Respiratory disorders are commonly regarded as complex disorders to diagnose due to their multi-factorial nature, encompassing the interplay between hereditary variables, comorbidities, environmental exposures, and therapies, among other contributing factors. This study presents a Clinical Decision Support System (CDSS) for the early detection of respiratory disorders using a one-dimensional convolutional neural network (1D-CNN) model. The ICBHI 2017 Breathing Sound Database, which contains samples of different breathing sounds, was used in this research. During pre-processing, audio clips were resampled to a uniform rate, and breathing cycles were segmented into individual instances of the lung sound. A One-Dimensional Convolutional Neural Network (1D-CNN) consisting of convolutional layers, max pooling layers, dropout layers, and fully connected layers, was designed to classify the processed clips into four categories: normal, crackles, wheezes, and combined crackles and wheezes. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied to the training data. Hyperparameters were optimized using grid search with k−fold cross-validation. The model achieved an overall accuracy of 0.95, outperforming state-of-the-art methods. Particularly, the normal and crackles categories attained the highest F1-scores of 0.97 and 0.95, respectively. The model’s robustness was further validated through 5−fold and 10−fold cross-validation experiments. This research highlighted an essential aspect of diagnosing lung sounds through artificial intelligence and utilized the 1D-CNN to classify lung sounds accurately. The proposed advancement of technology shall enable medical care practitioners to diagnose lung disorders in an improved manner, leading to better patient care.

This study aimed to find the molecular basis of Bardet-Biedl syndrome (BBS) in Pakistani consanguineous families. A total of 12 affected families were enrolled. Clinical investigations were performed to access the BBS-associated phenotypes. Whole exome sequencing was conducted on one affected individual from each family. The computational functional analysis predicted the variants’ pathogenic effects and modeled the mutated proteins. Whole-exome sequencing revealed 9 pathogenic variants in six genes associated with BBS in 12 families. The BBS6/MKS was the most common BBS causative gene identified in five families (5/12, 41.6%), with one novel (c.1226G>A, p.Gly409Glu) and two reported variants. c.774G>A, Thr259LeuTer21 was the most frequent BBS6/MMKS allele in three families 3/5 (60%). Two variants, c.223C>T, p.Arg75Ter and a novel, c. 252delA, p.Lys85STer39 were detected in the BBS9 gene. A novel 8bp deletion c.387_394delAAATAAAA, p. Asn130GlyfsTer3 was found in BBS3 gene. Three known variants were detected in the BBS1, BBS2, and BBS7 genes. Identification of novel likely pathogenic variants in three genes reaffirms the allelic and genetic heterogeneity of BBS in Pakistani patients. The clinical differences among patients carrying the same pathogenic variant may be due to other factors influencing the phenotype, including variants in other modifier genes.

Hereditary congenital cataract (HCC) is clinically and genetically heterogeneous. We investigated HCC that segregates in three inbred families (LUCC03, LUCC16, and LUCC24). Ophthalmological examinations revealed cataracts with variability related to the age of onset segregating in a recessive manner in these families. Exome sequencing of probands identified a novel homozygous c.2710delG;p.(Val904Cysfs*36) EPHA2 variant in LUCC03 and a known homozygous c.2353G>A;p.(Ala785Thr) EPHA2 variant in the other two recessive families. EPHA2 encodes a transmembrane tyrosine kinase receptor, which is primarily involved in membrane-transport, cell-cell adhesion, and repulsion signaling processes. Computational structural modeling predicts that substitution of a threonine for an alanine p.(Ala785Thr) results in the formation of three new hydrogen bonds with the neighboring residues, which causes misfolding of EPHA2 in both scenarios. Insights from our study will facilitate counseling regarding the molecular and phenotypic landscape of EPHA2-related HCC.

Background: Myelodysplastic syndromes (MDS) are clonal disorders of hematopoietic stem cells exhibiting ineffective hematopoiesis and tendency for transformation into acute myeloid leukemia (AML). The available karyotyping and fluorescent in situ hybridization provide limited information on molecular abnormalities for diagnosis/prognosis of MDS. Next generation DNA sequencing (NGS), providing deep insights into molecular mechanisms being involved in pathophysiology, was employed to study MDS in Pakistani cohort. Patients and methods: It was a descriptive cross-sectional study carried out at National institute of blood diseases and bone marrow transplant from 2016 to 2019. Total of 22 cases of MDS were included. Complete blood counts, bone marrow assessment and cytogenetic analysis was done. Patients were classified according to revised WHO classification 2016 and IPSS score was applied for risk stratification. Baseline blood samples were subjected to analysis by NGS using a panel of 54 genes associated with myeloid malignancies. Results: The median age of patients was 48.5 ± 9.19 years. The most common presenting complaint was weakness 10(45.45%). Cytogenetics analysis revealed abnormal karyotype in 10 (45.45%) patients. On NGS, 54 non-silent rare frequency somatic mutational events in 29 genes were observed (average of 3.82 (SD ± 2.08) mutations per patient), including mutations previously not observed in MDS or AML. Notably, two genes of cohesin complex, RAD21 and STAG2, and two tumor suppressor genes, CDKN2A and TP53, contained highest number of recurrent non-silent somatic mutations in the MDS. Strikingly, a missense somatic mutation p.M272Rof Rad21 was observed in 13 cases. Overall, non-silent somatic mutations in these four genes were observed in 21 of the 22 cases. The filtration with PharmGKB database highlighted a non-synonymous genetic variant rs1042522 [G > C] located in the TP53. Genotype GG and GC of this variant are associated with decreased response to cisplatin and paclitaxel chemotherapy. These two genotypes were found in 13 cases. Conclusion: Sequencing studies suggest that numerous genetic variants are involved in the initiation of MDS and in the development of AML. In countries like Pakistan where financial reservation of patients makes the use of such analysis even more difficult when the availability of advanced techniques is already a prevailing issue, our study could be an initiating effort in adding important information to the local data. Further studies and large sample size are needed in future to enlighten molecular profiling and ultimately would be helpful to compare and contrast the molecular characteristics of Asian versus global population.

Glaucoma is a neurodegenerative ophthalmic disorder and is considered among the leading causes of irreversible blindness. Primary open-angle glaucoma (POAG) is the most common type of glaucoma that affects after 30 years of life, progressing slowly, and manifests as decreased visual acuity leading to blindness if not treated. POAG is genetically heterogeneous, inherited most commonly in autosomal dominant mode. Several genes have been reported for POAG with myocilin (Myoc) being most common. The present study has been conducted to screen 25 POAG families with 2 or more affected members for their association with Myoc and CYP1B1 (the most common gene in primary congenital glaucoma). After approval from Institutional Ethical Review Committee (ERC), 25 POAG families were enrolled from the southern province (Sindh) of Pakistan. Written informed consent was obtained from all participating individuals and diagnosis was confirmed by consultant ophthalmologists using various instruments and means. Venous blood was obtained from affected individuals and their normal family members for DNA extraction and subsequent analysis. All samples were initially screened for the Myoc gene followed by CYP1B1. Screening for Myoc revealed one previously reported variant c.144G>T in POAG-06 whereas screening for CYP1B1 in all 25 families showed a novel variant c.649G>A in POAG-02. The pathogenicity of the novel variant was confirmed using various bioinformatics tools. This is the first report of any POAG family found associated with a novel variant in CYP1B1 from the southern province of Pakistan whereas one family found associated with a reported variant in Myoc. The remaining 23 POAG families did not found to be associated with either Myoc or CYP1B1 indicating genetic heterogeneity of the population in this part of the world.