The importance of sleep is paramount for maintaining physical, emotional and mental wellbeing. Though the relationship between physical activity known to be important, it not yet fully understood. explosion in popularity actigraphy wearable devices, provides a unique opportunity understand this relationship. Leveraging information source requires new tools developed facilitate data-driven research patient-recommendations. In paper we explore use deep learning build quality prediction models...

Accurately measuring sleep and its quality with polysomnography (PSG) is an expensive task. Actigraphy, alternative, has been proven cheap relatively accurate. However, the largest experiments conducted to date, have had only hundreds of participants. In this work, we processed data recently published Multi-Ethnic Study Atherosclerosis (MESA) Sleep study both PSG actigraphy synchronized. We propose adoption publicly available large dataset, which at least one order magnitude larger than any...

ABSTRACT This study aims to identify differences in the functional neural connectivity of brain paediatric patients with obstructive sleep apnea. Using EEG signals from 3673 patients, we grouped subjects into OSA or control groups based on oxygen desaturation levels and apnea‐hypopnea index (AHI), applied topological data analysis (TDA) techniques. We evaluated our approach through statistical testing TDA‐based features, which indicate fundamental apnea as compared controls. There were...

Lack of sleep can erode mental and physical well-being, often exacerbating health problems such as obesity. Wearable devices that capture analyze quality through predictive methodologies help patients medical practitioners make behavioral decisions lead to better improved health. In the web extra at https://youtu.be/_zL-t4gk210, guest editor Katarzyna Wac interviews author Aarti Sathyanarayana, a PhD student in University Minnesota's Department Computer Science.

Abstract Childhood epilepsy with centrotemporal spikes, previously known as Benign Epilepsy Centro-temporal Spikes (BECTS) or Rolandic Epilepsy, is one of the most common forms focal childhood epilepsy. Despite its prevalence, BECTS often misdiagnosed missed entirely. This in part due to nocturnal and brief nature seizures, making it difficult identify during a routine electroencephalogram (EEG). Detecting brain activity that highly associated on brief, awake EEG has potential improve...

Human Activity Recognition (HAR) is a powerful tool for understanding human behaviour. Pervasive sensors, such as wearable devices, have an increasing market penetration and generate tremendous amount of data. The myriad available clinical consumer-grade wearables continuous time series person's daily physical exertion rest. Applying HAR to the activity can provide new insights by enriching feature set in health studies, enhancing personalisation effectiveness health, wellness, fitness...

In this work, we leverage machine learning techniques to identify potential biomarkers of oxygen desaturation during sleep exclusively from electroencephalogram (EEG) signals in pediatric patients with apnea. Development a technique which can successfully EEG apnea as well latent come subjects who experience desaturations but do not themselves occur events would provide strong step towards developing brain-based biomarker for order aid easier diagnosis disease. We large corpus data, and show...

Abstract Introduction Students commonly experience stress due to constant academic demands and societal pressures. This study aims investigate whether there are differences in sleep efficiency among students experiencing high, low, medium levels of stress. We performed statistical analyses on across various how affects daily patterns. Methods Using the GLOBEM dataset, we computed range scores for individual students, considering their highest lowest observed throughout study. classified days...

Abstract Introduction Existing sleep apnea identification methods require polysomnograms, requiring patients schedule the exam and to with many sensors attached their body. Oxygen desaturation occurs during in apnea, leading poor rest other significant complications. work shows potential of EEG signals as indicators identifying a correlation between diagnosis. However, further is required understand how blood oxygenation correlates features brain. Recent advancements signal processing allow...

In this work, we leverage machine learning techniques to identify potential biomarkers of oxygen desaturation during sleep exclusively from electroencephalogram (EEG) signals in pediatric patients with apnea. Development a technique which can successfully EEG apnea as well latent come subjects who experience desaturations but do not themselves occur events would provide strong step towards developing brain-based biomarker for order aid easier diagnosis disease. We large corpus data, and show...

Sleep staging is a challenging task, typically manually performed by sleep technologists based on electroencephalogram and other biosignals of patients taken during overnight studies. Recent work aims to leverage automated algorithms perform not signals, but rather the airflow signals subjects. Prior uses ideas from topological data analysis (TDA), specifically Hermite function expansions persistence curves (HEPC) featurize signals. However, finite order HEPC captures only partial...

Over seventy percent of Americans take at least one form prescription medication, with twenty taking more than five. The numbers emphasize how important it is for clinicians to understand the effects medication and whether these medications are effective. In this paper we propose a data driven framework predict effectiveness on patient, specifically in case diabetes. Our dataset contains claims from 1.5 million patients. A heuristic was established evaluate "effectiveness" Metformin using...

Topological data analysis (TDA) is an emerging technique for biological signal processing. TDA leverages the invariant topological features of signals in a metric space robust even presence noise. In this paper, we leverage on brain connectivity networks derived from electroencephalogram (EEG) to identify statistical differences between pediatric patients with obstructive sleep apnea (OSA) and without OSA. We large corpus data, show that enables us see difference dynamics two groups.Clinical...

Purpose: Evaluating the effects of antiseizure medication (ASM) on patients with epilepsy remains a slow and challenging process. Quantifiable noninvasive markers that are measurable in real-time provide objective useful information could guide clinical decision-making. We examined whether effect ASM can be quantitatively measured from EEGs. Methods: This retrospective analysis was conducted 67 long-term monitoring unit at Boston Children's Hospital. Two 30-second EEG segments were selected...

Topological data analysis (TDA) is an emerging technique for biological signal processing. TDA leverages the invariant topological features of signals in a metric space robust even presence noise. In this paper, we leverage on brain connectivity networks derived from electroencephalogram (EEG) to identify statistical differences between pediatric patients with obstructive sleep apnea (OSA) and without OSA. We large corpus data, show that enables us see difference dynamics two groups.

Abstract Introduction Obstructive sleep apnea (OSA) is difficult to diagnose and leads significant complications, including poor rest heart disease. Identification of OSA in patients typically requires a polysomnogram, which includes acquisition electroencephalogram (EEG) signals order assist with identification stages. Recent advancements signal processing technology, topological data analysis (TDA), provide novel new way analyze EEG before disordered breathing occurs. Methods We leverage...

The psychological wellbeing of adolescents, including their relationships with parents and friends, is highly affected by romantic relationship conflict. At-risk youth - who are involved the juvenile justice system especially vulnerable to aggression, defiance, behavioral problems experience conflict at rates that exceed those in community. pervasive usage mobile technology adolescents provides unprecedented data on social interactions, communication patterns, conflicts; as well an...

Depression is a prevalent mental health concern among students due to the relentless academic demands and societal pressures. This study tests hypothesis that with increased depression exhibit specific social interaction patterns like connecting others both online in-person, associated distinct personality traits. Leveraging smartphone passive sensing data from StudentLife dataset, we categorized into three clusters based on their big five survey responses. Our key finding reveals high...