Prediction and Analysis of Autism Spectrum Disorder Using Machine Learning Techniques.

Autism spectrum disorder is a severe, life-prolonged neurodevelopmental disease typified by disabilities that are chronic or limited in the development of socio-communication skills, thinking abilities, activities, and behavior. In children aged two to three years, the symptoms of autism are more evident and easier to recognize. The major part of the existing literature on autism spectrum disorder is covered by a prediction system based on traditional machine learning algorithms such as support vector machine, random forest, multiple layer perceptron, naive Bayes, convolution neural network, and deep neural network. The proposed models are validated by using performance measurement parameters such as accuracy, precision, and recall. In this research, autism spectrum disorder prediction has been investigated and compared using common parameters such as application type, simulation method, comparison methodology, and input data. The key purpose of this study is to give a centralized framework to use for researchers working on autism spectrum disorder prediction. The best results were obtained by using the random forest algorithm as it performs better than other traditional machine learning algorithms. The achieved accuracy is 89.23%. The workflow representations of the investigated frameworks assist readers in comprehending the fundamental workings and architectures of these frameworks.

Machine learning based skin lesion segmentation method with novel borders and hair removal techniques.

The effective segmentation of lesion(s) from dermoscopic skin images assists the Computer-Aided Diagnosis (CAD) systems in improving the diagnosing rate of skin cancer. The results of the existing skin lesion segmentation techniques are not up to the mark for dermoscopic images with artifacts like varying size corner borders with color similar to lesion(s) and/or hairs having low contrast with surrounding background. To improve the results of the existing skin lesion segmentation techniques for such kinds of dermoscopic images, an effective skin lesion segmentation method is proposed in this research work. The proposed method searches for the presence of corner borders in the given dermoscopc image and removes them if found otherwise it starts searching for the presence of hairs on it and eliminate them if present. Next, it enhances the resultant image using state-of-the-art image enhancement method and segments lesion from it using machine learning technique namely, GrabCut method. The proposed method was tested on PH2 and ISIC 2018 datasets containing 200 images each and its accuracy was measured with two evaluation metrics, i.e., Jaccard index, and Dice index. The evaluation results show that our proposed skin lesion segmentation method obtained Jaccard Index of 0.77, 0.80 and Dice index of 0.87, 0.82 values on PH2, and ISIC2018 datasets, respectively, which are better than state-of-the-art skin lesion segmentation techniques.

Development of a novel cell-based, In-Cell Western/ERK assay system for the high-throughput screening of agonists acting on the delta-opioid receptor.

Background: Extracellular signal-regulated kinases (ERKs) are important signaling mediators in mammalian cells and, as a result, one of the major areas of research focus. The detection and quantification of ERK phosphorylation as an index of activation is normally conducted using immunoblotting, which does not allow high-throughput drug screening. Plate-based immunocytochemical assays provide a cheaper and relatively high-throughput alternative method for quantifying ERK phosphorylation. Here, we present optimization steps aimed to increase assay sensitivity and reduce variance and cost using the LI-COR In-Cell Western (I-CW) system in a recombinant CHO-K1 cell line, over-expressing the human delta-opioid receptor (hDOPr) as a model. Methods: Cells cultured in 96-well microassay plates were stimulated with three standard/selective DOPr agonists (SNC80, ADL5859, and DADLE) and a novel selective DOPr agonist (PN6047) to elicit a phospho-ERK response as an index of activation. A number of experimental conditions were investigated during the assay development. Key results: Preliminary experiments revealed a clearly visible edge-effect which significantly increased assay variance across the plate and which was reduced by pre-incubation for 30 min at room temperature. ERK phosphorylation was detectable as early as 1 min after agonist addition, with a distinct peak at 3-5 min. Optimization of the cell seeding densities showed that 25,000 cells per well have the lowest basal phospho-ERK response and an optimal agonist ERK1/2 signal. Pre-incubation with apyrase (an ATPase) did not reduce the basal or agonist responses. All agonists produced concentration-dependent increases in phospho-ERK activation, and pertussis toxin was able to attenuate these ERK responses. Naltrindole, which is a selective DOPr antagonist, was able to antagonize the DOPr-mediated ERK activation of the ligands. Conclusion: We have developed an optimization protocol and highlighted a number of considerations when performing this high-throughput fluorescence immunocytochemical (ICC) assay measuring ERK phosphorylation in the human DOPr. The optimized protocol was found to be a more conducive option for the screening of delta agonists. This provides a basis for additional assay development to investigate opioid pharmacology. This protocol should be widely applicable for measuring ERK phosphorylation in any cell line and investigating other protein targets in GPCR drug discovery.

Formulation of ciprofloxacin-loaded oral self-emulsifying drug delivery system to improve the pharmacokinetics and antibacterial activity.

This study aims to increase the aqueous solubility of ciprofloxacin (CPN) to improve oral bioavailability. This was carried out by formulating a stable formulation of the Self-Emulsifying Drug Delivery System (SEDDS) using various ratios of lipid/oil, surfactant, and co-surfactant. A pseudo-ternary phase diagram was designed to find an area of emulsification. Eight formulations (F1-CPN-F8-CPN) containing oleic acid oil, silicone oil, olive oil, castor oil, sunflower oil, myglol oil, polysorbate-80, polysorbate-20, PEO-200, PEO-400, PEO-600, and PG were formulated. The resultant SEDDS were subjected to thermodynamic study, size, and surface charge studies to improve preparation. Improved composition of SEDDS F5-CPN containing 40% oil, 60% polysorbate-80, and propylene glycol (Smix ratio 6: 1) were thermodynamically stable emulsions having droplet size 202.6 nm, charge surface -13.9 mV, and 0.226 polydispersity index (PDI). Fourier transform infra-red (FT-IR) studies revealed that the optimized formulation and drug showed no interactions. Scanning electron microscope tests showed the droplets have an even surface and spherical shape. It was observed that within 5 h, the concentration of released CPN from optimized formulations F5-CPN was 93%. F5-CPN also showed a higher antibacterial action against S. aurous than free CPN. It shows that F5-CPN is a better formulation with a good release and high antibacterial activity.

Blended Ensemble Learning Prediction Model for Strengthening Diagnosis and Treatment of Chronic Diabetes Disease.

Diabetes mellitus (DM), commonly known as diabetes, is a collection of metabolic illnesses characterized by persistently high blood sugar levels. The signs of elevated blood sugar include increased hunger, frequent urination, and increased thirst. If DM is not treated properly, it may lead to several complications. Diabetes is caused by either insufficient insulin production by the pancreas or an insufficient insulin response by the body's cells. Every year, 1.6 million individuals die from this disease. The objective of this research work is to use relevant features to construct a blended ensemble learning (EL)-based forecasting system and find the optimal classifier for comparing clinical outputs. The EL based on Bayesian networks and radial basis functions has been proposed in this article. The performances of five machine learning (ML) techniques, namely, logistic regression (LR), decision tree (DT) classifier, support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF), are compared with the proposed EL technique. Experiments reveal that the EL method performs better than the existing ML approaches in predicting diabetic illness, with the remarkable accuracy of 97.11%. The proposed ensemble learning could be useful in assisting specialists in accurately diagnosing diabetes and assisting patients in receiving the appropriate therapy.

Assessment of Antimicrobial Potential of Plagiochasma rupestre Coupled with Healing Clay Bentonite and AGNPS.

The impact of individual component, i.e., plant extract (Plagiochasma rupestre), biosynthesized silver nanoparticles (AgNPs), and healing clay (bentonite) as antimicrobial agent is reported but their combined effect as a ternary system is a new approach. This study is aimed at investigating the impact of the proposed ternary system against selected human pathogens. AgNPs were synthesized by using Plagiochasma rupestre extract (aqueous) as reducing agent and neutral polymer (PVP) as stabilizer. The morphology, size, and structural properties of synthesized AgNPs were determined with XRD and SEM analysis which showed spherical monomodal particles with an average particle size of 25.5 nm. The antibacterial and antifungal activities of the individual and nanoternary system were investigated. The phytochemical screening of plant extract showed the presence of alkaloids, flavonoids, phenol, and glycosides in methanol extract as compare to aqueous and acetone extract. The antimicrobial activities of crude extracts of Plagiochasma rupestre with AgNPs and bentonite clay were studied as an appropriate candidate for treatment of microbial infections, especially bacterial and fungal diseases. The antioxidant activity of Plagiochasma rupestre aqueous extract and nanoparticles was assessed by (DPPH) free radical, and absorbance was checked at 517 nm. Crude extract has inhibitory effect towards bacteria and fungi, and bentonite clay also showed some degree of antimicrobial resistance. Strategy can be efficiently applied for future engineering and medical. The nanoternary systems showed 3 and 3.5 times higher antibacterial and antifungal activity, respectively, in comparison to Plagiochasma rupestre and bentonite clay, individually.

A Randomized Clinical Trial Comparing Two Treatment Strategies, Evaluating the Meaningfulness of HAM-D Rating Scale in Patients With Major Depressive Disorder.

Introduction: Due to the complexity of symptoms in major depressive disorder (MDD), the majority of depression scales fall short of accurately assessing a patient's progress. When selecting the most appropriate antidepressant treatment in MDD, a multidimensional scale such as the Hamilton Depression Rating scale (HAM-D) may provide clinicians with more information especially when coupled with unidimensional analysis of some key factors such as depressed mood, altered sleep, psychic and somatic anxiety and suicidal ideation etc. Methods: HAM-D measurements were carried out in patients with MDD when treated with two different therapeutic interventions. The prespecified primary efficacy variables for the study were changes in score from baseline to the end of the 12 weeks on HAM-D scale (i.e., ≤ 8 or ≥50% response). The study involved three assessment points (baseline, 6 weeks and 12 weeks). Results: Evaluation of both the absolute HAM-D scores and four factors derived from the HAM-D (depressed mood, sleep, psychic and somatic anxiety and suicidal ideation) revealed that the latter showed a greater promise in gauging the anti-depressant responses. Conclusion: The study confirms the assumption that while both drugs may improve several items on the HAM-D scale, the overall protocol may fall short of addressing the symptoms diversity in MDD and thus the analysis of factor (s) in question might be more relevant and meaningful.

Decision Support System for Predicting Survivability of Hepatitis Patients.

Background and Objective: Viral hepatitis is a major public health concern on a global scale. It predominantly affects the world's least developed countries. The most endemic regions are resource constrained, with a low human development index. Chronic hepatitis can lead to cirrhosis, liver failure, cancer and eventually death. Early diagnosis and treatment of hepatitis infection can help to reduce disease burden and transmission to those at risk of infection or reinfection. Screening is critical for meeting the WHO's 2030 targets. Consequently, automated systems for the reliable prediction of hepatitis illness. When applied to the prediction of hepatitis using imbalanced datasets from testing, machine learning (ML) classifiers and known methodologies for encoding categorical data have demonstrated a wide range of unexpected results. Early research also made use of an artificial neural network to identify features without first gaining a thorough understanding of the sequence data. Methods: To help in accurate binary classification of diagnosis (survivability or mortality) in patients with severe hepatitis, this paper suggests a deep learning-based decision support system (DSS) that makes use of bidirectional long/short-term memory (BiLSTM). Balanced data was utilized to predict hepatitis using the BiLSTM model. Results: In contrast to previous investigations, the trial results of this suggested model were encouraging: 95.08% accuracy, 94% precision, 93% recall, and a 93% F1-score. Conclusions: In the field of hepatitis detection, the use of a BiLSTM model for classification is better than current methods by a significant margin in terms of improved accuracy.

AdaBoost Ensemble Methods Using K-Fold Cross Validation for Survivability with the Early Detection of Heart Disease.

As a result of technology improvements, various features have been collected for heart disease diagnosis. Large data sets have several drawbacks, including limited storage capacity and long access and processing times. For medical therapy, early diagnosis of heart problems is crucial. Disease of heart is a devastating human disease that is quickly increasing in developed and also developing countries, resulting in death. In this type of disease, the heart normally fails to provide enough blood to different body parts in order to allow them to perform their regular functions. Early, as well as, proper diagnosis of this condition is very critical for averting further damage and also to save patients' lives. In this work, machine learning (ML) is utilized to find out whether a person has cardiac disease or not. Both the types of ensemble classifiers, namely, homogeneous as well as heterogeneous classifiers (formed by combining two separate classifiers), have been implemented in this work. The data mining preprocessing using Synthetic Minority Oversampling Technique (SMOTE) has been employed to cope with the imbalance problem of the class as well as noise. The proposed work has two steps. SMOTE is used in the initial phase to reduce the impact of data imbalance and the second phase is classifying data using Naive Bayes (NB), decision tree (DT) algorithms, and their ensembles. The experimental results demonstrate that the AdaBoost-Random Forest classifier provides 95.47% accuracy in the early detection of heart disease.

A Decision Support System for Diagnosing Diabetes Using Deep Neural Network.

Background and Objective: According to the WHO, diabetes mellitus is a long-term condition marked by high blood sugar levels. The consequences might be far-reaching. According to current increases in mortality, diabetes has risen to number 10 among the leading causes of mortality worldwide. When used to predict diabetes using unbalanced datasets from testing, machine learning (ML) classifiers and established approaches for encoding categorical data have exhibited a broad variety of surprising outcomes. Early studies also made use of an artificial neural network to extract features without obtaining a grasp of the sequence information. Methods: This study offers a deep learning-based decision support system (DSS), utilizing bidirectional long/short-term memory (BiLSTM), to accurately predict diabetic illness from patient data. In order to predict diabetes, the BiLSTM hybrid model was used after balancing the data set. Results: Unlike earlier studies, this proposed model's trial findings were promising, with an accuracy of 93.07%, 93% precision, 92% recall, and a 92% F1-score. Conclusions: Using a BILSTM model for classification outperforms current approaches in the diabetes detection domain.