Search

OBJECTIVE: Clinical deep phenotyping and phenotype annotation play a critical role in both the diagnosis of patients with rare disorders as well as in building computationally-tractable knowledge in the rare disorders field. These processes rely on using ontology concepts, often from the Human Phenotype Ontology, in conjunction with a phenotype concept recognition task (supported usually by machine learning methods) to curate patient profiles or existing scientific literature. With the significant shift in the use of large language models (LLMs) for most NLP tasks, we examine the performance of the latest Generative Pre-trained Transformer (GPT) models underpinning ChatGPT as a foundation for the tasks of clinical phenotyping and phenotype annotation. MATERIALS AND METHODS: The experimental setup of the study included seven prompts of various levels of specificity, two GPT models (gpt-3.5-turbo and gpt-4.0) and two established gold standard corpora for phenotype recognition, one consisting of publication abstracts and the other clinical observations. RESULTS: The best run, using in-context learning, achieved 0.58 document-level F1 score on publication abstracts and 0.75 document-level F1 score on clinical observations, as well as a mention-level F1 score of 0.7, which surpasses the current best in class tool. Without in-context learning, however, performance is significantly below the existing approaches. CONCLUSION: Our experiments show that gpt-4.0 surpasses the state of the art performance if the task is constrained to a subset of the target ontology where there is prior knowledge of the terms that are expected to be matched. While the results are promising, the non-deterministic nature of the outcomes, the high cost and the lack of concordance between different runs using the same prompt and input make the use of these LLMs challenging for this particular task.

The Human Phenotype Ontology (HPO) is a widely used resource that comprehensively organizes and defines the phenotypic features of human disease, enabling computational inference and supporting genomic and phenotypic analyses through semantic similarity and machine learning algorithms. The HPO has widespread applications in clinical diagnostics and translational research, including genomic diagnostics, gene-disease discovery, and cohort analytics. In recent years, groups around the world have developed translations of the HPO from English to other languages, and the HPO browser has been internationalized, allowing users to view HPO term labels and in many cases synonyms and definitions in ten languages in addition to English. Since our last report, a total of 2239 new HPO terms and 49235 new HPO annotations were developed, many in collaboration with external groups in the fields of psychiatry, arthrogryposis, immunology and cardiology. The Medical Action Ontology (MAxO) is a new effort to model treatments and other measures taken for clinical management. Finally, the HPO consortium is contributing to efforts to integrate the HPO and the GA4GH Phenopacket Schema into electronic health records (EHRs) with the goal of more standardized and computable integration of rare disease data in EHRs.

Improving health and social equity for persons living with a rare disease (PLWRD) is increasingly recognized as a global policy priority. However, there is currently no international alignment on how to define and describe rare diseases. A global reference is needed to establish a mutual understanding to inform a wide range of stakeholders for actions. A multi-stakeholder, global panel of rare disease experts, came together and developed an Operational Description of Rare Diseases. This reference describes which diseases are considered rare, how many persons are affected and why the rare disease population demands specific attention. The operational description of rare diseases is framed in two parts: a core definition of rare diseases, complemented by a descriptive framework of rare diseases. The core definition includes parameters that permit the identification of which diseases are considered rare, and how many persons are affected. The descriptive framework elaborates on the impact and burden of rare diseases on patients, their caregivers and families, healthcare systems, and society overall. The Operational Description of Rare Diseases establishes a common point of reference for decision-makers across the world who strive to understand and address the unmet needs of persons living with a rare disease. Adoption of this reference is essential to improving the visibility of rare conditions in health systems across the world. Greater recognition of the burden of rare diseases will motivate new actions and policies to address the unmet needs of the rare disease community. [ABSTRACT FROM AUTHOR]

Motivation Human Phenotype Ontology (HPO)-based phenotype concept recognition (CR) underpins a faster and more effective mechanism to create patient phenotype profiles or to document novel phenotype-centred knowledge statements. While the increasing adoption of large language models (LLMs) for natural language understanding has led to several LLM-based solutions, we argue that their intrinsic resource-intensive nature is not suitable for realistic management of the phenotype CR lifecycle. Consequently, we propose to go back to the basics and adopt a dictionary-based approach that enables both an immediate refresh of the ontological concepts as well as efficient re-analysis of past data. Results We developed a dictionary-based approach using a pre-built large collection of clusters of morphologically equivalent tokens—to address lexical variability and a more effective CR step by reducing the entity boundary detection strictly to candidates consisting of tokens belonging to ontology concepts. Our method achieves state-of-the-art results (0.76 F1 on the GSC+ corpus) and a processing efficiency of 10 000 publication abstracts in 5 s. Availability and implementation FastHPOCR is available as a Python package installable via pip. The source code is available at https://github.com/tudorgroza/fast%5fhpo%5fcr. A Java implementation of FastHPOCR will be made available as part of the Fenominal Java library available at https://github.com/monarch-initiative/fenominal. The up-to-date GCS-2024 corpus is available at https://github.com/tudorgroza/code-for-papers/tree/main/gsc-2024. [ABSTRACT FROM AUTHOR]

Purpose: Medications are commonly used during pregnancy to manage pre‐existing conditions and conditions that arise during pregnancy. However, not all medications are safe to use in pregnancy. This study utilized privacy‐preserving record linkage (PPRL) to examine medications dispensed under the national Pharmaceutical Benefits Scheme (PBS) to pregnant women in Western Australia (WA) overall and by medication safety category. Methods: In this retrospective, cross‐sectional, population‐based study, state perinatal records (Midwives Notification Scheme) were linked with national PBS dispensing data using PPRL. Live and stillborn neonates born between 2012 and 2019 in WA were included. The proportion of pregnancies during which the mother was dispensed a PBS medication was calculated, overall and by medication safety category. Factors associated with PBS medication dispensing were examined using logistic regression. Results: PPRL linkage identified matching records for 97.4% of women with perinatal records. A total of 271 739 pregnancies were identified, with 158 585 (58.4%) pregnancies involving the dispensing of at least one PBS medication. Category A medications (those considered safe in pregnancy) were the most commonly dispensed (n = 119 126, 43.8%) followed by B3 (n = 51 135, 18.8%) and B1 (n = 42 388, 15.6%) medication (those with unknown safety). Over the study period, the dispensing of PBS medications in pregnancy increased (OR: 1.06, 95%CI: 1.06, 1.07). The strongest predictor of medication dispensing in pregnancy was pre‐pregnancy dispensing (OR: 3.61, 95%CI: 3.54, 3.68). Other factors associated with medication use in pregnancy were smoking, older maternal age, obesity, and prior pregnancies. Conclusion: Privacy preserving record linkage provides a way to link cross‐jurisdictional data while preserving patient confidentiality and data security. The dispensing of PBS medication in pregnancy was common and increased over time, with approximately 60% of women dispensed at least one medication during pregnancy. [ABSTRACT FROM AUTHOR]

Rare disease (RD) is a term used to describe numerous, heterogeneous diseases that are geographically disparate. Approximately 400 million people worldwide live with an RD equating to roughly 1 in 10 people, with 71.9% of RDs having a genetic origin. RDs present a distinctive set of challenges to people living with rare diseases (PLWRDs), their families, healthcare professionals (HCPs), healthcare system, and societies at large. The possibility of inheriting a genetic disease has a substantial social and psychological impact on affected families. In addition to other concerns, PLWRDs and their families may feel stigmatized, experience guilt, feel blamed, and stress about passing the disease to future generations. Stigma can affect all stages of the journey of PLWRDs and their families, from pre-diagnosis to treatment access, care and support, and compliance. It adversely impacts the quality of life of RD patients. To better explore the impact of stigma associated with genetic testing for RDs, we conducted a literature search on PubMed and Embase databases to identify articles published on stigma and RDs from January 2013 to February 2023. There is a dearth of literature investigating the dynamics of stigma and RD genetic testing. The authors observed that the research into the implications of stigma for patient outcomes in low- and middleincome countries (LMICs) and potential interventions is limited. Herein, the authors present a review of published literature on stigma with a focus on RD genetic testing, the associated challenges, and possible ways to address these. [ABSTRACT FROM AUTHOR]

Rare genetic diseases affect 5–8% of the population but are often undiagnosed or misdiagnosed. Electronic health records (EHR) contain large amounts of data, which provide opportunities for analysing and mining. Data mining, in the form of cluster analysis and visualisation, was performed on a database containing deidentified health records of 1.28 million patients across 3 major hospitals in Singapore, in a bid to improve the diagnostic process for patients who are living with an undiagnosed rare disease, specifically focusing on Fabry Disease and Familial Hypercholesterolaemia (FH). On a baseline of 4 patients, we identified 2 additional patients with potential diagnosis of Fabry disease, suggesting a potential 50% increase in diagnosis. Similarly, we identified > 12,000 individuals who fulfil the clinical and laboratory criteria for FH but had not been diagnosed previously. This proof-of-concept study showed that it is possible to perform mining on EHR data albeit with some challenges and limitations. [ABSTRACT FROM AUTHOR]

This document is a correction notice for an article titled "Analysis and visualisation of electronic health records data to identify undiagnosed patients with rare genetic diseases." The original version of the article contained an error in the title and abstract, which have now been corrected. The article discusses the use of data analysis on a database of deidentified health records to improve the diagnostic process for patients with undiagnosed rare diseases, specifically focusing on Fabry Disease and Familial Hypercholesterolaemia. The article is licensed under a Creative Commons Attribution 4.0 International License. [Extracted from the article]

A growing number of genes have been identified in individuals with cerebral palsy (CP); however, many of these studies have poor compliance with the cerebral palsy clinical description. This systematic review aimed to assess the quality of the cerebral palsy clinical description/phenotype in cerebral palsy genetic studies published between 2010 and 2024 and report clinically relevant genes based on the quality of the cerebral palsy phenotype. An expert panel developed 6 criteria to review the reported cerebral palsy phenotype/description for each included study. Clinically relevant genes were extracted from each study and stratified into 2 tiers based on the quality. Eighteen studies were included. There was high confidence in the reported cerebral palsy description/phenotype from 8 studies. Of the initial 373 clinically relevant genes, 85 were tier II genes. Individual cerebral palsy motor disorder and phenotype data were absent for 349 of these individuals, limiting further analysis. The tier I gene list was composed of 6 genes: ATL1, COL4A1, GNAO1, KIF1A, SPAST, and TUBA1A. Bilateral spasticity was the most common motor disorder reported in individuals with variants in all 6 genes, and most individuals had accompanying conditions. Prioritizing the accurate reporting of motor and nonmotor phenotypes is crucial for future cerebral palsy genetic studies to further understand the underlying neurobiology. [ABSTRACT FROM AUTHOR]