Innovative Projects Realized

Wirelessly COVID-19 Patient Tracking and Risk Assessment Using Edge AI Platform

The ability of the health system to manage a massive influx of patients is based on the combination of four factors: the personnel, the equipment, the physical spaces and the system in place. A combination better known in jargon as the 4 “S” (staff, stuff, structure / space, system). A fifth factor that is often misunderstood is synchronicity. With great adaptation to the workspace and team structures, a newly trained staff with new equipment, and a system of critical processes that evolve according to the evolution of the environment and the healthcare system status, synchronicity is essential. This synchronicity requires real time data and automations to enable already pressured teams and a stressed healthcare organization to adapt to unforeseen requests and needs.

In this project, we want to rapidly assess the risk of COVID-19 infection of people living in a building or healthcare facilities through analyzing their distance to other people who might or might not have been in contact with COVID-19 patients. This will be achieved with the help of wireless data collection, and artificial intelligence algorithms running on the hardware and software platform located within or in proximity to the building.

North Perth Ontario: Developing a Response Plan

The consequences of the COVID-19 pandemic are far-reaching and extend beyond the spread of the disease and efforts to quarantine it. With emergency management efforts underway, opportunities exist to develop more effective and efficient response measures to increase the resiliency of our communities amidst this and future public health crises. Developing impactful resilience strategies requires a regional- and community-scale focus. While most Canadians live in urban centres, nearly 20% of the national population resides in small and/or rural centres. Across Canada’s rural landscape are communities facing unique realities, complex challenges, and numerous opportunities. In partnership with The Salvation Army – Listowel, this project will examine North Perth County as a case study to explore what planning activities are required in small and rural communities to best support ongoing recovery efforts and to increase resiliency and well-being over the long-term. Outcomes from this project will support rural communities to develop effective local policies and planning strategies to respond to the coronavirus pandemic and future disruptive events.

Development of Machine Learning Algorithms for Inferring Biomarkers Underlying Multi-Modal Physiological Signals of Patients with COVID-19

COVID-19 is a global pandemic disease and the best way to stop it is controlling its spread and treating the infected individuals. Detailed measures of clinical characteristics and outcomes in patients with COVID-19 like Reverse transcription-polymerase chain reaction (RT-PCR) are not accessible to a large population and require patients to spend hours waiting at the hospitals. As well, it is not yet known that the lung is the only host of this virus; an inflammation of the heart has been recently reported in patients with COVID-19. Most recent studies imply that COVID-19 might directly impact on the heart. Therefore, relying on one method for detecting COVID-19 is not sufficient, multi-modal sensors indicating different physiological activities are required. There is no unique solution to capture different but relevant physiological signals underlying COVID-19. Given medical imaging techniques (chest CT scans), pulmonary function tests (PFTs), and electrophysiological recordings (e.g., ECG and blood pressure) of patients with COVID-19, we, in collaboration with Dena Corporation and University of Toronto, aim to develop machine learning and signal processing algorithms for detecting biomarkers underlying COVID19 and inferring their correlational patterns.

Optimizing Pretrained Clinical Embeddings for Automatic COVID-related ICD Coding

We are building a machine learning algorithm to be able to better understand the unstructured clinical notes that doctors write about patients. This will help hospitals and healthcare systems standardize and extract insights from these notes to make them more useful for determining how sick COVID patients are and how they are improving over time.

Moving Beyond BMI: Cardiovascular fitness as biological marker of reproductive health

The Healthcare Foundation plays an active role in improving patient experiences across Newfoundland and Labrador. The significant findings from research funded by the Healthcare Foundation helps improve the way we diagnose and treat our population. After a grant is received a board member from the foundation is updated on the findings of the research, who then examines how the results will improve healthcare practices in the province. If our study yields significant results, offline resources may become available to the patient population, which can be accessed without seeing a physician. The survey will also provide information on the patient demographics to help inform future research of Infertility in our province.
Our original study entailed a comparison between obese-fit fertile women and obese-lean fertile women that we will use to determine the effects of cardiovascular fitness on biomarkers of fertility. We will work with the Healthcare Foundation to apply our findings to incorporate a new element into the standard care procedures at Eastern Health. Additional resources will be highly beneficial for fertility patients while enduring the long waitlists to help improve treatment outcomes.

Development of applications of the NanoCleanSQ surface coating in the fight against COVID-19

Envision SQ Inc. (EnvisionSQ), in a joint effort with the University of Guelph, is currently working on applications of their NanoCleanSQ disinfectant-sanitizer to help slow down the spread of the SARS-CoV-2 virus (the virus that causes COVID-19). NanoCleanSQ is a clear coating material and acts as a photocatalytic disinfectant that can be easily applied to virtually any hard surface to help prevent spread of viruses. While initial testing results indicate the coating kills bacteria and viruses, additional research is needed to understand how it can be deployed in various situations such as hospitals and long term care facilities. The results of the research undertaken by the interns is expected to lead to new product development and commercialization opportunities for EnvisionSQ.

Development of Airborne COVID-19 Isolation and Elimination Device

The key for controlling the transmission of COVID-19 is to isolate and eliminate COVID-19 contaminated air and droplets, particularly aerosols. However, this is very challenging for many healthcare settings such as dentistry, which are in dire need of an effective and feasible solution for reducing the COVID-19 risk. UBC Okanagan will partner with Care Health Meditech Developments Inc. to develop an innovative device, Airborne Infection Isolation and Elimination Device (AIIED), which will enable safe collection and disposal of COVID-19 contaminated air in dental operations. This project is of significant importance for Canada and the world as it reduces the need for production and/or purchase of Personal Protection Equipment (PPE) for combating the pandemic.

Thermal characteristics of viruses in humans, specifically COVID-19

The research project will focus on identifying thermal characteristics of COVID-19 in humans and applying the characteristics identified to detect COVID-19 in humans using non-invasive methodologies.

For this project, the thermal characteristics of viruses in humans, specifically COVID-19 will be studied. The aim will be to answer the following questions:

(1) What are the thermal characteristics in COVID-19 patients?
(2) Can thermal imaging be used to specifically identify subjects infected with the virus?
(3) Can this research advance existing thermal imaging solutions to improve current detection methods of COVID-19?

The goal, in part, is to help enable effective responses to viral-based pandemics and, possibly, a solution to help rebuild the Canadian economy.

Strategic Safety Stock Allocation in an AssemblySupply Chain Network

The supply chain structure of an engine assembly line consists of several complex flows and
processes to satisfy the requirements for on time delivery of these products. The difficulty in managing
such systems is due to the fact that more than 1000 parts should be available on time in a
synchronized manner to start the assembly procedures and deliver the products on time. Due to the
supplier lead time variability, quality inspection related delays and other sources of uncertainty, the
adherence to a production plan is almost impossible. This results in delays in the production schedule
which may result in delays in the delivery of engines to the customer.The objective of this research
project is to improve on time delivery performance of the engine assembly line and develop new
inventory policies for the supply chain operations to accommodate the transition to the moving
assembly line while keeping the inventory investment at an acceptable level.

Développement et validation d’une solution logicielle pour le contrôle à distance d’objets connectés pour favoriser l’interaction sociale des personnes âgées

En raison de la pandémie de COVID-19, les personnes âgées, en situation de confinement sont déconnectées de leurs liens sociaux, et donc plus isolées et sédentaires que d’habitude. L’isolement social est encore plus critique pour les aînés moins familiers avec les technologies numériques. La présente demande vise le développement et la validation d’une solution logicielle qui va permettre le contrôle et la gestion à distance d’objets connectés (ex. tablettes, téléphones ou casques de réalité virtuelle). Grâce à une telle solution, les personnes âgées qui seraient moins habiles avec la technologie seront accompagnées de façon sécuritaire et responsable pour des activités favorisant l’interaction sociale et/ou la stimulation à l’activité physique. Cette solution logicielle contribuera à réduire l’isolement, l’ennui, l’inactivité physique et le stress chez les aînés, incluant ceux ayant peu ou pas d’expériences d’utilisation de technologies numériques.

Effectiveness of Dual-Microphone Model-Based Speech Discrimination for Increasing Speech Intelligibility in In-Situ Babble Noise

Malaspina Labs Inc. conducts applied research and development of state-of-the-art audio processing
technologies that dramatically increase speech comprehension in noisy environments. Based in
Vancouver Canada, Malaspina Labs is driven by a core team of academic and industry researchers in
the fields of audio processing and speech isolation. We have a common goal of developing the
world’s most advanced speech processing software and implementing it on milliwatt-class target
devices. Malaspina Labs has demonstrated the effectiveness of its VoiceBoost™ model based
speech discrimination for ultra-low power mobile processors. By isolating speech-of-interest from
background noise including background speech, VoiceBoost™ has been shown to improve speech
quality by 36% over existing 3G phone and network noise reduction in real-world high noise
environments. This research internship project will advance the field for speech intelligibility and noise
reduction as well as the company’s audio processing technologies.

ALS in a dish: development of an in vitro human 3D model of the neuromuscular junction with functional readouts

In amyotrophic lateral sclerosis (ALS), the communication between motor neurons and skeletal muscle is lost, resulting in weakness and degeneration of muscle tissue. ALS animal models fail to reproduce the complexities of the disease, which is thought to account for the failure of new drugs in clinical trials. At The Neuro, human blood samples are obtained to generate pluripotent stem cells (PSCs), which are able to give rise to all the cell types of the human body. Our goal is to generate motor neurons from the PSCs of healthy controls and ALS patients to grow them with skeletal muscle in 3D in a special dish created by eNUVIO. This platorm will facilitate the acquisition of functional readouts similar to those obtained from electromyography and nerve conduction velocity, studies used for ALS diagnosis purposes. Furthermore, the model at the endwill be scalable for high-throughput drug screening purposes to facilitate the identification of lead compounds in our human NMJ on a dish platform.