Dataset Information

The New Version of the ANDDigest Tool with Improved AI-Based Short Names Recognition.

ABSTRACT: The body of scientific literature continues to grow annually. Over 1.5 million abstracts of biomedical publications were added to the PubMed database in 2021. Therefore, developing cognitive systems that provide a specialized search for information in scientific publications based on subject area ontology and modern artificial intelligence methods is urgently needed. We previously developed a web-based information retrieval system, ANDDigest, designed to search and analyze information in the PubMed database using a customized domain ontology. This paper presents an improved ANDDigest version that uses fine-tuned PubMedBERT classifiers to enhance the quality of short name recognition for molecular-genetics entities in PubMed abstracts on eight biological object types: cell components, diseases, side effects, genes, proteins, pathways, drugs, and metabolites. This approach increased average short name recognition accuracy by 13%.

SUBMITTER: Ivanisenko TV

PROVIDER: S-EPMC9738852 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The New Version of the ANDDigest Tool with Improved AI-Based Short Names Recognition.

Ivanisenko Timofey V TV Demenkov Pavel S PS Kolchanov Nikolay A NA Ivanisenko Vladimir A VA

International journal of molecular sciences 20221129 23

The body of scientific literature continues to grow annually. Over 1.5 million abstracts of biomedical publications were added to the PubMed database in 2021. Therefore, developing cognitive systems that provide a specialized search for information in scientific publications based on subject area ontology and modern artificial intelligence methods is urgently needed. We previously developed a web-based information retrieval system, ANDDigest, designed to search and analyze information in the Pub ...[more]

PMID: 36499269

Similar Datasets

Project description:BackgroundPatient education is the first step in implementing a cardiac rehabilitation (CR) program and a powerful tool for promoting behavioral changes in cardiac patients. In China, the clinical workload is so heavy that a short and reliable tool for assessing disease-related knowledge is needed for targeted patient education.ObjectiveThe aim of this study was to translate, adapt and validate the Chinese version of the Coronary Artery Disease Education Questionnaire - Short Version (CADE-Q SV).MethodsThe CADE-Q SV was translated to simplified Chinese and culturally adapted to the Chinese context. The translated version was reviewed by a committee of seven experts in cardiovascular disease, and the content validity of the questionnaire was established. The psychometric properties of the questionnaire were analyzed considering the responses of 240 CR patients. The Kuder-Richardson-20 (KR-20) coefficient and Cronbach's alpha were used to assess internal consistency. The intraclass correlation coefficient (ICC) was used to assess test-retest reliability. The criterion-related validity was evaluated by determining whether there were differences in the total scores of patients with different educational levels. Confirmatory factor analysis (CFA) was used to assess the factor structure.ResultsThree items from the original version were adapted to reflect Chinese culture. The content validity index was 0.94. The KR-20 score was 0.856. All ICC values were > 0.70. The knowledge scores of patients with different educational levels were significantly different, indicating that the criterion-related validity of the Chinese CADE-Q-SV was acceptable. CFA validated the five-factor structure of the Chinese CADE-Q-SV.ConclusionThe Chinese CADE-Q SV questionnaire has good reliability and validity. This short, efficient tool can be completed quickly, assess disease-related knowledge in cardiovascular patients and serve as a reference for individualized patient education in China. It can also be used to evaluate the effectiveness of CR-related patient education interventions.

Dataset Information

The New Version of the ANDDigest Tool with Improved AI-Based Short Names Recognition.

Publications

The New Version of the ANDDigest Tool with Improved AI-Based Short Names Recognition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets