Dataset Information

Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome.

ABSTRACT: The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automatic preprocessing, we extracted geometric and textural features. After incorporation of age, gender, and ethnicity, we used XGboost (eXtreme Gradient Boosting), a supervised machine learning classifier. The model was tested on an independent validation set. Finally, we compared the performances of our model with DeepGestalt (Face2Gene). The study included 1448 frontal and lateral facial photographs from 6 centers, corresponding to 634 patients (527 controls, 107 KS); 82 (78%) of KS patients had a variation in the KMT2D gene (KS1) and 23 (22%) in the KDM6A gene (KS2). We were able to distinguish KS from controls in the independent validation group with an accuracy of 95.8% (78.9-99.9%, p < 0.001) and distinguish KS1 from KS2 with an empirical Area Under the Curve (AUC) of 0.805 (0.729-0.880, p < 0.001). We report an automatic detection model for KS with high performances (AUC 0.993 and accuracy 95.8%). We were able to distinguish patients with KS1 from KS2, with an AUC of 0.805. These results outperform the current commercial AI-based solutions and expert clinicians.

SUBMITTER: Hennocq Q

PROVIDER: S-EPMC10822856 | biostudies-literature | 2024 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome.

Hennocq Quentin Q Willems Marjolaine M Amiel Jeanne J Arpin Stéphanie S Attie-Bitach Tania T Bongibault Thomas T Bouygues Thomas T Cormier-Daire Valérie V Corre Pierre P Dieterich Klaus K Douillet Maxime M Feydy Jean J Galliani Eva E Giuliano Fabienne F Lyonnet Stanislas S Picard Arnaud A Porntaveetus Thantrira T Rio Marlène M Rouxel Flavien F Shotelersuk Vorasuk V Toutain Annick A Yauy Kevin K Geneviève David D Khonsari Roman H RH Garcelon Nicolas N

Scientific reports 20240128 1

The field of dysmorphology has been changed by the use Artificial Intelligence (AI) and the development of Next Generation Phenotyping (NGP). The aim of this study was to propose a new NGP model for predicting KS (Kabuki Syndrome) on 2D facial photographs and distinguish KS1 (KS type 1, KMT2D-related) from KS2 (KS type 2, KDM6A-related). We included retrospectively and prospectively, from 1998 to 2023, all frontal and lateral pictures of patients with a molecular confirmation of KS. After automa ...[more]

PMID: 38282012

Similar Datasets

Project description:BackgroundThoracic aortic aneurysms and dissections (TAAD) are silent but possibly lethal condition with up to 40 % of cases being hereditary. Genetic background is heterogeneous. Recently next-generation sequencing enabled efficient and cost-effective examination of gene panels. Aim of the study was to define the diagnostic yield of NGS in the 51 TAAD patients and to look for genotype-phenotype correlations within families of the patients with TAAD.Methods51 unrelated TAAD patients were examined by either whole exome sequencing or TruSight One sequencing panel. We analyzed rare variants in 10 established thoracic aortic aneurysms-associated genes. Whenever possible, we looked for co-segregation in the families. Kaplan-Meier survival curve was constructed to compare the event-free survival depending on genotype. Aortic events were defined as acute aortic dissection or first planned aortic surgery.Results and discussionIn 21 TAAD patients we found 22 rare variants, 6 (27.3 %) of these were previously reported, and 16 (73.7 %) were novel. Based on segregation data, functional analysis and software estimations we assumed that three of novel variants were causative, nine likely causative. Remaining four were classified as of unknown significance (2) and likely benign (2). In all, 9 (17.6 %) of 51 probands had a positive result when considering variants classified as causative only and 18 (35.3 %) if likely causative were also included. Genotype-positive probands (n = 18) showed shorter mean event free survival (41 years, CI 35-46) than reference group, i.e. those (n = 29) without any plausible variant identified (51 years, CI 45-57, p = 0.0083). This effect was also found when the 'genotype-positive' group was restricted to probands with 'likely causative' variants (p = 0.0092) which further supports pathogenicity of these variants. The mean event free survival was particularly low (37 years, CI 27-47) among the probands with defects in the TGF beta signaling (p = 0.0033 vs. the reference group).ConclusionsThis study broadens the spectrum of genetic background of thoracic aneurysms and dissections and supports its potential role as a prognostic factor in the patients with the disease.

Dataset Information

Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome.

Publications

Next generation phenotyping for diagnosis and phenotype-genotype correlations in Kabuki syndrome.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets