Acta Scientific Medical Sciences (ASMS)(ISSN: 2582-0931)

Mini Review Volume 5 Issue 10

Explainable AI in Diabetes Prediction System

Dr. Jagreet Kaur1, Suryakant2 and Kuldeep Kaur3*

1Chief AI Officer at (XenonStack Private Limited), Founder and CEO at (Xenon DigiLabs Private Limited), AI and Analytics Department, Xenonstack, Punjab, India E-mail: jagreet@akira.ai
2ModelOps Specialist, AI and Analytics Department, Xenonstack, Punjab, India
3AI Ethics Researcher, AI and Analytics Department, Xenonstack, Punjab, India

*Corresponding Author: Kuldeep Kaur, AI Ethics Researcher, AI and Analytics Department, Xenonstack, Punjab, India.

Received: August 25, 2021; Published: September 22, 2021

Abstract

  Use of AI in healthcare improves the industry services. Discovering patterns from data using ML improves the decision making process. It allows the industry specialist to make data-driven and fact-based decisions. The use of ML models in Healthcare is continuously increasing but it proliferates the concerns of stakeholders due to complexity and black box functioning of ML models.

  Therefore Explainable AI approaches come into existence to make the ML model transparent and trustworthy. In this document a case study is represented in which the ML model is used to detect diabetes and for transparency Explainable AI approaches are defined to understand the AI system based on the concerns and queries [1] that would be raised by stakeholders. There are several approaches, libraries and packages that can be used to implement Explainable AI such as LIME [2], SHAP [3] etc. It allows the industry practitioner to use the right tools and approaches for making their AI system trustworthy and transparent.

Keywords: Diabetes; Healthcare; AI System

References

  1. Vaishak Belle., et al. “Principles and Practice of Explainable Machine Learning”. arXiv:2009.11698v1. 2020-09-18.
  2. Scott Lundberg., et al. “LIME”.
  3. Marco Tulio Correia Ribeiro., et al. “SHAP”.
  4. Ankur Teredesai., et al. “Explainable Models for Healthcare AI”. KenSci., Inc. (2018).
  5. Christoph Molnar. “Partial Dependence Plot”. 2021-08-22.
  6. Christoph Molnar. “Individual Conditional Expectation”. 2021-08-22.

Citation

Citation: Dr. Jagreet Kaur., et al. “Explainable AI in Diabetes Prediction System”.Acta Scientific Medical Sciences 5.10 (2021): 131-136.

Copyright

Copyright: © 2021 Dr. Jagreet Kaur., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.




Metrics

Acceptance rate30%
Acceptance to publication20-30 days
Impact Factor1.403

Indexed In





Contact US