Delirium and the risk of developing dementia: a cohort study of 12 949 patients.

BACKGROUND: Delirium is an important risk factor for subsequent dementia. However, the field lacks large studies with long-term follow-up of delirium in subjects initially free of dementia to clearly establish clinical trajectories. METHODS: We undertook a retrospective cohort study of all patients over the age of 65 diagnosed with an episode of delirium who were initially dementia free at onset of delirium within National Health Service Greater Glasgow & Clyde between 1996 and 2020 using the Safe Haven database. We estimated the cumulative incidence of dementia accounting for the competing risk of death without a dementia diagnosis. We modelled the effects of age at delirium diagnosis, sex and socioeconomic deprivation on the cause-specific hazard of dementia via cox regression. RESULTS: 12 949 patients with an incident episode of delirium were included and followed up for an average of 741 days. The estimated cumulative incidence of dementia was 31% by 5 years. The estimated cumulative incidence of the competing risk of death without dementia was 49.2% by 5 years. The cause-specific hazard of dementia was increased with higher levels of deprivation and also with advancing age from 65, plateauing and decreasing from age 90. There did not appear to be a relationship with sex. CONCLUSIONS: Our study reinforces the link between delirium and future dementia in a large cohort of patients. It highlights the importance of early recognition of delirium and prevention where possible.

Prediction models in first-episode psychosis: systematic review and critical appraisal.

BACKGROUND: People presenting with first-episode psychosis (FEP) have heterogenous outcomes. More than 40% fail to achieve symptomatic remission. Accurate prediction of individual outcome in FEP could facilitate early intervention to change the clinical trajectory and improve prognosis. AIMS: We aim to systematically review evidence for prediction models developed for predicting poor outcome in FEP. METHOD: A protocol for this study was published on the International Prospective Register of Systematic Reviews, registration number CRD42019156897. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidance, we systematically searched six databases from inception to 28 January 2021. We used the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies and the Prediction Model Risk of Bias Assessment Tool to extract and appraise the outcome prediction models. We considered study characteristics, methodology and model performance. RESULTS: Thirteen studies reporting 31 prediction models across a range of clinical outcomes met criteria for inclusion. Eleven studies used logistic regression with clinical and sociodemographic predictor variables. Just two studies were found to be at low risk of bias. Methodological limitations identified included a lack of appropriate validation, small sample sizes, poor handling of missing data and inadequate reporting of calibration and discrimination measures. To date, no model has been applied to clinical practice. CONCLUSIONS: Future prediction studies in psychosis should prioritise methodological rigour and external validation in larger samples. The potential for prediction modelling in FEP is yet to be realised.

Beyond Supervised Learning for Pervasive Healthcare.

The integration of machine/deep learning and sensing technologies is transforming healthcare and medical practice. However, inherent limitations in healthcare data, namely scarcity, quality, and heterogeneity, hinder the effectiveness of supervised learning techniques which are mainly based on pure statistical fitting between data and labels. In this article, we first identify the challenges present in machine learning for pervasive healthcare and we then review the current trends beyond fully supervised learning that are developed to address these three issues. Rooted in the inherent drawbacks of empirical risk minimization that underpins pure fully supervised learning, this survey summarizes seven key lines of learning strategies, to promote the generalization performance for real-world deployment. In addition, we point out several directions that are emerging and promising in this area, to develop data-efficient, scalable, and trustworthy computational models, and to leverage multi-modality and multi-source sensing informatics, for pervasive healthcare.

Development of a Semiautomated Database for Patients With Adult Congenital Heart Disease.

BACKGROUND: Databases for Congenital Heart Disease (CHD) are effective in delivering accessible datasets ready for statistical inference. Data collection hitherto has, however, been labour and time intensive and has required substantial financial support to ensure sustainability. We propose here creation and piloting of a semiautomated technique for data extraction from clinic letters to populate a clinical database. METHODS: PDF formatted clinic letters stored in a local folder, through a series of algorithms, underwent data extraction, preprocessing, and analysis. Specific patient information (diagnoses, diagnostic complexity, interventions, arrhythmia, medications, and demographic data) was processed into text files and structured data tables, used to populate a database. A specific data validation schema was predefined to verify and accommodate the information populating the database. Unsupervised learning in the form of a dimensionality reduction technique was used to project data into 2 dimensions and visualize their intrinsic structure in relation to the diagnosis, medication, intervention, and European Society of Cardiology classification lists of disease complexity. Ninety-three randomly selected letters were reviewed manually for accuracy. RESULTS: There were 1409 consecutive outpatient clinic letters used to populate the Scottish Adult Congenital Cardiac Database. Mean patient age was 35.4 years; 47.6% female; with 698 (49.5%) having moderately complex, 369 (26.1%) greatly complex, and 284 (20.1%) mildly complex lesions. Individual diagnoses were successfully extracted in 96.95%, and demographic data were extracted in 100% of letters. Data extraction, database upload, data analysis and visualization took 571 seconds (9.51 minutes). Manual data extraction in the categories of diagnoses, intervention, and medications yielded accuracy of the computer algorithm in 94%, 93%, and 93%, respectively. CONCLUSIONS: Semiautomated data extraction from clinic letters into a database can be achieved successfully with a high degree of accuracy and efficiency.

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition.

For abnormal gait recognition, pattern-specific features indicating abnormalities are interleaved with the subject-specific differences representing biometric traits. Deep representations are, therefore, prone to overfitting, and the models derived cannot generalize well to new subjects. Furthermore, there is limited availability of abnormal gait data obtained from precise Motion Capture (Mocap) systems because of regulatory issues and slow adaptation of new technologies in health care. On the other hand, data captured from markerless vision sensors or wearable sensors can be obtained in home environments, but noises from such devices may prevent the effective extraction of relevant features. To address these challenges, we propose a cascade of deep architectures that can encode cross-modal and cross-subject transfer for abnormal gait recognition. Cross-modal transfer maps noisy data obtained from RGBD and wearable sensors to accurate 4-D representations of the lower limb and joints obtained from the Mocap system. Subsequently, cross-subject transfer allows disentangling subject-specific from abnormal pattern-specific gait features based on a multiencoder autoencoder architecture. To validate the proposed methodology, we obtained multimodal gait data based on a multicamera motion capture system along with synchronized recordings of electromyography (EMG) data and 4-D skeleton data extracted from a single RGBD camera. Classification accuracy was improved significantly in both Mocap and noisy modalities.

A Single RGB Camera Based Gait Analysis With A Mobile Tele-Robot For Healthcare.

With the increasing awareness of high-quality life, there is a growing need for health monitoring devices running robust algorithms in home environment. Health monitoring technologies enable real-time analysis of users' health status, offering long-term healthcare support and reducing hospitalization time. The propose of this work is twofold, the software focuses on the analysis of gait, which is widely adopted for joint correction and assessing any lower limb, or spinal problem. On the hardware side, a novel marker-less gait analysis device using a low-cost RGB camera mounted on a mobile tele-robot is designed. As gait analysis with a single camera is much more challenging compared to previous works utilizing multi-cameras, a RGB-D camera or wearable sensors, we propose using vision-based human pose estimation approaches. More specifically, based on the out-put of state-of-the-art human pose estimation models, we devise measurements for four bespoke gait parameters: inversion/eversion, dorsiflexion/plantarflexion, ankle and foot progression angles. We thereby classify walking patterns into normal, supination, pronation and limp. We also illustrate how to run the proposed machine learning models in low-resource environments such as a single entry-level CPU. Experiments show that our single RGB camera method achieves competitive performance compared to multi-camera motion capture systems, at smaller hardware costs.

Coupled Real-Synthetic Domain Adaptation for Real-World Deep Depth Enhancement.

Advances in depth sensing technologies have allowed simultaneous acquisition of both color and depth data under different environments. However, most depth sensors have lower resolution than that of the associated color channels and such a mismatch can affect applications that require accurate depth recovery. Existing depth enhancement methods use simplistic noise models and cannot generalize well under real-world conditions. In this paper, a coupled real-synthetic domain adaptation method is proposed, which enables domain transfer between high-quality depth simulators and real depth camera information for super-resolution depth recovery. The method first enables the realistic degradation from synthetic images, and then enhances degraded depth data to high quality with a color-guided sub-network. The key advantage of the work is that it generalizes well to real-world datasets without further training or fine-tuning. Detailed quantitative and qualitative results are presented, and it is demonstrated that the proposed method achieves improved performance compared to previous methods fine-tuned on the specific datasets.

From Emotions to Mood Disorders: A Survey on Gait Analysis Methodology.

Mood disorders affect more than 300 million people worldwide and can cause devastating consequences. Elderly people and patients with neurological conditions are particularly susceptible to depression. Gait and body movements can be affected by mood disorders, and thus they can be used as a surrogate sign, as well as an objective index for pervasive monitoring of emotion and mood disorders in daily life. Here we review evidence that demonstrates the relationship between gait, emotions and mood disorders, highlighting the potential of a multimodal approach that couples gait data with physiological signals and home-based monitoring for early detection and management of mood disorders. This could enhance self-awareness, enable the development of objective biomarkers that identify high risk subjects and promote subject-specific treatment.

Early cortical specialization for face-to-face communication in human infants.

This study examined the brain bases of early human social cognitive abilities. Specifically, we investigated whether cortical regions implicated in adults' perception of facial communication signals are functionally active in early human development. Four-month-old infants watched two kinds of dynamic scenarios in which a face either established mutual gaze or averted its gaze, both of which were followed by an eyebrow raise with accompanying smile. Haemodynamic responses were measured by near-infrared spectroscopy, permitting spatial localization of brain activation (experiment 1), and gamma-band oscillatory brain activity was analysed from electroencephalography to provide temporal information about the underlying cortical processes (experiment 2). The results revealed that perceiving facial communication signals activates areas in the infant temporal and prefrontal cortex that correspond to the brain regions implicated in these processes in adults. In addition, mutual gaze itself, and the eyebrow raise with accompanying smile in the context of mutual gaze, produce similar cortical activations. This pattern of results suggests an early specialization of the cortical network involved in the perception of facial communication cues, which is essential for infants' interactions with, and learning from, others.

Deep Learning for Health Informatics.

With a massive influx of multimodality data, the role of data analytics in health informatics has grown rapidly in the last decade. This has also prompted increasing interests in the generation of analytical, data driven models based on machine learning in health informatics. Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reshape the future of artificial intelligence. Rapid improvements in computational power, fast data storage, and parallelization have also contributed to the rapid uptake of the technology in addition to its predictive power and ability to generate automatically optimized high-level features and semantic interpretation from the input data. This article presents a comprehensive up-to-date review of research employing deep learning in health informatics, providing a critical analysis of the relative merit, and potential pitfalls of the technique as well as its future outlook. The paper mainly focuses on key applications of deep learning in the fields of translational bioinformatics, medical imaging, pervasive sensing, medical informatics, and public health.

Nonrigid 2-D/3-D registration for patient specific bronchoscopy simulation with statistical shape modeling: phantom validation.

This paper presents a nonrigid registration two-dimensional/three-dimensional (2-D/3-D) framework and its phantom validation for subject-specific bronchoscope simulation. The method exploits the recent development of five degrees-of-freedom miniaturized catheter tip electromagnetic trackers such that the position and orientation of the bronchoscope can be accurately determined. This allows the effective recovery of unknown camera rotation and airway deformation, which is modelled by an active shape model (ASM). ASM captures the intrinsic variability of the tracheo-bronchial tree during breathing and it is specific to the class of motion it represents. The method reduces the number of parameters that control the deformation, and thus greatly simplifies the optimisation procedure. Subsequently, pq-based registration is performed to recover both the camera pose and parameters of the ASM. Detailed assessment of the algorithm is performed on a deformable airway phantom, with the ground truth data being provided by an additional six degrees-of-freedom electromagnetic (EM) tracker to monitor the level of simulated respiratory motion.

Patient-specific bronchoscopy visualization through BRDF estimation and disocclusion correction.

This paper presents an image-based method for virtual bronchoscope with photo-realistic rendering. The technique is based on recovering bidirectional reflectance distribution function (BRDF) parameters in an environment where the choice of viewing positions, directions, and illumination conditions are restricted. Video images of bronchoscopy examinations are combined with patient-specific three-dimensional (3-D) computed tomography data through two-dimensional (2-D)/3-D registration and shading model parameters are then recovered by exploiting the restricted lighting configurations imposed by the bronchoscope. With the proposed technique, the recovered BRDF is used to predict the expected shading intensity, allowing a texture map independent of lighting conditions to be extracted from each video frame. To correct for disocclusion artefacts, statistical texture synthesis was used to recreate the missing areas. New views not present in the original bronchoscopy video are rendered by evaluating the BRDF with different viewing and illumination parameters. This allows free navigation of the acquired 3-D model with enhanced photo-realism. To assess the practical value of the proposed technique, a detailed visual scoring that involves both real and rendered bronchoscope images is conducted.

NODDI and Tensor-Based Microstructural Indices as Predictors of Functional Connectivity.

In Diffusion Weighted MR Imaging (DWI), the signal is affected by the biophysical properties of neuronal cells and their relative placement, as well as extra-cellular tissue compartments. Typically, microstructural indices, such as fractional anisotropy (FA) and mean diffusivity (MD), are based on a tensor model that cannot disentangle the influence of these parameters. Recently, Neurite Orientation Dispersion and Density Imaging (NODDI) has exploited multi-shell acquisition protocols to model the diffusion signal as the contribution of three tissue compartments. NODDI microstructural indices, such as intra-cellular volume fraction (ICVF) and orientation dispersion index (ODI) are directly related to neuronal density and orientation dispersion, respectively. One way of examining the neurophysiological role of these microstructural indices across neuronal fibres is to look into how they relate to brain function. Here we exploit a statistical framework based on sparse Canonical Correlation Analysis (sCCA) and randomised Lasso to identify structural connections that are highly correlated with resting-state functional connectivity measured with simultaneous EEG-fMRI. Our results reveal distinct structural fingerprints for each microstructural index that also reflect their inter-relationships.

Patient-specific bronchoscope simulation with pq-space-based 2D/3D registration.

OBJECTIVE: The use of patient-specific models for surgical simulation requires photorealistic rendering of 3D structure and surface properties. For bronchoscope simulation, this requires augmenting virtual bronchoscope views generated from 3D tomographic data with patient-specific bronchoscope videos. To facilitate matching of video images to the geometry extracted from 3D tomographic data, this paper presents a new pq-space-based 2D/3D registration method for camera pose estimation in bronchoscope tracking. METHODS: The proposed technique involves the extraction of surface normals for each pixel of the video images by using a linear local shape-from-shading algorithm derived from the unique camera/lighting constraints of the endoscopes. The resultant pq-vectors are then matched to those of the 3D model by differentiation of the z-buffer. A similarity measure based on angular deviations of the pq-vectors is used to provide a robust 2D/3D registration framework. Localization of tissue deformation is considered by assessing the temporal variation of the pq-vectors between subsequent frames. RESULTS: The accuracy of the proposed method was assessed by using an electromagnetic tracker and a specially constructed airway phantom. Preliminary in vivo validation of the proposed method was performed on a matched patient bronchoscope video sequence and 3D CT data. Comparison to existing intensity-based techniques was also made. CONCLUSION: The proposed method does not involve explicit feature extraction and is relatively immune to illumination changes. The temporal variation of the pq distribution also permits the identification of localized deformation, which offers an effective way of excluding such areas from the registration process.

Relating resting-state fMRI and EEG whole-brain connectomes across frequency bands.

Whole brain functional connectomes hold promise for understanding human brain activity across a range of cognitive, developmental and pathological states. So called resting-state (rs) functional MRI studies have contributed to the brain being considered at a macroscopic scale as a set of interacting regions. Interactions are defined as correlation-based signal measurements driven by blood oxygenation level dependent (BOLD) contrast. Understanding the neurophysiological basis of these measurements is important in conveying useful information about brain function. Local coupling between BOLD fMRI and neurophysiological measurements is relatively well defined, with evidence that gamma (range) frequency EEG signals are the closest correlate of BOLD fMRI changes during cognitive processing. However, it is less clear how whole-brain network interactions relate during rest where lower frequency signals have been suggested to play a key role. Simultaneous EEG-fMRI offers the opportunity to observe brain network dynamics with high spatio-temporal resolution. We utilize these measurements to compare the connectomes derived from rs-fMRI and EEG band limited power (BLP). Merging this multi-modal information requires the development of an appropriate statistical framework. We relate the covariance matrices of the Hilbert envelope of the source localized EEG signal across bands to the covariance matrices derived from rs-fMRI with the means of statistical prediction based on sparse Canonical Correlation Analysis (sCCA). Subsequently, we identify the most prominent connections that contribute to this relationship. We compare whole-brain functional connectomes based on their geodesic distance to reliably estimate the performance of the prediction. The performance of predicting fMRI from EEG connectomes is considerably better than predicting EEG from fMRI across all bands, whereas the connectomes derived in low frequency EEG bands resemble best rs-fMRI connectivity.

Consensus between pipelines in structural brain networks.

Structural brain networks may be reconstructed from diffusion MRI tractography data and have great potential to further our understanding of the topological organisation of brain structure in health and disease. Network reconstruction is complex and involves a series of processesing methods including anatomical parcellation, registration, fiber orientation estimation and whole-brain fiber tractography. Methodological choices at each stage can affect the anatomical accuracy and graph theoretical properties of the reconstructed networks, meaning applying different combinations in a network reconstruction pipeline may produce substantially different networks. Furthermore, the choice of which connections are considered important is unclear. In this study, we assessed the similarity between structural networks obtained using two independent state-of-the-art reconstruction pipelines. We aimed to quantify network similarity and identify the core connections emerging most robustly in both pipelines. Similarity of network connections was compared between pipelines employing different atlases by merging parcels to a common and equivalent node scale. We found a high agreement between the networks across a range of fiber density thresholds. In addition, we identified a robust core of highly connected regions coinciding with a peak in similarity across network density thresholds, and replicated these results with atlases at different node scales. The binary network properties of these core connections were similar between pipelines but showed some differences in atlases across node scales. This study demonstrates the utility of applying multiple structural network reconstrution pipelines to diffusion data in order to identify the most important connections for further study.

A Framework for Inter-Subject Prediction of Functional Connectivity From Structural Networks.

Functional connections between brain regions are supported by structural connectivity. Both functional and structural connectivity are estimated from in vivo magnetic resonance imaging and offer complementary information on brain organization and function. However, imaging only provides noisy measures, and we lack a good neuroscientific understanding of the links between structure and function. Therefore, inter-subject joint modeling of structural and functional connectivity, the key to multimodal biomarkers, is an open challenge. We present a probabilistic framework to learn across subjects a mapping from structural to functional brain connectivity. Expanding on our previous work [1], our approach is based on a predictive framework with multiple sparse linear regression. We rely on the randomized LASSO to identify relevant anatomo-functional links with some confidence interval. In addition, we describe resting-state functional magnetic resonance imaging in the setting of Gaussian graphical models, on the one hand imposing conditional independences from structural connectivity and on the other hand parameterizing the problem in terms of multivariate autoregressive models. We introduce an intrinsic measure of prediction error for functional connectivity that is independent of the parameterization chosen and provides the means for robust model selection. We demonstrate our methodology with regions within the default mode and the salience network as well as, atlas-based cortical parcellation.

Automated gaze-contingent objects elicit orientation following in 8-month-old infants.

The current study tested whether the purely amodal cue of contingency elicits orientation following behavior in 8-month-old infants. We presented 8-month-old infants with automated objects without human features that did or did not react contingently to the infants' fixations recorded by an eye tracker. We found that an object's occasional orientation toward peripheral targets was reciprocated by a congruent visual orientation following response by infants only when it had displayed gaze-contingent interactivity. Our finding demonstrates that infants' gaze-following behavior does not depend on the presence of a human being. The results are consistent with the idea that, in 8-month-old infants, the detection of contingent reactivity, like other communicative signals, can itself elicit the illusion of being addressed.

A probabilistic framework to infer brain functional connectivity from anatomical connections.

We present a novel probabilistic framework to learn across several subjects a mapping from brain anatomical connectivity to functional connectivity, i.e. the covariance structure of brain activity. This prediction problem must be formulated as a structured-output learning task, as the predicted parameters are strongly correlated. We introduce a model selection framework based on cross-validation with a parametrization-independent loss function suitable to the manifold of covariance matrices. Our model is based on constraining the conditional independence structure of functional activity by the anatomical connectivity. Subsequently, we learn a linear predictor of a stationary multivariate autoregressive model. This natural parameterization of functional connectivity also enforces the positive-definiteness of the predicted covariance and thus matches the structure of the output space. Our results show that functional connectivity can be explained by anatomical connectivity on a rigorous statistical basis, and that a proper model of functional connectivity is essential to assess this link.

Non-rigid 2D-3D registration with catheter tip EM tracking for patient specific bronchoscope simulation.

This paper investigates the use of Active Shape Models (ASM) to capture the variability of the intra-thoracic airway tree. The method significantly reduces the dimensionality of the non-rigid 2D/3D registration problem and leads to a rapid and robust registration framework. In this study, EM tracking data has been also incorporated through a probabilistic framework for providing a statistically optimal pose given both the EM and the image-based registration measurements. Comprehensive phantom experiments have been conducted to assess the key numerical factors involved in using catheter tip EM tracking for deformable 2D/3D registration.