Brain-region specific autism prediction from electroencephalogram signals using graph convolution neural network.

BACKGROUND: Brain variations are responsible for developmental impairments, including autism spectrum disorder (ASD). EEG signals efficiently detect neurological conditions by revealing crucial information about brain function abnormalities. OBJECTIVE: This study aims to utilize EEG data collected from both autistic and typically developing children to investigate the potential of a Graph Convolutional Neural Network (GCNN) in predicting ASD based on neurological abnormalities revealed through EEG signals. METHODS: In this study, EEG data were gathered from eight autistic children and eight typically developing children diagnosed using the Childhood Autism Rating Scale at the Central Institute of Psychiatry, Ranchi. EEG recording was done using a HydroCel GSN with 257 channels, and 71 channels with 10-10 international equivalents were utilized. Electrodes were divided into 12 brain regions. A GCNN was introduced for ASD prediction, preceded by autoregressive and spectral feature extraction. RESULTS: The anterior-frontal brain region, crucial for cognitive functions like emotion, memory, and social interaction, proved most predictive of ASD, achieving 87.07% accuracy. This underscores the suitability of the GCNN method for EEG-based ASD detection. CONCLUSION: The detailed dataset collected enhances understanding of the neurological basis of ASD, benefiting healthcare practitioners involved in ASD diagnosis.

Validation of social cognition and interaction training's (SCIT) videos and photographs in Indian setting.

Background: Social cognition deficit is one of the marked characteristics of schizophrenia. Accumulated evidence suggests that social cognition and interaction training (SCIT) is associated with improved performance in social cognition and social skills in patients diagnosed with psychotic disorders. The cultural influence on social cognition is quite considerable. So, studies in the area of social cognition domains need to adapt and use culturally appropriate tools and measures to see the effectiveness. This study aimed to validate the materials used in SCIT training in Indian setting. Materials and Methods: The original script of video clips was translated into Hindi and was reshot, and the images were remade. A panel of experts rated the videos and images on a 5-point Likert scale. Furthermore, the content validity and internal consistency of the materials were calculated. Results: The content validity ratio (CVR) critical value was 0.357, and all the videos and images received more than the CVR critical value. The intraclass correlation coefficient for videos was 0.974, for SCIT photographs was 0.971, for "spotting character" was 0.975, and for "emotion shaping" was 0.965, indicating good internal consistency. Discussion: The majority of the experts in the panel found the videos and images adequate and appropriate for the Indian setting. In addition, the videos and photographs both yielded good internal consistency.

Regression Imputation and Optimized Gaussian Naïve Bayes Algorithm for an Enhanced Diabetes Mellitus Prediction Model

Abstract Diabetes mellitus (DM) is a category of metabolic disorders caused by high blood sugar. The DM affects human metabolism, and this disease causes many complications like Heart disease, Neuropathy, Diabetic retinopathy, kidney problems, skin disorder and slow healing. It is therefore essential to predict the presence of DM using an automated diabetes diagnosis system, which can be implemented using machine learning algorithms. A variety of automated diabetes prediction systems have been proposed in previous studies. Even so, the low prediction accuracy of DM prediction systems is a major issue. This proposed work developed a diabetes mellitus prediction system to improve the diabetes mellitus prediction accuracy using Optimized Gaussian Naive Bayes algorithm. This proposed model using the Pima Indians diabetes dataset as an input to build the DM predictive model. The missing values of an input dataset are imputed using regression imputation method. The sequential backward feature elimination method is used in this proposed model for selecting the relevant risk factors of diabetes disease. The proposed machine learning classifier named Optimized Gaussian Naïve Bayes (OGNB) is applied to the selected risk factors to create an enhanced Diabetes diagnostic system which predicts Diabetes in an individual. The performance analysis of this prediction architecture shows that, over other traditional machine learning classifiers, the Optimized Gaussian Naïve Bayes achieves an 81.85% classifier accuracy. This proposed DM prediction system is effective as compared to other diabetes prediction systems found in the literature. According to our experimental study, the OGNB based diabetes mellitus prediction system is more appropriate for DM disease prediction.

Bacteriocin from Bacillus subtilis as a novel drug against diabetic foot ulcer bacterial pathogens.

OBJECTIVE: To isolate and identify Bacillus subtilis (B. subtilis) from soil and to characterize and partially purify the bacteriocin. To evaluate the antimicrobial activity against four diabetic foot ulcer bacterial pathogens. METHODS: Genotypic identification was done based on Bergey's manual of systemic bacteriology. Antimicrobial susceptibility test was done by Kirby-Bauer disc diffusion method. Colonies were identified by colony morphology and biochemical characterization and also compared with MTCC 121 strain. Further identification was done by 16S rRNA sequencing. Inhibitory activities of partially purified bacteriocin on all the DFU isolates were done by agar well diffusion method. The strain was identified to produce bacteriocin by stab overlay assay. Bacteriocin was extracted by organic solvent extraction using chloroform, further purified by HPLC and physical, and chemical characterization was performed. RESULTS: The four isolates showed high level of resistance to amoxyclav and sensitivity to ciprofloxacin. HPLC purification revealed that the extracts are bacteriocin. The phylogenetic tree analysis results showed that the isolate was 99% related to B. subtilis BSF01. The results reveled activity to all the four isolates and high level of activity was seen in case of Klebsiella sp. CONCLUSIONS: Partially purified bacteriocin was found to have antimicrobial activity against the four diabetic foot ulcer bacterial pathogens, which can thus be applied as a better drug molecule on further studies. The strain B. subtilis are found to be safe for use and these antimicrobial peptides can be used as an antimicrobial in humans to treat DFU bacterial pathogens.