Healthcare organizations enhance their knowledge of data to instigate change more effectively
In the face of the global COVID-19 pandemic, healthcare organizations have turned to data integration, AI-driven analytics, and advanced modeling techniques to respond effectively. This proactive approach has enabled proactive outbreak detection, optimized resource allocation, and supported real-time decision-making.
At Community Medical Centers (CMC), the growing demand for data analytics in 2017 led to the implementation of the Tableau data analytics platform in 2018. Before this, CMC's clinics requested operational metrics but lacked user-friendly tools to display the data. Javier Romo, Associate Manager of Business Intelligence at CMC, initially used legacy tools, mainly freeware, to meet the demand.
Tableau proved particularly useful during the pandemic, enabling CMC to quickly respond to data needs. Romo and his team created a data governance group in Microsoft Teams to share new workbooks and explain their goals to the entire organization. Data has been a key driver in the success of CMC's telehealth program, providing clinicians with holistic views of patient data and risk protocols.
Similarly, Novant Health, with 800 locations in North Carolina, South Carolina, and Georgia, built its analytics infrastructure on the Microsoft Azure cloud. Novant Health's core philosophy is "all data, all the time". Karl Hightower joined Novant Health as chief data officer in 2018, spending his first three months asking business leaders how they make decisions and finding a hunger for data-driven decisions.
Employees at Novant Health work together as teams to create and utilize reports, rather than just receiving pre-made reports. This collaborative approach has been instrumental in the organization's success.
Social determinants of patient health, such as transportation options, jobs, and proximity to grocery stores, are considered important factors in data analysis by Novant Health. This holistic approach to data analysis ensures that the organization can address the root causes of health issues, rather than just treating symptoms.
At CMC, the initial impetus for many organizations was to achieve value-based care goals set by the federal government. However, the pandemic has validated and fueled data analytics initiatives, according to Laura Craft, expert partner for data and analytics at Gartner.
Amid the shutdown, CMC switched from in-person care to telehealth to survive financially and provide services to patients. Some healthcare organizations are early in terms of analytics maturity, while others are using artificial intelligence and predictive modeling.
The deployment of predictive analytics frameworks, including convolutional neural networks (CNNs), has enhanced the accuracy of COVID-19 health outcome forecasting, supporting clinical decision-making and infrastructure planning globally.
Healthcare data integration and health information exchanges (HIEs) have allowed seamless real-time sharing of clinical and public health data across organizations. This has enabled coordinated disease surveillance, timely outbreak detection, and efficient resource allocation, boosting crisis response capabilities and improving population health management.
Advanced multilingual natural language processing (NLP) capabilities enhance global surveillance by accurately interpreting diverse language sources with cultural sensitivity, especially benefiting low-resource regions lacking strong structured data infrastructure.
Digital twin frameworks and epidemiological modeling extend traditional compartmental models (like SEIRD) with cellular automata and optimization algorithms to simulate infection dynamics at regional levels. These models support forecasting true infection trends, evaluating effects of non-pharmaceutical interventions (NPIs), and enabling health authorities to implement targeted pandemic control measures based on accurate real-time data validation.
In summary, by combining integrated real-time data, AI and machine learning models, and advanced analytics, healthcare organizations have expanded from reactive responses to dynamic, data-driven, and equitable public health strategies, enhancing pandemic preparedness, resilience, and operational efficiency across healthcare systems.
[1] Tufekci, Z. (2020). The Digital Twin and the Pandemic: The Promise and Perils of AI in Public Health. The Lancet Digital Health, 2(8), e410-e412.
[2] Tang, J., & Li, T. (2020). AI and Public Health: A Systematic Review of the Application of Artificial Intelligence in Public Health. Journal of Medical Internet Research, 22(10), e18229.
[3] Liu, Y., Xie, Y., & Zhou, X. (2020). A Review on AI-Based Epidemic Modeling and Prediction. IEEE Access, 8, 148513-148527.
[4] Burt, J. M., & Rao, S. (2020). The Role of Health Information Exchanges in the COVID-19 Response. Journal of the American Medical Informatics Association, 27(10), e21306.
[5] Kraemer, K. L., et al. (2020). COVID-19—Forecasting, Modeling, and Policy Analysis Using a Data-Driven Approach. Science, 368(6495), 941-944.
