Protocol for: A Simple, Accessible, Literature-based Drug Repurposing Pipeline DOI
Maximin Lange, Meredith Martyn, Eoin Gogarty

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 19, 2024

Abstract We will develop a novel approach to drug repurposing, utilising Natural Language Processing (NLP) and Literature Based Discovery (LBD) techniques. This present simplified, accessible repurposing pipeline using Word2Vec embeddings trained on PubMed abstracts identify potential new medications be repurposed. this in the context of antipsychotics, but it could repeated for any available medication. The research is structured three stages: Identification candidate algorithm scientific literature. Empirical testing identified candidates large hospital dataset explore protective effects against disease onset. Validation findings second, independent assess generalizability. method addresses limitations current machine learning-based approaches, including lack external validation limited accessibility. By leveraging Word2Vec’s ability capture semantic relationships between words, study aims uncover hidden connections medical literature that may lead therapeutic discoveries. protocol emphasizes transparency reproducibility, utilizing publicly electronic health record (EHR) databases validation. allows tangible results even researchers with learning expertise, bridging gap biomedical information systems communities.

Language: Английский

Generative AI in Medicine and Healthcare: Moving Beyond the ‘Peak of Inflated Expectations’ DOI Creative Commons
Peng Zhang,

Jiayu Shi,

Maged N. Kamel Boulos

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(12), P. 462 - 462

Published: Dec. 9, 2024

The rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, personalized health monitoring. This paper reviews the advancements medicine-specific LLMs, integration Retrieval-Augmented Generation (RAG) prompt engineering, their applications improving diagnostic accuracy educational utility. Despite potential, these technologies present challenges, including bias, hallucinations, need for robust safety protocols. also discusses regulatory ethical considerations necessary integrating models into mainstream healthcare. By examining current studies developments, this aims to provide a comprehensive overview state LLMs medicine highlight future directions research application. study concludes that while hold immense safe effective practice requires rigorous testing, ongoing evaluation, continuous collaboration among stakeholders.

Language: Английский

Citations

3
Protocol for: A Simple, Accessible, Literature-based Drug Repurposing Pipeline DOI
Maximin Lange, Meredith Martyn, Eoin Gogarty

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: July 19, 2024

Abstract We will develop a novel approach to drug repurposing, utilising Natural Language Processing (NLP) and Literature Based Discovery (LBD) techniques. This present simplified, accessible repurposing pipeline using Word2Vec embeddings trained on PubMed abstracts identify potential new medications be repurposed. this in the context of antipsychotics, but it could repeated for any available medication. The research is structured three stages: Identification candidate algorithm scientific literature. Empirical testing identified candidates large hospital dataset explore protective effects against disease onset. Validation findings second, independent assess generalizability. method addresses limitations current machine learning-based approaches, including lack external validation limited accessibility. By leveraging Word2Vec’s ability capture semantic relationships between words, study aims uncover hidden connections medical literature that may lead therapeutic discoveries. protocol emphasizes transparency reproducibility, utilizing publicly electronic health record (EHR) databases validation. allows tangible results even researchers with learning expertise, bridging gap biomedical information systems communities.

Language: Английский

Citations

0