Computer Engineering Commons^™

Towards Better Remote Healthcare Experiences: An Mhealth Video Conferencing System For Improving Healthcare Outcomes, El Sayed Mahmoud, Edward Sykes, Blake Eram, Sandy Schwenger, Jimmy Poulin, Mark Cheers

Publications and Scholarship

This work investigated how to combine mobile cloud computing, video conferencing and user interface design principles to promote the effectiveness and the ease of using online healthcare appointment platforms. The Jitsi Meet video conference technology was selected from amongst 27 competing systems based on efficiency and security criteria. This platform was used as the foundation on which we designed, developed and evaluated of our video conferencing system specially designed for improving doctor-patient interaction and experiences. Nine doctor- patient functions were developed in order to facilitate efficient and effective online healthcare appointments, such as providing the doctor with the ability to …

3d Reconstruction Of Spine Image From 2d Mri Slices Along One Axis, Somoballi Ghoshal, Sourav Banu, Amlan Chakrabarti, Susmita Sur-Kolay, Alok Pandit

Journal Articles

Magnetic resonance imaging (MRI) is a very effective method for identifying any abnormality in the structure and physiology of the spine. However, MRI is time consuming as well as costly. In this work, the authors propose an algorithm which can reduce the time of MRI and thus the cost, with minimal compromise on accuracy. They reconstruct a three-dimensional (3D) image of the spine from a sequence of 2D MRI slices along any one axis with reasonable slice gap. In order to preserve the image at the edges properly, they regenerate the 3D image by using a combination of bicubic and …

Supporting Coordination Of Children With Asd Using Neurological Music Therapy: A Pilot Randomized Control Trial Comparing An Elastic Touch-Display With Tambourines, Franceli L. Cibrian, Melisa Madrigal, Marina Avelais, Monica Tentori

Engineering Faculty Articles and Research

Aim

To evaluate the efficacy of Neurologic Music Therapy (NMT) using a traditional and a technological intervention (elastic touch-display) in improving the coordination of children with Autism Spectrum Disorder (ASD), as a primary outcome, and the timing and strength control of their movements as secondary outcomes.

Methods

Twenty-two children with ASD completed 8 NMT sessions, as a part of a 2-month intervention. Participants were randomly assigned to either use an elastic touch-display (experimental group) or tambourines (control group). We conducted pre- and post- assessment evaluations, including the Developmental Coordination Disorder Questionnaire (DCDQ) and motor assessments related to the control of …

Circus In Motion: A Multimodal Exergame Supporting Vestibular Therapy For Children With Autism, Oscar Peña, Franceli L. Cibrian, Monica Tentori

Engineering Faculty Articles and Research

Exergames are serious games that involve physical exertion and are thought of as a form of exercise by using novel input models. Exergames are promising in improving the vestibular differences of children with autism but often lack of adaptation mechanisms that adjust the difficulty level of the exergame. In this paper, we present the design and development of Circus in Motion, a multimodal exergame supporting children with autism with the practice of non-locomotor movements. We describe how the data from a 3D depth camera enables the tracking of non-locomotor movements allowing children to naturally interact with the exergame . A …

Machine Learning Approaches For Fracture Risk Assessment: A Comparative Analysis Of Genomic And Phenotypic Data In 5130 Older Men, Qing Wu, Fatma Nasoz, Jongyun Jung, Bibek Bhattarai, Mira V. Han

Public Health Faculty Publications

The study aims were to develop fracture prediction models by using machine learning approaches and genomic data, as well as to identify the best modeling approach for fracture prediction. The genomic data of Osteoporotic Fractures in Men, cohort Study (n = 5130), were analyzed. After a comprehensive genotype imputation, genetic risk score (GRS) was calculated from 1103 associated Single Nucleotide Polymorphisms for each participant. Data were normalized and split into a training set (80%) and a validation set (20%) for analysis. Random forest, gradient boosting, neural network, and logistic regression were used to develop prediction models for major osteoporotic fractures …

Is It Safe For My Child’S Asthma?, Utkarshani Jaimini, Amit Sheth, Krishnaprasad Thirunarayan, Maninder Kalra, Marco Valtorta

Publications

kHealth-Asthma, a personalised digital healthcare framework is developed to address the above shortcomings by continuous monitoring of the child’s digital phenotype, indoor, and outdoor environmental data. The kHealth-Asthma study has recruited 140 children (ongoing) with an aim to complete recruitment of 150 children. The study period is either 1 month or 3 month depending on the choice of the study participant. kHealth-Asthma collects 29 multi-modal parameters leading to 1852 data points per patient per day (i.e. deployment: 1 month:1852*30=55,560 data points per patient and 3 month:1852*90=166,680 data points per patient). The digital phenotype collected using the kHealth-Asthma generates a Digital …

Mining User-Generated Content Of Mobile Patient Portal: Dimensions Of User Experience, Mohammad Al-Ramahi, Cherie Noteboom

Faculty Research & Publications

Patient portals are positioned as a central component of patient engagement through the potential to change the physician-patient relationship and enable chronic disease self-management. The incorporation of patient portals provides the promise to deliver excellent quality, at optimized costs, while improving the health of the population. This study extends the existing literature by extracting dimensions related to the Mobile Patient Portal Use. We use a topic modeling approach to systematically analyze users’ feedback from the actual use of a common mobile patient portal, Epic’s MyChart. Comparing results of Latent Dirichlet Allocation analysis with those of human analysis validated the extracted …

Non-Obstetrical Robotic-Assisted Laparoscopic Surgery In Pregnancy: A Systematic Literature Review., Courtney Capella, Joseph Godovchik, Thenappan Chandrasekar, Huda B. Al-Kouatly

Department of Urology Faculty Papers

Urologic and gynecologic surgeons are the top utilizers of robotic surgery; however, non-obstetrical robotic-assisted laparoscopic surgery (RALS) in pregnant patients is infrequent. A systematic literature review was performed to ascertain the frequency, indication and complications of RALS in pregnancy. Results showed thirty-eight pregnancies from eleven publications between 2008-2020. Five cases were for urologic indication and thirty-three for gynecologic indication. Minimal surgical alterations were required. Although no adverse maternal-fetal outcomes were reported, there are not enough cases published to determine safety. This review demonstrates the feasibility of RALS for the pregnant population in the hands of competent robotic surgeons.

Ml-Medic: A Preliminary Study Of An Interactive Visual Analysis Tool Facilitating Clinical Applications Of Machine Learning For Precision Medicine, Laura Stevens, David Kao, Jennifer Hall, Carsten Görg, Kaitlyn Abdo, Erik Linstead

Engineering Faculty Articles and Research

Accessible interactive tools that integrate machine learning methods with clinical research and reduce the programming experience required are needed to move science forward. Here, we present Machine Learning for Medical Exploration and Data-Inspired Care (ML-MEDIC), a point-and-click, interactive tool with a visual interface for facilitating machine learning and statistical analyses in clinical research. We deployed ML-MEDIC in the American Heart Association (AHA) Precision Medicine Platform to provide secure internet access and facilitate collaboration. ML-MEDIC’s efficacy for facilitating the adoption of machine learning was evaluated through two case studies in collaboration with clinical domain experts. A domain expert review was also …

Supporting Self-Regulation Of Children With Adhd Using Wearables: Tensions And Design Challenges, Franceli L. Cibrian, Kimberley D. Lakes, Arya Tavakoulnia, Kayla Guzman, Sabrina Schuck, Gillian R. Hayes

Engineering Faculty Articles and Research

The design of wearable applications supporting children with Attention Deficit Hyperactivity Disorders (ADHD) requires a deep understanding not only of what is possible from a clinical standpoint but also how the children might understand and orient towards wearable technologies, such as a smartwatch. Through a series of participatory design workshops with children with ADHD and their caregivers, we identified tensions and challenges in designing wearable applications supporting the self-regulation of children with ADHD. In this paper, we describe the specific challenges of smartwatches for this population, the balance between self-regulation and co-regulation, and tensions when receiving notifications on a smartwatch …

El Artista Está En Línea: E-Performance En El Tiempo De Covid-19, Ezequiel N. González

Independent Study Project (ISP) Collection

Esta investigación propone una lectura detallada y comparativa de varias e-performances creadas por el artista visual uruguayo Ernesto Rizzo y la performer argentina Susy Shock, trazando un corpus de trabajo creado durante la crisis de COVID-19 y compartido en Instagram desde finales de marzo a finales de mayo de 2020. Al centrarse en el giro digital del arte de performance debido a las particularidades de la cuarentena, esta investigación busca distinguir este momento de "e-performance", entendiendo cuáles serán sus ramificaciones para el/la artista y el arte de performance en general. Así, a través de una reflexión teórica sobre el terreno …

Learning In The Machine: To Share Or Not To Share?, Jordan Ott, Erik Linstead, Nicholas Lahaye, Pierre Baldi

Engineering Faculty Articles and Research

Weight-sharing is one of the pillars behind Convolutional Neural Networks and their successes. However, in physical neural systems such as the brain, weight-sharing is implausible. This discrepancy raises the fundamental question of whether weight-sharing is necessary. If so, to which degree of precision? If not, what are the alternatives? The goal of this study is to investigate these questions, primarily through simulations where the weight-sharing assumption is relaxed. Taking inspiration from neural circuitry, we explore the use of Free Convolutional Networks and neurons with variable connection patterns. Using Free Convolutional Networks, we show that while weight-sharing is a pragmatic optimization …

Scalable Profiling And Visualization For Characterizing Microbiomes, Camilo Valdes

FIU Electronic Theses and Dissertations

Metagenomics is the study of the combined genetic material found in microbiome samples, and it serves as an instrument for studying microbial communities, their biodiversities, and the relationships to their host environments. Creating, interpreting, and understanding microbial community profiles produced from microbiome samples is a challenging task as it requires large computational resources along with innovative techniques to process and analyze datasets that can contain terabytes of information.

The community profiles are critical because they provide information about what microorganisms are present in the sample, and in what proportions. This is particularly important as many human diseases and environmental disasters …

A Hybrid Agent-Based And Equation Based Epidemiological Model For The Spread Of Infectious Diseases, Elizabeth Hunter

Doctoral

Infectious disease models are essential in understanding how an outbreak might occur and how best to mitigate an outbreak. One of the most important factors in modelling a disease is choosing an appropriate model and determining the assump tions needed to create the model. The main research questions this thesis addresses are how do we create a model for the spread of infectious diseases that captures heterogeneous agents without using an inordinate amount of computing power and how can we use that model to plan for future infectious disease outbreaks. We start our work by analysing and comparing equation based …

Applications Of Cloud-Based Quantum Computers With Cognitive Computing Algorithms In Automated, Evidence-Based Virginia Geriatric Healthcare, Henry Childs

Auctus: The Journal of Undergraduate Research and Creative Scholarship

Quantum computers have recently headlined IBM’s next generation of products promoting computational evolution. After the successful release of the cloud-streaming quantum computer IBM Watson Q, the company has released projections for future development of quantum devices. Because of the incredible processing power of these machines and the expected integration into everyday life in the near future, what implications can this have in the healthcare field?

I am studying cloud-based quantum computers with natural language processing (NLP) algorithms and patient health record data because I want to understand automated, evidenced-based co-optimized treatment of home-bound geriatric patients in order to help my …

Automated Assessment Of Cardiothoracic Ratios On Chest Radiographs Using Deep Learning, Varun Danda, Paras Lakhani, Md

Phase 1

Introduction: The cardiothoracic ratio (CTR) is a quantitative measure of cardiac size that can measured from chest radiography (CXR). Although radiologists using digital workstations possess the ability to calculate CTR, clinical demands prevent calculation for every case. In this study, the efficacy of a deep convolutional neural network (dCNN) to assess CTR was evaluated.

Methods: 611 HIPAA-compliant de-identified CXRs were obtained from [institution blinded] and public databases. Using ImageJ, a board-certified radiologist (reader #1) and a medical student (reader #2), measured the CTR by marking four pixels on all CXRs: the right- and left-most chest wall, the right- and left-most …

Internet Of Things For Sustainable Human Health, Abdul Salam

Faculty Publications

The sustainable health IoT has the strong potential to bring tremendous improvements in human health and well-being through sensing, and monitoring of health impacts across the whole spectrum of climate change. The sustainable health IoT enables development of a systems approach in the area of human health and ecosystem. It allows integration of broader health sub-areas in a bigger archetype for improving sustainability in health in the realm of social, economic, and environmental sectors. This integration provides a powerful health IoT framework for sustainable health and community goals in the wake of changing climate. In this chapter, a detailed description …

Assessment Of Dobhoff Tube Malposition On Radiographs Using Deep Learning, Kevin George, Paras Lakhani, Md

Phase 1

Introduction: Dobhoff tubes (DHT) are narrow-bore flexible devices that deliver enteral nutrition for critically ill patients. Tracheobronchial insertion of DHTs presents a significant risk for pulmonary complications. Thus, DHT insertion requires radiologist confirmation of correct placement with chest x-ray (CXR), increasing clinical delays. To address this, we demonstrate the novel application of Deep Convolutional Neural Networks (DCNNs) to automatically and accurately identify DHTs in CXRs in real time.

Methods: 141 de-identified HIPAA compliant frontal view chest radiographs containing DHTs in various positions were obtained. The DHTs were first manually segmented and verified by a board certified radiologist. Images were split …

3d Convolutional Neural Networks For The Diagnosis Of 6 Unique Pathologies On Head Ct, Travis Clarke, Paras Lakhani, Md

Phase 1

Introduction: Head CT scans are a standard first-line tool used by physicians in the diagnosis of neurological pathologies. Recently, the development of deep learning models such as convolutional neural networks (CNNs) has allowed the rapid identification of bleeds and other pathologies on CT scans. This study aims to show that by training 3D CNNs with a larger, curated dataset, a more comprehensive list of potential diagnoses can be included in the detailed model.

Methods: A retrospective study was performed using a dataset of 66,000 head CT studies from the Thomas Jefferson University health system. Studies were acquired using a natural …

Explainable Ai Using Knowledge Graphs, Manas Gaur, Ankit Desai, Keyur Faldu, Amit Sheth

Publications

During the last decade, traditional data-driven deep learning (DL) has shown remarkable success in essential natural language processing tasks, such as relation extraction. Yet, challenges remain in developing artificial intelligence (AI) methods in real-world cases that require explainability through human interpretable and traceable outcomes. The scarcity of labeled data for downstream supervised tasks and entangled embeddings produced as an outcome of self-supervised pre-training objectives also hinders interpretability and explainability. Additionally, data labeling in multiple unstructured domains, particularly healthcare and education, is computationally expensive as it requires a pool of human expertise. Consider Education Technology, where AI systems fall along a …

Deformable Multisurface Segmentation Of The Spine For Orthopedic Surgery Planning And Simulation, Rabia Haq, Jérôme Schmid, Roderick Borgie, Joshua Cates, Michel Audette

Computational Modeling & Simulation Engineering Faculty Publications

Purpose: We describe a shape-aware multisurface simplex deformable model for the segmentation of healthy as well as pathological lumbar spine in medical image data.

Approach: This model provides an accurate and robust segmentation scheme for the identification of intervertebral disc pathologies to enable the minimally supervised planning and patient-specific simulation of spine surgery, in a manner that combines multisurface and shape statistics-based variants of the deformable simplex model. Statistical shape variation within the dataset has been captured by application of principal component analysis and incorporated during the segmentation process to refine results. In the case where shape statistics hinder detection …