Systematic hand-held echocardiography in patients hospitalised with acute coronary syndrome.

AIMS: Transthoracic echocardiography is recommended in all patients with acute coronary syndrome but is time-consuming and lacks an evidence base. We aimed to assess the feasibility, diagnostic accuracy and time-efficiency of hand-held echocardiography in patients with acute coronary syndrome and describe the impact of echocardiography on clinical management in this setting. METHODS AND RESULTS: Patients with acute coronary syndrome underwent both hand-held and transthoracic echocardiography with agreement between key imaging parameters assessed using kappa statistics. The immediate clinical impact of hand-held echocardiography in this population was systematically evaluated.Overall, 262 patients (65±12 years, 71% male) participated. Agreement between hand-held and transthoracic echocardiography was good-to-excellent (kappa 0.60-1.00) with hand-held echocardiography having an overall negative predictive value of 95%. Hand-held echocardiography was performed rapidly (7.7±1.6 min) and completed a median of 5 [interquartile range 3-20] hours earlier than transthoracic echocardiography. Systematic hand-held echocardiography in all patients with acute coronary syndrome identified an important cardiac abnormality in 50% and the clinical management plan was changed by echocardiography in 42%. In 85% of cases, hand-held echocardiography was sufficient for patient decision-making and transthoracic echocardiography was no longer deemed necessary. CONCLUSIONS: In patients with acute coronary syndrome, hand-held echocardiography provides comparable results to transthoracic echocardiography, can be more rapidly applied and gives sufficient imaging information for decision-making in the vast majority of patients. Systematic echocardiography has clinical impact in half of patients, supporting the clinical utility of echocardiography in this population, and providing an evidence-base for current guidelines.

Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction.

Background: While low-dose computed tomography scans are traditionally used for attenuation correction in hybrid myocardial perfusion imaging (MPI), they also contain additional anatomic and pathologic information not utilized in clinical assessment. We seek to uncover the full potential of these scans utilizing a holistic artificial intelligence (AI)-driven image framework for image assessment. Methods: Patients with SPECT/CT MPI from 4 REFINE SPECT registry sites were studied. A multi-structure model segmented 33 structures and quantified 15 radiomics features for each on CT attenuation correction (CTAC) scans. Coronary artery calcium and epicardial adipose tissue scores were obtained from separate deep-learning models. Normal standard quantitative MPI features were derived by clinical software. Extreme Gradient Boosting derived all-cause mortality risk scores from SPECT, CT, stress test, and clinical features utilizing a 10-fold cross-validation regimen to separate training from testing data. The performance of the models for the prediction of all-cause mortality was evaluated using area under the receiver-operating characteristic curves (AUCs). Results: Of 10,480 patients, 5,745 (54.8%) were male, and median age was 65 (interquartile range [IQR] 57-73) years. During the median follow-up of 2.9 years (1.6-4.0), 651 (6.2%) patients died. The AUC for mortality prediction of the model (combining CTAC, MPI, and clinical data) was 0.80 (95% confidence interval [0.74-0.87]), which was higher than that of an AI CTAC model (0.78 [0.71-0.85]), and AI hybrid model (0.79 [0.72-0.86]) incorporating CTAC and MPI data (p<0.001 for all). Conclusion: In patients with normal perfusion, the comprehensive model (0.76 [0.65-0.86]) had significantly better performance than the AI CTAC (0.72 [0.61-0.83]) and AI hybrid (0.73 [0.62-0.84]) models (p<0.001, for all).CTAC significantly enhances AI risk stratification with MPI SPECT/CT beyond its primary role - attenuation correction. A comprehensive multimodality approach can significantly improve mortality prediction compared to MPI information alone in patients undergoing cardiac SPECT/CT.

Endoluminal larynx anatomy model - towards facilitating deep learning and defining standards for medical images evaluation with artificial intelligence algorithms.

The pioneering nature of this work covers the answers to two questions: (1) Is an up-to-date anatomical model of the larynx needed for modern endoscopic diagnostics, and (2) can such a digital segmentation model be utilized for deep learning purposes. The idea presented in this article has never been proposed before, and this is a breakthrough in numerical approaches to aerodigestive videoendoscopy imaging. The approach described in this article assumes defining a process for data acquisition, integration, and segmentation (labeling), for the needs of a new branch of knowledge: digital medicine and digital diagnosis support expert systems. The first and crucial step of such a process is creating a digital model of the larynx, which has to be then validated utilizing multiple clinical, as well as technical metrics. The model will form the basis for further artificial intelligence (AI) requirements, and it may also contribute to the development of translational medicine.

Action goals and the praxis network: an fMRI study.

The praxis representation network (PRN) of the left cerebral hemisphere is typically linked to the control of functional interactions with familiar tools. Surprisingly, little is known about the PRN engagement in planning and execution of tool-directed actions motivated by non-functional but purposeful action goals. Here we used functional neuroimaging to perform both univariate and multi-voxel pattern analyses (MVPA) in 20 right-handed participants who planned and later executed, with their dominant and non-dominant hands, disparate grasps of tools for different goals, including: (1) planning simple vs. demanding functional grasps of conveniently vs. inconveniently oriented tools with an intention to immediately use them, (2) planning simple-but non-functional-grasps of inconveniently oriented tools with a goal to pass them to a different person, (3) planning reaching movements directed at such tools with an intention to move/push them with the back of the hand, and (4) pantomimed execution of the earlier planned tasks. While PRN contributed to the studied interactions with tools, the engagement of its critical nodes, and/or complementary right hemisphere processing, was differently modulated by task type. E.g., planning non-functional/structural grasp-to-pass movements of inconveniently oriented tools, regardless of the hand, invoked the left parietal and prefrontal nodes significantly more than simple, non-demanding functional grasps. MVPA corroborated decoding capabilities of critical PRN areas and some of their right hemisphere counterparts. Our findings shed new lights on how performance of disparate action goals influences the extraction of object affordances, and how or to what extent it modulates the neural activity within the parieto-frontal brain networks.

Psychophysiology of positive and negative emotions, dataset of 1157 cases and 8 biosignals.

Subjective experience and physiological activity are fundamental components of emotion. There is an increasing interest in the link between experiential and physiological processes across different disciplines, e.g., psychology, economics, or computer science. However, the findings largely rely on sample sizes that have been modest at best (limiting the statistical power) and capture only some concurrent biosignals. We present a novel publicly available dataset of psychophysiological responses to positive and negative emotions that offers some improvement over other databases. This database involves recordings of 1157 cases from healthy individuals (895 individuals participated in a single session and 122 individuals in several sessions), collected across seven studies, a continuous record of self-reported affect along with several biosignals (electrocardiogram, impedance cardiogram, electrodermal activity, hemodynamic measures, e.g., blood pressure, respiration trace, and skin temperature). We experimentally elicited a wide range of positive and negative emotions, including amusement, anger, disgust, excitement, fear, gratitude, sadness, tenderness, and threat. Psychophysiology of positive and negative emotions (POPANE) database is a large and comprehensive psychophysiological dataset on elicited emotions.

Manual praxis and language-production networks, and their links to handedness.

While Liepmann was one of the first researchers to consider a relationship between skilled manual actions (praxis) and language for tasks performed "freely from memory", his primary focus was on the relations between the organization of praxis and left-hemisphere dominance. Subsequent attempts to apply his apraxia model to all cases he studied - including his first patient, a "non-pure right-hander" treated as an exception - left the praxis-handedness issue unresolved. Modern neuropsychological and recent neuroimaging evidence either showed closer associations of praxis and language, than between handedness and any of these two functions, or focused on their dissociations. Yet, present-day developments in neuroimaging and statistics allow us to overcome the limitations of the earlier work on praxis-language-handedness links, and to better quantify their interrelationships. Using functional magnetic resonance imaging (fMRI), we studied tool use pantomimes and subvocal word generation in 125 participants, including righthanders (NRH = 52), ambidextrous individuals (mixedhanders; NMH = 31), and lefthanders (NLH = 42). Laterality indices were calculated both in two critical cytoarchitectonic maps, and 180 multi-modal parcellations of the human cerebral cortex, using voxel count and signal intensity, and the most relevant regions of interest and their networks were further analyzed. We found that atypical organization of praxis was present in all handedness groups (RH = 25.0%, MH = 22.6%; LH = 45.2%), and was about two and a half times as common as atypical organization of language (RH = 3.8%; MH = 6.5%; LH = 26.2%), contingent on ROI selection/LI-calculation method. Despite strong associations of praxis and language, regardless of handedness and typicality, dissociations of atypically represented praxis from typical left-lateralized language were common (~20% of cases), whereas the inverse dissociations of atypically represented language from typical left-lateralized praxis were very rare (in ~2.5% of all cases). The consequences of the existence of such different phenotypes for theoretical accounts of manual praxis, and its links to language and handedness are modeled and discussed.

Decoding Brain States for Planning Functional Grasps of Tools: A Functional Magnetic Resonance Imaging Multivoxel Pattern Analysis Study.

OBJECTIVES: We used multivoxel pattern analysis (MVPA) to investigate neural selectivity for grasp planning within the left-lateralized temporo-parieto-frontal network of areas (praxis representation network, PRN) typically associated with tool-related actions, as studied with traditional neuroimaging contrasts. METHODS: We used data from 20 participants whose task was to plan functional grasps of tools, with either right or left hands. Region of interest and whole-brain searchlight analyses were performed to show task-related neural patterns. RESULTS: MVPA revealed significant contributions to functional grasp planning from the anterior intraparietal sulcus (aIPS) and its immediate vicinities, supplemented by inputs from posterior subdivisions of IPS, and the ventral lateral occipital complex (vLOC). Moreover, greater local selectivity was demonstrated in areas near the superior parieto-occipital cortex and dorsal premotor cortex, putatively forming the dorso-dorsal stream. CONCLUSIONS: A contribution from aIPS, consistent with its role in prospective grasp formation and/or encoding of relevant tool properties (e.g., potential graspable parts), is likely to accompany the retrieval of manipulation and/or mechanical knowledge subserved by the supramarginal gyrus for achieving action goals. An involvement of vLOC indicates that MVPA is particularly sensitive to coding of object properties, their identities and even functions, for a support of grip formation. Finally, the engagement of the superior parieto-frontal regions as revealed by MVPA is consistent with their selectivity for transient features of tools (i.e., variable affordances) for anticipatory hand postures. These outcomes support the notion that, compared to traditional approaches, MVPA can reveal more fine-grained patterns of neural activity. (JINS, 2018, 24, 1013-1025).