Maayan Ben Sasson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Maayan Ben Sasson has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Aryeh Tiktinsky
Allen Institute for AI, Seattle, USA
1 shared publicationBen Eyal
Allen Institute for AI, Seattle, USA
1 shared publicationDan Bareket
Allen Institute for AI, Seattle, USA
1 shared publicationE. Ben-Arye
Faculty of Medicine, Technion- IsraelInstitute of Technology, Haifa, Israel; Integrative Oncology Program, Oncology Service, Lin Medical Center, ClalitHealth Services, Haifa, Israel
1 shared publicationE. Schiff
Internal B Medicine Department, Israel; Complementary Medicine Service, BnaiZion Medical Center, Haifa, Israel; Faculty of Medicine, Technion- IsraelInstitute of Technology, Haifa, Israel
1 shared publicationHillel Taub-Tabib
Allen Institute for AI, Seattle, USA
1 shared publication
Latest Publications
- Open Access
- 13 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-15
Identifying symptom etiologies using syntactic patterns and large language models
Differential diagnosis is a crucial aspect of medical practice, as it guides clinicians to accurate diagnoses and effective treatment plans. Traditional resources, such as medical books and services like UpToDate, are constrained by manual curation, potentially missing out on novel or less common findings. This paper introduces and analyzes two novel methods to mine etiologies from scientific literature. The first method employs a traditional Natural Language Processing (NLP) approach based on syntactic patterns. By using a novel application of human-guided pattern bootstrapping patterns are derived quickly, and symptom etiologies are extracted with significant coverage. The second method utilizes generative models, specifically GPT-4, coupled with a fact verification pipeline, marking a pioneering application of generative techniques in etiology extraction. Analyzing this second method shows that while it is highly precise, it offers lesser coverage compared to the syntactic approach. Importantly, combining both methodologies yields synergistic outcomes, enhancing the depth and reliability of etiology mining.
- 13 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-15
Open AccessIdentifying symptom etiologies using syntactic patterns and large language models
Differential diagnosis is a crucial aspect of medical practice, as it guides clinicians to accurate diagnoses and effective treatment plans. Traditional resources, such as medical books and services like UpToDate, are constrained by manual curation, potentially missing out on novel or less common findings. This paper introduces and analyzes two novel methods to mine etiologies from scientific literature. The first method employs a traditional Natural Language Processing (NLP) approach based on syntactic patterns. By using a novel application of human-guided pattern bootstrapping patterns are derived quickly, and symptom etiologies are extracted with significant coverage. The second method utilizes generative models, specifically GPT-4, coupled with a fact verification pipeline, marking a pioneering application of generative techniques in etiology extraction. Analyzing this second method shows that while it is highly precise, it offers lesser coverage compared to the syntactic approach. Importantly, combining both methodologies yields synergistic outcomes, enhancing the depth and reliability of etiology mining.
- 1 May 2020
- Published by Elsevier in Complementary Therapies in Medicine
- Vol. 50, 102345
Dietary and herbal supplements use among patients hospitalized in internal medicine departments
- 1 May 2020
- Published by Elsevier in Complementary Therapies in Medicine
- Vol. 50, 102345
Dietary and herbal supplements use among patients hospitalized in internal medicine departments