Would you trust an AI doctor? Building reliable medical predictions with kernel dropout uncertainty
Would you trust an AI doctor? Building reliable medical predictions with kernel dropout uncertainty
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. 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.
Language models, Medical Text, Reliability
326-337
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
50ba09b3-b2f4-4e1a-881f-ad26fbb0a1a5
Hacid, Hakim
797389ed-bfaa-426d-977c-73647812ee22
Zhang, Dell
ae078ed1-bc72-431f-a6c9-eaaf9c73e946
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
27 November 2024
Azam, Ubaid
243c228b-8e17-4bba-9b3f-c788c0f9e858
Razzak, Imran
85c57ead-8a63-4aec-bba3-559a43dd5888
Vishwakarma, Shelly
50ba09b3-b2f4-4e1a-881f-ad26fbb0a1a5
Hacid, Hakim
797389ed-bfaa-426d-977c-73647812ee22
Zhang, Dell
ae078ed1-bc72-431f-a6c9-eaaf9c73e946
Jameel, Shoaib
ae3c588e-4a59-43d9-af41-ea30d7caaf96
Azam, Ubaid, Razzak, Imran, Vishwakarma, Shelly, Hacid, Hakim, Zhang, Dell and Jameel, Shoaib
(2024)
Would you trust an AI doctor? Building reliable medical predictions with kernel dropout uncertainty.
Barhamgi, Mahmoud, Wang, Hua and Wang, Xin
(eds.)
In Web Information Systems Engineering – WISE 2024: 25th International Conference, Proceedings, Part IV.
vol. 15439 LNCS,
Springer Singapore.
.
(doi:10.1007/978-981-96-0573-6_24).
Record type:
Conference or Workshop Item
(Paper)
Abstract
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. 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
Wise_Camera_ready_submission
- Accepted Manuscript
Restricted to Repository staff only
Request a copy
More information
Published date: 27 November 2024
Venue - Dates:
25th International Conference on Web Information Systems Engineering, WISE 2024, , Doha, Qatar, 2024-12-02 - 2024-12-05
Keywords:
Language models, Medical Text, Reliability
Identifiers
Local EPrints ID: 503256
URI: http://eprints.soton.ac.uk/id/eprint/503256
ISSN: 0302-9743
PURE UUID: 3d0ba7af-34cd-445a-9267-81a9bfd2cf1b
Catalogue record
Date deposited: 25 Jul 2025 16:38
Last modified: 28 Jul 2025 17:01
Export record
Altmetrics
Contributors
Author:
Ubaid Azam
Author:
Imran Razzak
Author:
Shelly Vishwakarma
Author:
Hakim Hacid
Author:
Dell Zhang
Author:
Shoaib Jameel
Editor:
Mahmoud Barhamgi
Editor:
Hua Wang
Editor:
Xin Wang
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