Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial panels vary widely in size and overlap. We developed an autonomous AI agent integrating Reasoning and Acting (ReAct) with Retrieval-Augmented Generation (RAG) to classify 10,211 Human Phenotype Ontology terms. It uses American College of Medical Genetics (ACMG)-endorsed severity guidelines and American College of Obstetricians and Gynecologists (ACOG) quality-of-life criteria to retrieve PubMed literature, generate interpretable reasoning chains, and independently verify claims. At the phenotype level, using expert-curated cohorts, the agent achieved 93.55% accuracy (MCC 0.9237) with 82.6% to 91.4% of claims supported by direct evidence or valid inferences. Gene-level severity was aggregated across 8,738 pairs, identifying 3,283 autosomal recessive pairs with severe or profound presentations. External validation showed 95.2% concordance with Mackenzie's Mission gene list. This system enables standardized panel design by providing reliable, automated classification supported by direct evidence.
Tohid Ghasemnejad, A. Argha, M. Grosser et al.· 0 citations
AIM
To evaluate genetic testing practices (exome sequencing, commercial panel, and in-house genetic panels) from a large tertiary hospital for determining gaps, and to identify clinical associations with pathogenic genetic variants.
METHOD
This retrospective cohort study included patients (age < 18 years) from a neurology department for whom genetic testing was requested for neurological disorders, epilepsy, and movement disorders (2020-2023). Logistic regression was used to identify clinical features predictive of positive results. The clinical benefits of genetic testing were studied.
RESULTS
Three hundred and ninety patients underwent genetic testing by exome sequencing (n = 125), commercial panel (n = 143), in-house epilepsy (n = 78), and movement disorder (n = 44) gene panels. Exome sequencing had the highest pathogenic yield (n = 49, 39%), followed by epilepsy (n = 22, 28%), movement disorder (n = 11, 25%), and commercial (n = 22, 15%) panels. Variants of uncertain significance were highest in commercial (64%) and epilepsy (34%) panels. Among the exome sequencing cohort, the predominant clinical features were developmental delay (89%), intellectual disability (51%), and epilepsy (35%). Pathogenic variants in the exome sequencing cohort were more likely in patients with severe developmental delay (33%, p = 0.03) and hypotonia (39%, p = 0.05). There was significant utility of genetic testing in informing clinical decision making (49% of pathogenic variants in exome sequencing cohort).
INTEPRETATION
Exome sequencing outperforms gene panels in confirming genetic diagnoses in paediatric neurological disorders, and highlights the need for building local diagnostic genetic-testing resources.
Wafa Bani Uraba, Byoung Chan Lee, S. Mohammad et al.· Developmental Medicine & Chi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
