by June Kaminski, RN MSN PhD(c)

Citation: Kaminski, J. (2024). Editorial. Spotlight on Canadian Informatics Breakthroughs in 2024. Canadian Journal of Nursing Informatics, 19(4).  https://cjni.net/journal/?p=14004

In 2024, Canada’s health informatics landscape continued to be revolutionized by groundbreaking advancements that underscored the nation’s ability to harness technology for improved patient outcomes, system efficiency, and equitable care delivery. These achievements, spanning artificial intelligence (AI), telehealth, digital transformation, and ethical innovation, collectively helped to transform the way Canadians interact with the healthcare system.

Artificial Intelligence: A Personalized Approach to Care

Artificial Intelligence (AI) remained at the forefront of Canadian health informatics this year, with researchers and institutions leveraging advanced algorithms to redefine patient care. Canadian AI models achieved remarkable progress in combining diverse data streams, such as electronic health records (EHRs), medical imaging, genetic sequencing, and even wearable device metrics.

For example, AI-enabled platforms analyzed imaging data to detect cancers earlier and with greater accuracy, while predictive models provided clinicians with actionable insights to prevent hospital readmissions.

Breast Cancer Detection

Dr. April Khademi, a biomedical engineer at Toronto Metropolitan University, developed an AI tool to assist pathologists in diagnosing breast cancer more consistently and reliably. Supported by the Canadian Cancer Society (CCS), her research demonstrated that AI integration boosts diagnostic accuracy and optimizes workflow, thereby enhancing patient care and outcomes (Canadian Cancer Society, 2024; Dy et al, 2024).

Lung Cancer Detection

Another CCS-funded project led by Dr Renelle Myers (British Columbia) and Dr. Rayjean Hung (Ontario) focused on improving early detection of lung cancer using machine learning analytics. Researchers applied AI to detect tumor signals in data and predict imminent tumor occurrences based on CT images. This approach addresses significant gaps in lung cancer detection in Canada and has the potential to establish new methods for early diagnosis, when treatment is more likely to be successful (BC Cancer Foundation, 2024).

AI in Medical Imaging

AI’s role in medical imaging extended beyond detection to include segmentation and diagnosis of tumor lesions. By learning from image data inputs and constructing algorithm models, AI can automatically recognize and diagnose tumors, showing promising application prospects. “By learning from image data input and constructing algorithm models, AI is able to recognize, segment, and diagnose tumor lesion automatically, showing promising application prospects” (Zheng et al., 2023, p. 1).

These developments underscore Canada’s commitment to integrating AI technologies in healthcare, aiming to improve early cancer detection and patient outcomes through advanced imaging data analysis.

Predictive Models and Improved Care

In 2024, Canadian healthcare institutions have also advanced the use of predictive models to provide clinicians with actionable insights aimed at preventing hospital readmissions. These models analyze patient data to identify individuals at high risk of readmission, enabling targeted interventions to improve patient outcomes and reduce healthcare costs.

Survival-Inspired Readmission Models

Sacha Davis and Russell Greiner (2024), researchers at the University of Alberta developed a survival-inspired readmission model that leverages longitudinal patient data. By analyzing sequences of medical events, the model predicts the time until a potential readmission. This approach allows clinicians to implement timely interventions for patients at elevated risk, thereby enhancing care continuity and reducing readmission rates.

Integration of Patient-Reported Outcome Measures (PROMs)

A systematic review by Yu and colleagues (2024) highlighted the potential of incorporating Patient-Reported Outcome Measures (PROMs) into predictive models to enhance their accuracy. By including patients’ self-reported health status, these models provide a more comprehensive assessment of readmission risk, enabling personalized care plans that address specific patient needs and reduce the likelihood of readmission.

Machine Learning and Deep Learning Approaches

Advancements in machine learning and deep learning have further refined predictive models. Techniques such as the extraction of biomedical concepts from clinical texts have improved the precision of readmission predictions. These models analyze unstructured data from electronic health records to identify subtle indicators of readmission risk, supporting clinicians in making informed decisions about patient care (Samani et al., 2024). These developments demonstrate Canada’s commitment to leveraging predictive analytics in healthcare, providing clinicians with valuable tools to proactively manage patient care and prevent hospital readmissions.

Emergency Department Workflow Optimization

Startups like Toronto-based Hero AI demonstrated how real-time analytics could optimize emergency department workflows, reducing patient wait times and enhancing safety.

Hero AI, a Toronto-based healthcare technology company founded in 2020 by Dr. Devin Singh, has developed real-time analytics solutions to optimize emergency department (ED) workflows, aiming to reduce patient wait times and enhance safety (Hero AI, 2024).

Real-Time Monitoring and AI-Powered Dashboards

Hero AI’s platform provides healthcare teams with AI-powered dashboards that display real-time ED activity, including patient census and flow. This continuous monitoring enables staff to identify and address potential bottlenecks promptly, facilitating more efficient patient management and resource allocation (Hewitt, 2024).

Waiting Room Safety Module

The platform includes a Waiting Room Safety Module that continuously monitors the ED waiting room to ensure high-risk patients are not left waiting excessively. It automates the detection of high-risk medical and surgical patients based on vital signs, medical history, demographics, and clinical notes. Alerts are sent to providers via the mobile Beacon App, which features customizable user interfaces and encrypted chat for seamless care coordination (Hero AI, 2024).

Personalized Patient Dashboard

Hero AI also offers a Patient Facing Beacon App that provides patients with personalized dashboards generated from their real-time electronic health record data. This transparency empowers patients by keeping them informed about their care status, potentially reducing anxiety associated with waiting times (Hero AI, 2024).

Operational Efficiency and Safety Enhancements

By integrating these real-time analytics and AI-driven tools, Hero AI (2024) aims to improve ED operational efficiency, reduce patient wait times, and enhance safety. The platform’s adaptability allows for rapid customization to meet the unique needs of different hospitals, promoting widespread adoption and impact across various healthcare settings. These innovations demonstrate Hero AI’s commitment to transforming emergency department workflows through advanced technology, ultimately improving patient care and operational performance in healthcare facilities.

Ethical AI and Data Integrity

As AI adoption accelerated, so too did the scrutiny of its ethical implications. Canadian researchers emphasized the importance of high-quality, unbiased datasets to ensure equitable AI outputs. Canada has always been at the forefront of AI ethics scrutiny and planning (Nettel, 2023). New frameworks were developed to address issues such as algorithmic bias, patient data privacy, and the transparency of AI decision-making processes.

As AI adoption accelerates across industries, so too does the scrutiny of its ethical implications, prompting researchers and policymakers to address key challenges to ensure responsible development and deployment. In Canada, this scrutiny was particularly pronounced, with researchers and institutions emphasizing the need for high-quality, unbiased datasets as a cornerstone for equitable AI outputs. These datasets are seen as crucial in mitigating algorithmic bias, which can lead to systemic inequities if left unchecked (O’Reilly, 2024).

To address these challenges, Canadian researchers collaborated across sectors to develop comprehensive frameworks, guidelines and laws such as the Artificial Intelligence and Data Act (AIDA) (Gallagher, 2024). These frameworks were designed to tackle critical issues such as:

Algorithmic Bias

Researchers identified that biases in training datasets could disproportionately impact marginalized communities, leading to unfair outcomes in areas such as healthcare, employment, and law enforcement. Efforts were made to establish rigorous data auditing processes, diversify datasets, and implement fairness-aware machine learning techniques.

Patient Data Privacy

With AI being increasingly applied in healthcare, ensuring the privacy and security of sensitive patient data became a top priority. New protocols were developed to anonymize data, implement robust encryption methods, and ensure compliance with privacy regulations like Canada’s Personal Information Protection and Electronic Documents Act (PIPEDA).

Transparency and Explainability

As AI systems grow more complex, their decision-making processes became less transparent, raising concerns about accountability. Canadian researchers and policymakers advocated for AI models to be explainable, ensuring stakeholders could understand how decisions were made. This includes developing tools to visualize AI processes, adopting interpretable algorithms, and creating standardized reporting methods for AI systems.

These efforts underscore Canada’s commitment to leading in ethical AI development, setting an example by integrating values of fairness, privacy, and accountability into AI technologies. Through this proactive approach, Canada aims to balance innovation with the societal responsibility of minimizing harm and maximizing the benefits of AI adoption.

Telehealth: Bridging Gaps in Accessibility

Telehealth solutions gained unprecedented momentum in 2024, becoming an integral part of Canada’s healthcare delivery system. With advancements in video consultation platforms, remote diagnostic tools, and mobile health applications, patients in even the most remote areas could access high-quality care.

One major milestone was the introduction of AI-powered telemedicine platforms capable of preliminary diagnostics. These systems allowed patients to input symptoms and receive AI-guided recommendations, which were then reviewed by healthcare professionals. Additionally, telemonitoring devices for chronic conditions like diabetes and heart disease empowered patients to manage their health proactively, with their data seamlessly integrated into EHRs for clinician review.

Island Health’s “Hospital at Home” program, now expanded to several provinces, relies heavily on telehealth technology. Patients receive acute-level care, including virtual check-ins, remote vital sign monitoring, and medication delivery, all from the comfort of their homes. This approach not only enhances patient satisfaction but also reduces strain on overcrowded hospitals (Zeidenberg, 2024).

Island Health’s “Hospital at Home” program is an innovative healthcare initiative designed to provide acute-level hospital care to patients in their own homes. Originating in British Columbia, this model has expanded to several provinces across Canada due to its success in addressing both patient and systemic needs.

Key Features of the HaH Program

Island Health’s “Hospital at Home” program (HaH) offers several benefits that streamline the service and improve client care.

Virtual Check-Ins

Patients receive regular consultations with healthcare professionals via telehealth platforms. This includes video calls and phone check-ins to assess progress, answer questions, and adjust care plans.

Remote Vital Sign Monitoring

Advanced technology, such as wearable devices and remote monitoring tools, allows healthcare providers to track vital signs like heart rate, blood pressure, oxygen levels, and temperature in real-time. Alerts are set up to notify clinicians of any significant changes.

Medication Delivery and Administration

Medications, including intravenous infusions, when necessary, are delivered directly to patients’ homes. Trained healthcare workers may visit to administer complex treatments or train family members on their use.

Home Visits by Healthcare Teams

When required, nurses, physiotherapists, or other healthcare providers visit patients to perform procedures, collect samples, or provide physical therapy and wound care. “All patients in the HaH program receive a daily in-person visit from an RN – at minimum. Those requiring additional support receive more frequent visits” (Zeidenberg, 2024a, p. 12).

Care Coordination

Multidisciplinary teams collaborate remotely to tailor and adjust treatment plans. This includes doctors, nurses, pharmacists, and specialists working together to ensure seamless care.

The “Hospital at Home” program has numerous benefits. Patients experience enhanced satisfaction and comfort by recovering in their own homes, often with the support of family members. This approach also alleviates the strain on overcrowded hospitals by freeing up beds and resources for patients who need them most. Moreover, it is cost-effective, reducing expenses associated with inpatient care, and has been linked to improved outcomes, such as fewer hospital-acquired infections.

However, the program does face challenges, including ensuring reliable internet connectivity, selecting appropriate patients for at-home care, and maintaining 24/7 support for emergencies. Despite these challenges, the program has shown significant potential in transforming acute care delivery, reflecting a broader shift toward integrating technology and innovative models into healthcare systems to enhance both efficiency and patient-centered care.

Telehealth and Mental Health: A Winning Combination

In 2024, telehealth expanded its scope to address mental health challenges, a growing concern in post-pandemic Canada. Virtual mental health platforms provided counseling and therapy sessions, often supplemented by AI-powered chatbots that offered immediate support for individuals in crisis. This approach not only reduced stigma around seeking help but also cut down wait times for professional care.

Organizations like Kids Help Phone enhanced their reach using AI-driven chat systems that supported young Canadians struggling with mental health issues. These systems could detect the urgency of cases and escalate to human counselors as needed, ensuring timely interventions.

Organizations like Kids Help Phone have leveraged AI-driven chat systems to significantly enhance their ability to reach and support young people facing mental health challenges. These systems utilize natural language processing (NLP) and machine learning algorithms to engage with users in real-time, providing immediate responses to their concerns. AI can detect key indicators of distress, such as keywords or emotional tone, allowing the system to assess the urgency of the situation. If the AI identifies a high-risk or urgent case, it can promptly escalate the conversation to a human counselor who can provide further assistance.

This approach ensures that individuals in need receive timely support, especially during off-hours or in cases where human counselors might be unavailable. It also allows the service to scale, reaching more people without overburdening the limited number of counselors. The AI chat systems are designed to provide a safe, non-judgmental space for young people to express their emotions, seek advice, and access coping strategies.

Additionally, these systems often incorporate features that guide users through self-help resources, mental wellness exercises, or coping mechanisms, which can be particularly helpful in the early stages of distress. The integration of AI in such services helps organizations like Kids Help Phone better manage the high volume of inquiries while maintaining a compassionate and responsive approach to mental health support.

Digitization of Long-Term Care

Informatics has also made great in-roads in Canadian long-term care. In collaboration with PointClickCare, the Registered Nurses’ Association of Ontario (RNAO) launched digital tools to standardize care in long-term care facilities. By digitizing evidence-based assessment protocols, care providers reduced manual documentation, freeing up time to focus on direct patient care. This shift led to a notable improvement in the efficiency and quality of admissions, with some facilities reporting up to 60 minutes saved per resident (Zeidenberg, 2024b).

The Registered Nurses’ Association of Ontario (RNAO), in collaboration with PointClickCare, introduced a suite of digital tools aimed at standardizing care in long-term care facilities. This initiative sought to enhance care delivery by integrating evidence-based assessment protocols into a digital platform, enabling care providers to streamline processes and focus more on direct patient care. The digital tools replaced manual documentation with automated workflows, simplifying tasks such as initial assessments, care planning, and ongoing monitoring.

By digitizing these protocols, facilities saw significant reductions in the time spent on paperwork. The automated system ensured that assessments were completed consistently and accurately, reducing the likelihood of errors or omissions. This freed up valuable time for nurses and other care providers to engage more meaningfully with residents, address their needs, and improve overall care quality.

One of the most notable impacts was on the admissions process, which became significantly more efficient. Facilities reported saving up to 60 minutes per resident during admissions, which translated into smoother transitions for new residents and reduced administrative burden for staff. Moreover, the use of standardized, evidence-based protocols contributed to better care consistency across facilities, supporting improved health outcomes for residents.

The partnership between RNAO and PointClickCare exemplifies the potential of technology to transform long-term care by enhancing efficiency, accuracy, and resident-focused care. It also highlights the importance of collaboration between healthcare organizations and technology providers to create tools that address real-world challenges faced by care teams in long-term care settings.

Looking Ahead: The Future of Health Informatics in Canada

2024 demonstrated that health informatics is not just a tool but a cornerstone of modern healthcare. By embracing AI, telehealth, and digital solutions, Canada set a global example of how to innovate while prioritizing equity and ethics. Yet challenges remain—such as ensuring interoperability among disparate systems, training healthcare professionals in new technologies, and addressing the digital divide.

Canada’s health informatics breakthroughs in 2024 have set the stage for a future where technology and healthcare are inseparable. From empowering patients through telehealth to enhancing operational efficiency with AI, these innovations represent a new era of personalized, accessible, and equitable healthcare. The year 2024 will undoubtedly be remembered as a turning point in Canadian healthcare history.

As we move into 2025, ongoing collaboration among healthcare providers, technologists, policymakers, and patients will be crucial. Together, they can build a resilient, inclusive, and tech-enabled healthcare system that ensures better health for all Canadians.

References

BC Cancer Foundation. (2024). Innovative early lung cancer detection is saving lives. https://bccrc.ca/articles/innovative-early-lung-cancer-detection-saving-lives

Canadian Cancer Society. (2024). Advancing cancer diagnosis with AI-powered medical imaging tool. https://cancer.ca/en/about-us/stories/2024/advancing-cancer-diagnosis-with-ai-powered-medical-imaging-tool

Davis, S., & Greiner, R. (2024). Survival models and longitudinal medical events for hospital readmission forecasting. BMC Health Services Research, 24(1), 1–14. doi:10.1186/s12913-024-11771-w

Dy, A., Nguyen, N.-N. J., Meyer, J., Dawe, M., Shi, W., Androutsos, D., Fyles, A., Liu, F.-F., Done, S., & Khademi, A. (2024). AI improves accuracy, agreement and efficiency of pathologists for Ki67 assessments in breast cancer. Scientific Reports, 14(1), 1–12. doi:10.1038/s41598-024-51723-2

Gallagher, M. (2024, April 11). Canada’s Artificial Intelligence and Data Act (AIDA) 2024: A comprehensive guide. Cox & Palmer. https://coxandpalmerlaw.com/publication/aida-2024/

Hero AI. (2024). Your healthcare AI platform. https://www.heroai.ca/

Hewitt, K. (2024). ‘We’re improving patient safety’: How one CS grad is using AI to personalize health-care operations.’ Department of Computer Science, University of Toronto. https://web.cs.toronto.edu/news-events/news/devin-singh-hero-ai

Island Health Authority. (n.d.). About Hospital at Home. https://www.islandhealth.ca/our-services/hospital-home-services/hospital-home

Kid’s Help Phone. https://kidshelpphone.ca/

Nettel, P. F. (2023, May 1). Canada’s AI Policy: Leading the way in ethics, innovation, and talent. Oxford Insights. https://oxfordinsights.com/insights/spotlight-series-canada/

O’Reilly, K. (2024, June 18). 87% of healthcare informatics leaders are concerned about possible data bias in AI, voicing the need for policies on the ethical use of data and AI. Philips News. https://www.philips.com/a-w/about/news/archive/standard/news/articles/2024/87-percent-of-healthcare-informatics-leaders-are-concerned-about-possible-data-bias-in-ai-voicing-the-need-for-policies-on-the-ethical-use-of-data-and-ai.html

Samani, R., Dehghani, M. & ????????, F. (2024). Enhancing readmission prediction with deep learning: Extracting biomedical concepts from clinical texts. arXiv (Cornell University). https://doi.org/10.48550/arXiv.2403.09722

Yu, M., Harrison, M., & Bansback, N. (2024). Can prediction models for hospital readmission be improved by incorporating patient-reported outcome measures? A systematic review and narrative synthesis. Quality of Life Research: An International Journal of Quality of Life aspects of Treatment, Care and Rehabilitation, 33(7), 1767–1779. https://doi.org/10.1007/s11136-024-03638-8

Zeidenberg, N. (2024a, April). Island Health innovates by delivering quality care to patients at home. Canadian Healthcare Technology, 29(3), 12-13, 19.  https://issuu.com/jerryzeidenberg/docs/canadian_healthcare_technology_2024-03

Zeidenberg, N. (2024b, May). RNAO, PointClickCare digitize LTC resident assessments. Canadian Healthcare Technology, 29(3), 29(4), 1-2. https://issuu.com/jerryzeidenberg/docs/canadian_healthcare_technology_2024-04

Zheng, D., He, X., & Jing, J. (2023). Overview of artificial intelligence in breast cancer medical imaging. Journal of Clinical Medicine, 12(2), 419. doi:10.3390/jcm12020419