Restoring private autism dataset from sanitized database using an optimized key produced from enhanced combined PSO-GWO framework.

The timely identification of autism spectrum disorder (ASD) in children is imperative to prevent potential challenges as they grow. When sharing data related to autism for an accurate diagnosis, safeguarding its security and privacy is a paramount concern to fend off unauthorized access, modification, or theft during transmission. Researchers have devised diverse security and privacy models or frameworks, most of which often leverage proprietary algorithms or adapt existing ones to address data leakage. However, conventional anonymization methods, although effective in the sanitization process, proved inadequate for the restoration process. Furthermore, despite numerous scholarly contributions aimed at refining the restoration process, the accuracy of restoration remains notably deficient. Based on the problems identified above, this paper presents a novel approach to data restoration for sanitized sensitive autism datasets with improved performance. In the prior study, we constructed an optimal key for the sanitization process utilizing the proposed Enhanced Combined PSO-GWO framework. This key was implemented to conceal sensitive autism data in the database, thus avoiding information leakage. In this research, the same key was employed during the data restoration process to enhance the accuracy of the original data recovery. Therefore, the study enhanced the restoration process for ASD data's security and privacy by utilizing an optimal key produced via the Enhanced Combined PSO-GWO framework. When compared to existing meta-heuristic algorithms, the simulation results from the autism data restoration experiments demonstrated highly competitive accuracies with 99.90%, 99.60%, 99.50%, 99.25%, and 99.70%, respectively. Among the four types of datasets used, this method outperforms other existing methods on the 30-month autism children dataset, mostly.

The survival outcomes and prognostic factors of hepatocellular carcinoma among type 2 diabetes patients: a two-centre retrospective cohort study.

BACKGROUND: To determine the survival outcomes and prognostic factors associated with hepatocellular carcinoma (HCC) survival in type 2 diabetes (T2D) patients. METHODS: This was a retrospective cohort study involving two hepatobiliary centres from January 1, 2012, to June 30, 2018. Medical records were analysed for sociodemographic, clinical characteristics, laboratory testing, and HCC treatment information. Survival outcomes were examined using the Kaplan-Meier and log-rank test. Prognostic factors were determined using multivariate Cox regression. RESULTS: A total of 212 patients were included in the study. The median survival time was 22 months. The 1-, 3-, and 5-year survival rates were 64.2%, 34.2%, and 18.0%, respectively. Palliative treatment (adjusted hazard ratio [AHR] = 2.82, 95% confidence interval [CI] 1.75-4.52), tumour size ≥ 5 cm (AHR = 2.02, 95%CI: 1.45-2.82), traditional medication (AHR = 1.94, 95%CI: 1.27-2.98), raised alkaline phosphatase (AHR = 1.74, 95%CI: 1.25-2.42), and metformin (AHR = 1.44, 95%CI: 1.03-2.00) were significantly associated with poor prognosis for HCC survival. Antiviral hepatitis treatment (AHR = 0.54, 95% CI: 0.34-0.87), nonalcoholic fatty liver disease (NAFLD) (AHR = 0.50, 95% CI: 0.30-0.84), and family history of malignancies (AHR = 0.50, 95%CI: 0.26-0.96) were identified as good prognostic factors for HCC survival. DISCUSSION: Traditional medication, metformin treatment, advanced stage and raised alkaline phosphatase were the poor prognostic factors, while antiviral hepatitis treatment, NAFLD, and family history of malignancies were the good prognostic factors for our HCC cases comorbid with T2D.

Prediction of hepatocellular carcinoma risk in patients with type-2 diabetes using supervised machine learning classification model.

Background: Hepatocellular carcinoma (HCC) among type-2 diabetes (T2D) patients is an increasing burden to diabetes management. This study aims to develop and select the best machine learning (ML) classification model for predicting HCC in T2D for HCC early detection. Methods: A case-control study was conducted utilising computerised medical records in two hepatobiliary centres. The predictors were chosen using multiple logistic regression. IBM SPSS Modeler® was used to assess the discriminative performance of support vector machine (SVM), logistic regression (LR), artificial neural network (ANN), chi-square automatic interaction detection (CHAID), and their ensembles. Results: Subjects (N = 424) were split into 60% training (n = 248) and 40% testing (n = 176) groups. The independent predictors identified were race, viral hepatitis, abdominal pain/discomfort, unintentional weight loss, statins, alcohol consumption, non-alcoholic fatty liver, platelet <150 ×103/µL, alkaline phosphatase >129 IU/L, and alanine transaminase ≥25 IU/L. The performances of all models differed significantly (Cochran's Q-test,p = 0.001) but not between the ensembled and SVM model (McNemar test, p = 0.687). SVM model was selected as the best model due to its simplicity, high accuracy (85.28%), and high AUC (0.914). A web-based application was developed using the best model's algorithm for HCC prediction. Conclusions: If further validation studies confirm these results, the SVM model's application potentially augments early HCC detection in T2D patients.

Risk factors of hepatocellular carcinoma in type 2 diabetes patients: A two-centre study in a developing country.

Type 2 diabetes mellitus (T2DM) is increasingly known as a risk factor of hepatocellular carcinoma (HCC). In this study, we determined the risk factors associated with HCC in T2DM patients. This was a matched case-control study conducted at two hepatobiliary referral centres in a developing country. Patients' sociodemographic, clinical, and biochemical characteristics between 1 January 2012 and 30 June 2018 were extracted from the electronic medical records and analysed using multivariate logistic regression analysis. A total of 212 case-control pairs were included. Significant risk factors included Chinese and Malay ethnicities that interacted with viral hepatitis (adjusted odds ratio [AOR] = 11.77, 95% confidence interval [CI]: 1.39-99.79) and (AOR = 37.94, 95% CI: 3.92-367.61) respectively, weight loss (AOR = 5.28, 95% CI: 2.29-12.19), abdominal pain/ discomfort (AOR = 6.73, 95% CI: 3.34-13.34), alcohol (AOR = 4.08, 95% CI: 1.81-9.22), fatty liver (AOR = 3.29, 95% CI: 1.40-7.76), low platelet (AOR = 4.03, 95% CI:1.90-8.55), raised alanine transaminase (AOR = 2.11, 95% CI: 1.16-3.86). and alkaline phosphatase (ALP) levels (AOR = 2.17, 95% CI: 1.17-4.00). Statins reduced the risk of HCC by 63% (AOR = 0.37, 95% CI: 0.21-0.65). The identification of these factors aids the risk stratification for HCC among T2DM patients for early detection and decision-making in patient management in the primary care setting.

A Review of Machine Learning Methods of Feature Selection and Classification for Autism Spectrum Disorder.

Autism Spectrum Disorder (ASD), according to DSM-5 in the American Psychiatric Association, is a neurodevelopmental disorder that includes deficits of social communication and social interaction with the presence of restricted and repetitive behaviors. Children with ASD have difficulties in joint attention and social reciprocity, using non-verbal and verbal behavior for communication. Due to these deficits, children with autism are often socially isolated. Researchers have emphasized the importance of early identification and early intervention to improve the level of functioning in language, communication, and well-being of children with autism. However, due to limited local assessment tools to diagnose these children, limited speech-language therapy services in rural areas, etc., these children do not get the rehabilitation they need until they get into compulsory schooling at the age of seven years old. Hence, efficient approaches towards early identification and intervention through speedy diagnostic procedures for ASD are required. In recent years, advanced technologies like machine learning have been used to analyze and investigate ASD to improve diagnostic accuracy, time, and quality without complexity. These machine learning methods include artificial neural networks, support vector machines, a priori algorithms, and decision trees, most of which have been applied to datasets connected with autism to construct predictive models. Meanwhile, the selection of features remains an essential task before developing a predictive model for ASD classification. This review mainly investigates and analyzes up-to-date studies on machine learning methods for feature selection and classification of ASD. We recommend methods to enhance machine learning's speedy execution for processing complex data for conceptualization and implementation in ASD diagnostic research. This study can significantly benefit future research in autism using a machine learning approach for feature selection, classification, and processing imbalanced data.

Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading.

OBJECTIVE: Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. METHODOLOGY: We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. RESULTS: We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. CONCLUSION: We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to other reported FS methods.

Round Randomized Learning Vector Quantization for Brain Tumor Imaging.

Brain magnetic resonance imaging (MRI) classification into normal and abnormal is a critical and challenging task. Owing to that, several medical imaging classification techniques have been devised in which Learning Vector Quantization (LVQ) is amongst the potential. The main goal of this paper is to enhance the performance of LVQ technique in order to gain higher accuracy detection for brain tumor in MRIs. The classical way of selecting the winner code vector in LVQ is to measure the distance between the input vector and the codebook vectors using Euclidean distance function. In order to improve the winner selection technique, round off function is employed along with the Euclidean distance function. Moreover, in competitive learning classifiers, the fitting model is highly dependent on the class distribution. Therefore this paper proposed a multiresampling technique for which better class distribution can be achieved. This multiresampling is executed by using random selection via preclassification. The test data sample used are the brain tumor magnetic resonance images collected from Universiti Kebangsaan Malaysia Medical Center and UCI benchmark data sets. Comparative studies showed that the proposed methods with promising results are LVQ1, Multipass LVQ, Hierarchical LVQ, Multilayer Perceptron, and Radial Basis Function.