Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR).

BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate/severe MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

Mutation spectrum of autosomal recessive non-syndromic hearing loss in central Iran.

OBJECTIVE: To identify the spectrum of mutations in connexin 26 gene and frequency of two deletions in connexin 30 gene in central Iran. METHODS: After extraction of DNA from 300 blood samples, connexin 26 gene coding region was amplified using specific primers. PCR products were used for bidirectional sequencing. Multiplex PCR was used for detection of del(GJB6-D13S1830) and del(GJB6-D13S1854) in the GJB6 gene. RESULTS: Eighteen different mutations including two novel variants in GJB2 gene were detected. The GJB2 mutations were observed in 23.3% of all the subjects. In addition, none of the deaf patients carried the del(GJB6-D13S1830) and del(GJB6-D13S1854) in the GJB6 gene. The 35delG mutation was the most common mutation, accounting for 32.65% of the mutant alleles. CONCLUSION: The present study indicates that mutations in the GJB2 gene particularly 35delG are important causes for ARNSHL. 60% of the patients were heterozygous carriers. Thus, further investigation is needed to detect the genetic cause of hearing loss in patients with mono allelic mutations in the coding region of GJB2.

A new compound heterozygous mutation in GJB2 causes nonsyndromic hearing loss in a consanguineous Iranian family.

OBJECTIVE: To investigate mutations in GJB2 in a consanguineous Iranian family with multiple members affected by non-syndromic hearing loss. METHODS: DNA was extracted from blood samples and the coding region of the conexin 26 gene was amplified using PCR. Bidirectional sequencing was carried out on PCR products. RESULTS: Direct sequencing of the PCR products led to the identification of a novel compound heterozygous mutation of c.551G>C/c.397T>G (p.R184P/p.W133G) and a previously reported homozygous mutation c.551G>C (R184P/R184P). Compound heterozygous mutation was identified in the father and his daughter and homozygous mutation was identified in his affected son. In silico analysis of p.W133G predicted mutation has deleterious effect on protein structure. CONCLUSION: These results show the usefulness of GJB2 mutation screening and bioinformatic analysis for genetic diagnosis and counseling of non-syndromic hearing loss.