Title: | P14.075C – Automated patient matching from facial photos – initial feasibility study Automated patient matching from facial photos – initial feasibility study |
Keywords: | photos; facial |
Authors: | N. Ekhilevitch1,2, T. Hershkovitz1, A. Kurolap2, M. Steinberg1, H. N.Baris1,2, N. Fleischer3; 1The Genetics Institute,Rambam Health Care Campus, Haifa, Israel, 2The Ruth and Bruce Rappaport Faculty of Medicine,Technion-Israel Institute of Technology, Haifa, Israel, 3FDNA Inc., Boston, MA, United States. |
Abstract: | Introduction: The importance of matching patients for diagnosis and gene discovery necessitates connecting clinicians and researchers from around the world. This is an initial feasibility study to assess if the automated facial recognition technology is able to provide connections between undiagnosed patients with similar facial phenotype. Methods: We composed a survey of 53 pairs of possibly matching facial photos of diagnosed, undiagnosed and control patients, asked four geneticists to rate the similarity between each pair and compared their results to the Patient Matching technology of the Facial Dysmorphology Novel Analysis (FDNA) algorithm. We used Pearson Correlation coefficient and the area under the curve (AUC) of the ROC curve to assess correlations. Results: Of the diagnosed pairs, the phenotype comparison performance of the FDNA technology (3.6 on similar pairs, 3.25 on different pairs) and the geneticists (2.5 on similar pairs, 2.25 on different pairs) was comparable, with a slight advantage to the technology. This trend is also seen by AUC: 0.65 for the technology vs. AUC 0.51 for the mean of the clinician’s answers. The overall agreement level between the four geneticists is relatively low (mean correlation 0.52). Conclusions: The importance of the task and the comparable results is a strong motivator to continue with a second stage of a feasibility study, with more photos, more clinicians and without the intrinsic biases – familiarity of geneticists with the patients. Future applications of this technology could complement next generation sequencing in undiagnosed patients and lead to the discovery of rare novel syndromes |
Presentation Time: | Monday, May 29, 2017, 10:15 AM -11:15 AM |
More entries about Scientific Abstracts
FDNA and Face2Gene Featured at ESHG
A flock of researchers from around the globe shared their findings in dysmorphology and molecular genetics at this year’s Read more
Phenotype analysis of congenital and neurodevelopmental disorders in the next generation sequencing era
Am J Med Genet C Semin Med Genet. 2017 Sep;175(3):320-328. doi: 10.1002/ajmg.c.31568. Epub 2017 Aug 2. Carey JC. Abstract: The designation, Read more
S. Odent, et al. Interest of searching dysmorphic features in Autism Spectrum Disorder: Comparison of clinical geneticists and Face2Gene photos analyses
Title: P09.022B – Interest of searching dysmorphic features in Autism Spectrum Disorder: Comparison of clinical geneticists and Face2Gene photos analyses Read more
N. Ekhilevitch, et al. Automated patient matching from facial photos – initial feasibility study
Title: P14.075C – Automated patient matching from facial photos – initial feasibility study Automated patient matching from facial photos – Read more
S. B. Kamphausen, M. Zenker. From Face to Gene – Identifying the Genotype of RASopathies with FDNA. ESHG 2017
Title: P14.083C – From Face to Gene – Identifying the Genotype of RASopathies with FDNA Keywords: RASopathies; Facial Dysmorphology Novel Read more
M. A. Mencarelli, et al. Clinical Application of a Facial Dysmorphology Tool: a performance analysis
Title: P14.042B – Clinical Application of a Facial Dysmorphology Tool: a performance analysis Keywords: Facial Dysmorphology Tool Authors: D. Lopergolo1, Read more
L. Morlan. The utility of computer-assisted facial recognition in the etiologic diagnosis of patients with global developmental delay & intellectual disability
Title: P14.041A – the utility of computer-assisted facial recognition in the etiologic diagnosis of patients with global developmental delay & Read more
T. Liehr. Next generation phenotyping in Emanuel and Pallister Killian syndrome using computer-aided facial dysmorphology analysis of 2D photos
Title: P14.003C – Next generation phenotyping in Emanuel and Pallister Killian syndrome using computer-aided facial dysmorphology analysis of 2D photos Read more
Himanshu Goel, et al. Case study: Next-generation phenotyping complementing next generation sequencing
Abstract Number: (501) Case study: Next-generation phenotyping complementing next generation sequencing Topic: Clinical Genetics Presenting Author: Himanshu Goel Co-Authors: Z. Yüksel, Centogene AG, Rostock, Read more
B. Russell, et al. Bohring-Opitz Syndrome Patient Support Group an Essential Element for Optimizing Facial Dysmorphism Recognition Software Tool
Abstract Number: (384) Bohring-Opitz Syndrome Patient Support Group an Essential Element for Optimizing Facial Dysmorphism Recognition Software Tool Topic: Clinical Genetics Presenting Read more