Clinical Significance of Myocardial Injury in Patients Hospitalized for COVID-19: A Prospective, Multicenter, Cohort Study.

BACKGROUND: Hospitalized COVID-19 patients with troponin elevation have a higher prevalence of cardiac abnormalities than control individuals. However, the progression and impact of myocardial injury on COVID-19 survivors remain unclear. OBJECTIVES: This study sought to evaluate myocardial injury in COVID-19 survivors with troponin elevation with baseline and follow-up imaging and to assess medium-term outcomes. METHODS: This was a prospective, longitudinal cohort study in 25 United Kingdom centers (June 2020 to March 2021). Hospitalized COVID-19 patients with myocardial injury underwent cardiac magnetic resonance (CMR) scans within 28 days and 6 months postdischarge. Outcomes were tracked for 12 months, with quality of life surveys (EuroQol-5 Dimension and 36-Item Short Form surveys) taken at discharge and 6 months. RESULTS: Of 342 participants (median age: 61.3 years; 71.1% male) with baseline CMR, 338 had a 12-month follow-up, 235 had a 6-month CMR, and 215 has baseline and follow-up quality of life surveys. Of 338 participants, within 12 months, 1.2% died; 1.8% had new myocardial infarction, acute coronary syndrome, or coronary revascularization; 0.8% had new myopericarditis; and 3.3% had other cardiovascular events requiring hospitalization. At 6 months, there was a minor improvement in left ventricular ejection fraction (1.8% ± 1.0%; P < 0.001), stable right ventricular ejection fraction (0.4% ± 0.8%; P = 0.50), no change in myocardial scar pattern or volume (P = 0.26), and no imaging evidence of continued myocardial inflammation. All pericardial effusions (26 of 26) resolved, and most pneumonitis resolved (95 of 101). EuroQol-5 Dimension scores indicated an overall improvement in quality of life (P < 0.001). CONCLUSIONS: Myocardial injury in severe hospitalized COVID-19 survivors is nonprogressive. Medium-term outcomes show a low incidence of major adverse cardiovascular events and improved quality of life. (COVID-19 Effects on the Heart; ISRCTN58667920).

Challenges for augmenting intelligence in cardiac imaging.

Artificial Intelligence (AI), through deep learning, has brought automation and predictive capabilities to cardiac imaging. However, despite considerable investment, tangible health-care cost reductions remain unproven. Although AI holds promise, there has been insufficient time for both methodological development and prospective clinical trials to establish its advantage over human interpretations in terms of its effect on patient outcomes. Challenges such as data scarcity, privacy issues, and ethical concerns impede optimal AI training. Furthermore, the absence of a unified model for the complex structure and function of the heart and evolving domain knowledge can introduce heuristic biases and influence underlying assumptions in model development. Integrating AI into diverse institutional picture archiving and communication systems and devices also presents a clinical hurdle. This hurdle is further compounded by an absence of high-quality labelled data, difficulty sharing data between institutions, and non-uniform and inadequate gold standards for external validations and comparisons of model performance in real-world settings. Nevertheless, there is a strong push in industry and academia for AI solutions in medical imaging. This Series paper reviews key studies and identifies challenges that require a pragmatic change in the approach for using AI for cardiac imaging, whereby AI is viewed as augmented intelligence to complement, not replace, human judgement. The focus should shift from isolated measurements to integrating non-linear and complex data towards identifying disease phenotypes-emphasising pattern recognition where AI excels. Algorithms should enhance imaging reports, enriching patients' understanding, communication between patients and clinicians, and shared decision making. The emergence of professional standards and guidelines is essential to address these developments and ensure the safe and effective integration of AI in cardiac imaging.

The Impact of Bariatric Surgery on Coronary Microvascular Function Assessed Using Automated Quantitative Perfusion CMR.

BACKGROUND: Coronary microvascular function is impaired in patients with obesity, contributing to myocardial dysfunction and heart failure. Bariatric surgery decreases cardiovascular mortality and heart failure, but the mechanisms are unclear. OBJECTIVES: The authors studied the impact of bariatric surgery on coronary microvascular function in patients with obesity and its relationship with metabolic syndrome. METHODS: Fully automated quantitative perfusion cardiac magnetic resonance and metabolic markers were performed before and 6 months after bariatric surgery. RESULTS: Compared with age- and sex-matched healthy volunteers, 38 patients living with obesity had lower stress myocardial blood flow (MBF) (P = 0.001) and lower myocardial perfusion reserve (P < 0.001). A total of 27 participants underwent paired follow-up 6 months post-surgery. Metabolic abnormalities reduced significantly at follow-up including mean body mass index by 11 ± 3 kg/m2 (P < 0.001), glycated hemoglobin by 9 mmol/mol (Q1-Q3: 4-19 mmol/mol; P < 0.001), fasting insulin by 142 ± 131 pmol/L (P < 0.001), and hepatic fat fraction by 5.6% (2.6%-15.0%; P < 0.001). Stress MBF increased by 0.28 mL/g/min (-0.02 to 0.75 mL/g/min; P = 0.003) and myocardial perfusion reserve by 0.13 (-0.25 to 1.1; P = 0.036). The increase in stress MBF was lower in those with preoperative type 2 diabetes mellitus (0.1 mL/g/min [-0.09 to 0.46 mL/g/min] vs 0.75 mL/g/min [0.31-1.25 mL/g/min]; P = 0.002). Improvement in stress MBF was associated with reduction in fasting insulin (beta = -0.45 [95% CI: -0.05 to 0.90]; P = 0.03). CONCLUSIONS: Coronary microvascular function is impaired in patients with obesity, but can be improved significantly with bariatric surgery. Improvements in microvascular function are associated with improvements in insulin resistance but are attenuated in those with preoperative type 2 diabetes mellitus.

Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization.

BACKGROUND: Late gadolinium enhancement (LGE) of the myocardium has significant diagnostic and prognostic implications, with even small areas of enhancement being important. Distinguishing between definitely normal and definitely abnormal LGE images is usually straightforward, but diagnostic uncertainty arises when reporters are not sure whether the observed LGE is genuine or not. This uncertainty might be resolved by repetition (to remove artifact) or further acquisition of intersecting images, but this must take place before the scan finishes. Real-time quality assurance by humans is a complex task requiring training and experience, so being able to identify which images have an intermediate likelihood of LGE while the scan is ongoing, without the presence of an expert is of high value. This decision-support could prompt immediate image optimization or acquisition of supplementary images to confirm or refute the presence of genuine LGE. This could reduce ambiguity in reports. METHODS: Short-axis, phase-sensitive inversion recovery late gadolinium images were extracted from our clinical cardiac magnetic resonance (CMR) database and shuffled. Two, independent, blinded experts scored each individual slice for "LGE likelihood" on a visual analog scale, from 0 (absolute certainty of no LGE) to 100 (absolute certainty of LGE), with 50 representing clinical equipoise. The scored images were split into two classes-either "high certainty" of whether LGE was present or not, or "low certainty." The dataset was split into training, validation, and test sets (70:15:15). A deep learning binary classifier based on the EfficientNetV2 convolutional neural network architecture was trained to distinguish between these categories. Classifier performance on the test set was evaluated by calculating the accuracy, precision, recall, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Performance was also evaluated on an external test set of images from a different center. RESULTS: One thousand six hundred and forty-five images (from 272 patients) were labeled and split at the patient level into training (1151 images), validation (247 images), and test (247 images) sets for the deep learning binary classifier. Of these, 1208 images were "high certainty" (255 for LGE, 953 for no LGE), and 437 were "low certainty". An external test comprising 247 images from 41 patients from another center was also employed. After 100 epochs, the performance on the internal test set was accuracy = 0.94, recall = 0.80, precision = 0.97, F1-score = 0.87, and ROC AUC = 0.94. The classifier also performed robustly on the external test set (accuracy = 0.91, recall = 0.73, precision = 0.93, F1-score = 0.82, and ROC AUC = 0.91). These results were benchmarked against a reference inter-expert accuracy of 0.86. CONCLUSION: Deep learning shows potential to automate quality control of late gadolinium imaging in CMR. The ability to identify short-axis images with intermediate LGE likelihood in real-time may serve as a useful decision-support tool. This approach has the potential to guide immediate further imaging while the patient is still in the scanner, thereby reducing the frequency of recalls and inconclusive reports due to diagnostic indecision.

Diagnosis and prognosis of abnormal cardiac scintigraphy uptake suggestive of cardiac amyloidosis using artificial intelligence: a retrospective, international, multicentre, cross-tracer development and validation study.

BACKGROUND: The diagnosis of cardiac amyloidosis can be established non-invasively by scintigraphy using bone-avid tracers, but visual assessment is subjective and can lead to misdiagnosis. We aimed to develop and validate an artificial intelligence (AI) system for standardised and reliable screening of cardiac amyloidosis-suggestive uptake and assess its prognostic value, using a multinational database of 99mTc-scintigraphy data across multiple tracers and scanners. METHODS: In this retrospective, international, multicentre, cross-tracer development and validation study, 16 241 patients with 19 401 scans were included from nine centres: one hospital in Austria (consecutive recruitment Jan 4, 2010, to Aug 19, 2020), five hospital sites in London, UK (consecutive recruitment Oct 1, 2014, to Sept 29, 2022), two centres in China (selected scans from Jan 1, 2021, to Oct 31, 2022), and one centre in Italy (selected scans from Jan 1, 2011, to May 23, 2023). The dataset included all patients referred to whole-body 99mTc-scintigraphy with an anterior view and all 99mTc-labelled tracers currently used to identify cardiac amyloidosis-suggestive uptake. Exclusion criteria were image acquisition at less than 2 h (99mTc-3,3-diphosphono-1,2-propanodicarboxylic acid, 99mTc-hydroxymethylene diphosphonate, and 99mTc-methylene diphosphonate) or less than 1 h (99mTc-pyrophosphate) after tracer injection and if patients' imaging and clinical data could not be linked. Ground truth annotation was derived from centralised core-lab consensus reading of at least three independent experts (CN, TT-W, and JN). An AI system for detection of cardiac amyloidosis-associated high-grade cardiac tracer uptake was developed using data from one centre (Austria) and independently validated in the remaining centres. A multicase, multireader study and a medical algorithmic audit were conducted to assess clinician performance compared with AI and to evaluate and correct failure modes. The system's prognostic value in predicting mortality was tested in the consecutively recruited cohorts using cox proportional hazards models for each cohort individually and for the combined cohorts. FINDINGS: The prevalence of cases positive for cardiac amyloidosis-suggestive uptake was 142 (2%) of 9176 patients in the Austrian, 125 (2%) of 6763 patients in the UK, 63 (62%) of 102 patients in the Chinese, and 103 (52%) of 200 patients in the Italian cohorts. In the Austrian cohort, cross-validation performance showed an area under the curve (AUC) of 1·000 (95% CI 1·000-1·000). Independent validation yielded AUCs of 0·997 (0·993-0·999) for the UK, 0·925 (0·871-0·971) for the Chinese, and 1·000 (0·999-1·000) for the Italian cohorts. In the multicase multireader study, five physicians disagreed in 22 (11%) of 200 cases (Fleiss' kappa 0·89), with a mean AUC of 0·946 (95% CI 0·924-0·967), which was inferior to AI (AUC 0·997 [0·991-1·000], p=0·0040). The medical algorithmic audit demonstrated the system's robustness across demographic factors, tracers, scanners, and centres. The AI's predictions were independently prognostic for overall mortality (adjusted hazard ratio 1·44 [95% CI 1·19-1·74], p<0·0001). INTERPRETATION: AI-based screening of cardiac amyloidosis-suggestive uptake in patients undergoing scintigraphy was reliable, eliminated inter-rater variability, and portended prognostic value, with potential implications for identification, referral, and management pathways. FUNDING: Pfizer.

Electrophysiological Characterization of Subclinical and Overt Hypertrophic Cardiomyopathy by Magnetic Resonance Imaging-Guided Electrocardiography.

BACKGROUND: Ventricular arrhythmia in hypertrophic cardiomyopathy (HCM) relates to adverse structural change and genetic status. Cardiovascular magnetic resonance (CMR)-guided electrocardiographic imaging (ECGI) noninvasively maps cardiac structural and electrophysiological (EP) properties. OBJECTIVES: The purpose of this study was to establish whether in subclinical HCM (genotype [G]+ left ventricular hypertrophy [LVH]-), ECGI detects early EP abnormality, and in overt HCM, whether the EP substrate relates to genetic status (G+/G-LVH+) and structural phenotype. METHODS: This was a prospective 211-participant CMR-ECGI multicenter study of 70 G+LVH-, 104 LVH+ (51 G+/53 G-), and 37 healthy volunteers (HVs). Local activation time (AT), corrected repolarization time, corrected activation-recovery interval, spatial gradients (GAT/GRTc), and signal fractionation were derived from 1,000 epicardial sites per participant. Maximal wall thickness and scar burden were derived from CMR. A support vector machine was built to discriminate G+LVH- from HV and low-risk HCM from those with intermediate/high-risk score or nonsustained ventricular tachycardia. RESULTS: Compared with HV, subclinical HCM showed mean AT prolongation (P = 0.008) even with normal 12-lead electrocardiograms (ECGs) (P = 0.009), and repolarization was more spatially heterogenous (GRTc: P = 0.005) (23% had normal ECGs). Corrected activation-recovery interval was prolonged in overt vs subclinical HCM (P < 0.001). Mean AT was associated with maximal wall thickness; spatial conduction heterogeneity (GAT) and fractionation were associated with scar (all P < 0.05), and G+LVH+ had more fractionation than G-LVH+ (P = 0.002). The support vector machine discriminated subclinical HCM from HV (10-fold cross-validation accuracy 80% [95% CI: 73%-85%]) and identified patients at higher risk of sudden cardiac death (accuracy 82% [95% CI: 78%-86%]). CONCLUSIONS: In the absence of LVH or 12-lead ECG abnormalities, HCM sarcomere gene mutation carriers express an aberrant EP phenotype detected by ECGI. In overt HCM, abnormalities occur more severely with adverse structural change and positive genetic status.

Technical development and feasibility of a reusable vest to integrate cardiovascular magnetic resonance with electrocardiographic imaging.

BACKGROUND: Electrocardiographic imaging (ECGI) generates electrophysiological (EP) biomarkers while cardiovascular magnetic resonance (CMR) imaging provides data about myocardial structure, function and tissue substrate. Combining this information in one examination is desirable but requires an affordable, reusable, and high-throughput solution. We therefore developed the CMR-ECGI vest and carried out this technical development study to assess its feasibility and repeatability in vivo. METHODS: CMR was prospectively performed at 3T on participants after collecting surface potentials using the locally designed and fabricated 256-lead ECGI vest. Epicardial maps were reconstructed to generate local EP parameters such as activation time (AT), repolarization time (RT) and activation recovery intervals (ARI). 20 intra- and inter-observer and 8 scan re-scan repeatability tests. RESULTS: 77 participants were recruited: 27 young healthy volunteers (HV, 38.9 ± 8.5 years, 35% male) and 50 older persons (77.0 ± 0.1 years, 52% male). CMR-ECGI was achieved in all participants using the same reusable, washable vest without complications. Intra- and inter-observer variability was low (correlation coefficients [rs] across unipolar electrograms = 0.99 and 0.98 respectively) and scan re-scan repeatability was high (rs between 0.81 and 0.93). Compared to young HV, older persons had significantly longer RT (296.8 vs 289.3 ms, p = 0.002), ARI (249.8 vs 235.1 ms, p = 0.002) and local gradients of AT, RT and ARI (0.40 vs 0.34 ms/mm, p = 0,01; 0.92 vs 0.77 ms/mm, p = 0.03; and 1.12 vs 0.92 ms/mm, p = 0.01 respectively). CONCLUSION: Our high-throughput CMR-ECGI solution is feasible and shows good reproducibility in younger and older participants. This new technology is now scalable for high throughput research to provide novel insights into arrhythmogenesis and potentially pave the way for more personalised risk stratification. CLINICAL TRIAL REGISTRATION: Title: Multimorbidity Life-Course Approach to Myocardial Health-A Cardiac Sub-Study of the MRC National Survey of Health and Development (NSHD) (MyoFit46). National Clinical Trials (NCT) number: NCT05455125. URL: https://clinicaltrials.gov/ct2/show/NCT05455125?term=MyoFit&draw=2&rank=1.

Extended Total Temporomandibular Joint Replacement - A Feasible Option for Functional and Aesthetic Reconstruction of Mandibular Defects Involving the Temporomandibular Joint.

Study design: Retrospective case series. Objective: Alloplastic temporomandibular joint replacement has been established as a standard technique for end- stage temporomandibular (TMJ) pathologies. Joint replacement when there are extensive mandibular defects remains a challenging clinical problem. Custom-made extended temporomandibular joint replacement is a feasible option but there is limited information about this emerging technique. Methods: Included were all patients undergoing extended TMJ-replacements (TMJe), all operatrions were carried out by the senior author. Surgical technique was either single stage or two stage protocol. Surgical details and pitfalls and outcome of more than 2 years follow-up with reference to thirteen including twelve patients were recorded. Results: The most common diagnosis was ameloblastoma of the mandibular ramus. Single stage or two stagge regime were carried out depending on resection requirements and involvement of teeth. Improved mouth opening of more than 30mm was achieved in 10 of 12 patients. One patient with previous TMJ replacement reported temporary weakness of the facial nerve, which resolved after 10 months. Conclusions: The authors suggest a simplified anatomically based single-stage or two-stage regime, with both regimes achieved excellent anatomic reconstruction, facial appearance and function with low surgical morbidity. Custom-made extended temporomandibular joint protheses appear an advanced and reliable solution for reconstruction of combined complex mandibular defects including the temporomandibular joint. If surgical clearance of the pathology can be achieved, a single-stage regime is favoured.

Improved Diagnostic Criteria for Apical Hypertrophic Cardiomyopathy.

BACKGROUND: There is no acceptable maximum wall thickness (MWT) threshold for diagnosing apical hypertrophic cardiomyopathy (ApHCM), with guidelines referring to ≥15 mm MWT for all hypertrophic cardiomyopathy subtypes. A normal myocardium naturally tapers apically; a fixed diagnostic threshold fails to account for this. Using cardiac magnetic resonance, "relative" ApHCM has been described with typical electrocardiographic features, loss of apical tapering, and cavity obliteration but also with MWT <15 mm. OBJECTIVES: The authors aimed to define normal apical wall thickness thresholds in healthy subjects and use these to accurately identify ApHCM. METHODS: The following healthy subjects were recruited: healthy UK Biobank imaging substudy subjects (n = 4,112) and an independent healthy volunteer group (n = 489). A clinically defined disease population of 104 ApHCM subjects was enrolled, with 72 overt (MWT ≥15 mm) and 32 relative (MWT <15 mm but typical electrocardiographic/imaging findings) ApHCM subjects. Cardiac magnetic resonance-derived MWT was measured in 16 segments using a published clinically validated machine learning algorithm. Segmental normal reference ranges were created and indexed (for age, sex, and body surface area), and diagnostic performance was assessed. RESULTS: In healthy cohorts, there was no clinically significant age-related difference for apical wall thickness. There were sex-related differences, but these were not clinically significant after indexing to body surface area. Therefore, segmental reference ranges for apical hypertrophy required indexing to body surface area only (not age or sex). The upper limit of normal (the largest of the 4 apical segments measured) corresponded to a maximum apical MWT in healthy subjects of 5.2 to 5.6 mm/m2 with an accuracy of 0.94 (the unindexed equivalent being 11 mm). This threshold was categorized as abnormal in 99% (71/72) of overt ApHCM patients, 78% (25/32) of relative ApHCM patients, 3% (122/4,112) of UK Biobank subjects, and 3% (13/489) of healthy volunteers. CONCLUSIONS: Per-segment indexed apical wall thickness thresholds are highly accurate for detecting apical hypertrophy, providing confidence to the reader to diagnose ApHCM in those not reaching current internationally recognized criteria.

Design and Implementation of an Innovative, Rapid Data-Monitoring Strategy for Public Health Emergencies: Pilot of the United States School COVID-19 Mitigation Strategies Project.

During the COVID-19 pandemic, an urgent need existed for near-real-time data collection to better understand how individual beliefs and behaviors, state and local policies, and organizational practices influenced health outcomes. We describe the processes, methods, and lessons learned during the development and pilot testing of an innovative rapid data collection process we developed to inform decision-making during the COVID-19 public health emergency. We used a fully integrated mixed-methods approach to develop a structured process for triangulating quantitative and qualitative data from traditional (cross-sectional surveys, focus groups) and nontraditional (social media listening) sources. Respondents included students, parents, teachers, and key school personnel (eg, nurses, administrators, mental health providers). During the pilot phase (February-June 2021), data from 12 cross-sectional and sector-based surveys (n = 20 302 participants), 28 crowdsourced surveys (n = 26 820 participants), 10 focus groups (n = 64 participants), and 11 social media platforms (n = 432 754 503 responses) were triangulated with other data to support COVID-19 mitigation in schools. We disseminated findings through internal dashboards, triangulation reports, and policy briefs. This pilot demonstrated that triangulating traditional and nontraditional data sources can provide rapid data about barriers and facilitators to mitigation implementation during an evolving public health emergency. Such a rapid feedback and continuous improvement model can be tailored to strengthen response efforts. This approach emphasizes the value of nimble data modernization efforts to respond in real time to public health emergencies.

Microstructural and Microvascular Phenotype of Sarcomere Mutation Carriers and Overt Hypertrophic Cardiomyopathy.

BACKGROUND: In hypertrophic cardiomyopathy (HCM), myocyte disarray and microvascular disease (MVD) have been implicated in adverse events, and recent evidence suggests that these may occur early. As novel therapy provides promise for disease modification, detection of phenotype development is an emerging priority. To evaluate their utility as early and disease-specific biomarkers, we measured myocardial microstructure and MVD in 3 HCM groups-overt, either genotype-positive (G+LVH+) or genotype-negative (G-LVH+), and subclinical (G+LVH-) HCM-exploring relationships with electrical changes and genetic substrate. METHODS: This was a multicenter collaboration to study 206 subjects: 101 patients with overt HCM (51 G+LVH+ and 50 G-LVH+), 77 patients with G+LVH-, and 28 matched healthy volunteers. All underwent 12-lead ECG, quantitative perfusion cardiac magnetic resonance imaging (measuring myocardial blood flow, myocardial perfusion reserve, and perfusion defects), and cardiac diffusion tensor imaging measuring fractional anisotropy (lower values expected with more disarray), mean diffusivity (reflecting myocyte packing/interstitial expansion), and second eigenvector angle (measuring sheetlet orientation). RESULTS: Compared with healthy volunteers, patients with overt HCM had evidence of altered microstructure (lower fractional anisotropy, higher mean diffusivity, and higher second eigenvector angle; all P<0.001) and MVD (lower stress myocardial blood flow and myocardial perfusion reserve; both P<0.001). Patients with G-LVH+ were similar to those with G+LVH+ but had elevated second eigenvector angle (P<0.001 after adjustment for left ventricular hypertrophy and fibrosis). In overt disease, perfusion defects were found in all G+ but not all G- patients (100% [51/51] versus 82% [41/50]; P=0.001). Patients with G+LVH- compared with healthy volunteers similarly had altered microstructure, although to a lesser extent (all diffusion tensor imaging parameters; P<0.001), and MVD (reduced stress myocardial blood flow [P=0.015] with perfusion defects in 28% versus 0 healthy volunteers [P=0.002]). Disarray and MVD were independently associated with pathological electrocardiographic abnormalities in both overt and subclinical disease after adjustment for fibrosis and left ventricular hypertrophy (overt: fractional anisotropy: odds ratio for an abnormal ECG, 3.3, P=0.01; stress myocardial blood flow: odds ratio, 2.8, P=0.015; subclinical: fractional anisotropy odds ratio, 4.0, P=0.001; myocardial perfusion reserve odds ratio, 2.2, P=0.049). CONCLUSIONS: Microstructural alteration and MVD occur in overt HCM and are different in G+ and G- patients. Both also occur in the absence of hypertrophy in sarcomeric mutation carriers, in whom changes are associated with electrocardiographic abnormalities. Measurable changes in myocardial microstructure and microvascular function are early-phenotype biomarkers in the emerging era of disease-modifying therapy.

Artificial intelligence in medical device software and high-risk medical devices - a review of definitions, expert recommendations and regulatory initiatives.

INTRODUCTION: Artificial intelligence (AI) encompasses a wide range of algorithms with risks when used to support decisions about diagnosis or treatment, so professional and regulatory bodies are recommending how they should be managed. AREAS COVERED: AI systems may qualify as standalone medical device software (MDSW) or be embedded within a medical device. Within the European Union (EU) AI software must undergo a conformity assessment procedure to be approved as a medical device. The draft EU Regulation on AI proposes rules that will apply across industry sectors, while for devices the Medical Device Regulation also applies. In the CORE-MD project (Coordinating Research and Evidence for Medical Devices), we have surveyed definitions and summarize initiatives made by professional consensus groups, regulators, and standardization bodies. EXPERT OPINION: The level of clinical evidence required should be determined according to each application and to legal and methodological factors that contribute to risk, including accountability, transparency, and interpretability. EU guidance for MDSW based on international recommendations does not yet describe the clinical evidence needed for medical AI software. Regulators, notified bodies, manufacturers, clinicians and patients would all benefit from common standards for the clinical evaluation of high-risk AI applications and transparency of their evidence and performance.

Behavioral health and treatment-seeking behaviors among deployed vs. non-deployed service members: How impactful is deployment on well-being?

Increasing attention has been dedicated to studying behavioral health of non-deployed military personnel. This investigation explored the impacts of a variety of sociodemographic and health factors on key behavioral health outcomes among active duty personnel. A secondary analysis was conducted using 2014 Defense Health Agency Health Related Behaviors Survey data (unweighted n = 45,762, weighted n = 1,251,606). Three logistic regression models investigated factors associated with reporting symptomatology consistent with depression, anxiety, and stress. We found that after adjusting for sociodemographic and other health variables (e.g., sleep), deployment was associated with stress but not anxiety or depression. Although deployed personnel were more likely to report increased levels of stress overall, few differences with respect to the sources of stressors were identified. While behavioral health screening and treatment needs may differ for non-deployed and deployed personnel, programs to support mental and physical well-being among all service members should be robustly promoted.

Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging.

Purpose: Neural networks have potential to automate medical image segmentation but require expensive labeling efforts. While methods have been proposed to reduce the labeling burden, most have not been thoroughly evaluated on large, clinical datasets or clinical tasks. We propose a method to train segmentation networks with limited labeled data and focus on thorough network evaluation. Approach: We propose a semi-supervised method that leverages data augmentation, consistency regularization, and pseudolabeling and train four cardiac magnetic resonance (MR) segmentation networks. We evaluate the models on multiinstitutional, multiscanner, multidisease cardiac MR datasets using five cardiac functional biomarkers, which are compared to an expert's measurements using Lin's concordance correlation coefficient (CCC), the within-subject coefficient of variation (CV), and the Dice coefficient. Results: The semi-supervised networks achieve strong agreement using Lin's CCC ( > 0.8 ), CV similar to an expert, and strong generalization performance. We compare the error modes of the semi-supervised networks against fully supervised networks. We evaluate semi-supervised model performance as a function of labeled training data and with different types of model supervision, showing that a model trained with 100 labeled image slices can achieve a Dice coefficient within 1.10% of a network trained with 16,000+ labeled image slices. Conclusion: We evaluate semi-supervision for medical image segmentation using heterogeneous datasets and clinical metrics. As methods for training models with little labeled data become more common, knowledge about how they perform on clinical tasks, how they fail, and how they perform with different amounts of labeled data is useful to model developers and users.

Apical Ischemia Is a Universal Feature of Apical Hypertrophic Cardiomyopathy.

BACKGROUND: Apical hypertrophic cardiomyopathy (ApHCM) accounts for ≈10% of hypertrophic cardiomyopathy cases and is characterized by apical hypertrophy, apical cavity obliteration, and tall ECG R waves with ischemic-looking deep T-wave inversion. These may be present even with <15 mm apical hypertrophy (relative ApHCM). Microvascular dysfunction is well described in hypertrophic cardiomyopathy. We hypothesized that apical perfusion defects would be common in ApHCM. METHODS: A 2-center study using cardiovascular magnetic resonance short- and long-axis quantitative adenosine vasodilator stress perfusion mapping. One hundred patients with ApHCM (68 overt hypertrophy [≥15 mm] and 32 relative ApHCM) were compared with 50 patients with asymmetrical septal hypertrophy hypertrophic cardiomyopathy and 40 healthy volunteer controls. Perfusion was assessed visually and quantitatively as myocardial blood flow and myocardial perfusion reserve. RESULTS: Apical perfusion defects were present in all overt ApHCM patients (100%), all relative ApHCM patients (100%), 36% of asymmetrical septal hypertrophy hypertrophic cardiomyopathy, and 0% of healthy volunteers (P<0.001). In 10% of patients with ApHCM, perfusion defects were sufficiently apical that conventional short-axis views missed them. In 29%, stress myocardial blood flow fell below rest values. Stress myocardial blood flow was most impaired subendocardially, with greater hypertrophy or scar, and with apical aneurysms. Impaired apical myocardial blood flow was most strongly predicted by thicker apical segments (ß-coefficient, -0.031 mL/g per min [CI, -0.06 to -0.01]; P=0.013), higher ejection fraction (-0.025 mL/g per min [CI, -0.04 to -0.01]; P<0.005), and ECG maximum R-wave height (-0.023 mL/g per min [CI, -0.04 to -0.01]; P<0.005). CONCLUSIONS: Apical perfusion defects are universally present in ApHCM at all stages. Its ubiquitous presence along with characteristic ECG suggests ischemia may play a disease-defining role in ApHCM.

Myocardial Involvement After Hospitalization for COVID-19 Complicated by Troponin Elevation: A Prospective, Multicenter, Observational Study.

BACKGROUND: Acute myocardial injury in hospitalized patients with coronavirus disease 2019 (COVID-19) has a poor prognosis. Its associations and pathogenesis are unclear. Our aim was to assess the presence, nature, and extent of myocardial damage in hospitalized patients with troponin elevation. METHODS: Across 25 hospitals in the United Kingdom, 342 patients with COVID-19 and an elevated troponin level (COVID+/troponin+) were enrolled between June 2020 and March 2021 and had a magnetic resonance imaging scan within 28 days of discharge. Two prospective control groups were recruited, comprising 64 patients with COVID-19 and normal troponin levels (COVID+/troponin-) and 113 patients without COVID-19 or elevated troponin level matched by age and cardiovascular comorbidities (COVID-/comorbidity+). Regression modeling was performed to identify predictors of major adverse cardiovascular events at 12 months. RESULTS: Of the 519 included patients, 356 (69%) were men, with a median (interquartile range) age of 61.0 years (53.8, 68.8). The frequency of any heart abnormality, defined as left or right ventricular impairment, scar, or pericardial disease, was 2-fold greater in cases (61% [207/342]) compared with controls (36% [COVID+/troponin-] versus 31% [COVID-/comorbidity+]; P<0.001 for both). More cases than controls had ventricular impairment (17.2% versus 3.1% and 7.1%) or scar (42% versus 7% and 23%; P<0.001 for both). The myocardial injury pattern was different, with cases more likely than controls to have infarction (13% versus 2% and 7%; P<0.01) or microinfarction (9% versus 0% and 1%; P<0.001), but there was no difference in nonischemic scar (13% versus 5% and 14%; P=0.10). Using the Lake Louise magnetic resonance imaging criteria, the prevalence of probable recent myocarditis was 6.7% (23/342) in cases compared with 1.7% (2/113) in controls without COVID-19 (P=0.045). During follow-up, 4 patients died and 34 experienced a subsequent major adverse cardiovascular event (10.2%), which was similar to controls (6.1%; P=0.70). Myocardial scar, but not previous COVID-19 infection or troponin, was an independent predictor of major adverse cardiovascular events (odds ratio, 2.25 [95% CI, 1.12-4.57]; P=0.02). CONCLUSIONS: Compared with contemporary controls, patients with COVID-19 and elevated cardiac troponin level have more ventricular impairment and myocardial scar in early convalescence. However, the proportion with myocarditis was low and scar pathogenesis was diverse, including a newly described pattern of microinfarction. REGISTRATION: URL: https://www.isrctn.com; Unique identifier: 58667920.

An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar.

BACKGROUND AND OBJECTIVES: Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent. METHODS: DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality. RESULTS: The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction. CONCLUSIONS: Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.