What is the clinical evidence from this study?

Study design: Meta-Analysis. Population: Coronary artery disease (n=73023). Intervention: SPECT imaging-based machine learning models vs. Conventional logistic regression and total perfusion deficit models. Primary outcome: Sensitivity for predicting major adverse cardiovascular events (MACE) (Sensitivity 83.1%, 95% CI 78.6-87.6).

November 26, 2024EJNMMI Research16 citationsOpen Access

Machine learning for prognostic prediction in coronary artery disease with SPECT data: a systematic review and meta-analysis

VÇVedat ÇiçekCardiac Imaging ECEzgi Hasret Kozan CikirikciKoç University MBMert BabaoğluÜsküdar University

Key Result

SPECT imaging-based machine learning models demonstrated a pooled sensitivity of 83.1% and specificity of 89.4% for predicting major adverse cardiovascular events in patients with coronary artery disease.

Study Design

Type

Meta-Analysis (n=73,023)

Structured PICO

Does machine learning-based analysis of SPECT images improve prognostic prediction of major adverse cardiovascular events and all-cause mortality in patients with coronary artery disease compared to traditional models?

Population

73,023 patients with coronary artery disease from 12 retrospective studies evaluating the prognostic performance of SPECT-based machine learning models.

Intervention

Machine learning (ML)-based analysis of SPECT images (with or without integration of demographic data)

Comparator

Traditional logistic regression (LR) models and total perfusion deficit

Outcome

Prognostic prediction of major adverse cardiovascular events and all-cause mortalityhard clinical

Machine learning models applied to SPECT imaging, particularly when integrated with demographic data, demonstrate superior prognostic capabilities for MACE and mortality in CAD patients compared to traditional models.

Main Result

Effect estimate: Sensitivity 83.1% (95% CI 78.6-87.6)

Limitations

Heterogeneity of ML/DL applications and techniques across the included studies
Small number of studies appraising particular outcomes or utilizing specific ML/DL techniques
Variability in TPD calculation methods due to use of both rest and stress SPECT images
Lack of a standardized benchmark for evaluating model performance across studies

Abstract

BACKGROUND: Single-photon emission computed tomography (SPECT) analysis relies on qualitative visual assessment or semi-quantitative measures like total perfusion deficit that play a critical role in the non-invasive diagnosis of coronary artery disease by assessing regional blood flow abnormalities. Recently, machine learning (ML) -based analysis of SPECT images for coronary artery disease diagnosis has shown promise, with its utility in predicting long-term patient outcomes (prognosis) remaining an active area of investigation. In this review, we comprehensively examine the current landscape of ML-based analysis of SPECT imaging with an emphasis on prognostication of coronary artery disease. MAIN BODY: Our systematic search yielded twelve retrospective studies, investigating SPECT-based ML models for prognostic prediction in coronary artery disease patients, with a total sample size of 73,023 individuals. Several of these studies demonstrate the superior prognostic capabilities of ML models over traditional logistic regression (LR) models and total perfusion deficit, especially when incorporating demographic data alongside SPECT imaging. Meta-analysis of 6 studies revealed promising performance of the included ML models, with sensitivity and specificity exceeding 65% for major adverse cardiovascular events and all-cause mortality. Notably, the integration of demographic information with SPECT imaging in ML frameworks shows statistically significant improvements in prognostic performance. CONCLUSION: Our review suggests that ML models either independently or in combination with demographic data enhance prognostic prediction in coronary artery disease.

问 AI

Bookmark

View Full Paper