The Therapeutic Odyssey: Positioning Genomic Sequencing in the Search for a Child's Best Possible Life.

Background: The desire of parents to obtain a genetic diagnosis for their child with intellectual disability and associated symptoms has long been framed as a diagnostic odyssey, an arduous and sometimes perilous journey focused on the goal of identifying a cause for the child's condition.Methods: Semi-structured interviews (N = 60) were conducted with parents of children (N = 59, aged 2-24 years) with intellectual disability and/or developmental delay (IDD) who underwent genome sequencing at a single pediatric multispecialty clinic. Interviews were conducted after parents received their child's sequencing result (positive findings, negative findings, or variants of unknown significance). Thematic analysis was performed on all interviews.Results: Parents reported that obtaining a genetic diagnosis was one important step in their overall goal of helping their child live their best life possible life. They intended to use the result as a tool to help their child by seeking the correct school placement and obtaining benefits and therapeutic services.Conclusions: For the parents of children with IDD, the search for a genetic diagnosis is best conceptualized as a part of parents' ongoing efforts to leverage various diagnoses to obtain educational and therapeutic services for their children. Cleaving parents' search for a genetic diagnosis from these broader efforts obscures the value that some parents place on a sequencing result in finding and tailoring therapies and services beyond the clinic. Interviews with parents reveal, therefore, that genomic sequencing is best understood as one important stage of an ongoing therapeutic odyssey that largely takes place outside the clinic. Findings suggest the need to expand translational research efforts to contextualize a genetic diagnosis within parents' broader efforts to obtain educational and therapeutic services outside clinical contexts.

Deep learning in rare disease. Detection of tubers in tuberous sclerosis complex.

OBJECTIVE: To develop and test a deep learning algorithm to automatically detect cortical tubers in magnetic resonance imaging (MRI), to explore the utility of deep learning in rare disorders with limited data, and to generate an open-access deep learning standalone application. METHODS: T2 and FLAIR axial images with and without tubers were extracted from MRIs of patients with tuberous sclerosis complex (TSC) and controls, respectively. We trained three different convolutional neural network (CNN) architectures on a training dataset and selected the one with the lowest binary cross-entropy loss in the validation dataset, which was evaluated on the testing dataset. We visualized image regions most relevant for classification with gradient-weighted class activation maps (Grad-CAM) and saliency maps. RESULTS: 114 patients with TSC and 114 controls were divided into a training set, a validation set, and a testing set. The InceptionV3 CNN architecture performed best in the validation set and was evaluated in the testing set with the following results: sensitivity: 0.95, specificity: 0.95, positive predictive value: 0.94, negative predictive value: 0.95, F1-score: 0.95, accuracy: 0.95, and area under the curve: 0.99. Grad-CAM and saliency maps showed that tubers resided in regions most relevant for image classification within each image. A stand-alone trained deep learning App was able to classify images using local computers with various operating systems. CONCLUSION: This study shows that deep learning algorithms are able to detect tubers in selected MRI images, and deep learning can be prudently applied clinically to manually selected data in a rare neurological disorder.