End-to-End Development of an AI Web Application for Rare Disease Healthcare
Location
Hager-Lubbers Exhibition Hall
Description
PURPOSE: Develop a web app with an interactive dashboard to aid diagnosing rare diseases with complex phenotypes. Utilize generative AI models trained on genetic data to identify patterns of altered gene expression linked to affected organs, cell types, and biological contexts. Offer clinicians insights and visualizations to improve diagnosis and prognosis. SUBJECTS: Focus on patients with rare diseases, particularly those with complex phenotypes. Analyze genetic data, including single-cell RNA-seq data from patient blood samples, to uncover underlying genetic disorder. METHODS AND MATERIALS: Utilize generative AI models trained on human and mouse genetic data to interpret patients' genetic information. Process single-cell RNA-seq data to identify patterns of altered gene expression associated with rare diseases. Integrate interactive dashboard for visualization and statistical comparison of results. ANALYSES: Process genetic data, identify patterns of altered gene expression, and statistically compare results across samples to pinpoint affected organs, cell types, and biological contexts linked to rare disease phenotypes. RESULTS: Present findings through accessible graphs and visualizations via the dashboard interface. Enable clinicians to easily interpret results, identify target areas, and gain insights into underlying genetic factors contributing to rare diseases. CONCLUSIONS: Offer clinicians a powerful tool to enhance diagnostic capabilities for rare diseases. Leverage generative AI models and genetic data analysis to make more accurate diagnoses and improve prognosis for patients with rare diseases.
End-to-End Development of an AI Web Application for Rare Disease Healthcare
Hager-Lubbers Exhibition Hall
PURPOSE: Develop a web app with an interactive dashboard to aid diagnosing rare diseases with complex phenotypes. Utilize generative AI models trained on genetic data to identify patterns of altered gene expression linked to affected organs, cell types, and biological contexts. Offer clinicians insights and visualizations to improve diagnosis and prognosis. SUBJECTS: Focus on patients with rare diseases, particularly those with complex phenotypes. Analyze genetic data, including single-cell RNA-seq data from patient blood samples, to uncover underlying genetic disorder. METHODS AND MATERIALS: Utilize generative AI models trained on human and mouse genetic data to interpret patients' genetic information. Process single-cell RNA-seq data to identify patterns of altered gene expression associated with rare diseases. Integrate interactive dashboard for visualization and statistical comparison of results. ANALYSES: Process genetic data, identify patterns of altered gene expression, and statistically compare results across samples to pinpoint affected organs, cell types, and biological contexts linked to rare disease phenotypes. RESULTS: Present findings through accessible graphs and visualizations via the dashboard interface. Enable clinicians to easily interpret results, identify target areas, and gain insights into underlying genetic factors contributing to rare diseases. CONCLUSIONS: Offer clinicians a powerful tool to enhance diagnostic capabilities for rare diseases. Leverage generative AI models and genetic data analysis to make more accurate diagnoses and improve prognosis for patients with rare diseases.