Sign in Subscribe
Artificial intelligence

AI-Powered Healthcare Access Prediction Shows Promise in Underserved Communities

Strategic Insights

— 1 min read

A new study has demonstrated the effectiveness of using artificial intelligence (AI) to predict healthcare access and outcomes in underserved communities. Researchers from the Department of Computer Science and Engineering developed a deep learning model that leverages bias-attenuating approaches to provide more accurate and fair predictions. The study, funded by Manipal University Jaipur, integrated fairness-aware learning techniques, data augmentation strategies, and hyperparameter optimization to achieve high accuracy while minimizing disparities.

Key Takeaways:

  • The AI model was able to significantly reduce prediction bias, often achieving high accuracy for various demographics.
  • The proposed method achieved better fairness and interpretability than conventional models.
  • The study offers critical insights into the potential of AI-enabled health equity solutions and their implications for policy interventions and clinical decision making.
  • The model maintained consistently high performance across varying levels of healthcare access, with an AUC ranging from 0.94 to 0.99.
  • The research was conducted by Akash Saxena and Saurabh Sharma from the Department of Computer Science and Engineering, Compucom Institute of Technology and Management Jaipur.
  • Additional authors on the research include Punit Kumar Johari, Ankur Pandey, and Sunil Kumar.
  • The study's findings highlight the importance of using AI to address health disparities and improve healthcare access for underserved communities.

Statistics:

  • AUC range: 0.94 to 0.99, indicating reduced bias compared to conventional models.
  • Performance across varying levels of healthcare access: consistently high performance maintained.
  • Number of authors: 6 (Akash Saxena, Saurabh Sharma, Punit Kumar Johari, Ankur Pandey, Sunil Kumar, and the Department of Computer Science and Engineering).

Sources:

  • A fair and interpretable deep learning approach for healthcare access prediction in underserved communities. Discover Artificial Intelligence. 2025, 5(1):1-22.
  • VerticalNews. "New study results on artificial intelligence have been published." Department of Computer Science and Engineering, 2025.
  • NewsRx. "Research Results from Department of Computer Science and Engineering Update Understanding of Artificial Intelligence." Robotics & Machine Learning, September 1, 2025, p 663.

Read more