotid artery stenting

Objective

Transcarotid artery revascularization (TCAR) is thought to be a promising technique and instrument for treating carotid stenosis with favorable outcomes. Since there remain several differences in anatomic characteristics among races, this study was conducted to investigate the anatomic eligibility of TCAR in Chinese patients who underwent carotid revascularization.

Methods

A retrospective review of patients with carotid stenosis from 2019 to 2021 was conducted. The anatomic eligibility of TCAR was based on the instruction of the ENROUTE Transcarotid Neuroprotection System. The carotid artery characteristics and configuration of the circle of Willis (CoW) were evaluated by CT angiography. The demographic and clinical characteristics and procedure-related complications were recorded. Logistic regression was used to analyze the independent factors for TCAR eligibility.

Results

Of 289 consecutive patients [222 for carotid endarterectomy (CEA) and 67 for transfemoral carotid artery stenting (TF-CAS)] identified, a total of 215 patients (74.4%) met TCAR anatomic eligibility. Specifically, 83.7% had mild common carotid artery (CCA) puncture site plaque, 95.2% had 4-9 mm internal carotid artery diameters, 95.8% had >6 mm CCA diameter, and 98.3% had >5 cm clavicle to carotid bifurcation distance. Those who were female (OR, 5.967; 95% CI: 2.545-13.987; P < 0.001), were of an older age (OR, 1.226; 95% CI: 1.157-1.299; P < 0.001), and higher body mass index (OR, 1.462; 95% CI: 1.260-1.697; P < 0.001) were prone to be associated with TCAR ineligibility. In addition, 71 patients with TCAR eligibility (33.0%) were found to combine with incomplete CoW. A high risk for CEA was found in 29 patients (17.3%) with TCAR eligibility, and a high risk for TF-CAS was noted in nine patients (19.1%) with TCAR eligibility. Overall, cranial nerve injury (CNI) was found in 22 patients after CEA, while 19 of them (11.3%) met TCAR eligibility.

Conclusion

A significant proportion of Chinese patients meet the anatomic criteria of TCAR, making TCAR a feasible treatment option in China. Anatomic and some demographic factors play key roles in TCAR eligibility. Further analysis indicates a potential reduction of procedure-related complications in patients with high-risk carotid stenosis under the TCAR procedure.

Independent role of circle of Willis for peri-procedural evaluation of carotid endarterectomy in patients with severe carotid stenosis

OBJECTIVES

In patients with severe carotid stenosis (CS), collateral circulation via circle of Willis (CoW) is considered a compensatory response to maintain blood flow. The aim of this study was to evaluate the impact of CoW in patients with severe CS throughout carotid endarterectomy (CEA).

METHODS

A database of patients (n = 124) undergoing CEA was sampled from 2013 to 2020. Severe CS was defined as 90-99% caliber stenosis and collateral circulation was identified by CoW opening. Baseline characteristics, Age-related white matter change (ARWMC) score, immediate neurologic events (INEs) and manifestations were recorded and compared. Correlation and regression analysis for CoW were further investigated.

RESULTS

All patients enrolled were divided into two groups regarding to the visualized CoW opening and complete CoW was noticed in 57 patients. The prevalence of complete CoW was higher among asymptomatic patients (n = 39, 68.4%), while higher percentage of TIA or previous stroke were noticed in incomplete CoW (n = 45, 67.2%). Patients with incomplete CoW had a significantly higher median ARWMC score and remarkable cerebral perfusion deficit (P < 0.05*). Totally, 4 INEs (6.0%) were noted in patients with incomplete CoW after CEA. Cerebral hyperperfusion syndrome (CHS) was noticed in 10 patients and early-phase of postoperative hypertension (EPOH) in 15 ones with incomplete CoW versus patients with complete CoW (14.9% and 22.4% vs 3.5% and 7.0%, P < 0.05). Correlation analysis showed strong relationship between CoW opening and peri-operative factors like pre-operative symptoms, ARWMC, CHS and EPOH (P < 0.05*). Overall, CoW opening was an independent predictor of both CHS and EPOH (95% CI, 0.021-0.715 and 0.060-0.949, P < 0.05*) with logistic regression.

CONCLUSIONS

Sufficient collateral circulation via CoW may promote ipsilateral cerebral perfusion and mitigate WMC in patients with severe CS. In addition, collaterals may improve the predictive power of the risk scale for post-procedural complications after CEA.