Online Masterclass in Equitable AI in Health Care - Wednesday, 17 January 2024

[Quantitative Life Sciences]

  The Africa-Europe Cluster of Research Excellence: Addressing Global 
and African Challenges Through Methods of Artificial Intelligence, Data 
Science, and Theoretical and Computational Thinking
presents a Masterclass in

Equitable AI in Health Care to be held on Wednesday, 17 January 2024
South Africa: 12h00-15h30 (GMT+2) | Sweden: 11h00-14h30 (GMT+1)

A half-day discussion of machine learning in health care for 
researchers, PhD students, equitable AI enthusiasts, data scientists and 
medical practitioners.

This masterclass describes and evaluates a novel active learning 
approach for incrementally improving the accuracy of a Natural Language 
Processing (NLP), while optimising for gender-equitable outcomes in 
healthcare systems.
The approach employs an iterative cyclic model, incorporating data 
annotation using NLP, human auditing to improve the annotation accuracy 
especially for data with demographic segmentation, testing on new data 
(with intentional bias favoring underperforming demographics), and a 
loopback system for retraining the model and applying it on new data.

We describe experimental integration of the audit tool with distinct NLP 
tasks in two separate contexts:

i. annotation of medical symptoms collected in Hausa and English 
languages based on responses to a
research questionnaire about health access in Northern Nigeria;
ii. message intent classification in English and Swahili languages based 
on spontaneous user messages to a health guide chatbot in both Nigeria 
and Kenya.

Our findings indicate that this gender-aware audit workflow is language 
agnostic and capable of mitigating demographic inequity while improving 
overall system accuracy.


  For more information, visit core-ai.sun.ac.za

-- 
Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-2240623
www.ictp.it/research/qls.aspx
e-mail: qls at ictp.it