Publications by authors named "Mathews B Fish"
The Registry of Fast Myocardial Perfusion Imaging with Next-Generation SPECT (REFINE SPECT) has been expanded to include more patients and CT attenuation correction imaging. We present the design and initial results from the updated registry. The updated REFINE SPECT is a multicenter, international registry with clinical data and image files.
View Article and Find Full Text PDFArticle Synopsis
- Myocardial perfusion imaging (MPI) is widely used to diagnose coronary artery disease, but many patients have normal results; this study explores whether machine learning can identify unique patient profiles among those with normal scans and assess their risk of death or myocardial infarction.
- The research involved a large cohort of over 21,000 patients from an international MPI registry, employing unsupervised clustering to discover four distinct patient phenotypes, revealing differing characteristics and stress testing requirements among them.
- Findings indicated that one specific cluster of patients (Cluster 4), despite having normal scans, faced a significantly higher risk of serious cardiovascular events, suggesting that identifying these phenotypes could enhance risk assessment and patient management.
Article Synopsis
- A new explainable deep learning model has been developed to predict specific cardiovascular risks (like death, acute coronary syndrome, and need for revascularization) based on myocardial perfusion imaging (MPI) combined with clinical data.
- The model was tested with a large group of patients and showed better performance in predicting short-term risks in the first six months post-scan, outperforming traditional methods.
- It provides individualized risk assessments and visual explanations for patients, potentially helping to focus on modifiable risk factors and improve shared decision-making in healthcare.
Article Synopsis
- The study aimed to use unsupervised machine learning to classify patients with known coronary artery disease (CAD) based on their risk profiles during SPECT myocardial perfusion imaging.
- Out of 37,298 patients in the REFINE SPECT registry, 9,221 with CAD were analyzed, identifying three distinct clusters that varied in clinical characteristics, particularly concerning body mass index, diabetes, and hypertension.
- The cluster analysis provided superior risk stratification for all-cause mortality compared to traditional methods based on stress total perfusion deficit, indicating its potential for enhancing patient management in CAD.
Direct Risk Assessment From Myocardial Perfusion Imaging Using Explainable Deep Learning.
JACC Cardiovasc Imaging
February 2023
Article Synopsis
- Myocardial perfusion imaging (MPI) is commonly used to assess heart disease risk, but there is a need for better predictive methods, which led to the creation of the HARD MACE-DL model.
- This deep learning model was developed to predict the risk of death or nonfatal myocardial infarction by analyzing various cardiac metrics alongside patient demographics from over 29,000 subjects across several medical centers.
- The HARD MACE-DL model demonstrated superior accuracy in predicting cardiac events compared to traditional methods, achieving a higher prognostic accuracy and excellent calibration in both internal and external validation tests.
Article Synopsis
- AI models are effective at diagnosing coronary artery disease (CAD) but can overestimate disease risk due to biased training on high-risk populations.
- A study tested three different training methods, with the third model (using data from low-risk patients) providing the best calibration and predictive accuracy, especially for women.
- Improved AI accuracy in assessing CAD risk is crucial for appropriate patient management, particularly in lower-risk groups where misestimation can lead to unnecessary treatments.
Article Synopsis
- The study analyzed the prognostic value of ischemic total perfusion defect (ITPD) in predicting major adverse cardiac events (MACE) in both men and women, using advanced SPECT imaging in an international registry.
- Data from 17,833 patients revealed that ITPD was a significant predictor of MACE, with an interaction indicating differing impacts between sexes; specifically, men had worse survival rates when ITPD was less than 5%, while women had worse survival when ITPD was 5% or more.
- Overall, the findings suggest that moderate to severe ischemia, as measured by ITPD, poses a greater risk for adverse outcomes in women compared to men.
Article Synopsis
- A machine learning model was developed to predict which patients will exhibit abnormal perfusion on myocardial perfusion imaging (MPI) based on clinical information available before tests.
- The model was trained on data from 20,418 patients and tested externally with 9,019 patients, utilizing 30 pre-test features for its predictions.
- Results showed the model outperformed existing clinical models in predicting abnormal perfusion, indicating its potential to improve test selection by physicians.
Article Synopsis
- - Artificial intelligence, specifically deep learning (DL), shows potential to enhance the accuracy of myocardial perfusion imaging (MPI), primarily as a supportive tool for doctors rather than a fully autonomous system.
- - In a study involving 240 patients, physicians’ diagnostic accuracy improved when interpreting MPI with access to explainable DL predictions (AUC 0.779) compared to those who relied solely on standard methods (AUC 0.747).
- - The integration of DL results led to a significant overall improvement in diagnostic performance, with a net reclassification improvement of 17.2%, although the degree of benefit varied among different physicians based on their acceptance of the technology.
Article Synopsis
- Machine learning models can help predict major adverse cardiovascular events (MACE), but missing values in patient data can negatively impact their accuracy.
- The study examined seven different methods for handling missing values using data from 20,179 patients, evaluating their effects on prediction performance of MACE risk.
- Results showed that all methods with missing data performed worse than a model without missing values, indicating that addressing missing data is crucial for improving patient-level predictions in cardiovascular risk assessment.
Article Synopsis
- - A study analyzed 19,690 patients undergoing nuclear stress testing to understand the factors influencing myocardial ischemia, which is crucial for effective cardiac stress testing.
- - Key predictors of myocardial ischemia included left ventricular ejection fraction (LVEF), male gender, and total perfusion deficit (TPD), with significant differences in prevalence based on these factors and others like age and risk factors.
- - The findings indicated that LVEF and rest TPD were consistently strong predictors of ischemia across multiple testing centers, highlighting the importance of these measurements in assessing heart health.
Article Synopsis
- A study analyzed the risk of major adverse cardiovascular events (MACE) in patients with diabetes mellitus (DM) undergoing cardiac stress testing, comparing those without known coronary artery disease (CAD) to those with CAD but no DM.
- After matching for characteristics, the study found similar MACE rates between both groups, but identified stress testing mode, total perfusion deficit (TPD), and left ventricular function as key predictors of MACE.
- The results highlighted that patients with DM who underwent pharmacologic stress testing and had a TPD greater than 10% experienced significantly higher MACE risk compared to non-ischemic, exercised patients without DM.
Article Synopsis
- The study evaluates the independent prognostic value of phase analysis in single-photon emission computed tomography (SPECT) myocardial perfusion imaging, in relation to major adverse cardiac events (MACE).
- It included data from over 19,000 patients, finding that phase variables like phase entropy were significant predictors of MACE, with a notable increase in MACE rates across different levels of phase entropy.
- This research suggests that incorporating phase analysis into cardiac assessments can improve risk stratification for MACE beyond traditional measures like total perfusion deficit and left ventricular ejection fraction.
Article Synopsis
- The study developed a new explainable deep learning model, CAD-DL, for detecting obstructive coronary artery disease (CAD) using myocardial perfusion imaging (MPI), aiming to improve diagnostic acceptance in clinical settings.
- Data from 3,578 patients revealed that CAD-DL outperformed traditional methods, showing higher accuracy in identifying obstructive CAD during testing, with an area under the curve (AUC) of 0.83 compared to 0.78 for total perfusion deficit and 0.71 for reader diagnosis.
- CAD-DL can be integrated into regular clinical software and provides quick diagnostic results in under 12 seconds, making it a practical tool for routine use in hospitals.*
Article Synopsis
- The study aimed to simplify risk assessment for major adverse cardiac events (MACE) using machine learning (ML) from myocardial perfusion imaging (MPI) by focusing on the fewest manual and imaging variables needed for accurate predictions.
- The research included over 20,000 patients and compared the performance of various ML models, highlighting that models with fewer variables can still match the accuracy of more complex ones when predicting cardiac risks.
- The findings suggest that reduced ML models maintain a comparable prognostic performance to traditional methods, potentially making cardiac risk assessment more efficient and less error-prone.
Article Synopsis
- Stress-only myocardial perfusion imaging (MPI) can significantly cut down on radiation exposure, scanning time, and costs, leading to the development of an automated algorithm that accurately identifies patients who don't require additional rest imaging.
- A machine learning score (MLS) was created to predict obstructive coronary artery disease (CAD) using clinical data and results from stress-only MPI, showing higher predictive accuracy than traditional reader diagnosis methods.
- The MLS demonstrated a sensitivity of 95% for detecting obstructive CAD, outperforming other assessments and supporting a strategy that prioritizes stress imaging to streamline the diagnostic process.
Article Synopsis
- - Shape index and eccentricity index are important measures of left ventricular shape that can help predict serious heart events, but they're often overlooked in clinical evaluations.
- - A study analyzed data from over 14,000 patients who underwent myocardial perfusion imaging to see how these indices relate to major adverse cardiovascular events (MACE) like heart attacks and death.
- - The findings revealed that poststress changes in the shape index were particularly significant for predicting MACE, suggesting that these measures should be considered in assessing patient risk after imaging tests.
Background: We hypothesized early post-stress left ventricular ejection fraction reserve (EFR) on solid-state-SPECT is associated with major cardiac adverse events (MACE).
Methods: 151 patients (70 ± 12 years, male 50%) undergoing same-day rest/regadenoson stress Tc-sestamibi solid-state SPECT were followed for MACE. Rest imaging was performed in the upright and supine positions.
Article Synopsis
- Obese patients pose challenges in SPECT myocardial perfusion imaging (MPI) due to increased soft tissue affecting results, prompting a study on whether automated quantitative analysis can better assess their cardiac risk based on obesity levels.
- The study classified participants by body mass index (BMI) and found that higher total perfusion deficit (TPD) was linked to an increased risk of major adverse cardiac events (MACE), particularly in those with lower BMI categories and significant thresholds of TPD.
- Automated quantitative methods showed superior prognostic accuracy compared to visual analysis, especially for patients with higher obesity levels, suggesting that combining different metrics can enhance risk stratification in this population.
Article Synopsis
- - This study investigated the benefits of early revascularization in patients with significant ischemia using data from a large international registry of myocardial perfusion imaging (SPECT-MPI) between 2009 and 2014.
- - It found that patients showing greater than 10.2% ischemic total perfusion deficit (TPD) after automatic quantification had a lower risk of major adverse cardiovascular events (MACE) if they underwent revascularization within 90 days.
- - The results suggest that early revascularization may be particularly beneficial for patients with moderate to severe ischemia, contributing to better cardiovascular outcomes compared to those who do not receive early intervention.
Article Synopsis
- Researchers developed a machine learning (ML) method to automatically determine when to cancel rest scans in SPECT myocardial perfusion imaging (MPI), aiming to decrease radiation exposure and costs.
- The study used data from over 20,000 patients to train the ML model, which predicted major adverse cardiac events (MACE) and established three score thresholds to match physician decision-making.
- Results showed that patients recommended for rest scan cancellation by ML had significantly lower MACE and all-cause mortality rates compared to those selected by traditional methods, indicating better prognostic safety with the ML approach.
Article Synopsis
- This study investigates the differences in the risk of major adverse cardiovascular events (MACE) between patients with diabetes and those without, based on the total perfusion deficit (TPD) during myocardial imaging.
- It found that patients with diabetes had a higher risk of MACE at every level of TPD, with those having more severe ischemia facing more than double the risk compared to non-diabetic patients.
- Even minimal ischemia in diabetic patients (TPD < 1%) was associated with a high risk of MACE, suggesting that diabetic individuals are at increased cardiovascular risk even with slight perfusion issues.
Aims: To optimize per-vessel prediction of early coronary revascularization (ECR) within 90 days after fast single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) using machine learning (ML) and introduce a method for a patient-specific explanation of ML results in a clinical setting.
Methods And Results: A total of 1980 patients with suspected coronary artery disease (CAD) underwent stress/rest 99mTc-sestamibi/tetrofosmin MPI with new-generation SPECT scanners were included. All patients had invasive coronary angiography within 6 months after SPECT MPI.
Aims: Ischaemia on single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is strongly associated with cardiovascular risk. Transient ischaemic dilation (TID) and post-stress wall motion abnormalities (WMA) are non-perfusion markers of ischaemia with incremental prognostic utility. Using a large, multicentre SPECT MPI registry, we assessed the degree to which these features increased the risk of major adverse cardiovascular events (MACE) in patients with less than moderate ischaemia.
View Article and Find Full Text PDFObjectives: This study compared the ability of automated myocardial perfusion imaging analysis to predict major adverse cardiac events (MACE) to that of visual analysis.
Background: Quantitative analysis has not been compared with clinical visual analysis in prognostic studies.
Methods: A total of 19,495 patients from the multicenter REFINE SPECT (REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT) study (64 ± 12 years of age, 56% males) undergoing stress Tc-99m-labeled single-photon emission computed tomography (SPECT) myocardial perfusion imaging were followed for 4.