Supervised and Unsupervised Deep Learning Approaches for EEG Seizure Prediction.

Epilepsy affects more than 50 million people worldwide, making it one of the world's most prevalent neurological diseases. The main symptom of epilepsy is seizures, which occur abruptly and can cause serious injury or death. The ability to predict the occurrence of an epileptic seizure could alleviate many risks and stresses people with epilepsy face. We formulate the problem of detecting preictal (or pre-seizure) with reference to normal EEG as a precursor to incoming seizure. To this end, we developed several supervised deep learning approaches model to identify preictal EEG from normal EEG. We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event. These deep learning models were trained and evaluated on two large EEG seizure datasets in a person-specific manner. We found that both supervised and unsupervised approaches are feasible; however, their performance varies depending on the patient, approach and architecture. This new line of research has the potential to develop therapeutic interventions and save human lives.

Strategies to Mitigate Age-Related Bias in Machine Learning: Scoping Review.

BACKGROUND: Research suggests that digital ageism, that is, age-related bias, is present in the development and deployment of machine learning (ML) models. Despite the recognition of the importance of this problem, there is a lack of research that specifically examines the strategies used to mitigate age-related bias in ML models and the effectiveness of these strategies. OBJECTIVE: To address this gap, we conducted a scoping review of mitigation strategies to reduce age-related bias in ML. METHODS: We followed a scoping review methodology framework developed by Arksey and O'Malley. The search was developed in conjunction with an information specialist and conducted in 6 electronic databases (IEEE Xplore, Scopus, Web of Science, CINAHL, EMBASE, and the ACM digital library), as well as 2 additional gray literature databases (OpenGrey and Grey Literature Report). RESULTS: We identified 8 publications that attempted to mitigate age-related bias in ML approaches. Age-related bias was introduced primarily due to a lack of representation of older adults in the data. Efforts to mitigate bias were categorized into one of three approaches: (1) creating a more balanced data set, (2) augmenting and supplementing their data, and (3) modifying the algorithm directly to achieve a more balanced result. CONCLUSIONS: Identifying and mitigating related biases in ML models is critical to fostering fairness, equity, inclusion, and social benefits. Our analysis underscores the ongoing need for rigorous research and the development of effective mitigation approaches to address digital ageism, ensuring that ML systems are used in a way that upholds the interests of all individuals. TRIAL REGISTRATION: Open Science Framework AMG5P; https://osf.io/amg5p.

Artificial intelligence-driven virtual rehabilitation for people living in the community: A scoping review.

Virtual Rehabilitation (VRehab) is a promising approach to improving the physical and mental functioning of patients living in the community. The use of VRehab technology results in the generation of multi-modal datasets collected through various devices. This presents opportunities for the development of Artificial Intelligence (AI) techniques in VRehab, namely the measurement, detection, and prediction of various patients' health outcomes. The objective of this scoping review was to explore the applications and effectiveness of incorporating AI into home-based VRehab programs. PubMed/MEDLINE, Embase, IEEE Xplore, Web of Science databases, and Google Scholar were searched from inception until June 2023 for studies that applied AI for the delivery of VRehab programs to the homes of adult patients. After screening 2172 unique titles and abstracts and 51 full-text studies, 13 studies were included in the review. A variety of AI algorithms were applied to analyze data collected from various sensors and make inferences about patients' health outcomes, most involving evaluating patients' exercise quality and providing feedback to patients. The AI algorithms used in the studies were mostly fuzzy rule-based methods, template matching, and deep neural networks. Despite the growing body of literature on the use of AI in VRehab, very few studies have examined its use in patients' homes. Current research suggests that integrating AI with home-based VRehab can lead to improved rehabilitation outcomes for patients. However, further research is required to fully assess the effectiveness of various forms of AI-driven home-based VRehab, taking into account its unique challenges and using standardized metrics.

User Perception of Smart Home Surveillance Among Adults Aged 50 Years and Older: Scoping Review.

BACKGROUND: Smart home technology (SHT) can be useful for aging in place or health-related purposes. However, surveillance studies have highlighted ethical issues with SHTs, including user privacy, security, and autonomy. OBJECTIVE: As digital technology is most often designed for younger adults, this review summarizes perceptions of SHTs among users aged 50 years and older to explore their understanding of privacy, the purpose of data collection, risks and benefits, and safety. METHODS: Through an integrative review, we explored community-dwelling adults' (aged 50 years and older) perceptions of SHTs based on research questions under 4 nonmutually exclusive themes: privacy, the purpose of data collection, risk and benefits, and safety. We searched 1860 titles and abstracts from Ovid MEDLINE, Ovid Embase, Cochrane Database of Systematic Reviews, and Cochrane Central Register of Controlled Trials, Scopus, Web of Science Core Collection, and IEEE Xplore or IET Electronic Library, resulting in 15 included studies. RESULTS: The 15 studies explored user perception of smart speakers, motion sensors, or home monitoring systems. A total of 13 (87%) studies discussed user privacy concerns regarding data collection and access. A total of 4 (27%) studies explored user knowledge of data collection purposes, 7 (47%) studies featured risk-related concerns such as data breaches and third-party misuse alongside benefits such as convenience, and 9 (60%) studies reported user enthusiasm about the potential for home safety. CONCLUSIONS: Due to the growing size of aging populations and advances in technological capabilities, regulators and designers should focus on user concerns by supporting higher levels of agency regarding data collection, use, and disclosure and by bolstering organizational accountability. This way, relevant privacy regulation and SHT design can better support user safety while diminishing potential risks to privacy, security, autonomy, or discriminatory outcomes.

Protocol for metadata and image collection at diabetic foot ulcer clinics: enabling research in wound analytics and deep learning.

BACKGROUND: The escalating impact of diabetes and its complications, including diabetic foot ulcers (DFUs), presents global challenges in quality of life, economics, and resources, affecting around half a billion people. DFU healing is hindered by hyperglycemia-related issues and diverse diabetes-related physiological changes, necessitating ongoing personalized care. Artificial intelligence and clinical research strive to address these challenges by facilitating early detection and efficient treatments despite resource constraints. This study establishes a standardized framework for DFU data collection, introducing a dedicated case report form, a comprehensive dataset named Zivot with patient population clinical feature breakdowns and a baseline for DFU detection using this dataset and a UNet architecture. RESULTS: Following this protocol, we created the Zivot dataset consisting of 269 patients with active DFUs, and about 3700 RGB images and corresponding thermal and depth maps for the DFUs. The effectiveness of collecting a consistent and clean dataset was demonstrated using a bounding box prediction deep learning network that was constructed with EfficientNet as the feature extractor and UNet architecture. The network was trained on the Zivot dataset, and the evaluation metrics showed promising values of 0.79 and 0.86 for F1-score and mAP segmentation metrics. CONCLUSIONS: This work and the Zivot database offer a foundation for further exploration of holistic and multimodal approaches to DFU research.

Undersampling and cumulative class re-decision methods to improve detection of agitation in people with dementia.

Agitation is one of the most prevalent symptoms in people with dementia (PwD) that can place themselves and the caregiver's safety at risk. Developing objective agitation detection approaches is important to support health and safety of PwD living in a residential setting. In a previous study, we collected multimodal wearable sensor data from 17 participants for 600 days and developed machine learning models for detecting agitation in 1-min windows. However, there are significant limitations in the dataset, such as imbalance problem and potential imprecise labels as the occurrence of agitation is much rarer in comparison to the normal behaviours. In this paper, we first implemented different undersampling methods to eliminate the imbalance problem, and came to the conclusion that only 20% of normal behaviour data were adequate to train a competitive agitation detection model. Then, we designed a weighted undersampling method to evaluate the manual labeling mechanism given the ambiguous time interval assumption. After that, the postprocessing method of cumulative class re-decision (CCR) was proposed based on the historical sequential information and continuity characteristic of agitation, improving the decision-making performance for the potential application of agitation detection system. The results showed that a combination of undersampling and CCR improved F1-score and other metrics to varying degrees with less training time and data. Supplementary Information: The online version contains supplementary material available at 10.1007/s13534-023-00313-8.

Walking path images from real-time location data predict degree of cognitive impairment.

BACKGROUND: We propose a novel approach that uses spatial walking patterns produced by real-time location systems to classify the severity of cognitive impairment (CI) among residents of a memory care unit. METHODS: Each participant was classified as "No-CI", "Mild-Moderate CI" or "Severe CI" based on their Mini-Mental State Examination scores. The location data was distributed into windows of various durations (5, 10, 15 and 30 min) and transformed into images used to train a custom convolutional neural network (CNN) at each window size. Class Activation Mapping was applied to the top-performing models to determine the features of images associated with each class. RESULTS: The best performing model achieved an accuracy of 87.38 % (30-min window length) with an overall pattern that larger window sizes perform better. The class activation maps were effectively consolidated into a Cognitive Impairment Classification Value (CICV) score that distinguishes between No-CI, Mild-Moderate CI, and Severe CI. CONCLUSION: The class activation maps show that the CNN made relevant and intuitive distinctions for paths corresponding to each class. Future work should validate the proposed techniques with participants who are well-characterized clinically, over larger and diversified settings, and towards classification of neuropsychiatric symptoms such as motor agitation, mood, or apathy.

Sensor-based assessment of social isolation in community-dwelling older adults: a scoping review.

Social isolation (SI) is a state of low social interaction with peers associated with various adverse health consequences in older adults living in the community. SI is most often assessed through retrospective self-reports, which can be prone to recall or self-report biases and influenced by stigma. Ambient and wearable sensors have been explored to objectively assess SI based on interactions of a person within the environment and physiological data. However, because this field is in its infancy, there is a lack of clarity regarding the application of sensors and their data in assessing SI and the methods to develop these assessments. To understand the current state of research in sensor-based assessment of SI in older adults living in the community and to make recommendations for the field moving forward, we conducted a scoping review. The aims of the scoping review were to (i) map the types of sensors (and their associated data) that have been used for objective SI assessment, and (ii) identify the methodological approaches used to develop the SI assessment. Using an established scoping review methodology, we identified eight relevant articles. Data from motion sensors and actigraph were commonly applied and compared and correlated with self-report measures in developing objective SI assessments. Variability exists in defining SI, feature extraction and the use of sensors and self-report assessments. Inconsistent definitions and use of various self-report scales for measuring SI create barriers to studying the concept and extracting features to build predictive models. Recommendations include establishing a consistent definition of SI for sensor-based assessment research and development and consider capturing its complexity through innovative domain-specific features.

Privacy-protecting behaviours of risk detection in people with dementia using videos.

BACKGROUND: People living with dementia often exhibit behavioural and psychological symptoms of dementia that can put their and others' safety at risk. Existing video surveillance systems in long-term care facilities can be used to monitor such behaviours of risk to alert the staff to prevent potential injuries or death in some cases. However, these behaviours of risk events are heterogeneous and infrequent in comparison to normal events. Moreover, analysing raw videos can also raise privacy concerns. PURPOSE: In this paper, we present two novel privacy-protecting video-based anomaly detection approaches to detect behaviours of risks in people with dementia. METHODS: We either extracted body pose information as skeletons or used semantic segmentation masks to replace multiple humans in the scene with their semantic boundaries. Our work differs from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction. We used anonymized videos of normal activities to train customized spatio-temporal convolutional autoencoders and identify behaviours of risk as anomalies. RESULTS: We showed our results on a real-world study conducted in a dementia care unit with patients with dementia, containing approximately 21 h of normal activities data for training and 9 h of data containing normal and behaviours of risk events for testing. We compared our approaches with the original RGB videos and obtained a similar area under the receiver operating characteristic curve performance of 0.807 for the skeleton-based approach and 0.823 for the segmentation mask-based approach. CONCLUSIONS: This is one of the first studies to incorporate privacy for the detection of behaviours of risks in people with dementia. Our research opens up new avenues to reduce injuries in long-term care homes, improve the quality of life of residents, and design privacy-aware approaches for people living in the community.

Ageism and Artificial Intelligence: Protocol for a Scoping Review.

BACKGROUND: Artificial intelligence (AI) has emerged as a major driver of technological development in the 21st century, yet little attention has been paid to algorithmic biases toward older adults. OBJECTIVE: This paper documents the search strategy and process for a scoping review exploring how age-related bias is encoded or amplified in AI systems as well as the corresponding legal and ethical implications. METHODS: The scoping review follows a 6-stage methodology framework developed by Arksey and O'Malley. The search strategy has been established in 6 databases. We will investigate the legal implications of ageism in AI by searching grey literature databases, targeted websites, and popular search engines and using an iterative search strategy. Studies meet the inclusion criteria if they are in English, peer-reviewed, available electronically in full text, and meet one of the following two additional criteria: (1) include "bias" related to AI in any application (eg, facial recognition) and (2) discuss bias related to the concept of old age or ageism. At least two reviewers will independently conduct the title, abstract, and full-text screening. Search results will be reported using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) reporting guideline. We will chart data on a structured form and conduct a thematic analysis to highlight the societal, legal, and ethical implications reported in the literature. RESULTS: The database searches resulted in 7595 records when the searches were piloted in November 2021. The scoping review will be completed by December 2022. CONCLUSIONS: The findings will provide interdisciplinary insights into the extent of age-related bias in AI systems. The results will contribute foundational knowledge that can encourage multisectoral cooperation to ensure that AI is developed and deployed in a manner consistent with ethical values and human rights legislation as it relates to an older and aging population. We will publish the review findings in peer-reviewed journals and disseminate the key results with stakeholders via workshops and webinars. TRIAL REGISTRATION: OSF Registries AMG5P; https://osf.io/amg5p. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/33211.

Wearable multimodal sensors for the detection of behavioral and psychological symptoms of dementia using personalized machine learning models.

Introduction: Behavioral and psychological symptoms of dementia (BPSD) signal distress or unmet needs and present a risk to people with dementia and their caregivers. Variability in the expression of these symptoms is a barrier to the performance of digital biomarkers. The aim of this study was to use wearable multimodal sensors to develop personalized machine learning models capable of detecting individual patterns of BPSD. Methods: Older adults with dementia and BPSD (n = 17) on a dementia care unit wore a wristband during waking hours for up to 8 weeks. The wristband captured motion (accelerometer) and physiological indicators (blood volume pulse, electrodermal activity, and skin temperature). Agitation or aggression events were tracked, and research staff reviewed videos to precisely annotate the sensor data. Personalized machine learning models were developed using 1-minute intervals and classifying the presence of behavioral symptoms, and behavioral symptoms by type (motor agitation, verbal aggression, or physical aggression). Results: Behavioral events were rare, representing 3.4% of the total data. Personalized models classified behavioral symptoms with a median area under the receiver operating curve (AUC) of 0.87 (range 0.64-0.95). The relative importance of the different sensor features to the predictive models varied both by individual and behavior type. Discussion: Patterns of sensor data associated with BPSD are highly individualized, and future studies of the digital phenotyping of these behaviors would benefit from personalization.

Indoor Location Data for Tracking Human Behaviours: A Scoping Review.

Real-time location systems (RTLS) record locations of individuals over time and are valuable sources of spatiotemporal data that can be used to understand patterns of human behaviour. Location data are used in a wide breadth of applications, from locating individuals to contact tracing or monitoring health markers. To support the use of RTLS in many applications, the varied ways location data can describe patterns of human behaviour should be examined. The objective of this review is to investigate behaviours described using indoor location data, and particularly the types of features extracted from RTLS data to describe behaviours. Four major applications were identified: health status monitoring, consumer behaviours, developmental behaviour, and workplace safety/efficiency. RTLS data features used to analyse behaviours were categorized into four groups: dwell time, activity level, trajectory, and proximity. Passive sensors that provide non-uniform data streams and features with lower complexity were common. Few studies analysed social behaviours between more than one individual at once. Less than half the health status monitoring studies examined clinical validity against gold-standard measures. Overall, spatiotemporal data from RTLS technologies are useful to identify behaviour patterns, provided there is sufficient richness in location data, the behaviour of interest is well-characterized, and a detailed feature analysis is undertaken.

Onset and Offset Detection of Respiratory EMG Data Based on Energy Operator Signal.

Onset and offset detection of electromyography (EMG) data is an important step in respiratory muscle coordination assessment. Impaired respiratory coordination can indicate breathing disorders and lung diseases. In this paper, we present an algorithm for onset and offset timing detection of real-world EMG signals from respiratory muscles, which are contaminated with electrocardiogram (ECG) artifacts. The algorithm is based on the Energy Operator signal, has a low computational cost, and includes a filtering procedure to remove ECG artifacts from EMG. Analysis of EMG signals from 2 respiratory muscles of 5 participants' data shows high agreement between the algorithm and manual method with a mean difference between two methods of 0.0407 seconds.

Factors Affecting the Implementation, Use, and Adoption of Real-Time Location System Technology for Persons Living With Cognitive Disabilities in Long-term Care Homes: Systematic Review.

BACKGROUND: As the aging population continues to grow, the number of adults living with dementia or other cognitive disabilities in residential long-term care homes is expected to increase. Technologies such as real-time locating systems (RTLS) are being investigated for their potential to improve the health and safety of residents and the quality of care and efficiency of long-term care facilities. OBJECTIVE: The aim of this study is to identify factors that affect the implementation, adoption, and use of RTLS for use with persons living with dementia or other cognitive disabilities in long-term care homes. METHODS: We conducted a systematic review of the peer-reviewed English language literature indexed in MEDLINE, Embase, PsycINFO, and CINAHL from inception up to and including May 5, 2020. Search strategies included keywords and subject headings related to cognitive disability, residential long-term care settings, and RTLS. Study characteristics, methodologies, and data were extracted and analyzed using constant comparative techniques. RESULTS: A total of 12 publications were included in the review. Most studies were conducted in the Netherlands (7/12, 58%) and used a descriptive qualitative study design. We identified 3 themes from our analysis of the studies: barriers to implementation, enablers of implementation, and agency and context. Barriers to implementation included lack of motivation for engagement; technology ecosystem and infrastructure challenges; and myths, stories, and shared understanding. Enablers of implementation included understanding local workflows, policies, and technologies; usability and user-centered design; communication with providers; and establishing policies, frameworks, governance, and evaluation. Agency and context were examined from the perspective of residents, family members, care providers, and the long-term care organizations. CONCLUSIONS: There is a striking lack of evidence to justify the use of RTLS to improve the lives of residents and care providers in long-term care settings. More research related to RTLS use with cognitively impaired residents is required; this research should include longitudinal evaluation of end-to-end implementations that are developed using scientific theory and rigorous analysis of the functionality, efficiency, and effectiveness of these systems. Future research is required on the ethics of monitoring residents using RTLS and its impact on the privacy of residents and health care workers.

DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders.

Human falls rarely occur; however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations, it is also difficult to extract domain-specific features to identify falls. In this paper, we present a novel framework, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.

Diagnosis of Obstructive Sleep Apnea during Wakefulness Using Upper Airway Negative Pressure and Machine Learning.

Background and Rational: Obstructive Sleep Apnea (OSA) is a common disorder, affecting almost 10% of adults, but very underdiagnosed. This is largely due to limited access to overnight sleep testing using polysomnography (PSG). Our goal was to distinguish OSA from healthy individual using a simple maneuver during wakefulness in combination with machine learning methods. Methods: Participants have undergone an overnight PSG to determine their ground truth OSA severity. Separately, they were asked to breathe through a nasal mask or a mouth piece through which negative pressure (NP) was applied, during wakefulness. Airflow waveforms were acquired and several features were extracted and used to train various classifiers to predict OSA. Results and Discussion: The performance of each classifier and experimental setup was calculated. The best results were obtained using Random Forest classifier for distinguishing OSA from healthy individuals with a very good area under the curve of 0.80. To the best of our knowledge, this is the first study to deploy machine learning and NP with promising path to diagnose OSA during wakefulness.

Agitation Detection in People Living with Dementia using Multimodal Sensors.

People Living with Dementia (PLwD) often exhibit behavioral and psychological symptoms of dementia; with agitation being one of the most prevalent symptoms. Agitated behaviour in PLwD indicates distress and confusion and increases the risk to injury to both the patients and the caregivers. In this paper, we present the use of wearable devices to detect agitation in PLwD. We hypothesize that combining multi-modal sensor data can help in building better classifiers to identify agitation in PLwD in comparison to a single sensor. We present a unique study to collect motion and physiological data from PLwD. This multi-modal sensor data is subsequently used to build predictive models to detect agitation in PLwD. The results on Random Forest for 28 days of data from PLwD show a strong evidence to support our hypothesis and highlight the importance of using multi-modal sensor data for detecting agitation events amongst them.

Challenges in Collecting Big Data in A Clinical Environment with Vulnerable Population: Lessons Learned from A Study Using A Multi-modal Sensors Platform.

Agitation is one of the most common behavioural and psychological symptoms in people living with dementia (PLwD). This behaviour can cause tremendous stress and anxiety on family caregivers and healthcare providers. Direct observation of PLwD is the traditional way to measure episodes of agitation. However, this method is subjective, bias-prone and timeconsuming. Importantly, it does not predict the onset of the agitation. Therefore, there is a need to develop a continuous monitoring system that can detect and/or predict the onset of agitation. In this study, a multi-modal sensor platform with video cameras, motion and door sensors, wristbands and pressure mats were set up in a hospital-based dementia behavioural care unit to develop a predictive system to identify the onset of agitation. The research team faced several barriers in the development and initiation of the study, namely addressing concerns about the study ethics, logistics and costs of study activities, device design for PLwD and limitations of its use in the hospital. In this paper, the strategies and methodologies that were implemented to address these challenges are discussed for consideration by future researchers who will conduct similar studies in a hospital setting.

Detecting agitation and aggression in people with dementia using sensors-A systematic review.

Agitation and aggression are among the most challenging symptoms of dementia. Agitated persons with dementia can harm themselves, their caregivers, or other patients in a care facility. Automatic detection of agitation would be useful to alert caregivers so that appropriate interventions can be performed. The building blocks in the automatic detection of agitation and aggression are appropriate sensing platforms and generalized predictive models. In this article, we perform a systematic review of studies that use different types of sensors to detect agitation and aggression in persons with dementia. We conclude that actigraphy shows some evidence of correlation with incidences of agitation and aggression; however, multimodal sensing has not been fully evaluated for this purpose. Based on this systematic review, we provide guidelines and recommendations for future research directions in this field.

Review of fall detection techniques: A data availability perspective.

A fall is an abnormal activity that occurs rarely; however, missing to identify falls can have serious health and safety implications on an individual. Due to the rarity of occurrence of falls, there may be insufficient or no training data available for them. Therefore, standard supervised machine learning methods may not be directly applied to handle this problem. In this paper, we present a taxonomy for the study of fall detection from the perspective of availability of fall data. The proposed taxonomy is independent of the type of sensors used and specific feature extraction/selection methods. The taxonomy identifies different categories of classification methods for the study of fall detection based on the availability of their data during training the classifiers. Then, we present a comprehensive literature review within those categories and identify the approach of treating a fall as an abnormal activity to be a plausible research direction. We conclude our paper by discussing several open research problems in the field and pointers for future research.