Research project Patient and Public AI-assisted Interventions
With better descriptions of a patient’s state and history, more efficient recommendations can be provided. We explore how AI tools can be put to practical use in healthcare. We focus on complex and multimodal data and use cases such as COVID-19 public health interventions or patient phenotyping for adverse drug events, sepsis, or cancer.
The integration of Artificial Intelligence (AI) in healthcare has brought about transformative advancements, revolutionizing the landscape of patient care and public health interventions. By harnessing the power of AI to analyze multimodal patient data and identify patterns, healthcare providers and public health authorities can enhance the precision and efficiency of interventions.
This will lead to improved patient outcomes and more effective responses to public health challenges. As technology continues to evolve, the interaction between AI and healthcare promises even greater steps in understanding, preventing, and managing health-related issues on a global scale. For example, electronic phenotyping is crucial for identifying fine-grained patient clusters, and utilizing multimodal information can effectively create meaningful patient profiles essential in population and public health. In the same context of public health interventions, exemplified by crises like the COVID-19 pandemic, AI models can be employed to find a delicate balance between optimizing intervention effectiveness and considering economic and societal well-being.
In essence, the integration of AI into healthcare signifies a technological leap and a paradigm shift towards a more comprehensive and data-informed healthcare model. From refining diagnostics to empowering clinicians and enhancing public health strategies, AI plays a pivotal role in shaping a future where healthcare is both individualized and strategically aligned to address the diverse health challenges communities face on a broader scale.
This is Maria Bampa’s PhD project. Main supervisor is Panagiotis Papapetrou, co-supervisors are Ioanna Miliou and Jaakko Holmén.
The full title of this research project is “Patient and Public AI-assisted Interventions: The use of multimodal data in Machine Learning to improve healthcare”.
Project description
Over the past decade, industries have experienced a swift transition towards digitalization, and healthcare is no exception. The increasing complexity of data management and handling, driven by data volume, variety, velocity, and veracity, necessitates advanced analytics for uncovering meaningful insights.
Healthcare data are derived from various sources and are described by distinctive characteristics beyond sheer size, influencing the facilitation and complexity of extracting actionable insights regarding an observable phenomenon. Typically, these datasets encompass varied, multimodal, temporal, incomplete, and imprecise complex observations for analysis. The challenge lies in addressing this heterogeneous and intricate data landscape to derive insights for enhanced healthcare outcomes.
In this project, we aim to understand how health observational data can best describe the patient’s state and history. The objective is to create rich and comprehensive representations that reflect the diverse temporal and contextual aspects of multisource and/or multimodal health data. Building on the comprehensive data representations, we aim to identify and define patient phenotypes that carry meaningful clinical significance, contribute to more effective approaches at a population level, and inform effective public health interventions. Additionally, we aim to provide meaningful sequences of decisions that will act as interventions at the public health level using various data sources and modalities in the context of COVID-19.
Project members
Project managers
Maria Bampa
Research assistant
Panagiotis Papapetrou
Professor, deputy head of department
Members
Ioanna Miliou
Senior lecturer
Jaakko Hollmén
Senior lecturer
