Impact of Clinical Features on Disease Diagnosis Using Knowledge Graph Embedding and Machine Learning: A Detailed Analysis DOI
Shivani Dhiman, Anjali Thukral, Punam Bedi

и другие.

Communications in computer and information science, Год журнала: 2024, Номер unknown, С. 340 - 352

Опубликована: Янв. 1, 2024

Язык: Английский

Developing an agriculture ontology for extracting relationships from texts using Natural Language Processing to enhance semantic understanding DOI
Saurabh Bhattacharya, Manju Pandey

International Journal of Information Technology, Год журнала: 2024, Номер unknown

Опубликована: Март 29, 2024

Язык: Английский

Процитировано

2

A systematic review of Automatic Term Extraction: What happened in 2022? DOI
Giorgio Maria Di Nunzio, Stefano Marchesin, Gianmaria Silvello

и другие.

Digital Scholarship in the Humanities, Год журнала: 2023, Номер 38(Supplement_1), С. i41 - i47

Опубликована: Июнь 1, 2023

Abstract Automatic Term Extraction (ATE) systems have been studied for many decades as, among other things, one of the most important tools tasks such as information retrieval, sentiment analysis, named entity recognition, and others. The interest in this topic has even increased recent years given support improvement new neural approaches. In article, we present a follow-up on discussions about pipeline that allows extracting key terms from medical reports, presented at MDTT 2022, analyze very last papers ATE systematic review fashion. We analyzed journal conference published 2022 (and partially 2023) cluster them into subtopics according to focus better presentation.

Язык: Английский

Процитировано

5

RDKG-115: Assisting drug repurposing and discovery for rare diseases by trimodal knowledge graph embedding DOI Creative Commons
Chaoyu Zhu, Xiaoqiong Xia, Nan Li

и другие.

Computers in Biology and Medicine, Год журнала: 2023, Номер 164, С. 107262 - 107262

Опубликована: Июль 17, 2023

Rare diseases (RDs) may affect individuals in small numbers, but they have a significant impact on global scale. Accurate diagnosis of RDs is challenging, and there severe lack drugs available for treatment. Pharmaceutical companies shown preference drug repurposing from existing developed other due to the high investment, risk, long cycle involved RD development. Compared traditional approaches, knowledge graph embedding (KGE) based methods are more efficient convenient, as treat link prediction task. KGE models allow enrichment by incorporating multimodal information various sources. In this study, we constructed RDKG-115, rare disease involving 115 RDs, composed 35,643 entities, 25 relations, 5,539,839 refined triplets, 372,384 high-quality literature 4 biomedical datasets: DRKG, Pathway Commons, PharmKG, PMapp. Subsequently, trimodal model containing structure, category, description embeddings using reverse-hyperplane projection. We utilized infer 4199 reliable new inferred triplets RDKG-115. Finally, calculated potential molecules each taking multiple sclerosis case study. This study provides paradigm large-scale screening discovery which will speed up development process ultimately benefit patients with RDs. The source code data at https://github.com/ZhuChaoY/RDKG-115.

Язык: Английский

Процитировано

5

Knowledge reduction by combining interval Type-2 Fuzzy similarity measures and interval Type-2 Fuzzy formal lattice DOI
Sahar Cherif, Nesrine Baklouti, Adel M. Alimi

и другие.

International Journal of Information Technology, Год журнала: 2024, Номер 16(6), С. 3723 - 3728

Опубликована: Май 18, 2024

Язык: Английский

Процитировано

1

Constructing a subject-based ontology through the utilization of a semantic knowledge graph DOI
Chien D.C. Ta, Thien Khai Tran

International Journal of Information Technology, Год журнала: 2023, Номер 16(2), С. 1063 - 1071

Опубликована: Окт. 31, 2023

Язык: Английский

Процитировано

3

Biomedical Named Entity Recognition from Malaria Literature using BioBERT DOI

N. Devika,

V. S. Anoop,

Jose Thekkiniath

и другие.

Опубликована: Авг. 17, 2023

The unprecedented growth of unstructured text data in the healthcare domain makes it difficult to find and extract relevant information manually. Biomedical named entity recognition deals with process automatically identifying entities clinical significance, such as symptoms, treatment, names drugs, organisms, from documents electronic health records radiology reports. This is first but essential step for building many text-understanding applications conversational agents retrieval. Pre-trained language or linguistic models have recently gained popularity natural processing due their inherent ability manage contexts better. proposed approach fine-tunes pre-trained BioBERT model, which one current state-of-the-art biomedical models, on a large set Malaria entities. work implements compares different machine learning algorithms feature extraction techniques establish usefulness approach. method found be outperforming our chosen baselines shows better precision f-measure extensive performance comparison experiments.

Язык: Английский

Процитировано

1

Impact of Clinical Features on Disease Diagnosis Using Knowledge Graph Embedding and Machine Learning: A Detailed Analysis DOI
Shivani Dhiman, Anjali Thukral, Punam Bedi

и другие.

Communications in computer and information science, Год журнала: 2024, Номер unknown, С. 340 - 352

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0