Workshop: Health AI Systems Thinking for Equity

Dato: Tirsdag den 21. januar 2025
Tid: Kl. 09.00 – 17.00
Sted: IDA Mødecenter

Registration and participation fee:
Due to the high demand for this workshop, we have introduced an application process to ensure a balanced and diverse representation of professional backgrounds and interests.
Participation fee: 50 DKK (no-show: 500 DKK)

To apply for a ticket, please complete the participation application form via this Google Forms link. You will be notified of your application status within one week of submission. If your application is approved, you will receive a link to purchase your ticket at 50 DKK. Please note, a no-show fee of 500 DKK will apply to ensure commitment. We encourage you to apply as soon as possible, as seats will be allocated on a rolling basis, and we anticipate reaching capacity quickly.  Eligible applicants whose applications arrive after all seats have been filled will be placed on a waiting list and contacted if a spot becomes available.

Link til tilmelding via IDA

Workshop Programme: 

Artificial intelligence (AI) has the potential to transform healthcare worldwide. bearing promises of increased accuracy, efficiency, and cost-effectiveness, in areas as diverse as drug discovery, clinical diagnosis, and disease management.

Furthermore, AI has been promoted as a tool that could expand the reach of quality healthcare to traditionally underserved patients and regions. But even with appropriate representation of marginalized communities with high-quality data, the social patterning of the data generation process can still produce AI that is bound to preserve and even scale existing disparities in care with resulting inequities in patient outcomes.

Creating algorithms from the digital exhaust of flawed human systems by AI developers who are not cognizant of the backstory of the data, risks cementing inequities as permanent fixtures in healthcare delivery systems. This course will introduce students to a portfolio of methodologies that learn patterns from the data. More importantly, it will explore data issues that if not addressed will have profound consequences on downstream prediction, classification, and optimization tasks.

Learning Objectives / Key Takeaways 

Upon successful completion of this course, you should be able to:

• Work with data scientists, social scientists, and clinicians across the life cycle of health AI and apply systems thinking to the application of AI to healthcare
• Learn good code documentation for reproducibility of AI development
• Develop a critical understanding of how the dataset came about from collection to aggregation to standardization
• Perform exploratory data analysis with a special emphasis on data bias
• Understand the basic principles of different machine learning methodologies
• Interpret and communicate analysis results
• Think about potential downstream harm from algorithm implementation

Who should participate:
Students, scientists, and analysts engaged in development, deployment or assessment and analysis of AI in healthcare and open to cross-disciplinary collaboration.

Speakers:

Speakers

• Leo Anthony Celi Associate Professor at Harvard Medical School, and Clinical Research Director of the Laboratory of Computational Physiology at the MIT
• Martin Sillesen Clinical Research Lecturer in Surgery, Rigshospitalet. Brings clinical insights into health technology research, with a special interest in the applications of AI in surgical practices.
• Anna Schneider-Kamp Qualitative Health Researcher, Associate Professor, Department of Business and Management, University of Southern Denmark
  Specializes in qualitative health research, with a focus on the intersection of health, business, and management practices.
• Matilda Dorotic Associate Professor, Department of Marketing, BI Norwegian Business School, Norway. Expert in incentive structures and marketing strategies in healthcare, studying how market mechanisms influence patient and provider behavior.
• Ericka Johnson Professor, echnology and Social Change, Linköping University
  Focuses on the social impacts of technology, including ethical frameworks and social challenges associated with health AI.
• Mads Bundgaard Nørløv MSc BME student, Johns Hopkins Center for Bioengineering Innovation and Design & Founder/Chair, Copenhagen MedTech Innovator in bioengineering with expertise in medtech entrepreneurship, fostering cross-disciplinary collaborations in health technology.
• João Matos PhD Student, University of Oxford Researching applications of AI in healthcare with a focus on ethical considerations in patient data management.
• David Restrepo PhD Student, Applied Mathematics, CentraleSupélec, University Paris-Saclay. Specialist in mathematical modeling for healthcare, exploring new applications of AI in medical diagnostics.
• Chris Sauer MD, MPH, PhD, Physician, Universitätsmedizin Essen, and MIT Researcher Medical professional and researcher focused on integrating AI with medical practice to improve patient outcomes.
• Nikolaj Munch Andersen Senior Tech Advisor, Danish Ministry of Foreign Affairs (Udenrigsministeriet) Advisor on technology policy with a focus on AI regulations and international tech governance.

Program Committee:

• Henning Boje Andersen
  Professor Emeritus, Technical University of Denmark. Department of Technology, Management, and Economics / IDA Risk / DSKS Forskning.
• Martin Sillesen
  Clinical Research Lecturer in Surgery, Rigshospitalet.
• Jonathan Patscheider
  Vice President, Trust Stamp
• Lasse Hyldig Hansen
  Behavioural Adviser, Danish Competition and Consumer Authority & Research Assistant, Aarhus University

Agenda

Workshop teasers

Introduction to Machine Learning

This is a primer on machine learning concepts including but not limited to cross-validation, data leakage, benchmarks, performance metrics, and fairness evaluation. Publicly available high-resolution datasets (not registries) will be introduced: MIMIC (US), eICU-CRD (US), AmsterdamUMCdb (Netherlands), HiRID (Switzerland), SICdb (Austria).

Bias-athon

The Bias-athon is designed to address and mitigate biases in artificial intelligence (AI) systems. This workshop will leverage interdisciplinarity to identify, understand, and develop strategies to understand biases in clinical AI datasets. Participants will engage in hands-on sessions where they explore various types of biases, such as measurement bias, and variation in the degree of monitoring from social determinants of care, and their impact on AI performance.

Language Model Prompt-athon

A prompt-athon is focused on enhancing effectiveness and reducing the bias of large language models. This workshop is designed for clinicians who are already or who are thinking of using these tools for summarizing patient courses, drafting content for progress notes and letters to other providers and patients, and soliciting differential diagnoses, treatment recommendations, and prognostication. Participants will be introduced to various prompt engineering techniques that can leverage the power of this technology. Through collaborative exercises, attendees will experiment with different types of prompts, analyze the outputs, and refine their strategies to achieve better results. The event will also include discussions on the challenges of prompt design, such as avoiding ambiguity and ensuring context-appropriateness.

Policy Workshop

The Policy Workshop is organized to explore the regulatory and ethical frameworks surrounding the use of AI technologies. Sessions will cover a range of topics, including transparency and accountability, power structures, and the political economy that drives the impact of AI. Participants will engage in brainstorming and dialogue and propose solutions to complex policy issues. The goal is to engender a systems-thinking mindset among developers and users of AI to improve population health.

QUESTIONS THAT PARTICIPANTS MUST ANSWER IN ORDER TO COMPLETE SIGN-UP

1. Describe your current role and how it relates to the development, deployment, and/or evaluation and analysis of AI technologies in healthcare. Include any specific projects or study programmes and your involvement.
2. What do you hope to gain from participating in this workshop, and how do you anticipate applying the insights to your work or studies?

Organizers:
IDA Risk – IDA Engineering Society; MIT/Massachusets Institute of Technology; DSKS – Dansk Selskab for Kvalitet i Sundhedssektoren; Rigshospitalet/ Københavns Universitet; DTU Health Tech;  Copenhagen Medtech.   

Sponsor

The workshop is sponsored by DDSA – Danish Data Science Academy