Search

Background: Anger is a frequent problem for many people with intellectual disabilities, and is often expressed as verbal and/or physical aggression. Cognitive–behaviour therapy (CBT) is the treatment of choice for common mental health problems, but CBT has only recently been adapted for people with intellectual disabilities. Anger is the main psychological presentation in which controlled trials have been used to evaluate CBT interventions for people with intellectual disabilities but these do not include rigorous randomised studies. Objectives: To evaluate (1) the impact of a staff-delivered manualised CBT anger management intervention on (a) reported anger among people with mild to moderate intellectual disabilities, and (b) anger coping skills, aggression, mental health, quality of life and costs of health and social care; (2) factors that influence outcome; and (3) the experience of service users, lay therapists and service managers. Design: A cluster randomised controlled trial based on 30 day centres (15 intervention and 15 control). Intention-to-treat comparisons of outcomes used a two-level linear regression model to allow for clustering within centres with baseline outcome levels as a covariate. Comparison of cost data used non-parametric bootstrapping. Qualitative analysis used interpretative phenomenological analysis and thematic analysis. Setting: Recruited day centres had four-plus service users with problem anger who were prepared to participate, two-plus staff willing to be lay therapists, a supportive manager and facilities for group work, and no current anger interventions. Participants: A total of 212 service users with problem anger were recruited. Thirty-three were deemed ineligible (30 could not complete assessments and three withdrew before randomisation). Retention at follow-up was 81%, with 17 withdrawals in each arm. Two to four staff per centre were recruited as lay therapists. Eleven service users, nine lay therapists and eight managers were interviewed. Interventions: The manualised intervention comprised 12 weekly 2-hour group sessions supplemented by ‘homework’. Lay therapists received training and ongoing supervision from a clinical psychologist. Treatment fidelity, group attendance and resources used in intervention delivery were monitored. Main outcome measures: The primary outcome was the service user-rated Provocation Index (PI), a measure of response to hypothetical situations that may provoke anger. Secondary trial outcomes were the key worker-rated PI; the service user- and key worker-rated Profile of Anger Coping Skills (PACS); the service user-rated PACS imaginal provocation test (PACS-IPT), a measure of response to actual situations known to provoke anger; aggression; mental health; self-esteem; quality of life; and health and social care resource use. Assessments were administered before randomisation and at 16 weeks and 10 months after randomisation. Results: Fourteen treatment groups were delivered, each with 12 sessions lasting an average of 114 minutes, with a mean of 4.9 service users and 2.0 lay therapists. The mean hourly cost per service user was £25.26. The mean hourly excess cost over treatment as usual was £12.34. There was no effect of intervention on the primary outcome – self-rated PI. There was a significant impact on the following secondary outcomes at the 10-month follow-up: key worker-rated PI, self-rated PACS-IPT and self- and key worker-rated PACS. Key workers and home carers reported significantly lower aggression at 16 weeks, but not at 10 months. There was no impact on mental health, self-esteem, quality of life or total cost of health and social care. Service users, key workers and service managers were uniformly positive. Conclusions: The intervention was effective at changing anger coping skills and staff-rated anger. Impact on self-rated anger was equivocal. With hindsight there are reasons, from an analysis of factors influencing outcomes, to think that self-rated PI was not a well-chosen primary outcome. Widespread implementation of manualised lay therapist-led but psychologist-supervised anger management CBT for people with mild to moderate intellectual disabilities is recommended. Trial registration: Current Controlled Trials ISRCTN37509773. Funding: This project was funded by the NIHR Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol. 17, No. 21. See the HTA programme website for further project information.

Objective . Spike sorting is a set of techniques used to analyze extracellular neural recordings, attributing individual spikes to individual neurons. This field has gained significant interest in neuroscience due to advances in implantable microelectrode arrays, capable of recording thousands of neurons simultaneously. High-density electrodes, combined with efficient and accurate spike sorting systems, are essential for various applications, including brain machine interfaces (BMIs), experimental neural prosthetics, real-time neurological disorder monitoring, and neuroscience research. However, given the resource constraints of modern applications, relying solely on algorithmic innovation is not enough. Instead, a co-optimization approach that combines hardware and spike sorting algorithms must be taken to develop neural recording systems suitable for resource-constrained environments, such as wearable devices and BMIs. This co-design requires careful consideration when selecting appropriate spike-sorting algorithms that match specific hardware and use cases. Approach . We investigated the recent literature on spike sorting, both in terms of hardware advancements and algorithms innovations. Moreover, we dedicated special attention to identifying suitable algorithm-hardware combinations, and their respective real-world applicabilities. Main results . In this review, we first examined the current progress in algorithms, and described the recent departure from the conventional '3-step' algorithms in favor of more advanced template matching or machine-learning-based techniques. Next, we explored innovative hardware options, including application-specific integrated circuits, field-programmable gate arrays, and in-memory computing devices (IMCs). Additionally, the challenges and future opportunities for spike sorting are discussed. Significance . This comprehensive review systematically summarizes the latest spike sorting techniques and demonstrates how they enable researchers to overcome traditional obstacles and unlock novel applications. Our goal is for this work to serve as a roadmap for future researchers seeking to identify the most appropriate spike sorting implementations for various experimental settings. By doing so, we aim to facilitate the advancement of this exciting field and promote the development of innovative solutions that drive progress in neural engineering research., (© 2023 IOP Publishing Ltd.)

During the past two decades, epileptic seizure detection and prediction algorithms have evolved rapidly. However, despite significant performance improvements, their hardware implementation using conventional technologies, such as Complementary Metal-Oxide-Semiconductor (CMOS), in power and area-constrained settings remains a challenging task; especially when many recording channels are used. In this paper, we propose a novel low-latency parallel Convolutional Neural Network (CNN) architecture that has between 2-2,800x fewer network parameters compared to State-Of-The-Art (SOTA) CNN architectures and achieves 5-fold cross validation accuracy of 99.84% for epileptic seizure detection, and 99.01% and 97.54% for epileptic seizure prediction, when evaluated using the University of Bonn Electroencephalogram (EEG), CHB-MIT and SWEC-ETHZ seizure datasets, respectively. We subsequently implement our network onto analog crossbar arrays comprising Resistive Random-Access Memory (RRAM) devices, and provide a comprehensive benchmark by simulating, laying out, and determining hardware requirements of the CNN component of our system. We parallelize the execution of convolution layer kernels on separate analog crossbars to enable 2 orders of magnitude reduction in latency compared to SOTA hybrid Memristive-CMOS Deep Learning (DL) accelerators. Furthermore, we investigate the effects of non-idealities on our system and investigate Quantization Aware Training (QAT) to mitigate the performance degradation due to low Analog-to-Digital Converter (ADC)/Digital-to-Analog Converter (DAC) resolution. Finally, we propose a stuck weight offsetting methodology to mitigate performance degradation due to stuck [Formula: see text] memristor weights, recovering up to 32% accuracy, without requiring retraining. The CNN component of our platform is estimated to consume approximately 2.791 W of power while occupying an area of 31.255 mm 2 in a 22 nm FDSOI CMOS process.

Health professionals extensively use Two-Dimensional (2D) Ultrasound (US) videos and images to visualize and measure internal organs for various purposes including evaluation of muscle architectural changes. US images can be used to measure abdominal muscles dimensions for the diagnosis and creation of customized treatment plans for patients with Low Back Pain (LBP), however, they are difficult to interpret. Due to high variability, skilled professionals with specialized training are required to take measurements to avoid low intra-observer reliability. This variability stems from the challenging nature of accurately finding the correct spatial location of measurement endpoints in abdominal US images. In this paper, we use a Deep Learning (DL) approach to automate the measurement of the abdominal muscle thickness in 2D US images. By treating the problem as a localization task, we develop a modified Fully Convolutional Network (FCN) architecture to generate blobs of coordinate locations of measurement endpoints, similar to what a human operator does. We demonstrate that using the TrA400 US image dataset, our network achieves a Mean Absolute Error (MAE) of 0.3125 on the test set, which almost matches the performance of skilled ultrasound technicians. Our approach can facilitate next steps for automating the process of measurements in 2D US images, while reducing inter-observer as well as intra-observer variability for more effective clinical outcomes.

The advent of dedicated Deep Learning (DL) accelerators and neuromorphic processors has brought on new opportunities for applying both Deep and Spiking Neural Network (SNN) algorithms to healthcare and biomedical applications at the edge. This can facilitate the advancement of medical Internet of Things (IoT) systems and Point of Care (PoC) devices. In this paper, we provide a tutorial describing how various technologies including emerging memristive devices, Field Programmable Gate Arrays (FPGAs), and Complementary Metal Oxide Semiconductor (CMOS) can be used to develop efficient DL accelerators to solve a wide variety of diagnostic, pattern recognition, and signal processing problems in healthcare. Furthermore, we explore how spiking neuromorphic processors can complement their DL counterparts for processing biomedical signals. The tutorial is augmented with case studies of the vast literature on neural network and neuromorphic hardware as applied to the healthcare domain. We benchmark various hardware platforms by performing a sensor fusion signal processing task combining electromyography (EMG) signals with computer vision. Comparisons are made between dedicated neuromorphic processors and embedded AI accelerators in terms of inference latency and energy. Finally, we provide our analysis of the field and share a perspective on the advantages, disadvantages, challenges, and opportunities that various accelerators and neuromorphic processors introduce to healthcare and biomedical domains.

Background: Adults with intellectual disabilities have substantial health inequalities and poor access to health care. We assessed whether practice nurse-delivered health checks could improve the health of adults with intellectual disabilities compared with standard care., Methods: In this cluster-design, single-blind, randomised controlled trial, we included general practices in Scotland, UK. From June to December, 2011, we randomly assigned (1:1) these general practices to either health checks plus standard care (health-checks group), or standard care only (control group), and we recruited the patients from these practices. Randomisation was done with stratification by number of GPs per practice and number of registered patients with intellectual disabilities (<20 or ≥20). Two research assistants were masked to allocation, and undertook the review of 9 month medical records and interviews. Participants and carers were not masked. The intervention was one health check designed especially for people with intellectual disabilities delivered by a practice nurse. The objective was improvement in health and health care 9 months after randomisation, and the primary outcome was the incidence of newly detected health needs being met by this timepoint. Whether needs were met was established by the investigators being masked to group allocation. The analysis was by intention to treat. This trial is registered with Current Controlled Trials, number ISRCTN43324841., Findings: Between June 26 and Dec 20, 2011, we recruited 38 practices. 85 participants (from 16 practices) were randomly assigned to intervention and 67 (from 17 practices) to standard care; five of the identified practices did not supply any participants. 83 intervention and 66 standard care participants completed the trial. More newly detected health needs were met in the intervention group than in the control standard care group (median 1 [range 0-8], 76·4% met [SD 36·5] vs 2 [0-11], 72·6% met [35·4]; odds ratio [OR] 1·73 [95% CI 0·93-3·22], p=0·085), although this difference was not significant. Significantly more health monitoring needs were met in the intervention group than standard care (median 2 [0-20], 69·9% [SD 34·2] vs 2 [0-22], 56·8% [29·4], OR 2·38 [95% CI 1·31-4·32, p=0·0053]). The probability that health checks are cost effective was between 0·6 and 0·8, irrespective of the cost-effectiveness threshold level. Costs per patient were -£71·48 for health checks and -£20·56 for standard care. The difference (-£50·92) was not significant [95% CI -434 to 362]. No adverse events were attributable to the intervention., Interpretation: Health checks given by practice nurses to adults with intellectual disabilities produced health-care improvements that were more conducive to longer-term health than standard care given to this population. The intervention dominated standard care, being both cheaper and more effective. Health-check programmes might therefore be indicated for adults with intellectual disabilities., Funding: Scottish Government Change Fund, NHS Greater Glasgow and Clyde Research and Development., (Copyright © 2014 Elsevier Ltd. All rights reserved.)

Background: Many people with intellectual disabilities display high levels of anger, and cognitive-behavioural anger management interventions are used routinely. However, for these methods to be used optimally, a better understanding is needed of different forms of anger assessment. The aim of this study was to investigate the relationship of a range of measures to self- and carer reports of anger expression, including instruments used to assess mental health and challenging behaviour., Method: Adults with intellectual disabilities, who had been identified as having problems with anger control, their key-workers and home carers all rated the service users' trait anger, using parallel versions of the same instrument (the Provocation Inventory). In addition, service users completed a battery of mental health assessments (the Glasgow Depression Scale, Glasgow Anxiety Scale and Rosenberg Self-Esteem Scale), and both groups of carers completed a battery of challenging behaviour measures (the Hyperactivity and Irritability domains of the Aberrant Behavior Checklist and the Modified Overt Anger Scale)., Results: Participants had high levels of mental health problems (depression: 34%; anxiety: 73%) and severe challenging behaviour (26%). Hierarchical linear regression analysis was used to explore the extent to which anger ratings by the three groups of respondents were predicted by demographic factors, mental health measures and challenging behaviour measures. Older service users rated themselves as less angry and were also rated as less angry by home carers, but not by key-workers. More intellectually able service users were rated as more angry by both sets of carers, but not by the service users themselves. Significantly, mental health status (but not challenging behaviour) predicted service users' self-ratings of anger, whereas challenging behaviour (but not mental health status) predicted carers' ratings of service users' anger., Conclusions: Service users and their carers appear to use different information when rating the service users' anger. Service users' self-ratings reflect their internal emotional state and mental health, as reflected by their ratings of anxiety and depression, whereas staff rate service users' anger on the basis of overt behaviours, as measured by challenging behaviour scales., (© 2013 John Wiley & Sons Ltd.)

Scotland has a national programme to improve mental health and well-being and addressing stigma among mental health practitioners is a priority. This study explores practitioner attitudes towards patients in medium and low secure forensic mental health settings through qualitative and quantitative approaches. Two questionnaires were used with nursing staff. A qualitative questionnaire asked participants to list examples of positive and negative practice and anti-discriminatory and discriminatory attitudes towards patients within forensic services. A quantitative questionnaire then asked participants to answer questions about a hypothetical man with schizophrenia called Harry. The overall balance of responses was more positive than negative in the qualitative results, particularly regarding patient rights, empowerment and control. However, there were a significant minority of negative attitudes in relation to recovery pessimism and desire for social distance. This was supported by the quantitative results where practitioners showed high stigma scores for avoidance and segregation. There were no significant differences in attitudes between medium and low secure settings. However overall, males reported more negative attitudes in relation to blame and avoidance and younger participants demonstrated more negative attitudes than older participants in relation to fear and danger. The implications for addressing stigma are discussed in relation to the wider national anti-stigma campaign and forensic services specifically., (© 2010 Blackwell Publishing.)