Directive Explanations for Monitoring the Risk of Diabetes Onset – ACM IUI 2023

Presented at ACM IUI 2023 in Sydney, Australia: https://iui.acm.org/2023/accepted_papers.html

About Me:

I am an Explainable AI Researcher from India working in KU Leuven, Belgium.

PROFESSIONAL SUMMARY
✫ Experienced Data Scientist and AI/ML Engineer with 7+ years of experience in Data Science, Machine Learning, IoT, and Software Development with 2 years of people management experience.
✫ Author of one of the top books on Explainable AI – “Applied Machine Learning Explainability Techniques” which is available on Amazon: https://amzn.to/3PqQPpv
✫ Seasoned trainer, subject matter expert and mentor in Data Science and Machine Learning with UpGrad and MUST Research
✫ Active community contributor with speaking and presentation experience at top conferences like ODSC, Indo-Data Week. GIDS and content creator at Towards Data Science, Medium, YouTube

MY DAY-JOB:
➣ I am currently working as an Explainable AI (XAI) Researcher at KU Leuven with the mission of bringing AI closer to end-users.

MY PASSION AND FORTE:
➣ I am passionate about building customer-centric AI products. I have led high-performing engineering teams, leading with innovation and conceptualizing forward-thinking highly scalable products and robust solutions.

EXPERIENCE SUMMARY:
➣ KU Leuven: 1+ year of experience in XAI Research in a highly focused scientific research environment.
➣ West Pharmaceutical Services: 3+ years of experience as the AI Lead for democratizing AI practice. I have contributed towards forming the AI Center of Excellence at West, leading and managing a global team of 10+ team members focused towards building industrial AI products.
➣ Microsoft: 2+ years of experience in Software Engineering and Microsoft Azure Cloud Platform Development.
➣ Intel: 1+ year of experience in research and development with emerging technologies related to IoT and ML for Smart Homes.

SPECIALIZED IN:
➣ Machine Learning and Deep Learning
➣ Computer Vision
➣ Time Series Analysis
➣ NLP
➣ Statistical Data Analysis
➣ Software Development

REACHABLE THROUGH:
➣ LinkedIn: https://www.linkedin.com/in/aditya-bhattacharya-b59155b6/
➣ Personal website: http://aditya-bhattacharya.net/
➣ TopMate: https://topmate.io/aditya_bhattacharya
➣ Medium: https://adib0073.medium.com/
➣ Twitter: https://twitter.com/adib0073

Welcome to my website! In this webpage, I will present a short summary of my talk at ACM IUI 2023. You can download the full paper from this link – https://arxiv.org/abs/2302.10671.

Paper Title: Directive Explanations for Monitoring the Risk of Diabetes Onset: Introducing Directive Data-Centric Explanations and Combinations to Support What-If Explorations

Abstract: Explainable artificial intelligence is increasingly used in machine learning (ML) based decision-making systems in healthcare. However, little research has compared the utility of different explanation methods in guiding healthcare experts for patient care. Moreover, it is unclear how useful, understandable, actionable and trustworthy these methods are for healthcare experts, as they often require technical ML knowledge. This paper presents an explanation dashboard that predicts the risk of diabetes onset and explains those predictions with data-centric, feature-importance, and example-based explanations. We designed an interactive dashboard to assist healthcare experts, such as nurses and physicians, in monitoring the risk of diabetes onset and recommending measures to minimize risk. We conducted a qualitative study with 11 healthcare experts and a mixed-methods study with 45 healthcare experts and 51 diabetic patients to compare the different explanation methods in our dashboard in terms of understandability, usefulness, actionability, and trust. Results indicate that our participants preferred our representation of data-centric explanations that provide local explanations with a global overview over other methods. Therefore, this paper highlights the importance of visually directive data-centric explanation method for assisting healthcare experts to gain actionable insights from patient health records. Furthermore, we share our design implications for tailoring the visual representation of different explanation methods for healthcare experts.

Access to the Slide Deck:

Are you interested in Explainable AI?

If you are interested in Explainable AI, then you must take a look at my book on Explainable AI, available on Amazon.