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.

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]

The clinical utility of computational phenotyping for both genetic and rare diseases is increasingly appreciated; however, its true potential is yet to be fully realized. Alongside the growing clinical and research availability of sequencing technologies, precise deep and scalable phenotyping is required to serve unmet need in genetic and rare diseases. To improve the lives of individuals affected with rare diseases through deep phenotyping, global big data interrogation is necessary to aid our understanding of disease biology, assist diagnosis, and develop targeted treatment strategies. This includes the application of cutting-edge machine learning methods to image data. As with most digital tools employed in health care, there are ethical and data governance challenges associated with using identifiable personal image data. There are also risks with failing to deliver on the patient benefits of these new technologies, the biggest of which is posed by data siloing. The Minerva Initiative has been designed to enable the public good of deep phenotyping while mitigating these ethical risks. Its open structure, enabling collaboration and data sharing between individuals, clinicians, researchers and private enterprise, is key for delivering precision public health. [ABSTRACT FROM AUTHOR]