From uncertainty to trust: kernel dropout for AI-powered medical predictions
From uncertainty to trust: kernel dropout for AI-powered medical predictions
AI-driven medical predictions with trustworthy confidence are essential for ensuring the responsible use of AI in healthcare applications. The growing capabilities of AI raise questions about their trustworthiness in healthcare, particularly due to opaque decision-making and limited data availability. This paper proposes a novel approach to address these challenges, introducing a Bayesian Monte Carlo Dropout model with kernel modelling. Our model is designed to enhance reliability on small medical datasets, a crucial barrier to the wider adoption of AI in healthcare. This model leverages existing language models for improved effectiveness and seamlessly integrates with current workflows. Extensive evaluations of public medical datasets showcase our model's superior performance across diverse tasks. We demonstrate significant improvements in reliability, even with limited data, offering a promising step towards building trust in AI-driven medical predictions and unlocking its potential to improve patient care.
cs.LG
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
c98f51e0-a07e-4b21-becd-75d7249643ea
Hacid, Hakim
797389ed-bfaa-426d-977c-73647812ee22
Zhang, Dell
df7b0ed5-137a-4832-b03f-75cd92c8e83c
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
16 April 2024
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
c98f51e0-a07e-4b21-becd-75d7249643ea
Hacid, Hakim
797389ed-bfaa-426d-977c-73647812ee22
Zhang, Dell
df7b0ed5-137a-4832-b03f-75cd92c8e83c
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
[Unknown type: UNSPECIFIED]
Abstract
AI-driven medical predictions with trustworthy confidence are essential for ensuring the responsible use of AI in healthcare applications. The growing capabilities of AI raise questions about their trustworthiness in healthcare, particularly due to opaque decision-making and limited data availability. This paper proposes a novel approach to address these challenges, introducing a Bayesian Monte Carlo Dropout model with kernel modelling. Our model is designed to enhance reliability on small medical datasets, a crucial barrier to the wider adoption of AI in healthcare. This model leverages existing language models for improved effectiveness and seamlessly integrates with current workflows. Extensive evaluations of public medical datasets showcase our model's superior performance across diverse tasks. We demonstrate significant improvements in reliability, even with limited data, offering a promising step towards building trust in AI-driven medical predictions and unlocking its potential to improve patient care.
Text
2404.10483v2
- Author's Original
Available under License Other.
More information
Published date: 16 April 2024
Keywords:
cs.LG
Identifiers
Local EPrints ID: 503219
URI: http://eprints.soton.ac.uk/id/eprint/503219
PURE UUID: f2f07abb-e8dd-445c-a3fa-8c8f8410664e
Catalogue record
Date deposited: 24 Jul 2025 16:38
Last modified: 25 Jul 2025 02:06
Export record
Altmetrics
Contributors
Author:
Ubaid Azam
Author:
Imran Razzak
Author:
Shelly Vishwakarma
Author:
Hakim Hacid
Author:
Dell Zhang
Author:
Shoaib Jameel
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics