The Construction of a Risk Prediction Model Based on Neural Network for Pre-operative Acute Ischemic Stroke in Acute Type A Aortic Dissection Patients

Risk prediction of preoperative acute ischemic stroke in acute type A aortic dissection

OBJECTIVES

To predict preoperative acute ischemic stroke (AIS) in acute type A aortic dissection (ATAAD).

METHODS

In this multi-center retrospective study, 508 consecutive patients diagnosed as ATAAD between April 2020 and March 2021 were considered for inclusion. The patients were divided into a development cohort and two validation cohorts based on time periods and centers. Clinical data and imaging findings obtained were analyzed. Univariable and multivariable logistic regression analyses were performed to identify predictors associated with preoperative AIS. The performance of resulting nomogram was evaluated in discrimination and calibration on all cohorts.

RESULTS

A total of 224 patients were in the development cohort, 94 in the temporal validation cohort, and 118 in the geographical validation cohort. Six predictors were identified: age, syncope, D-dimer, moderate to severe aortic valve insufficiency, diameter ratio of true lumen in ascending aorta  < 0.33, and common carotid artery dissection. The nomogram established showed good discrimination (area under the receiver operating characteristic curve [AUC], 0.803; 95% CI: 0.742, 0.864) and calibration (Hosmer-Lemeshow test p = 0.300) in the development cohort. External validation showed good discrimination and calibration abilities in both temporal (AUC, 0.778; 95% CI: 0.671, 0.885; Hosmer-Lemeshow test p = 0.161) and geographical cohort (AUC, 0.806; 95% CI: 0.717, 0.895; Hosmer-Lemeshow test p = 0.100).

CONCLUSIONS

A nomogram, based on simple imaging and clinical variables collected on admission, showed good discrimination and calibration abilities in predicting preoperative AIS for ATAAD patients.

KEY POINTS

• A nomogram based on simple imaging and clinical findings may predict preoperative acute ischemic stroke in patients with acute type A aortic dissection in emergencies. • The nomogram showed good discrimination and calibration abilities in validation cohorts.

Prediction of preoperative in-hospital mortality rate in patients with acute aortic dissection by machine learning: a two-centre, retrospective cohort study

OBJECTIVES

To conduct a comprehensive analysis of demographic information, medical history, and blood pressure (BP) and heart rate (HR) variability during hospitalisation so as to establish a predictive model for preoperative in-hospital mortality of patients with acute aortic dissection (AD) by using machine learning techniques.

DESIGN

Retrospective cohort study.

SETTING

Data were collected from the electronic records and the databases of Shanghai Ninth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine and the First Affiliated Hospital of Anhui Medical University between 2004 and 2018.

PARTICIPANTS

380 inpatients diagnosed with acute AD were included in the study.

PRIMARY OUTCOME

Preoperative in-hospital mortality rate.

RESULTS

A total of 55 patients (14.47%) died in the hospital before surgery. The results of the areas under the receiver operating characteristic curves, decision curve analysis and calibration curves indicated that the eXtreme Gradient Boosting (XGBoost) model had the highest accuracy and robustness. According to the SHapley Additive exPlanations analysis of the XGBoost model, Stanford type A, maximum aortic diameter >5.5 cm, high variability in HR, high variability in diastolic BP and involvement of the aortic arch had the greatest impact on the occurrence of in-hospital deaths before surgery. Moreover, the predictive model can accurately predict the preoperative in-hospital mortality rate at the individual level.

CONCLUSION

In the current study, we successfully constructed machine learning models to predict the preoperative in-hospital mortality of patients with acute AD, which can help identify high-risk patients and optimise the clinical decision-making. Further applications in clinical practice require the validation of these models using a large-sample, prospective database.

TRIAL REGISTRATION NUMBER

ChiCTR1900025818.

An Explainable Machine Learning Pipeline for Stroke Prediction on Imbalanced Data

Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients' class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.