Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Explainable surgical procedures recommender system leveraging large language models
Information Systems, University of Haifa, Haifa, Israel.ORCID iD: 0000-0001-7955-1048
Sheba Medical Center, Tel HaShomer, Israel.ORCID iD: 0009-0000-7782-6343
Jönköping University, School of Engineering, JTH, Department of Computing. Department of Information Systems, University of Haifa, Haifa, Israel.ORCID iD: 0000-0002-7851-8147
2025 (English)In: ACM Transactions on Recommender Systems, E-ISSN 2770-6699, article id 3767326Article in journal (Refereed) Epub ahead of print
Abstract [en]

Significant advancements have recently been made in the fields of recommender systems and natural language processing, particularly with large language models (LLMs). In most cases, recommender systems have been used to suggest items and enhance personalization for users, while LLMs have been applied to textual tasks such as text completion, translation, and summarization. In this study, we demonstrate that integrating recommender system models with recent LLMs can effectively suggest appropriate surgical procedures for patients. We employ several LLMs to process clinical text in a morphologically rich language, serving three crucial roles: information representation, information enrichment, and explaining the surgical procedure suggestions made by the recommender system. Our method was evaluated using real-world clinical data, considering patients’ demographic attributes and health conditions. To assess the explainability of our method, we conducted an extensive experiment involving several clinicians. The results achieved by our method indicate that using recommender systems and LLMs can lead to high performance and improved explanations. Our study has the potential to enhance the personalization of healthcare and could be adopted by health services to assist healthcare professionals in recommending appropriate surgical procedures.

Place, publisher, year, edition, pages
ACM Digital Library, 2025. article id 3767326
Keywords [en]
Information systems, Expert systems, Applied computing, Health care information systems, Computing methodologies, Machine learning, Recommender Systems, Healthcare, Large Language Models, Explainability, Hebrew
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:hj:diva-70208DOI: 10.1145/3767326Local ID: ;intsam;70208OAI: oai:DiVA.org:hj-70208DiVA, id: diva2:2014916
Available from: 2025-11-19 Created: 2025-11-19 Last updated: 2025-11-19

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Authority records

Lazebnik, Teddy

Search in DiVA

By author/editor
Solomon, AdirGlebov, MaximLazebnik, Teddy
By organisation
JTH, Department of Computing
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 30 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf