(FoRCE): Powering clinical trials research through a secure and integrated data management platform
Critical care units are one of the most data-rich environments in clinical settings, with data being generated by advanced patient monitoring, frequent laboratory and radiologic tests, and around-the-clock evaluation. There are substantial opportunities in linking data that are collected as a part of such clinical practice with data collected in a research setting, such as genome wide studies or comprehensive imaging protocols. However, security and privacy issues have historically been a significant barrier to the storage, analysis, and linkage of such biomedical data. Further, disparate technologies hinder collaboration across teams, most of which lack the secure systems required to enable federation and sharing of these data. This is particularly true when clinical practice or research designs require close to real time analysis and timely feedback, such as when dealing with streamed medical data or output from clinical laboratories. Current commercial and research solutions often fail to integrate different data types, are incapable of handling streaming data, and rely solely on the security measures put in place by the organizations that deploy them.
This proposal seeks to build FoRCE (Focus on Research and Clinical Evaluation), a scalable and adaptable add-on module to the existing Indoc Informatics platform that will address the critical gaps in cybersecurity and privacy infrastructure within shared clinical and research settings, while fulfilling important unmet needs for both the clinical and research communities. FoRCE will provide the secure architecture and processes to support the collection, federation and sharing of data from distributed clinical settings, including critical care units, clinical laboratories, and imaging facilities. The proposed platform will address several key issues including security considerations, infrastructure and software requirements for linkage, and solutions for handling streaming real time medical data, and ensuring regulatory and ethics compliance when linking diverse medical data modalities in a clinical setting.
FoRCE will be designed and developed with broad applicability in mind, and will therefore allow the different data types from numerous technologies and across multiple disease states to utilize the platform. The long term impact of FoRCE on improving the health of Ontarians is of course dependent on its utilization within research and clinical settings. An initial project which will utilize the platform as part of the testing and validation of FoRCE includes Dr. Maslove’s integrated approach to merging genomic and physiologic data streams from the ICU in the context of clinical research. FoRCE will enable Dr. Maslove’s team of critical care researchers to move beyond predictors of survival to focus on predictors of response to therapy, so that clinical trials in the ICU can be optimized to produce actionable evidence and personalized results. This will lead to better allocation of ICU resources, which in Canada cost nearly $3,000 per patient per day – $3.72 billion per year.
Cloud-based Framework for Analysing COVID-19 Data
Edge computing (EC) has shown to have a significant impact on offloading traffic/computations/AI tasks from backhaul links/servers and improving users’ Quality of Service (QoS). It is anticipated that EC in general and its use to implement AI at the edge (a.k.a. edge intelligence, EI) will be necessary components of all digital business by 2022 and that 40% of large enterprises will integrate EC/EI into their production systems by 2021.
The objective of the proposed research is to transform the already existing yet latent computing resources into on-demand clusters of distributed EC/EI workers, with a focus on distributed learning and intelligence. The proposed research will develop foundational elements of the COVID-19 and future pandemic analysis platform using KDS’s Distributed Compute Protocol (DCP). DCP allows massive computing resources to be accessed in parallel.
The proposed DCP COVID-19 project will support the Looking Glass project, a free and open platform to better inform remediation strategies, public health interventions, and vaccine campaign strategies against COVID-19 – as well as time strategies to relax lockdown measures during the recovery phase – for municipalities, state/federal authorities by modelling transmission patterns of diseases based on reports from epidemiologists fused with economic report data, and high-resolution mobility data.
Identifying disease clusters, spatial patterns, and methods of transmission of endemic, epidemic and pandemic diseases are essential to inform policymakers, programs, and interventions at both local and global scales. Health authorities depend on alerts provided by front-line employees or by members of the public when there is a disease cluster. The recent emergence of the COVID-19 as a global pandemic is one example of a critical public health threat that challenged management systems.
Image detection for infection control
In a world of pandemics such as SARS and COVID-19, our health care environments have shown their vulnerability. Unfortunately, we have seen outbreaks in long term care facilities in Quebec, Alberta, BC and Ontario, with dozens of seniors at each site contracting and passing from COVID. In addition to life lost, health care workers themselves are put at risk which leads to a shortage of workers during urgent times. Additional costs are realized as patients require more investigations, longer stays in hospitals and additional treatments. Utilizing a MaskRCNN model to separate objects in video, we propose utilizing real-time image detection of humans (visitors and health care workers) using protective wear (I.e. masks, gloves, and gowns) in health care settings to safeguard workers and patients. Our model is also being trained to determine if PPE is donned and doffed accurately, as literature has shown that roughly 40% of Canadian healthcare workers do this incorrectly, further increasing transmission. The results of this project will provide MedDuck with a novel form of image detectionability that will have immediate real-world application.
Multilevel streaming data analytics infrastructure for predictive analytics
Predictive Analytics for digital media processing is facing the challenge of handling an increasing volume, velocity and variety of big data and there has been an enormous drive lately in the area of streaming data analytics. We are rapidly moving towards the Internet of Things (IoT) where predictive analytics will need to analyze and integrate streaming data from many different devices and digital media sources including structured data from the traditional relational databases and unstructured data from the recent big data storage systems. Therefore, we need an infrastructure to enable long-term multilevel knowledge extraction where 1) the 1st level analytics performed by a stream processing engine will identify important data components from multiple data streams and move them into a memory buffer. 2) Then an in-memory data analytics engine will be used to perform the 2nd and the subsequent levels of analytics for knowledge extraction and integration with other big data sources. 3) Finally, only the important data stream components and the extracted knowledge can be stored for future analytics into a big data store. We propose to develop an infrastructure to facilitate complex multilevel predictive analytics and to streamline the process of knowledge extraction and integration for both streaming and non-streaming data. A variety of open source stream processing engines exist today. However, none support such multilevel analytics. We will use open source streaming and in-memory data analytics engines and SOSCIP’s cloud and big memory systems. The infrastructure will be validated using streaming financial and business news and social media data analytics for identifying business growth, stress and risk signals. It will contribute to Canada’s economy by leveraging predictive analytics for decision support in areas such as cybersecurity, health and e-government.
Transition to turbulence on aircraft engine nacelles
Turbulence significantly affects the aerodynamic drag of aircrafts. Reducing its impact can result in substantial economic benefits to the aerospace industry and to the public, principally in terms of reduced fuel consumption and therefore, lower operational costs. One of the main causes of turbulence, on an engine nacelle, is the presence of surface imperfections: gaps between metal plates, roughness, ice formations, rivets. This project will examine how these surface imperfections affect the generation of turbulence, and what manufacturing tolerances are required to delay the onset of turbulence, thereby decreasing the aerodynamic drag. This will be achieved through a combination of high fidelity numerical models of the flow over the nacelle, combined with the development of simplified models to be transitioned to the industrial partner.
Watson #HERE4U Military Edition
Mental health issues affect a large percentage of the military population. The #HERE4U Military Edition will be an instant messaging smartphone application to connect military family members (adults only) who are dealing with mental health problems to a mental health counseling solution that uses the IBM Watson cognitive platform. Being able to engage with Watson in a secure, private and anonymous manner will encourage military personnel to reach out for help where they might not have in the past to obtain timely advice. Watson will engage with the client to identify a presenting problem and when clinically serious, engage a counselor for guidance and referral; otherwise, Watson will carry on a conversation with the client, giving advice, referring to mental health resources, including self-help materials, as appropriate. The key challenge for this project is to collect unstructured case data and best practice literature that Watson can use to manage conversations.
Workplace of the Future
Ambient factors such as light, heat, and music can significantly impact physical comfort in employees. Additionally, affective states and cognitive load of workplace occupants can affect their quality of life, general happiness, and cognitive capacity. This research aims to design and develop a smart workplace capable of detecting, analyzing, and acting on the environmental ambient factors, thus optimizing both physical comfort and happiness in employees in the workplace. To achieve this goal, this project targets the development of tools and methods using artificial intelligence, machine learning, and deep learning for ubiquitous monitoring, analysis, and interpretation employee happiness, cognitive load, and physical comfort based on information obtained from a variety of different wearable and non-contact sensors. Moreover, algorithms and models will be developed for aggregation of individual preferred and perceived ambient conditions, and cognitive/affective states. Finally, the obtained information will be used to autonomously and intelligently tune ambient and organizational parameters for optimum employee happiness, comfort, and performance. With the recent COVID-19 pandemic and the necessity for organizations to adopt to new workplace models, particular attention will be paid to distributed and remote working conditions. Machine learning will be used to understand affective and cognitive factors such as happiness, stress, and cognitive load from remote audio and video calls in addition to wearable sensors where possible.