Objectives There is a need in clinical genomics for systems that assist in clinical diagnosis, analysis of genomic information and periodic reanalysis of results, and can use information from the electronic health record to do so. Such systems should be built using the concepts of human-centred design, fit within clinical workflows and provide solutions to priority problems. Methods We adapted a commercially available diagnostic decision support system (DDSS) to use extracted findings from a patient record and combine them with genomic variant information in the DDSS interface. Three representative patient cases were created in a simulated clinical environment for user testing. A semistructured interview guide was created to illuminate factors relevant to human factors in CDS design and organisational implementation. Results Six individuals completed the user testing process. Tester responses were positive and noted good fit with real-world clinical genetics workflow. Technical issues related to interface, interaction and design were minor and fixable. Testers suggested solving issues related to terminology and usability through training and infobuttons. Time savings was estimated at 30%–50% and additional uses such as in-house clinical variant analysis were suggested for increase fit with workflow and to further address priority problems. Conclusion This study provides preliminary evidence for usability, workflow fit, acceptability and implementation potential of a modified DDSS that includes machine-assisted chart review. Continued development and testing using principles from human-centred design and implementation science are necessary to improve technical functionality and acceptability for multiple stakeholders and organisational implementation potential to improve the genomic diagnosis process.
To evaluate the efficacy of ChatGPT 4 (GPT-4) in delivering genetic information about BRCA1, HFE, and MLH1, building on previous findings with ChatGPT 3.5 (GPT-3.5). To focus on assessing the utility, limitations, and ethical implications of using ChatGPT in medical settings.
Introduction Adolescent idiopathic scoliosis (AIS) is a common musculoskeletal disorder with strong evidence for a genetic contribution. CNVs play an important role in congenital scoliosis, but their role in idiopathic scoliosis has been largely unexplored. Methods Exome sequence data from 1197 AIS cases and 1664 in-house controls was analysed using coverage data to identify rare CNVs. CNV calls were filtered to include only highly confident CNVs with >10 average reads per region and mean log-ratio of coverage consistent with single-copy duplication or deletion. The frequency of 55 common recurrent CNVs was determined and correlated with clinical characteristics. Results Distal chromosome 16p11.2 microduplications containing the gene SH2B1 were found in 0.7% of AIS cases (8/1197). We replicated this finding in two additional AIS cohorts (8/1097 and 2/433), resulting in 0.7% (18/2727) of all AIS cases harbouring a chromosome 16p11.2 microduplication, compared with 0.06% of local controls (1/1664) and 0.04% of published controls (8/19584) (p=2.28×10 −11 , OR=16.15). Furthermore, examination of electronic health records of 92 455 patients from the Geisinger health system showed scoliosis in 30% (20/66) patients with chromosome 16p11.2 microduplications containing SH2B1 compared with 7.6% (10/132) of controls (p=5.6×10 −4 , OR=3.9). Conclusions Recurrent distal chromosome 16p11.2 duplications explain nearly 1% of AIS. Distal chromosome 16p11.2 duplications may contribute to scoliosis pathogenesis by directly impairing growth or by altering expression of nearby genes, such as TBX6 . Individuals with distal chromosome 16p11.2 microduplications should be screened for scoliosis to facilitate early treatment.
Abstract Introduction Currently, one of the commonly used methods for disseminating electronic health record (EHR)-based phenotype algorithms is providing a narrative description of the algorithm logic, often accompanied by flowcharts. A challenge with this mode of dissemination is the potential for under-specification in the algorithm definition, which leads to ambiguity and vagueness. Methods This study examines incidents of under-specification that occurred during the implementation of 34 narrative phenotyping algorithms in the electronic Medical Record and Genomics (eMERGE) network. We reviewed the online communication history between algorithm developers and implementers within the Phenotype Knowledge Base (PheKB) platform, where questions could be raised and answered regarding the intended implementation of a phenotype algorithm. Results We developed a taxonomy of under-specification categories via an iterative review process between two groups of annotators. Under-specifications that lead to ambiguity and vagueness were consistently found across narrative phenotype algorithms developed by all involved eMERGE sites. Discussion & Conclusion Our findings highlight that under-specification is an impediment to the accuracy and efficiency of the implementation of current narrative phenotyping algorithms, and we propose approaches for mitigating these issues and improved methods for disseminating EHR phenotyping algorithms.
Abstract Epilepsy, defined by the occurrence of two or more unprovoked seizures or one unprovoked seizure with a propensity for others, affects 0.64% of the population and can lead to significant morbidity and mortality. A majority of unexplained epilepsy (seizures not attributed to an acquired etiology, such as trauma or infection) is estimated to have an underlying genetic etiology. Despite rapid progress in understanding of the genetic underpinnings of the epilepsies, there are no recent evidence‐based guidelines for genetic testing and counseling for this population. This practice guideline provides evidence‐based recommendations for approaching genetic testing in the epilepsies using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) Evidence to Decision framework. We used evidence from a recent systematic evidence review and meta‐analysis of diagnostic yield of genetic tests in patients with epilepsy. We also compiled data from other sources, including recently submitted conference abstracts and peer‐reviewed journal articles. We identified and prioritized outcomes of genetic testing as critical, important or not important and based our recommendations on outcomes deemed critical and important. We considered the desirable and undesirable effects, value and acceptability to relevant stakeholders, impact on health equity, cost‐effectiveness, certainty of evidence, and feasibility of the interventions in individuals with epilepsy. Taken together, we generated two clinical recommendations: (1) Genetic testing is strongly recommended for all individuals with unexplained epilepsy, without limitation of age, with exome/genome sequencing and/or a multi‐gene panel (>25 genes) as first‐tier testing followed by chromosomal microarray, with exome/genome sequencing conditionally recommended over multi‐gene panel. (2) It is strongly recommended that genetic tests be selected, ordered, and interpreted by a qualified healthcare provider in the setting of appropriate pre‐test and post‐test genetic counseling. Incorporation of genetic counselors into neurology practices and/or referral to genetics specialists are both useful models for supporting providers without genetics expertise to implement these recommendations.
Abstract Objective Given the importance AI in genomics and its potential impact on human health, the American Medical Informatics Association—Genomics and Translational Biomedical Informatics (GenTBI) Workgroup developed this assessment of factors that can further enable the clinical application of AI in this space. Process A list of relevant factors was developed through GenTBI workgroup discussions in multiple in-person and online meetings, along with review of pertinent publications. This list was then summarized and reviewed to achieve consensus among the group members. Conclusions Substantial informatics research and development are needed to fully realize the clinical potential of such technologies. The development of larger datasets is crucial to emulating the success AI is achieving in other domains. It is important that AI methods do not exacerbate existing socio-economic, racial, and ethnic disparities. Genomic data standards are critical to effectively scale such technologies across institutions. With so much uncertainty, complexity and novelty in genomics and medicine, and with an evolving regulatory environment, the current focus should be on using these technologies in an interface with clinicians that emphasizes the value each brings to clinical decision-making.
