-
Nov 20, 2024 | 
nature.com | Fangyi Chen |Wendy Chung |Casey TA |Kai Wang |Chunhua Weng
AbstractPatients with rare diseases often experience prolonged diagnostic delays. Ordering appropriate genetic tests is crucial yet challenging, especially for general pediatricians without genetic expertise.
-
Sep 8, 2024 | 
nature.com | Qiao Jin |Yiliang Zhou |Song Wang |Jordan G. Nestor |Ali Soroush |Zhiyong Lu | +1 more
AbstractLarge language models (LLMs) hold great promise in summarizing medical evidence. Most recent studies focus on the application of proprietary LLMs. Using proprietary LLMs introduces multiple risk factors, including a lack of transparency and vendor dependency. While open-source LLMs allow better transparency and customization, their performance falls short compared to the proprietary ones.
-
Sep 8, 2024 | 00296-9&sz=64)
cell.com | Kai Wang |Chunhua Weng |Cong Liu
Keywordslarge language modelrare disease diagnosisgene prioritizationprecision medicineartificial intelligencegenerative pre-trained transformersphenotypesIntroductionPhenotype-driven gene prioritization is a process that involves identifying and ranking candidate diagnostic genes by examining an individual’s phenotypes.
-
Jun 13, 2024 | 
biorxiv.org | Andy Wang |Cong Liu |Jingye Yang |Chunhua Weng
AbstractObjective: We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO). Methods: We developed an in-house template-based script to generate two corpora for fine-tuning. The first (NAME) contains standardized HPO names, sourced from the HPO vocabularies, along with their corresponding identifiers.
-
Apr 14, 2024 | 
biorxiv.org | Andy Wang |Cong Liu |Jingye Yang |Chunhua Weng
AbstractObjective: We aim to develop a novel method for rare disease concept normalization by fine-tuning Llama 2, an open-source large language model (LLM), using a domain-specific corpus sourced from the Human Phenotype Ontology (HPO). Methods: We developed an in-house template-based script to generate two corpora for fine-tuning. The first (NAME) contains standardized HPO names, sourced from the HPO vocabularies, along with their corresponding identifiers.
-
Dec 29, 2023 | 
biorxiv.org | Andy Wang |Cong Liu |Jingye Yang |Chunhua Weng
AbstractObjective: We aim to develop a solution for rare disease concept normalization based on fine-tuning LLaMA 2, an open-source large language model (LLM), using a domain-specific corpus. Methods and Materials: We fine-tuned four LLaMA2 models, each comprising seven billion parameters, using sentences incorporating clinical concepts from the HPO and OMIM vocabularies.
-
Dec 13, 2023 | 
nature.com | Atlas Khan |Ning Shang |Jordan G. Nestor |Chunhua Weng |Ali Gharavi
AbstractChronic kidney disease (CKD) is determined by an interplay of monogenic, polygenic, and environmental risks. Autosomal dominant polycystic kidney disease (ADPKD) and COL4A-associated nephropathy (COL4A-AN) represent the most common forms of monogenic kidney diseases. These disorders have incomplete penetrance and variable expressivity, and we hypothesize that polygenic factors explain some of this variability.
-
Aug 24, 2023 | 
nature.com | Zhaoyi Sun |Jordan G. Nestor |Ali Soroush |Pierre Elias |Justin F. Rousseau |Chunhua Weng | +1 more
AbstractRecent advances in large language models (LLMs) have demonstrated remarkable successes in zero- and few-shot performance on various downstream tasks, paving the way for applications in high-stakes domains. In this study, we systematically examine the capabilities and limitations of LLMs, specifically GPT-3.5 and ChatGPT, in performing zero-shot medical evidence summarization across six clinical domains.
-
Feb 6, 2023 | 
nature.com | Lili Liu |Atlas Khan |Elena Sanchez-Rodriguez |Junying Zhang |Halima Moncrieffe |Leah C. Kottyan | +14 more
Correction to: Nature Communications https://doi.org/10.1038/s41467-022-34456-6, published online 11 November 2022The original version of this Article contained two errors in table 1. The correct version of the 13th row of the first column states “Chinese (East Asian)” instead of the incorrect “Chinese (European)”. The correct version of the 14th row of the first column states “Japanese (East Asian)” instead of the incorrect “Japanese (European)”.
