Predicting outcomes in patients with aortic stenosis using machine learning: the Aortic Stenosis Risk (ASteRisk) score

Machine Learning Prediction for Prognosis of Patients With Aortic Stenosis

Background

Aortic valve stenosis of any degree is associated with poor outcomes.

Objectives

The authors aimed to develop a risk prediction model for aortic stenosis (AS) prognosis using machine learning techniques.

Methods

A prognostic algorithm was developed using an AS registry of 10,407 patients undergoing echocardiography between 2008 and 2020. Clinical, echocardiographic, laboratory, and medication data were used to train and test a time-to-event model, the random survival forest (RSF), for AS patient's prognosis. The composite outcome included aortic valve replacement or mortality. The SHapley Additive exPlanations method attributed the importance of variables and provided personalized risk assessment. The algorithm was validated in 2 external cohorts of 11,738 and 954 patients with AS.

Results

The median follow-up of the primary cohort was 48 (21-87) months. In this period, 1,116 patients underwent aortic valve replacement, and 5,069 patients died. RSF had an area under the curve (AUC) of 0.83 (95% CI: 0.80-0.86) and 0.83 (95% CI: 0.81-0.84) for outcomes prediction at 1 and 5 years, respectively. Using a cut-off of 50%, the RSF sensitivity and specificity for the composite outcome, were 0.80 and 0.73, respectively. Validation performance in the 2 external cohorts was similar, with AUCs of 0.73 (95% CI: 0.72-0.74) and 0.74 (95% CI: 0.72-0.76), respectively. AS severity, age, serum albumin, pulmonary artery pressure, and chronic kidney disease emerged as the top significant variables in the model.

Conclusions

In patients with AS, a machine learning algorithm predicts outcomes with good accuracy, and prognostic characteristics were identified. The model can potentially guide risk factor modification and clinical decisions to improve patient prognosis.

Artificial Intelligence in the Screening, Diagnosis, and Management of Aortic Stenosis

The integration of artificial intelligence (AI) into clinical management of aortic stenosis (AS) has redefined our approach to the assessment and management of this heterogenous valvular heart disease (VHD). While the large-scale early detection of valvular conditions is limited by socioeconomic constraints, AI offers a cost-effective alternative solution for screening by utilizing conventional tools, including electrocardiograms and community-level auscultations, thereby facilitating early detection, prevention, and treatment of AS. Furthermore, AI sheds light on the varied nature of AS, once considered a uniform condition, allowing for more nuanced, data-driven risk assessments and treatment plans. This presents an opportunity to re-evaluate the complexity of AS and to refine treatment using data-driven risk stratification beyond traditional guidelines. AI can be used to support treatment decisions including device selection, procedural techniques, and follow-up surveillance of transcatheter aortic valve replacement (TAVR) in a reproducible manner. While recognizing notable AI achievements, it is important to remember that AI applications in AS still require collaboration with human expertise due to potential limitations such as its susceptibility to bias, and the critical nature of healthcare. This synergy underpins our optimistic view of AI's promising role in the AS clinical pathway.

The Emerging Role of Artificial Intelligence in Valvular Heart Disease

Valvular heart disease (VHD) is a morbid condition in which timely identification and evidence-based treatments can lead to improved outcomes. Artificial intelligence broadly refers to the ability for computers to perform tasks and problem solve like the human mind. Studies applying AI to VHD have used a variety of structured (eg, sociodemographic, clinical) and unstructured (eg, electrocardiogram, phonocardiogram, and echocardiograms) and machine learning modeling approaches. Additional researches in diverse populations, including prospective clinical trials, are needed to evaluate the effectiveness and value of AI-enabled medical technologies in clinical care for patients with VHD.

Enhanced detection of severe aortic stenosis via artificial intelligence: a clinical cohort study

OBJECTIVE

We developed an artificial intelligence decision support algorithm (AI-DSA) that uses routine echocardiographic measurements to identify severe aortic stenosis (AS) phenotypes associated with high mortality.

METHODS

631 824 individuals with 1.08 million echocardiograms were randomly spilt into two groups. Data from 442 276 individuals (70%) entered a Mixture Density Network (MDN) model to train an AI-DSA to predict an aortic valve area <1 cm², excluding all left ventricular outflow tract velocity or dimension measurements and then using the remainder of echocardiographic measurement data. The optimal probability threshold for severe AS detection was identified at the f1 score probability of 0.235. An automated feature also ensured detection of guideline-defined severe AS. The AI-DSA's performance was independently evaluated in 184 301 (30%) individuals.

RESULTS

The area under receiver operating characteristic curve for the AI-DSA to detect severe AS was 0.986 (95% CI 0.985 to 0.987) with 4622/88 199 (5.2%) individuals (79.0±11.9 years, 52.4% women) categorised as 'high-probability' severe AS. Of these, 3566 (77.2%) met guideline-defined severe AS. Compared with the AI-derived low-probability AS group (19.2% mortality), the age-adjusted and sex-adjusted OR for actual 5-year mortality was 2.41 (95% CI 2.13 to 2.73) in the high probability AS group (67.9% mortality)-5-year mortality being slightly higher in those with guideline-defined severe AS (69.1% vs 64.4%; age-adjusted and sex-adjusted OR 1.26 (95% CI 1.04 to 1.53), p=0.021).

CONCLUSIONS

An AI-DSA can identify the echocardiographic measurement characteristics of AS associated with poor survival (with not all cases guideline defined). Deployment of this tool in routine clinical practice could improve expedited identification of severe AS cases and more timely referral for therapy.

Machine learning prediction of progressive subclinical myocardial dysfunction in moderate aortic stenosis

Background

Moderate severity aortic stenosis (AS) is poorly understood, is associated with subclinical myocardial dysfunction, and can lead to adverse outcome rates that are comparable to severe AS. Factors associated with progressive myocardial dysfunction in moderate AS are not well described. Artificial neural networks (ANNs) can identify patterns, inform clinical risk, and identify features of importance in clinical datasets.

Methods

We conducted ANN analyses on longitudinal echocardiographic data collected from 66 individuals with moderate AS who underwent serial echocardiography at our institution. Image phenotyping involved left ventricular global longitudinal strain (GLS) and valve stenosis severity (including energetics) analysis. ANNs were constructed using two multilayer perceptron models. The first model was developed to predict change in GLS from baseline echocardiography alone and the second to predict change in GLS using data from baseline and serial echocardiography. ANNs used a single hidden layer architecture and a 70%:30% training/testing split.

Results

Over a median follow-up interval of 1.3 years, change in GLS (≤ or >median change) could be predicted with accuracy rates of 95% in training and 93% in testing using ANN with inputs from baseline echocardiogram data alone (AUC: 0.997). The four most important predictive baseline features (reported as normalized % importance relative to most important feature) were peak gradient (100%), energy loss (93%), GLS (80%), and DI < 0.25 (50%). When a further model was run including inputs from both baseline and serial echocardiography (AUC 0.844), the top four features of importance were change in dimensionless index between index and follow-up studies (100%), baseline peak gradient (79%), baseline energy loss (72%), and baseline GLS (63%).

Conclusions

Artificial neural networks can predict progressive subclinical myocardial dysfunction with high accuracy in moderate AS and identify features of importance. Key features associated with classifying progression in subclinical myocardial dysfunction included peak gradient, dimensionless index, GLS, and hydraulic load (energy loss), suggesting that these features should be closely evaluated and monitored in AS.