AI in Healthcare Program

Participants will explore the core technologies and terminology of Artificial Intelligence (AI) and its role in healthcare delivery. This week participants will learn the definition of AI, key AI technologies, essential terminology, and how AI impacts health outcomes. You will also learn about the importance of randomization in AI applications, as well as the reliability and validity of AI interventions. Additionally, the R.O.A.D. Management Framework will be introduced as a strategic tool to guide the effective integration of AI into healthcare systems, ensuring alignment with organizational goals and optimizing AI-driven outcomes.

Case Study: Claims automation and boosting hypertension classifier performance

This week, participants will be provided with an overview of six machine learning algorithms, highlighting their primary use cases and principles. Algorithms are defined as step-by-step problem-solving procedures and learners will understand their fundamental components, including how they function in various problem-solving scenarios. Participants will learn to assess machine learning models using key metrics and evaluate their effectiveness. Additionally, the module explores the differences between pseudo-innovation and real innovation in healthcare, emphasizing the importance of evidence-based evaluation to distinguish genuine advancements from mere trends.

This week, participants will explore the concept of the human baseline in AI, comparing it to risk-based approaches while considering manual processes and the effects of prospect theory and status quo bias. They will evaluate the role of predictive modeling, neural networks, and deep learning in healthcare, and examine how these techniques can be applied to address healthcare challenges. Participants will evaluate predictive techniques for hospital complications, analyze the effectiveness of these techniques in real-world applications, and explore data-driven approaches for assessing risk factors and outcomes.

Case Study: Correcting Optimism Bias in Organ Donation

In this week, participants will analyze AI's role in managing information overload in medical literature and explore strategies for effective data synthesis to support healthcare decision-making. They will examine the role of Large Language Models (LLMs) in healthcare, particularly their ability to automate administrative tasks and facilitate patient interactions, ultimately reducing clinician burnout by streamlining workflows. Participants will evaluate the limitations of LLMs, identifying areas where these models currently lack reliability and require improvements. They will discuss the challenges to the widespread adoption of LLMs in healthcare and the crucial need for human oversight in their applications.

In this week, participants will gain a comprehensive understanding of how robotic-assisted surgery enhances precision and outcomes in surgical procedures, contributing to improved recovery times and reduced complications. They will explore the benefits and risks of robotic surgery, while also examining the current technologies driving advancements in this field. Learners will delve into future trends and innovations, highlighting the ongoing evolution of robotic surgery. Additionally, the concept of robotic process automation (RPA) will be introduced, with a focus on its applications in healthcare. Participants will explore how automation streamlines repetitive tasks across industries, improving efficiency, reducing errors, and enhancing productivity in clinical settings. The benefits of integrating automation into healthcare operations will also be discussed, demonstrating its potential to transform healthcare delivery.

Case Study: Claims automation and boosting hypertension classifier performance

In this week participants will analyze co-morbidity data to identify key risk factors and assess how social and cultural influences impact health interactions and medication adherence. They will explore graph analytics and epidemiological models, such as Markov and S-E-I-R, to understand disease spread and its impact on public health. The week will also cover the role of AI in enhancing health outcomes, especially in the context of pandemics, where AI tools can be used to improve response strategies. Participants will gain insights into how AI-driven approaches can identify risk factors, inform public health interventions, and support disease spread analysis to better manage health crises.

Case Study: COVID-19 with Bayesian data augmentation

In this week, participants will analyze AI's role in precision medicine, focusing on how it has the potential to enhance health screening processes and personalized treatment protocols to improve patient outcomes. They will explore predictive models in healthcare, learning how these models aid in early disease identification, leading to more effective preventive healthcare strategies. By assessing how AI can contribute to disease burden reduction and optimizes treatment paths, participants will understand how AI can drive improvements in both individual patient care and broader healthcare practices.

Case Study: Predicting auto-immune diseases

This week participants will analyze the ethical, regulatory, and privacy challenges of AI in healthcare, focusing on strategies to promote fairness and ensure equitable access while safeguarding patient data. The discussion will cover ethical considerations, regulatory frameworks for AI technologies, and privacy concerns related to AI solutions. Learners will explore methods for protecting patient data, processes for exporting Electronic Health Records (EHRs), and best practices for data cleaning and management. Additionally, they will examine strategies for integrating AI models into EHR systems, ensuring compliance with industry standards and ethical guidelines.

Case Study: Series of cases in bias, randomization, human baseline, race unaware

This week participants will examine formal and informal leadership styles in healthcare, assessing their impact on team dynamics, decision-making, and AI implementation. They will analyze how social network-based change management influences AI adoption and explore the role of interpersonal connections in driving organizational change. The session also covers strategies for scaling AI pilot projects across health systems, addressing challenges in hospital-wide AI implementation, and identifying best practices for sustainable AI adoption in healthcare.

Case Study: Informal leadership in healthcare and social networks