Head-to-head comparison of diagnostic accuracy of stress-only myocardial perfusion imaging with conventional and cadmium-zinc telluride single-photon emission computed tomography in women with suspected coronary artery disease

Prediction of Major Adverse Coronary Events Using the Coronary Risk Score in Women

Purpose To establish a COronary Risk Score in WOmen (CORSWO) to predict major adverse coronary events (MACE). Materials and Methods This retrospective analysis included 2226 female individuals (mean age, 66.7 years ± 11.6 [SD]) from a cohort of 25 943 consecutive patients referred for clinical gated SPECT myocardial perfusion imaging (gSPECT MPI). During the follow-up (mean, 4 years ± 2.7) after gSPECT MPI, occurrence of MACE (unstable angina requiring hospitalization, nonfatal myocardial infarction, coronary revascularization, cardiac death) was assessed. The patients were divided into training (n = 1460) and validation (n = 766) groups. To obtain the predictor model, multiple Cox regression analyses were performed. Results In the training group, 148 female individuals had MACE (2.6% per year). The best model (area under the receiver operating characteristic curve [AUC]: 0.80 [95% CI: 0.74, 0.83]; Brier score: 0.08) to predict MACE in female individuals included the following variables: age older than 69 years (hazard ratio [HR]: 1.58, P = .01), diabetes mellitus (HR: 1.47, P = .03), pharmacologic test (HR: 1.63, P = .01), ST-segment depression (≥1 mm) (HR: 2.02, P < .001), myocardial ischemia greater than 5% (HR: 2.21, P < .001), perfusion defect at rest greater than 9% (HR: 1.96, P = .009), perfusion defect at stress greater than 6% (HR: 1.63, P = .03), and end-systolic volume index greater than 15 mL (HR: 2.04, P < .001). During validation, the model achieved moderate performance (AUC: 0.78 [95% CI: 0.70, 0.83]). CORSWO obtained from these variables allowed for stratification of female individuals into four risk levels: low (score: 0-3, HR: 1), moderate (score: 4-6, HR: 1.58), high (score: 7-11, HR: 4.13), and very high (score: >11, HR: 13.87). The high and very high risk levels (HR: 5.29) predicted MACE in female individuals, with excellent performance (AUC: 0.78 [95% CI: 0.72, 0.80]). Conclusion With clinical, stress test, and gSPECT MPI variables, CORSWO effectively stratified female individuals according to coronary risk and was able to detect those with high and very high risk. Keywords: SPECT, Cardiac, Coronary Arteries, Women, Risk Stratification, Cardiac Event, CORSWO, MACE, Gated SPECT Supplemental material is available for this article. ©RSNA, 2024.

Gender Medicine in Clinical Radiology Practice

Gender Medicine is rapidly emerging as a branch of medicine that studies how many diseases common to men and women differ in terms of prevention, clinical manifestations, diagnostic-therapeutic approach, prognosis, and psychological and social impact. Nowadays, the presentation and identification of many pathological conditions pose unique diagnostic challenges. However, women have always been paradoxically underestimated in epidemiological studies, drug trials, as well as clinical trials, so many clinical conditions affecting the female population are often underestimated and/or delayed and may result in inadequate clinical management. Knowing and valuing these differences in healthcare, thus taking into account individual variability, will make it possible to ensure that each individual receives the best care through the personalization of therapies, the guarantee of diagnostic-therapeutic pathways declined according to gender, as well as through the promotion of gender-specific prevention initiatives. This article aims to assess potential gender differences in clinical-radiological practice extracted from the literature and their impact on health and healthcare. Indeed, in this context, radiomics and radiogenomics are rapidly emerging as new frontiers of imaging in precision medicine. The development of clinical practice support tools supported by artificial intelligence allows through quantitative analysis to characterize tissues noninvasively with the ultimate goal of extracting directly from images indications of disease aggressiveness, prognosis, and therapeutic response. The integration of quantitative data with gene expression and patient clinical data, with the help of structured reporting as well, will in the near future give rise to decision support models for clinical practice that will hopefully improve diagnostic accuracy and prognostic power as well as ensure a more advanced level of precision medicine.

Simultaneous assessment of myocardial perfusion and adrenergic innervation in patients with heart failure by low-dose dual-isotope CZT SPECT imaging

BACKGROUND

In patients with heart failure (HF) sequential imaging studies have demonstrated a relationship between myocardial perfusion and adrenergic innervation. We evaluated the feasibility of a simultaneous low-dose dual-isotope 123I/99mTc-acquisition protocol using a cadmium-zinc-telluride (CZT) single-photon emission computed tomography (SPECT) camera.

METHODS AND RESULTS

Thirty-six patients with HF underwent simultaneous low-dose 123I-metaiodobenzylguanidine (MIBG)/99mTc-sestamibi gated CZT-SPECT cardiac imaging. Perfusion and innervation total defect sizes and perfusion/innervation mismatch size (defined by 123I-MIBG defect size minus 99mTc-sestamibi defect size) were expressed as percentages of the total left ventricular (LV) surface area. LV ejection fraction (EF) significantly correlated with perfusion defect size (P < .005), innervation defect size (P < .005), and early (P < .05) and late (P < .01) 123I-MIBG heart-to-mediastinum (H/M) ratio. In addition, late H/M ratio was independently associated with reduced LVEF (P < .05). Although there was a significant relationship (P < .001) between perfusion and innervation defect size, innervation defect size was larger than perfusion defect size (P < .001). At multivariable linear regression analysis, 123I-MIBG washout rate (WR) correlated with perfusion/innervation mismatch (P < .05).

CONCLUSIONS

In patients with HF, a simultaneous low-dose dual-isotope 123I/99mTc-acquisition protocol is feasible and could have important clinical implications.

Imaging of heart disease in women: review and case presentation

Cardiovascular diseases (CVD) remain the leading cause of mortality worldwide. Although major diagnostic and therapeutic advances have significantly improved the prognosis of patients with CVD in the past decades, these advances have less benefited women than age-matched men. Noninvasive cardiac imaging plays a key role in the diagnosis of CVD. Despite shared imaging features and strategies between both sexes, there are critical sex disparities that warrant careful consideration, related to the selection of the most suited imaging techniques, to technical limitations, and to specific diseases that are overrepresented in the female population. Taking these sex disparities into consideration holds promise to improve management and alleviate the burden of CVD in women. In this review, we summarize the specific features of cardiac imaging in four of the most common presentations of CVD in the female population including coronary artery disease, heart failure, pregnancy complications, and heart disease in oncology, thereby highlighting contemporary strengths and limitations. We further propose diagnostic algorithms tailored to women that might help in selecting the most appropriate imaging modality.

Regional myocardial perfusion imaging in predicting vessel-related outcome: interplay between the perfusion results and angiographic findings

BACKGROUND

Despite myocardial perfusion imaging (MPI) by cadmium-zinc-telluride (CZT) single-photon emission computed tomography (SPECT) camera is largely used in the diagnosis and risk stratification of patients with suspected or known coronary artery disease (CAD), no data are available on the prognostic value of a regional MPI evaluation. We evaluated the prognostic value of regional MPI by the CZT camera in predicting clinical outcomes at the vessel level in patients with available angiographic data.

METHODS AND RESULTS

Five hundred and forty-one subjects with suspected or known CAD referred to 99mTc-sestamibi gated CZT-SPECT cardiac imaging and with available angiographic data were studied. Both regional total perfusion deficit (TPD) and ischemic TPD (ITPD) were calculated separately for each vascular territory (left anterior descending, left circumflex, and right coronary artery). The outcome end points were cardiac death, target vessel-related myocardial infarction, or late coronary revascularization. The prevalence of CAD ≥ 50%, regional stress TPD, and regional ITPD was significantly higher in vessels with events as compared to those without (both P < 0.001). The receiver operating characteristics area under the curve for regional ITPD for the identification of vessel-related events was 0.81 (95% confidence interval 0.75-0.86). An ITPD value of 2.0% provided the best trade-off for identifying the vessel-related event. At multivariable analysis, both CAD ≥ 50% and ITPD ≥ 2.0% resulted in independent predictors of events.

CONCLUSIONS

Regional myocardial perfusion assessed by the CZT camera demonstrated good reliability in predicting vessel-related events in patients with suspected or known CAD.

A machine learning approach to characterize patients with asthma exacerbation attending an acute care setting

BACKGROUND

One of the main problems in poorly controlled asthma is the access to the Emergency Department (ED). Using a machine learning (ML) approach, the aim of our study was to identify the main predictors of severe asthma exacerbations requiring hospital admission.

METHODS

Consecutive patients with asthma exacerbation were screened for inclusion within 48 hours of ED discharge. A k-means clustering algorithm was implemented to evaluate a potential distinction of different phenotypes. K-Nearest Neighbor (KNN) as instance-based algorithm and Random Forest (RF) as tree-based algorithm were implemented in order to classify patients, based on the presence of at least one additional access to the ED in the previous 12 months.

RESULTS

To train our model, we included 260 patients (31.5% males, mean age 47.6 years). Unsupervised ML identified two groups, based on eosinophil count. A total of 86 patients with eosinophiles ≥370 cells/µL were significantly older, had a longer disease duration, more restrictions to daily activities, and lower rate of treatment compared to 174 patients with eosinophiles <370 cells/μL. In addition, they reported lower values of predicted FEV₁ (64.8±12.3% vs. 83.9±17.3%) and FEV₁/FVC (71.3±9.3 vs. 78.5±6.8), with a higher amount of exacerbations/year. In supervised ML, KNN achieved the best performance in identifying frequent exacerbators (AUROC: 96.7%), confirming the importance of spirometry parameters and eosinophil count, along with the number of prior exacerbations and other clinical and demographic variables.

CONCLUSIONS

This study confirms the key prognostic value of eosinophiles in asthma, suggesting the usefulness of ML in defining biological pathways that can help plan personalized pharmacological and rehabilitation strategies.

Low-dose dobutamine stress gated blood pool SPECT assessment of left ventricular contractile reserve in ischemic cardiomyopathy: a feasibility study

PURPOSE

The purpose of the present study was to evaluate the feasibility of gated blood pool single-photon emission computed tomography (GBPS) with low-dose dobutamine (LDD) stress test, performed on a single-photon emission computed tomography (SPECT) camera equipped with cadmium-zinc-telluride (CZT) solid-state detectors, in assessing of left ventricle (LV) contractile reserve in patients with ischemic cardiomyopathy (ICM).

METHODS

A total of 52 patients (age 59 ± 7.2 years, 47 men and 5 women) with ICM and a control group of 10 patients without obstructive coronary artery lesion underwent GBPS and transthoracic echocardiography (TTE) at rest and during LDD stress test (5, 10, 15 µg/kg/min). The duration of each GBPS step was 5 min. Stress-induced changes in LV ejection fraction (ΔLVEF), peak ejection rate, LV volumes, and mechanical dyssynchrony (phase histogram standard deviation, phase histogram bandwidth and entropy) obtained with GBPS were estimated.

RESULTS

All GBPS indices except end-diastolic volume showed significant dynamics during stress test in both groups. The majority of parameters in ICM patients showed significant changes at a dobutamine dose of 10 µg/kg/min as compared to the rest study. Seventeen percent of ICM patients, but none from the control group, showed a decrease in LVEF during stress, accompanied by a significant increase in entropy. The intra- and inter-observer reproducibility was excellent for both rest and stress studies. There was a moderate correlation (r = 0.5, p = 0.01) between GBPS and TTE, with a mean difference value of - 1.7 (95% confidence interval - 9.8; 6.4; p = 0.06) in ΔLVEF.

CONCLUSION

Low-dose dobutamine stress GBPS performed with high-efficiency CZT-SPECT cameras can be performed for evaluating stress-induced changes in LV contractility and dyssynchrony with lower acquisition time. A dobutamine dose of 10 µg/kg/min can potentially suffice to detect stress-induced changes in patients with ICM during GBPS.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT04508608 (August 7, 2020).

A machine learning-based approach to directly compare the diagnostic accuracy of myocardial perfusion imaging by conventional and cadmium-zinc telluride SPECT

BACKGROUND

We evaluated the performance of conventional (C) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride (CZT)-SPECT in a large cohort of patients with suspected or known coronary artery disease (CAD) and compared the diagnostic accuracy of the two systems using machine learning (ML) algorithms.

METHODS AND RESULTS

A total of 517 consecutive patients underwent stress myocardial perfusion imaging (MPI) by both C-SPECT and CZT-SPECT. In the overall population, an excellent correlation between stress MPI data and left ventricular (LV) functional parameters measured by C-SPECT and by CZT-SPECT was observed (all P < .001). ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (NN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for k-NN) was greater than that of C-SPECT (88% for RF and 53% for k-NN).

CONCLUSIONS

MPI data and LV functional parameters obtained by CZT-SPECT are highly reproducible and provide good correlation with those obtained by C-SPECT. ML approach showed that the accuracy and sensitivity of CZT-SPECT is greater than C-SPECT in detecting CAD.

Assessment of left ventricular volumes and ejection fraction using ultra-low-dose thallium-201 SPECT on a CZT camera: a comparison with magnetic resonance imaging

BACKGROUND

Cadmium-Zinc-Telluride (CZT) technology allows use of low activities of radiopharmaceuticals. The aim was to verify the values of left ventricular volume parameters, obtained via ultra-low-dose thallium Single Photon Emission Computed Tomography (SPECT) using a CZT camera.

METHODS AND RESULTS

Forty-five patients referred for an assessment of myocardial perfusion or viability imaging were examined using CZT-SPECT and 1.5 T magnetic resonance (MRI) scanner. The ultra-low-dose protocol with 0.5 Mbq 201-Tl per kg of body weight was used. The values of end-systolic (ESV) and end-diastolic volumes (EDV), left ventricular ejection fraction (EF) and myocardial mass (MM) were assessed using both techniques. A very good correlation was found between the EF, ESV, and EDV values assessed with CZT-SPECT and cardiac magnetic resonance MRI; the Pearson coefficients were 0.86, 0.95, and 0.91, respectively. A moderate correlation was found for myocardial mass, r = 0.57. Compared to MRI, SPECT systematically overestimated ESV and MM, while it underestimates the EF, with P ≤ .001 in all cases. There was no difference in EDV estimation.

CONCLUSIONS

Left ventricular volumes and ejection fraction assessed via ultra-low-dose CZT-SPECT showed very good correlation with the values obtained by MRI. A moderate correlation was found for myocardial mass.

Quantification of myocardial perfusion reserve by CZT-SPECT: A head to head comparison with 82Rubidium PET imaging

BACKGROUND

We measured myocardial blood flow (MBF) and perfusion reserve (MPR) by dynamic CZT-SPECT and 82Rb-PET in patients with suspected or known coronary artery disease (CAD) and compared the accuracy of the two methods in predicting obstructive CAD.

METHODS

Twenty-five patients with available coronary angiography data underwent 99mTc-sestamibi CZT-SPECT and 82Rb-PET cardiac imaging. Stress and rest MBF and MPR were calculated by both methods and compared. Diagnostic accuracies of CZT-SPECT and PET were also assessed using a receiver-operator-characteristic curve.

RESULTS

CZT-SPECT yielded similar baseline MBF, but higher hyperemic MBF and MPR values compared to PET. There was a modest correlation between the two methods for MPR (r = 0.56, P < .01). MPR by CZT-SPECT showed a good ability in identify a reduced MPR by PET, with an area under the curve of 0.85. A MPR cut-off of 2.5 was identified by CZT-SPECT for detection of abnormal MPR by PET, with a sensitivity, specificity and accuracy of 86%, 73% and 80%. The area under the curve for the identification of obstructive CAD by regional MPR were 0.83 for CZT-SPECT and 0.84 for PET (P = .90). At CZT-SPECT, a regional MPR of 2.1 provided the best trade-off between sensitivity and specificity for identifying obstructive CAD. Diagnostic accuracy of CZT-SPECT and PET using respective cut-off values was comparable (P = .62).

CONCLUSION

Hyperemic MBF and MPR values obtained by CZT-SPECT are higher than those measured by 82Rb-PET imaging, with a moderate correlation between the two methods. CZT-SPECT shows good diagnostic accuracy for the identification of obstructive CAD. These findings may encourage the use of this new technique to a better risk stratification and patient management.

Capabilities of Modern Semiconductor Gamma Cameras in Radionuclide Diagnosis of Coronary Artery Disease

This paper presents a review of the literature concerning the clinical application of modern semiconductor (CZT) gamma cameras in the radioinuclide diagnosis of coronary artery disease. It contains information on the diagnostic efficacy of myocardial perfusion studies performed with those cameras compared with the widely used scintillation (Anger) cameras, an overview of their effectiveness in comparison with coronary angiography (also fractional flow reserve) and currently available clinical results of a myocardial flow reserve measured with a dynamic SPECT study. Introduction of this imaging modality to the measurement of a myocardial flow reserve aims to facilitate access to this type of study compared to the less available and more expensive PET method used so far.

Impact of COVID-19 infection on short-term outcome in patients referred to stress myocardial perfusion imaging

PURPOSE

We assessed the impact of COVID-19 infection on cardiovascular events in patients with suspected or known coronary artery disease (CAD) referred to stress single-photon emission computed tomography myocardial perfusion imaging (MPS).

METHODS

A total of 960 consecutive patients with suspected or known CAD were submitted by referring physicians to stress MPS for assessment of myocardial ischemia between January 2018 and June 2019. All patients underwent stress-optional rest MPS. Perfusion defects were quantitated as % of LV myocardium and expressed as total perfusion defect (TPD), representing the defect extent and severity. A TPD ≥ 5% was considered abnormal.

RESULTS

During a mean follow-up of 27 months (range 4-38) 31 events occurred. Moreover, 55 (6%) patients had a COVID-19 infection. The median time from index MPS to COVID-19 infection was 16 months (range 6-24). At Cox multivariable analysis, abnormal MPS and COVID-19 infection resulted as independent predictors of events. There were no significant differences in annualized event rate in COVID-19 patients with or without abnormal MPS (p = 0.56). Differently, in patients without COVID-19, the presence of abnormal MPS was associated with higher event rate (p < .001). Patients with infection compared to those without had a higher event rate in the presence of both normal and abnormal TPD.

CONCLUSION

In patients with suspected or known CAD, the presence of COVID-19 infection during a short-term follow-up was associated with a higher rate of cardiovascular events.

Machine Learning Evaluation of Biliary Atresia Patients to Predict Long-Term Outcome after the Kasai Procedure

Kasai portoenterostomy (KP) represents the first-line treatment for biliary atresia (BA). The purpose was to compare the accuracy of quantitative parameters extracted from laboratory tests, US imaging, and MR imaging studies using machine learning (ML) algorithms to predict the long-term medical outcome in native liver survivor BA patients after KP. Twenty-four patients were evaluated according to clinical and laboratory data at initial evaluation (median follow-up = 9.7 years) after KP as having ideal (n = 15) or non-ideal (n = 9) medical outcomes. Patients were re-evaluated after an additional 4 years and classified in group 1 (n = 12) as stable and group 2 (n = 12) as non-stable in the disease course. Laboratory and quantitative imaging parameters were merged to test ML algorithms. Total and direct bilirubin (TB and DB), as laboratory parameters, and US stiffness, as an imaging parameter, were the only statistically significant parameters between the groups. The best algorithm in terms of accuracy, sensitivity, specificity, and AUCROC was naive Bayes algorithm, selecting only laboratory parameters (TB and DB). This preliminary ML analysis confirms the fundamental role of TB and DB values in predicting the long-term medical outcome for BA patients after KP, even though their values may be within the normal range. Physicians should be alert when TB and DB values change slightly.

Comparing the Prognostic Value of Stress Myocardial Perfusion Imaging by Conventional and Cadmium-Zinc Telluride Single-Photon Emission Computed Tomography through a Machine Learning Approach

We compared the prognostic value of myocardial perfusion imaging (MPI) by conventional- (C-) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride- (CZT-) SPECT in a cohort of patients with suspected or known coronary artery disease (CAD) using machine learning (ML) algorithms. A total of 453 consecutive patients underwent stress MPI by both C-SPECT and CZT-SPECT. The outcome was a composite end point of all-cause death, cardiac death, nonfatal myocardial infarction, or coronary revascularization procedures whichever occurred first. ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (KNN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for KNN) was greater than that of C-SPECT (88% for RF and 53% for KNN). A preliminary univariate analysis was performed through Mann-Whitney tests separately on the features of each camera in order to understand which ones could distinguish patients who will experience an adverse event from those who will not. Then, a machine learning analysis was performed by using Matlab (v. 2019b). Tree, KNN, support vector machine (SVM), Naïve Bayes, and RF were implemented twice: first, the analysis was performed on the as-is dataset; then, since the dataset was imbalanced (patients experiencing an adverse event were lower than the others), the analysis was performed again after balancing the classes through the Synthetic Minority Oversampling Technique. According to KNN and SVM with and without balancing the classes, the accuracy (p value = 0.02 and p value = 0.01) and recall (p value = 0.001 and p value = 0.03) of the CZT-SPECT were greater than those obtained by C-SPECT in a statistically significant way. ML approach showed that although the prognostic value of stress MPI by C-SPECT and CZT-SPECT is comparable, CZT-SPECT seems to have higher accuracy and recall.

MRI Radiomics for the Prediction of Fuhrman Grade in Clear Cell Renal Cell Carcinoma: a Machine Learning Exploratory Study

The Fuhrman nuclear grade is a recognized prognostic factor for patients with clear cell renal cell carcinoma (CCRCC) and its pre-treatment evaluation significantly affects decision-making in terms of management. In this study, we aimed to assess the feasibility of a combined approach of radiomics and machine learning based on MR images for a non-invasive prediction of Fuhrman grade, specifically differentiation of high- from low-grade tumor and grade assessment. Images acquired on a 3-Tesla scanner (T2-weighted and post-contrast) from 32 patients (20 with low-grade and 12 with high-grade tumor) were annotated to generate volumes of interest enclosing CCRCC lesions. After image resampling, normalization, and filtering, 2438 features were extracted. A two-step feature reduction process was used to between 1 and 7 features depending on the algorithm employed. A J48 decision tree alone and in combination with ensemble learning methods were used. In the differentiation between high- and low-grade tumors, all the ensemble methods achieved an accuracy greater than 90%. On the other end, the best results in terms of accuracy (84.4%) in the assessment of tumor grade were achieved by the random forest. These evidences support the hypothesis that a combined radiomic and machine learning approach based on MR images could represent a feasible tool for the prediction of Fuhrman grade in patients affected by CCRCC.

Health technology assessment through the six sigma approach in abdominoplasty: Scalpel vs electrosurgery

Abdominoplasty is a surgical procedure conducted to reduce excess abdominal skin and fat and improve body contouring. Despite being commonly performed, it is associated with a risk of complications such as infection, seroma, haematoma and wound dehiscence. To reduce the incidence of complications, different methods are used to create the abdominal flap, i.e., incision with a scalpel or electrosurgery. In this study, health technology assessment (HTA) using the Six Sigma methodology was conducted to compare these incision techniques in patients undergoing abdominoplasty. Two consecutively enroled groups of patients (33 in the scalpel group and 35 in the electrosurgery group) who underwent surgery at a single institution, the University of Campania "Luigi Vanvitelli", were analysed using the drain output as the main outcome for comparison of the incision techniques. While no difference was found regarding haematoma or seroma formation (no cases in either group), the main results also indicate a greater drain output (p-value<0.001) and a greater incidence of dehiscence (p-value=0.056) in patients whose incisions were made through electrosurgery. The combination of HTA and the Six Sigma methodology was useful to prove the possible advantages of creating skin incisions with a scalpel in full abdominoplasty, particularly a significant reduction in the total drain output and a reduction in wound healing problems, namely, wound dehiscence, when compared with electrosurgery, despite considering two limited and heterogeneous groups.

Machine learning analysis: general features, requirements and cardiovascular applications

Artificial intelligence represents the science which will probably change the future of medicine by solving actually challenging issues. In this special article, the general features of machine learning are discussed. First, a background explanation regarding the division of artificial intelligence, machine learning and deep learning is given and a focus on the structure of machine learning subgroups is shown. The traditional process of a machine learning analysis is described, starting from the collection of data, across features engineering, modelling and till the validation and deployment phase. Due to the several applications of machine learning performed in literature in the last decades and the lack of some guidelines, the need of a standardization for reporting machine learning analysis results emerged. Some possible standards for reporting machine learning results are identified and discussed deeply; these are related to study population (number of subjects), repeatability of the analysis, validation, results, comparison with current practice. The way to the use of machine learning in clinical practice is open and the hope is that, with emerging technology and advanced digital and computational tools, available from hospitalization and subsequently after discharge, it will also be possible, with the help of increasingly powerful hardware, to build assistance strategies useful in clinical practice.

A Six Sigma DMAIC methodology as a support tool for Health Technology Assessment of two antibiotics

Health Technology Assessment (HTA) and Six Sigma (SS) have largely proved their reliability in the healthcare context. The former focuses on the assessment of health technologies to be introduced in a healthcare system. The latter deals with the improvement of the quality of services, reducing errors and variability in the healthcare processes. Both the approaches demand a detailed analysis, evidence-based decisions, and efficient control plans. In this paper, the SS is applied as a support tool for HTA of two antibiotics with the final aim of assessing their clinical and organizational impact in terms of postoperative Length Of Stay (LOS) for patients undergoing tongue cancer surgery. More specifically, the SS has been implemented through its main tool, namely the DMAIC (Define, Measure, Analyse, Improve, Control) cycle. Moreover, within the DMAIC cycle, a modelling approach based on a multiple linear regression analysis technique is introduced, in the Control phase, to add complementary information and confirm the results obtained by the statistical analysis performed within the other phases of the SS DMAIC. The obtained results show that the proposed methodology is effective to determine the clinical and organizational impact of each of the examined antibiotics, when LOS is taken as a measure of performance, and guide the decision-making process. Furthermore, our study provides a systematic procedure which, properly combining different and well-assessed tools available in the literature, demonstrated to be a useful guidance for choosing the right treatment based on the available data in the specific circumstance.

Diagnostic analysis of new quantitative parameters of low-dose dynamic myocardial perfusion imaging with CZT SPECT in the detection of suspected or known coronary artery disease

The goal of this study is to explore and evaluate the diagnostic values of myocardial blood flow (MBF), myocardial flow reserve (MFR) and relative flow reserve (RFR) obtained with low-dose dynamic CZT SPECT for patients with suspected or known coronary artery disease (CAD). Fifty-seven consecutive patients who underwent low-dose dynamic CZT SPECT and CAG were enrolled. MBF, MFR and RFR were calculated on the vessel level with dedicated quantitative software, and the difference and correlation of each parameter was compared according to the reference standard of stenosis ≥ 50% or ≥ 75% on CAG, respectively. ROC curves were made by stress MBF (sMBF), rest MBF (rMBF), MFR and RFR. The optimal cut-off values and corresponding diagnostic efficacy were obtained and compared with each other. Results indicated that when stenosis ≥ 50% or ≥ 75% on CAG was used as the reference standard at the vessel level, there was no statistically significant difference in rMBF between the negative group and the positive group (P > 0.05), and the sMBF and MFR in positive groups were significantly lower than that in the negative group (all P < 0.05). There was a moderate to significant correlation between sMBF and MFR, sMBF and RFR, MFR and RFR (all P < 0.0001). These results indicate that low-dose dynamic CZT SPECT imaging can easily obtain the sMBF, MFR and RFR, and there is a good correlation among the three parameters, which has a certain diagnostic value for patients with suspected or known CAD, and is a useful supplement to the conventional qualitative or semi-quantitative diagnostic methods.

Effects of the COVID-19 pandemic on myocardial perfusion imaging for ischemic heart disease

Purpose

We assessed the effects of the COVID-19 pandemic on myocardial perfusion imaging (MPI) for ischemic heart disease during the lockdown imposed by the Italian Government.

Methods

We retrospectively reviewed the number and the findings of stress single-photon emission computed tomography (SPECT)-MPI performed between February and May 2020 during the COVID-19 pandemic at the University of Napoli Federico II. The number and the findings of stress SPECT-MPI studies acquired in the corresponding months of the years 2017, 2018, and 2019 were also evaluated for direct comparison.

Results

The number of stress SPECT-MPI studies performed during the COVID-19 pandemic (n = 123) was significantly lower (P < 0.0001) compared with the mean yearly number of procedures performed in the corresponding months of the years 2017, 2018, and 2019 (n = 413). Yet, the percentage of abnormal stress SPECT-MPI studies was similar (P = 0.65) during the pandemic (36%) compared with the mean percentage value of the corresponding period of the years 2017, 2018, and 2019 (34%).

Conclusion

The number of stress SPECT-MPI studies was significantly reduced during the COVID-19 pandemic compared with the corresponding months of the previous 3 years. The lack of difference in the prevalence of abnormal SPECT-MPI studies between the two study periods strongly suggests that many patients with potentially abnormal imaging test have been missed during the pandemic.

Assessing cardiovascular risks from a mid-thigh CT image: a tree-based machine learning approach using radiodensitometric distributions

The nonlinear trimodal regression analysis (NTRA) method based on radiodensitometric CT distributions was recently developed and assessed for the quantification of lower extremity function and nutritional parameters in aging subjects. However, the use of the NTRA method for building predictive models of cardiovascular health was not explored; in this regard, the present study reports the use of NTRA parameters for classifying elderly subjects with coronary heart disease (CHD), cardiovascular disease (CVD), and chronic heart failure (CHF) using multivariate logistic regression and three tree-based machine learning (ML) algorithms. Results from each model were assembled as a typology of four classification metrics: total classification score, classification by tissue type, tissue-based feature importance, and classification by age. The predictive utility of this method was modelled using CHF incidence data. ML models employing the random forests algorithm yielded the highest classification performance for all analyses, and overall classification scores for all three conditions were excellent: CHD (AUCROC: 0.936); CVD (AUCROC: 0.914); CHF (AUCROC: 0.994). Longitudinal assessment for modelling the prediction of CHF incidence was likewise robust (AUCROC: 0.993). The present work introduces a substantial step forward in the construction of non-invasive, standardizable tools for associating adipose, loose connective, and lean tissue changes with cardiovascular health outcomes in elderly individuals.