FastHPOCR: pragmatic, fast, and accurate concept recognition using the human phenotype ontology.

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_hpo_cr. 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.

Use of privacy-preserving record linkage to examine the dispensing of pharmaceutical benefits scheme medicines to pregnant women in Western Australia.

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.

An evaluation of GPT models for phenotype concept recognition.

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.

Surfacing undiagnosed disease: consideration, counting and coding.

The diagnostic odyssey for people living with rare diseases (PLWRD) is often prolonged for myriad reasons including an initial failure to consider rare disease and challenges to systemically and systematically identifying and tracking undiagnosed diseases across the diagnostic journey. This often results in isolation, uncertainty, a delay to targeted treatments and increase in risk of complications with significant consequences for patient and family wellbeing. This article aims to highlight key time points to consider a rare disease diagnosis along with elements to consider in the potential operational classification for undiagnosed rare diseases during the diagnostic odyssey. We discuss the need to create a coding framework that traverses all stages of the diagnostic odyssey for PLWRD along with the potential benefits this will have to PLWRD and the wider community.

Further evidence for distinct traits associated with RBM10 missense variants.

A case of a missense RBM10 variant in an adult with mild to moderate intellectual disability.

Autosomal recessive congenital ichthyosis due to homozygous variants in NIPAL4 with a dramatic response to ustekinumab.

Autosomal recessive congenital ichthyosis is a genetically and phenotypically heterogenous group of scaling skin disorders. We describe a patient with ARCI caused by homozygous variants in NIPAL4, in whom the dermatologic phenotype and an associated arthropathy, markedly improved with ustekinumab.

Enabling Global Clinical Collaborations on Identifiable Patient Data: The Minerva Initiative.

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.

Defining and expanding the phenotype of QARS-associated developmental epileptic encephalopathy.

OBJECTIVE: The study is aimed at widening the clinical and genetic spectrum and at assessing genotype-phenotype associations in QARS encephalopathy. METHODS: Through diagnostic gene panel screening in an epilepsy cohort, and recruiting through GeneMatcher and our international network, we collected 10 patients with biallelic QARS variants. In addition, we collected data on 12 patients described in the literature to further delineate the associated phenotype in a total cohort of 22 patients. Computer modeling was used to assess changes on protein folding. RESULTS: Biallelic pathogenic variants in QARS cause a triad of progressive microcephaly, moderate to severe developmental delay, and early-onset epilepsy. Microcephaly was present at birth in 65%, and in all patients at follow-up. Moderate (14%) or severe (73%) developmental delay was characteristic, with no achievement of sitting (85%), walking (86%), or talking (90%). Additional features included irritability (91%), hypertonia/spasticity (75%), hypotonia (83%), stereotypic movements (75%), and short stature (56%). Seventy-nine percent had pharmacoresistant epilepsy with mainly neonatal onset. Characteristic cranial MRI findings include early-onset progressive atrophy of cerebral cortex (89%) and cerebellum (61%), enlargement of ventricles (95%), and age-dependent delayed myelination (88%). A small subset of patients displayed a less severe phenotype. CONCLUSIONS: These data revealed first genotype-phenotype associations and may serve for improved interpretation of new QARS variants and well-founded genetic counseling.

Silver Russel syndrome in an aboriginal patient from Australia.

Silver-Russell syndrome (SRS OMIM 180860) is a rare, albeit well-recognized disorder characterized by severe intrauterine and postnatal growth retardation. It remains a clinical diagnosis with a molecular cause identifiable in approximately 60%-70% of patients. We report a 4-year-old Australian Aboriginal girl who was born at 32 weeks gestation with features strongly suggestive of SRS, after extensive investigation she was referred to our undiagnosed disease program (UDP). Genomic sequencing was performed which identified a heterozygous splice site variant in IGF2 which is predicted to be pathogenic by in-silico studies, paternal allelic origin, de novo status, and RNA studies on fibroblasts. We compare clinical findings with reported patients to add to the knowledge base on IGF2 variants and to promote the engagement of other Australian Aboriginal families in genomic medicine.