A machine learning method integrating ECG and gated SPECT for cardiac resynchronization therapy decision support.

PURPOSE: Cardiac resynchronization therapy (CRT) has been established as an important therapy for heart failure. Mechanical dyssynchrony has the potential to predict responders to CRT. The aim of this study was to report the development and the validation of machine learning models which integrate ECG, gated SPECT MPI (GMPS), and clinical variables to predict patients' response to CRT. METHODS: This analysis included 153 patients who met criteria for CRT from a prospective cohort study. The variables were used to model predictive methods for CRT. Patients were classified as "responders" for an increase of LVEF ≥ 5% at follow-up. In a second analysis, patients were classified as "super-responders" for an increase of LVEF ≥ 15%. For ML, variable selection was applied, and Prediction Analysis of Microarrays (PAM) approach was used to model response while Naïve Bayes (NB) was used to model super-response. These ML models were compared to models obtained with guideline variables. RESULTS: PAM had AUC of 0.80 against 0.72 of partial least squares-discriminant analysis with guideline variables (p = 0.52). The sensitivity (0.86) and specificity (0.75) were better than for guideline alone, sensitivity (0.75) and specificity (0.24). Neural network with guideline variables was better than NB (AUC = 0.93 vs. 0.87) however without statistical significance (p = 0.48). Its sensitivity and specificity (1.0 and 0.75, respectively) were better than guideline alone (0.78 and 0.25, respectively). CONCLUSIONS: Compared to guideline criteria, ML methods trended toward improved CRT response and super-response prediction. GMPS was central in the acquisition of most parameters. Further studies are needed to validate the models.

Integrating artificial intelligence and natural language processing for computer-assisted reporting and report understanding in nuclear cardiology.

Natural language processing (NLP) offers many opportunities in Nuclear Cardiology. These opportunities include applications in converting nuclear cardiology imaging reports to digital searchable information that may be used as Big Data for machine learning and registries. Another major NLP application is, with the support of AI, in automatically translating MPI image features directly into nuclear cardiology reports. This review describes the symbiotic relationship between AI and NLP in that NLP is being used to facilitate AI applications and, AI techniques are being used to facilitate NLP. This article reviews the fundamentals of NLP and describes various conventional and AI techniques that have been applied in imaging. Key nuclear cardiology applications are reviewed such as conversion of MPI free-text reports to digital documents as well as direct conversion of MPI images into structured medical reports.

4D display of CT LV endocardial and epicardial models morphed from PET Rb-82 perfusion studies accurately quantifies segmental myocardial thickening.

BACKGROUND: MPI-derived LV wall thickening assessments for diagnostic purposes has been part of clinical guidelines for two decades. It relies on visual evaluation of tomographic slices or regional quantification displayed in 2D polar maps. 4D displays have not entered clinical usage nor have they been validated on their potential to provide equivalent information. The purpose of this work was to validate a 4D realistic display recently designed to quantitatively represent the thickening information from gated MPI into CT-morphed endocardial and epicardial moving surfaces. METHODS: Forty patients who underwent 82Rb PET were selected based on LV perfusion quantification. CTA templates of heart anatomy were selected to represent the LV anatomy. Generic CT-derived LV endocardial and epicardial surfaces were modified to represent the end diastolic (ED) phase according to PET-derived ED LV dimensions and wall thickness. These CT myocardial surfaces were then morphed by means of thin plate spline (TPS) techniques, according to the gated PET slices count changes (WThPET) and LV wall motion (WMoPET). A geometric thickening (GeoTh) equivalent to LV WThPET was defined on epicardial and endocardial CT surfaces over the cardiac cycle and the two measures compared. WThPET and GeoTh correlations were performed on a case-by-case basis, by segment and by pooling all 17 segments. Pearson's correlation coefficients (PCC) were calculated to assess the equivalence of the two measures. RESULTS: Two cohorts of patients (normal and abnormal) were identified based on SSS. R coefficients were as follows: for all pooled segments PCCstress and PCCrest were respectively 0.91 and 0.89 (normal), and 0.9 and 0.91 (abnormal); when individual 17 segments were considered mean PCCstress = 0.92 [0.81-0.98] and mean PCCrest = 0.93 [0.83-0.98] for the abnormal perfusion group; mean PCCstress = 0.89 [0.78-0.97] and mean PCCrest = 0.89 [0.77-0.97] for the normal. When individual studies were considered, R was always > .70 with the exception of five abnormal studies. Inter-user analysis was also conducted. CONCLUSIONS: Our novel technique for the visualization of LV wall thickening by means of 4D CT endocardial and epicardial surface models accurately replicated 82Rb slice thickening results showing promise for its usage for diagnostic purposes.

Quantitation of diffuse myocardial ischemia with mental stress and its association with cardiovascular events in individuals with recent myocardial infarction.

Microcirculatory dysfunction during psychological stress may lead to diffuse myocardial ischemia. We developed a novel quantification method for diffuse ischemia during mental stress (dMSI) and examined its relationship with outcomes after a myocardial infarction (MI). We studied 300 patients ≤ 61 years of age (50% women) with a recent MI. Patients underwent myocardial perfusion imaging with mental stress and were followed for 5 years. dMSI was quantified from cumulative count distributions of rest and stress perfusion. Focal ischemia was defined in a conventional fashion. The main outcome was a composite outcome of recurrent MI, heart failure hospitalizations, and cardiovascular death. A dMSI increment of 1 standard deviation was associated with a 40% higher risk for adverse events (HR 1.4, 95% CI 1.2-1.5). Results were similar after adjustment for viability, demographic and clinical factors and focal ischemia. In sex-specific analysis, higher levels of dMSI (per standard deviation increment) were associated with 53% higher risk of adverse events in women (HR 1.5, 95% CI 1.2-2.0) but not in men (HR 0.9, 95% CI 0.5-1.4), P 0.001. A novel index of diffuse ischemia with mental stress was associated with recurrent events in women but not in men after MI.

Incremental value of left ventricular shape parameters measured by gated SPECT MPI in predicting the super-response to CRT.

BACKGROUND: The purpose of this study was to evaluate the predictive value of left ventricular (LV) shape parameters measured by gated SPECT myocardial perfusion imaging (MPI) in super-responders enrolled in the VISION-CRT trial. METHODS: One hundred and ninety-nine patients who met standard criteria for CRT from multiple centers were enrolled in this study. End-systolic eccentricity (ESE) and end-diastolic eccentricity (EDE) were measures of LV shape. Super-responders were the patients who had a relative increase in left ventricular ejection fraction (LVEF) ≥ 15%. RESULTS: Complete data were obtained in 165 patients, and 43.6% of them were classified as super-responders. ESE was an independent predictor of CRT super-responders in univariate (OR 12.59, 95% CI 1.56-101.35, P = .017) and multivariate analysis (OR 35.71, 95% CI 1.66-766.03, P = .006). ESE had an incremental value over significant clinical and SPECT imaging variables, including angiotensin-converting enzyme inhibitors or angiotensin II receptor blocker, coronary artery disease, myocardial infarction, LVEF, end-diastolic volume index, and scar burden (AUC 0.82 vs. 0.80, sensitivity 0.68 vs. 0.65, specificity 0.82 vs. 0.78). CONCLUSIONS: LV shape parameters derived from gated SPECT MPI have the promise to improve the prediction of the super-response to CRT. Moreover, ESE provides incremental value over existing clinical and nuclear imaging variables.

Development, diagnostic performance, and interobserver agreement of a 18F-flurpiridaz PET automated perfusion quantitation system.

BACKGROUND: Computerized methodologies standardize the myocardial perfusion imaging (MPI) interpretation process. METHODS: To develop an automated relative perfusion quantitation approach for 18F-flurpiridaz, PET MPI studies from all phase III trial participants of 18F-flurpiridaz were divided into 3 groups. Count distributions were obtained in N = 40 normal patients undergoing pharmacological or exercise stress. Then, N = 90 additional studies were selected in a derivation group. Following receiver operating characteristic curve analysis, various standard deviations below the mean normal were used as cutoffs for significant CAD, and interobserver variability determined. Finally, diagnostic performance was compared between blinded visual readers and blinded derivations of automated relative quantitation in the remaining N = 548 validation patients. RESULTS: Both approaches yielded comparable accuracies for the detection of global CAD, reaching 71% and 72% by visual reads, and 72% and 68% by automated relative quantitation, when using CAD ≥ 70% or ≥ 50% stenosis for significance, respectively. Similar results were observed when analyzing individual coronary territories. In both pharmacological and exercise stress, automated relative quantitation demonstrated significantly more interobserver agreement than visual reads. CONCLUSIONS: Our automated method of 18F-flurpiridaz relative perfusion analysis provides a quantitative, objective, and highly reproducible assessment of PET MPI in normal and CAD subjects undergoing either pharmacological or exercise stress.

Determination of [N-13]-ammonia extraction fraction in patients with coronary artery disease by calibration to invasive coronary and fractional flow reserve.

BACKGROUND: This study presents a new extraction fraction (EF) model based on physiological measures of invasive coronary flow reserve (CFR) and fractional flow reserve (FFR) in patients with suspected coronary artery disease (CAD) and normal index microcirculatory resistance (IMR). To ascertain the clinical relevance of the new EFs, flow measurements using the newly patient-determined EFs were compared to flow measurements using traditional animal-determined EFs. METHODS: 39 patients were retrospectively selected that included a total of 91 vascular territories with invasive coronary angiography physiological measures. [N-13]-ammonia dynamic rest/adenosine-stress PET imaging was conducted in all patients and absolute myocardial flow was estimated using four published compartmental models. The extraction fraction during hyperemic flow was iteratively estimated by maximizing the agreement between invasive CFR and FFR with the non-invasive analogs myocardial flow reserve (MFR) and relative flow reserve (RFR) at similar physiological states, respectively. RESULTS: Using the new patient-determined EFs, agreement between CFR vs MFR for Model 1 and 2 was moderate and poor for Model 3 and 4. All models showed moderate agreement for FFR vs RFR. When using published models of animal-determined EFs, agreement between CFR vs MFR remained moderate for Model 1 and 2, and poor for Model 3 and 4. Similarly, all models showed moderate agreement for FFR vs RFR using animal-determined EF values. None of the observed differences were statistically significant. CONCLUSIONS: Flow measurements using extraction fraction correction for [N-13]-ammonia based on calibration to invasive intracoronary angiography physiological measures in patients with CAD were not discordant from those reported in the literature. Either patient-determined or traditional animal-determined EF correction, when used with the appropriate flow model, yields moderate agreement with invasive measurements of coronary flow reserve and fractional flow reserve.

Reproducibility of global LV function and dyssynchrony parameters derived from phase analysis of gated myocardial perfusion SPECT: A multicenter comparison with core laboratory setting.

BACKGROUND: Gated myocardial perfusion scintigraphy (GMPS) phase analysis is an important tool to investigate the physiology of left ventricular (LV) dyssynchrony. We aimed to test the performance of GMPS LV function and phase analysis in different clinical settings and on a diverse population. METHODS: This is a post hoc analysis of a prospective, non-randomized, multinational, multicenter cohort study. Clinical evaluation and GMPS prior to cardiac resynchronization therapy (CRT)(baseline) and 6-month post CRT (follow-up) were done. LV end-systolic volume (LVESV), LV end-diastolic volume (LVEDV), LV ejection fraction (LVEF), LV phase standard deviation (LVPSD), and percentage of left ventricle non-viable (PLVNV) were obtained by 10 centers and compared to the core lab. RESULTS: 276 GMPS studies had all data available from individual sites and from core lab. There were no statistically significant differences between all variables except for LVPSD. When subjects with no mechanical dyssynchrony were excluded, LVPSD difference became non-significant. LVESV, LVEF, LVPSD and PLVNV had strong correlation in site against core lab comparison. Bland-Altman plots demonstrated good agreement. CONCLUSIONS: The presented correlation and agreement of LV function and dyssynchrony analysis over different sites with a diverse sample corroborate the strength of GMPS in the management of heart failure in clinical practice.

Clinical and gated SPECT MPI parameters associated with super-response to cardiac resynchronization therapy.

PURPOSE: We sought to evaluate the behavior of cardiac mechanical synchrony as measured by phase SD (PSD) derived from gated MPI SPECT (gSPECT) in patients with super-response after CRT and to evaluate the clinical and imaging characteristics associated with super-response. METHODS: 158 subjects were evaluated with gSPECT before and 6 months after CRT. Patients with an improvement of LVEF > 15% and NYHA class I/II or reduction in LV end-systolic volume > 30% and NYHA class I/II were labeled as super-responders (SR). RESULTS: 34 patients were classified as super-responders (22%) and had lower PSD (32° ± 17°) at 6 months after CRT compared to responders (45° ± 24°) and non-responders 46° ± 28° (P = .02 for both comparisons). Regression analysis identified predictors independently associated with super-response to CRT: absence of previous history of CAD (odds ratio 18.7; P = .002), absence of diabetes mellitus (odds ratio 13; P = .03), and history of hypertension (odds ratio .2; P = .01). CONCLUSION: LV dyssynchrony after CRT implantation, but not at baseline, was significantly better among super-responders compared to non-super-responders. The absence of diabetes, absence of CAD, and history of hypertension were independently associated with super-response after CRT.

Higher Activation of the Rostromedial Prefrontal Cortex During Mental Stress Predicts Major Cardiovascular Disease Events in Individuals With Coronary Artery Disease.

BACKGROUND: Psychological stress is a risk factor for major adverse cardiovascular events (MACE) in individuals with coronary artery disease. Certain brain regions that control both emotional states and cardiac physiology may be involved in this relationship. The rostromedial prefrontal cortex (rmPFC) is an important brain region that processes stress and regulates immune and autonomic functions. Changes in rmPFC activity with emotional stress (reactivity) may be informative of future risk for MACE. METHODS: Participants with stable coronary artery disease underwent acute mental stress testing using a series of standardized speech/arithmetic stressors and simultaneous brain imaging with high-resolution positron emission tomography brain imaging. We defined high rmPFC activation as a difference between stress and control scans greater than the median value for the entire cohort. Interleukin-6 levels 90 minutes after stress, and high-frequency heart rate variability during stress were also assessed. We defined MACE as a composite of cardiovascular death, myocardial infarction, unstable angina with revascularization, and heart failure hospitalization. RESULTS: We studied 148 subjects (69% male) with mean±SD age of 62±8 years. After adjustment for baseline demographics, risk factors, and baseline levels of interleukin-6 and high-frequency heart rate variability, higher rmPFC stress reactivity was independently associated with higher interleukin-6 and lower high-frequency heart rate variability with stress. During a median follow-up of 3 years, 34 subjects (21.3%) experienced a MACE. Each increase of 1 SD in rmPFC activation with mental stress was associated with a 21% increase risk of MACE (hazard ratio, 1.21 [95% CI, 1.08-1.37]). Stress-induced interleukin-6 and high-frequency heart rate variability explained 15.5% and 32.5% of the relationship between rmPFC reactivity and MACE, respectively. Addition of rmPFC reactivity to conventional risk factors improved risk reclassification for MACE prediction, and C-statistic improved from 0.71 to 0.76 (P=0.03). CONCLUSIONS: Greater rmPFC stress reactivity is associated with incident MACE. Immune and autonomic responses to mental stress may play a contributory role.

Quantitative clinical nuclear cardiology, part 2: Evolving/emerging applications.

Quantitative analysis has been applied extensively to image processing and interpretation in nuclear cardiology to improve disease diagnosis and risk stratification. This is Part 2 of a two-part continuing medical education article, which will review the potential clinical role for emerging quantitative analysis tools. The article will describe advanced methods for quantifying dyssynchrony, ventricular function and perfusion, and hybrid imaging analysis. This article discusses evolving methods to measure myocardial blood flow with positron emission tomography and single-photon emission computed tomography. Novel quantitative assessments of myocardial viability, microcalcification and in patients with cardiac sarcoidosis and cardiac amyloidosis will also be described. Lastly, we will review the potential role for artificial intelligence to improve image analysis, disease diagnosis, and risk prediction. The potential clinical role for all these novel techniques will be highlighted as well as methods to optimize their implementation.

Left ventricular systolic and diastolic dyssynchrony to improve cardiac resynchronization therapy response in heart failure patients with dilated cardiomyopathy.

BACKGROUND: The systolic and diastolic dyssynchrony is physiologically related, but measure different left ventricular mechanisms. Left ventricular systolic mechanical dyssynchrony (systolic LVMD) has shown significant clinical values in improving cardiac resynchronization therapy (CRT) response in the heart failure patients with dilated cardiomyopathy (DCM). Our recent study demonstrated that LV diastolic dyssynchrony (diastolic LVMD) parameters have important prognostic values for DCM patients. However, there are a limited number of studies about the clinical value of diastolic LVMD for CRT. This study aims to explore the predictive values of both systolic LVMD and diastolic LVMD for CRT in DCM patients. METHODS: Eighty-four consecutive CRT patients with both DCM and complete left bundle branch block (CLBBB) who received gated resting SPECT MPI at baseline were included in the present study. The phase analysis technique was applied on resting gated short-axis SPECT MPI images to measure systolic LVMD and diastolic LVMD, characterized by phase standard deviation (PSD) and phase histogram bandwidth (PBW). CRT response was defined as ≥ 5% improvement of LVEF at 6-month follow-up. Variables with P < 0.10 in the univariate analysis were included in the multivariate cox analysis. RESULTS: During the follow-up period, 59.5% (50 of 84) patients were CRT responders. The univariate cox regression analysis showed that at baseline QRS duration, non-sustained ventricular tachycardia (NS-VT), systolic PSD, systolic PBW, diastolic PSD, diastolic PBW, scar burden and LV lead in the scarred myocardium were statistically significantly associated with CRT response. The multivariate cox regression analysis showed that QRS duration, NS-VT, systolic PSD, systolic PBW, diastolic PSD, and diastolic PBW were independent predictive factors for CRT response. Furthermore, the rate of CRT response was 94.4% (17 of 18) in patients whose LV lead was in the segments with both the first three late contraction and the first three late relaxation; by contrast, the rate of CRT response was only 6.7% (1 of 15, P < 0.000) in patients whose LV lead was in the segments with neither the first three late contraction nor the first three late relaxation. CONCLUSION: Both systolic LVMD and diastolic LVMD from gated SPECT MPI have important predictive values for CRT response in DCM patients. Pacing at LV segments with both late contraction and late relaxation has potential to increase the CRT response.

Assessing myocardial perfusion in suspected coronary artery disease: rationale and design of the second phase 3, open-label multi-center study of flurpiridaz (F-18) injection for positron emission tomography (PET) imaging.

BACKGROUND: Positron emission tomography (PET) myocardial perfusion imaging (MPI) with the novel radiopharmaceutical Fluorine-18 Flurpiridaz has been shown in Phase 1, 2, and first Phase 3 clinical studies to be safe and effective in diagnosing coronary artery disease (CAD). We describe the methodology of the second FDA-mandated phase 3 prospective, open-label, international, multi-center trial of F-18 Flurpiridaz PET MPI. METHODS: The primary study end point is to assess the diagnostic efficacy of F-18 Flurpiridaz PET MPI in the detection of significant CAD [≥ 50% by quantitative invasive coronary angiography (ICA)] in patients with suspected CAD. The secondary endpoints are to evaluate the diagnostic efficacy of F-18 Flurpiridaz PET MPI compared to Tc-99 m-labeled SPECT MPI in the detection of CAD in all patients and in the following subgroups: (1) females; (2) patients with body mass index ≥ 30 kg/m2; and (3) diabetic patients. This trial's design differs from the first phase 3 trial in that (1) comparison to SPECT is now a secondary end point; (2) patients with known CAD are excluded; and (3) both SPECT and PET MPI are performed before ICA. CONCLUSIONS: This second phase 3 study will provide additional evidence on the diagnostic efficacy of F-18 Flurpiridaz PET MPI in the detection of significant CAD. TRIAL REGISTRATION NUMBER: NCT03354273.

Value of intraventricular dyssynchrony assessment by gated-SPECT myocardial perfusion imaging in the management of heart failure patients undergoing cardiac resynchronization therapy (VISION-CRT).

BACKGROUND: Placing the left ventricular (LV) lead in a viable segment with the latest mechanical activation (vSOLA) may be associated with optimal cardiac resynchronization therapy (CRT) response. We assessed the role of gated SPECT myocardial perfusion imaging (gSPECT MPI) in predicting clinical outcomes at 6 months in patients submitted to CRT. METHODS: Ten centers from 8 countries enrolled 195 consecutive patients. All underwent gSPECT MPI before and 6 months after CRT. The procedure was performed as per current guidelines, the operators being unaware of gSPECT MPI results. Regional LV dyssynchrony (Phase SD) and vSOLA were automatically determined using a 17 segment model. The lead was considered on-target if placed in vSOLA. The primary outcome was improvement in ≥1 of the following: ≥1 NYHA class, left ventricular ejection fraction (LVEF) by ≥5%, reduction in end-systolic volume by ≥15%, and ≥5 points in Minnesota Living With Heart Failure Questionnaire (MLHFQ). RESULTS: Sixteen patients died before the follow-up gSPECT MPI. The primary outcome occurred in 152 out of 179 (84.9%) cases. Mean change in LV phase standard deviation (PSD) at 6 months was 10.5°. Baseline dyssynchrony was not associated with the primary outcome. However, change in LV PSD from baseline was associated with the primary outcome (OR 1.04, 95% CI 1.01-1.07, P = .007). Change in LV PSD had an AUC of 0.78 (0.66-0.90) for the primary outcome. Improvement in LV PSD of 4° resulted in the highest positive likelihood ratio of 7.4 for a favorable outcome. In 23% of the patients, the CRT lead was placed in the vSOLA, and in 42% in either this segment or in a segment within 10° of it. On-target lead placement was not significantly associated with the primary outcome (OR 1.53, 95% CI 0.71-3.28). CONCLUSION: LV dyssynchrony improvement by gSPECT MPI, but not on-target lead placement, predicts clinical outcomes in patients undergoing CRT.

Diastolic dyssynchrony assessment by gated myocardial perfusion-SPECT in subjects who underwent cardiac resynchronization therapy.

BACKGROUND: Left ventricular diastolic dyssynchrony (LVDD) can be assessed by gated myocardial perfusion single-photon emission computed tomography (GMP-SPECT). LVDD is an area of interest in subjects who underwent cardiac resynchronization therapy (CRT). The aim of this post hoc analysis was to assess the role of LVDD in subjects with CRT who were followed up at 6-month period. MATERIAL & METHODS: Left ventricular diastolic dyssynchrony was assessed by GMP-SPECT at baseline and after CRT procedure in 160 subjects from 10 different cardiological centers. CRT procedure was performed as per current guidelines. Outcomes were defined as improvement in ≥1 New York Heart Association (NYHA) class, left ventricular ejection fraction (LVEF) by 5%, and reduction in end-systolic volume (ESV) by 15% and 5% points in Minnesota Living with Heart Failure Questionnaire. LVDD was defined as diastolic phase standard deviation ≥40 ± 14°. RESULTS: Improvement in NYHA functional class occurred in 105 (65.6%), LVEF in 74 (46.3%), decrease in ESV in 86 (53.8%), and Minnesota score in 85 (53.1%) cases. Baseline LV diastolic standard deviation was 53.53° ± 20.85 and at follow-up 40.44° ± 26.1283; (P < 0.001). LVDD was not associated with improvement in clinical outcomes at follow-up. CONCLUSION: CRT improves both systolic and diastolic dyssynchrony values at 6-month follow-up. LVDD at baseline is correlated with cardiac functionality at follow-up, but not with overall favorable clinical outcomes.

A new method to recommend left ventricular lead positions for improved CRT volumetric response and long-term prognosis.

OBJECTIVES: Using ECG-gated single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI), we sought to develop and validate a new method to recommend left ventricular (LV) lead positions in order to improve volumetric response and long-term prognosis after cardiac resynchronization therapy (CRT). METHODS: Seventy-nine patients received gated SPECT MPI at baseline, and echocardiography at baseline and follow-up. The volumetric response referred to a reduction of ≥ 15% in LV end-systolic volume 6 months after CRT. After excluding apical, septal, and scarred segments, there were three levels of recommended segments: (1) the optimal recommendation: the latest contracting viable segment; (2) the 2nd recommendation: the late contracting viable segments whose contraction delays were within 10° of the optimal recommendation; and (3) the 3rd recommendation: the viable segments adjacent to the optimal recommendation when there was no late contracting viable segment. RESULTS: After excluding 11 patients whose LV lead was placed in apical or scarred segments, 75.6% of the patients concordant to recommended LV segments (n = 41) responded to CRT while 51.9% of those with non-recommended LV lead locations (n = 27) were responders (P = .043). Response rates were 76.9%, 76.9% , and 73.3% (P = .967), respectively, when LV lead was implanted in the optimal recommendation (n = 13), the 2nd recommendation (n = 13), and the 3rd recommendation (n = 15). LV leads placed at recommended segments reduced composite events of all-cause mortality or heart failure (HF) rehospitalization compared with pacing at non-recommended segments (log-rank χ2 = 5.623, P = .018). CONCLUSIONS: Pacing in the recommended LV lead segments identified on gated SPECT MPI was associated with improved volumetric response to CRT and long-term prognosis.

Association of Mental Stress-Induced Myocardial Ischemia With Cardiovascular Events in Patients With Coronary Heart Disease.

Importance: Mental stress-induced myocardial ischemia is a recognized phenomenon in patients with coronary heart disease (CHD), but its clinical significance in the contemporary clinical era has not been investigated. Objective: To compare the association of mental stress-induced or conventional stress-induced ischemia with adverse cardiovascular events in patients with CHD. Design, Setting, and Participants: Pooled analysis of 2 prospective cohort studies of patients with stable CHD from a university-based hospital network in Atlanta, Georgia: the Mental Stress Ischemia Prognosis Study (MIPS) and the Myocardial Infarction and Mental Stress Study 2 (MIMS2). Participants were enrolled between June 2011 and March 2016 (last follow-up, February 2020). Exposures: Provocation of myocardial ischemia with a standardized mental stress test (public speaking task) and with a conventional (exercise or pharmacological) stress test, using single-photon emission computed tomography. Main Outcomes and Measures: The primary outcome was a composite of cardiovascular death or first or recurrent nonfatal myocardial infarction. The secondary end point additionally included hospitalizations for heart failure. Results: Of the 918 patients in the total sample pool (mean age, 60 years; 34% women), 618 participated in MIPS and 300 in MIMS2. Of those, 147 patients (16%) had mental stress-induced ischemia, 281 (31%) conventional stress ischemia, and 96 (10%) had both. Over a 5-year median follow-up, the primary end point occurred in 156 participants. The pooled event rate was 6.9 per 100 patient-years among patients with and 2.6 per 100 patient-years among patients without mental stress-induced ischemia. The multivariable adjusted hazard ratio (HR) for patients with vs those without mental stress-induced ischemia was 2.5 (95% CI, 1.8-3.5). Compared with patients with no ischemia (event rate, 2.3 per 100 patient-years), patients with mental stress-induced ischemia alone had a significantly increased risk (event rate, 4.8 per 100 patient-years; HR, 2.0; 95% CI, 1.1-3.7) as did patients with both mental stress ischemia and conventional stress ischemia (event rate, 8.1 per 100 patient-years; HR, 3.8; 95% CI, 2.6-5.6). Patients with conventional stress ischemia alone did not have a significantly increased risk (event rate, 3.1 per 100 patient-years; HR, 1.4; 95% CI, 0.9-2.1). Patients with both mental stress ischemia and conventional stress ischemia had an elevated risk compared with patients with conventional stress ischemia alone (HR, 2.7; 95% CI, 1.7-4.3). The secondary end point occurred in 319 participants. The event rate was 12.6 per 100 patient-years for patients with and 5.6 per 100 patient-years for patients without mental stress-induced ischemia (adjusted HR, 2.0; 95% CI, 1.5-2.5). Conclusions and Relevance: Among patients with stable coronary heart disease, the presence of mental stress-induced ischemia, compared with no mental stress-induced ischemia, was significantly associated with an increased risk of cardiovascular death or nonfatal myocardial infarction. Although these findings may provide insights into mechanisms of myocardial ischemia, further research is needed to assess whether testing for mental stress-induced ischemia has clinical value.

Quantitative Clinical Nuclear Cardiology, Part 1: Established Applications.

Single photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) has attained widespread clinical acceptance as a standard of care for patients with known or suspected coronary artery disease (CAD). A significant contribution to this success has been the use of computer techniques to provide objective quantitative assessment in the standardization of the interpretation of these studies. Software platforms have been developed as a pipeline to provide the quantitative algorithms researched, developed and validated to be clinically useful so diagnosticians everywhere can benefit from these tools. The goal of this CME article (PART 1) is to describe the many quantitative tools that are clinically established and more importantly how clinicians should use them routinely in the interpretation, clinical management and therapy guidance of patients with CAD.

Prognostic value of left-ventricular systolic and diastolic dyssynchrony measured from gated SPECT MPI in patients with dilated cardiomyopathy.

BACKGROUND: Left-ventricular systolic dyssynchrony (LVSD) has been an important prognostic factor in the patients with dilated cardiomyopathy (DCM). However, the association between the LV diastolic dyssynchrony (LVDD) and clinical outcome is not well established. This study aims to evaluate the prognostic values of both systolic and diastolic dyssynchrony in patients with DCM. METHODS: Fifty-two patients with DCM were enrolled and divided into two groups according to cardiac deaths from the follow-up data. The phase-analysis technique was applied on resting gated short-axis SPECT MPI images to measure LV systolic and diastolic dyssynchrony, including phase standard deviation (PSD), phase histogram bandwidth (PBW), and phase entropy (PE). Variables with P < 0.10 in the univariate analysis were included in the multivariate cox analysis. RESULTS: During the follow-up period (2.9 ± 1.7 years), 18 (34.6%) cardiac deaths were observed. Compared with survivors, patients with cardiac death had lower LVEF (P = 0.011), and more severe LV systolic and diastolic dyssynchrony. The univariate cox regression analysis showed that hypertension, NT-proBNP, LVEF, systolic PSD, systolic PE, and diastolic PBW were statistically significantly associated with cardiac death. The multivariate cox regression analysis showed that systolic PE and diastolic PE were independent predictive factors for cardiac death. Furthermore, the receiver operating characteristic (ROC) analysis, when applied into the combination of systolic PE and diastolic PE for predicting cardiac death, had an area under curve (AUC) of 0.766, a sensitivity of 0.765, and a specificity of 0.722. CONCLUSIONS: Both the LVSD and LVDD parameters from SPECT MPI have important prognostic values for DCM patients. Both systolic PE and diastolic PE are independent prognostic factors for cardiac death.

Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion SPECT imaging.

OBJECTIVES: To describe and validate an artificial intelligence (AI)-driven structured reporting system by direct comparison of automatically generated reports to results from actual clinical reports generated by nuclear cardiology experts. BACKGROUND: Quantitative parameters extracted from myocardial perfusion imaging (MPI) studies are used by our AI reporting system to generate automatically a guideline-compliant structured report (sR). METHOD: A new nonparametric approach generates distribution functions of rest and stress, perfusion, and thickening, for each of 17 left ventricle segments that are then transformed to certainty factors (CFs) that a segment is hypoperfused, ischemic. These CFs are then input to our set of heuristic rules used to reach diagnostic findings and impressions propagated into a sR referred as an AI-driven structured report (AIsR). The diagnostic accuracy of the AIsR for detecting coronary artery disease (CAD) and ischemia was tested in 1,000 patients who had undergone rest/stress SPECT MPI. RESULTS: At the high-specificity (SP) level, in a subset of 100 patients, there were no statistical differences in the agreements between the AIsr, and nine experts' impressions of CAD (P = .33) or ischemia (P = .37). This high-SP level also yielded the highest accuracy across global and regional results in the 1,000 patients. These accuracies were statistically significantly better than the other two levels [sensitivity (SN)/SP tradeoff, high SN] across all comparisons. CONCLUSIONS: This AI reporting system automatically generates a structured natural language report with a diagnostic performance comparable to those of experts.