Artificial intelligence (AI), in particular deep learning algorithms, has made great strides in image classification tasks, enabling the autonomous evaluation of intricate medical images. This is especially important when using ultrasonography, to diagnose thyroid cancer. AI can lessen radiologists' burden, improve image processing efficiency, and assist them in distinguishing between benign and malignant nodules. This method has a lot of potential to increase the accuracy of thyroid ailments ultrasound diagnosis. In this study Random Forest and Support Vector Machine were employed to classify cancerous and non-cancerous thyroid images, by extracting deep learning features of five Deep Learning (DL) models namely ResNet50, ResNet101, VGG16, VGG19, and MobileNet. The performance of the models was compared. To improve the performance of the models the images were filtered using Bilateral Filter (BF) and Enhanced using Contrast Enhancement (CEH) technique. Also, to further improve the performance of the models, the models were trained with images to which the CEH and BL were applied. The best-performing model turns out to be CE+BF+ResNet50-SVM with an accuracy of $\mathbf{9 7 . 0 2 \%}$, sensitivity of $\mathbf{9 7 \%}$, specificity of $\mathbf{9 6 . 0 3 \%}$, F1-Score of $\mathbf{9 6 . 4 9 \%}$, AUC of $\mathbf{9 7 . 0 2 \%}$ and precision of $\mathbf{9 5 . 9 8 \%}$.

The goal of this study is to evaluate and compare the prediction performance of three different models, Multiple Linear Regression (MLR), Artificial Neural Network (ANN), and Adaptive Neuro-Fuzzy Inference System (ANFIS), in predicting dementia. The models were trained and tested using a dataset of 149 participants and nine input variables, with a $70 \% / 30 \%$ data split. Performance indicators for evaluation were $\mathrm{R}^{2}$, RMSE, and MSE. The results show that all models correctly predicted dementia, with ANN and ANFIS marginally exceeding MLR in terms of prediction accuracy. The training and testing phases yielded a perfect $\mathrm{R}^{2}$ score of 1, suggesting a strong fit to the dataset. This study contributes to dementia prediction research by providing a detailed review of various models.

Osteoporosis, a prevalent skeletal disorder characterized by weakened bone strength and integrity, poses a significant health risk, particularly for older adults and postmenopausal women. Early detection is critical to mitigate fracture risks and improve patient outcomes. This research investigates the potential of pretrained convolutional neural networks for automated osteoporosis detection in knee X-ray images and highlighting the impact of image preprocessing techniques on model performance. We evaluate four pretrained models (ResNet-50, ResNet-101, VGG16, and VGG19) for feature extraction, coupled with a Random Forest classifier optimized using Bayesian Optimization. Our framework explores the effectiveness of different preprocessing methods, including Bilateral Filtering and Contrast Limited Adaptive Histogram Equalization, to enhance feature quality and improve classification accuracy. Evaluation on a dataset of knee X-ray images collected from the University of Sharjah Hospital reveals that VGG architectures, particularly VGG16, demonstrate superior performance in detecting knee osteoporosis. VGG16, preprocessed using Bilateral Filtering and CLAHE, achieved a $\mathbf{7 8 . 3 9 \%}$ accuracy, $\mathbf{8 0 . 0 0 \%}$ precision, and $\mathbf{7 6 . 9 2 \%}$ recall. This study underscores the importance of selecting both model architecture and preprocessing techniques for optimal performance. Further optimization and more data could potentially lead to a more robust and accurate model.

Adrenocortical Carcinoma (ACC) can be detected and diagnosed using CT scans with the help of deep learning models, such as the novel MSHA model. The dataset used in the study consists of 53 patients with verified ACC and their contrast-enhanced CT scans. The MSHA model combines various approaches based on attention-based contextual information with mixed-scale dense convolution, a self-attention mechanism, and hierarchical feature fusion. Evaluation criteria are utilized to assess the model’s performance, demonstrating outstanding precision, sensitivity, specificity, and an F1 score of $\mathbf{9 6. 0 \%}$, along with an accuracy of 96.65%. This performance surpasses well-established models such as ResNet50, VGG16, VGG19, and InceptionV3 and proves valuable for detecting and diagnosing ACC, enhancing patient care and outcomes.

Bone cancer is a serious morbidity and mortality factor that occurs in rare cases with less than ${1 \%}$ prevalence across all cancers. Despite being rare, bone cancer has a mortality rate, accounting for less than ${1 \%}$ of deaths worldwide and claiming about ${2, 1 0 0}$ people in the United States in 2022. This includes cancers in both adults and children. Most mortality cases are traced to the late detection of tumors and wrong systematic diagnostic and therapeutic decisional approaches deployed either by the concerned physicians, patients, or close associates. To circumvent the hurdles associated with poor therapeutic decision-making, relating to bone cancers and to eliminate scenarios associated with uncertainties in any decision-making platform, this study proposed the multicriteria decision-making (MCDM) method called fuzzy preference ranking organization method for enrichment evaluations (PROMETHEE) to compare, evaluate, and rank conventional and modern treatment approaches for bone cancer. Results from this study showed that, with a net flow of 0.1737, Radiofrequency was determined as the most preferred and most favorable treatment approach for bone cancer. Surgery, Cryotherapy, Immunotherapy, and Radiation therapy came second, third, fourth, and fifth with net flows of $0.1309,-0.0154,-0.0797$, and −0.0902 respectively. Chemotherapy with a net flow of $-{0 . 1 1 9 3}$ was the least preferred treatment alternative. However, the outranking results may differ if different weight preference functions are assigned to each selected criterion

The lungs regulate breathing and supply oxygen to every cell in the body. Simultaneously, they act as air filters, blocking potentially harmful particles and microbes from entering the respiratory system. Humans have built-in defences that keep their lungs safe. However, these cannot guarantee complete protection against lung diseases. The lungs are vulnerable to infection, inflammation, and malignant tumors. The aim of this research is to investigate the applications of three models, specifically an ANN, ANFIS, and a classical linear regression MLR for the prediction of lung cancer. To evaluate the models, we have considered four performance parameters: $\mathbf{R}^{2}$, MSE, RMSE, and R. To make the research robust, the study also deployed an MCDM tool called the fuzzy PROMETHEE to evaluate, compare, and rank the performance of the deployed models. The performance analysis revealed that ANFIS is the most effective model; hence, it is the central proposition of this study.

Genetic algorithms (GA) are search engines that either optimize or reduce predefined functions. The technique of selection is an important phase in GA. This research study aims to evaluate, compare, and rank the selection techniques in GA. The evaluated selection techniques are; roulette wheel selection, elitist selection, rank selection, tournament selection, truncation selection, Boltzmann selection, and stochastic Universal Sampling selection. The comparison was based on the following selected criteria; (performance accuracy, fitness value accuracy, execution time, preservation of diversity, computational cost, ease of use, and bias levels. The paper incorporates the aforementioned criteria into the fuzzy preference ranking organization method for enrichment evaluation (PROMETHEE). This decision-making tool was used to determine the most preferred selection techniques in GA. The results from this research study showed that with an outranking net flow of 0.0690 elitism was determined as the most effective selection technique for GA based on the given criteria and their importance levels. Followed by the tournament selection technique with a positive net flow of 0.0343 and then, the rank selection technique, roulette wheel selection technique, truncation selection technique, and stochastic universal sampling selection technique occupied the third, fourth, fifth, and sixth positions with a net flow of 0.0078, -0.0102, -0.0116, -0.0156. Boltzmann selection technique ranked least among the considered selection techniques with a net flow of -0.0738 due to its features with all the criteria. With this study, we have provided a supportive tool for the decision-makers in the selection of the genetic algorithm techniques, and we have shown the applicability of the fuzzy PROMETHEE approach in this case by providing the advantages and disadvantages of each decision point.

Global life expectancy (GLE) is the typical lifespan that an individual is expected to live on, determined statistically from data. In this study, it is predicted using a dataset of social, economic, health, and demographic variables from different nations to make robust predictive algorithms. This study focuses on using machine learning (ML) ensemble models to predict GLE. This involves using key factors from the dataset that influence GLE. In this study, we utilized ML ensemble models like Random Forest (RF), Light Gradient Boosting Machine (LGBM), Adaptive Boosting (AdaBoost), and eXtreme Gradient Boosting (XGB) for the prediction of GLE. The result showed that LGBM outperformed other models by scoring 1.1851, 1.8778, 0.9504, 0.9504, and 3.5259 as MAE, RMSE, R2, EVS and MSE respectively. The result can be used in healthcare policies, planning, budgeting, and allocations to enhance GLE. Also, we employed explainable artificial intelligence (XAI) for a universal interpretation of the model’s intricate performances. This study has the potential to contribute to the development of evidence-based policies and interventions to enhance global public health using precise GLE made through the application of ML ensemble techniques.

Mental Health (MH) is a fundamental and indispensable component of general well-being that permits an individual to perform their activities to the fullest, in harmony with themselves and their social and physical surroundings. It enables an individual to manage life’s challenges (literacy, attitudes toward disorders, and cognitive abilities) effectively. MH comorbidity commonly denotes the coexistence of several different MH problems, a matter of considerable importance in the realms of clinical care and the overall well-being of society. However, the precise prediction of comorbidity in mental health (MH) enables the implementation of earlier treatment strategies and improves overall treatment outcomes. In this study, we used Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Multi-layer Perceptron (MLP), K-Nearest Neighbors (KNN), Decision trees (DT), and AdaBoost with DT for the modeling of MH comorbidities. The aforementioned models were evaluated for accuracy using these metrics: Root Mean Squared Error (RMSE), Mean Squared Error (MSE), Rsquared ($\mathrm{R}^{\mathbf{2}}$), and Mean Absolute Error (MAE). The study found that KNN outperformed other models by achieving the highest scores of $0.0187,0.0109,0.00$, and 1.00 for RMSE, MAE, MSE, and $R^{2}$ respectively. In conclusion, ML can enhance the prediction of MH comorbidities. Therefore, with accurate and earlier predictions, patient satisfaction and effective medical therapies will be achieved.

Prostate-specific antigen (PSA) detection is very vital for the early, accurate diagnosis and management of prostate cancer. Enzyme-linked immunosorbent assay (ELISA) is a promising PSA detection method due to its high sensitivity, and researchers continuously explore its potential. However, selecting the best ELISA method from available options can be challenging. As a result, we focused on using the Preference Ranking Organization Method for Enrichment Evaluation (PROMETHEE) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to assess the optimal technique for prostate cancer detection. In this study, the PROMETHEE and TOPSIS were used to evaluate different types of ELISA methods such as Direct (D-ELISA), Indirect ELISA (I-ELISA), Sandwich ELISA (S-ELISA), and Competitive ELISA (C-ELISA) based on Detection range (DR), Incubation time (IT), Ease of use (EOU), Cost-effectiveness (CE), Specificity (Sp%), Sensitivity (Se%), Linearity (Li), Precision (Prec), Accuracy (Acc), Limit of detection (LOD) $(\mathrm{ng} / \mathrm{mL})$, and Coefficient of variation (CV%) as criteria. The results showed that C-ELISA ranked first with a net flow value (Phi) of 0.0030 in PROMETHEE and second with a performance rating (Pi) of ${0. 5 8 6 4}$ in TOPSIS. Conversely, D-ELISA ranked second with a net flow value of 0.0000 in PROMETHEE and first with a Pi value of 0.5944 in TOPSIS. In both analyses, I-ELISA and S-ELISA ranked third and fourth, respectively, among the selected ELISA methods. This study highlights the importance of PROMETHEE and TOPSIS in selecting the most appropriate ELISA method for accurate prostate cancer detection using PSA.

Pancreatic cancer remains one of the deadiest forms of cancer worldwide. The main challenge in pancreatic cancer diagnosis is primarily attributed to the late stage at which it is typically diagnosed. Computed tomography (CT) has been used to provide a concise visualization of the pancreas, however, due to late pancreatic tumor diagnosis, this imaging technique is yet to be highly effective in detecting this malignancy at an early stage. Therefore, this research aims to apply pre-trained deep learning models in classifying CT scan images for the early detection of pancreatic cancer. Residual Network 50 (ResNet50), MSHA, and EfficientNet are the algorithms applied to analyze CT scans and identify cancerous growths in the pancreas. The results show high classification precision, with the highest achieved precision score of $\mathbf{1 0 0. 0 0 \%}$ using MSHA. However, all the applied models had a high performance in detecting pancreatic cancer as they all had scores not less than $\mathbf{9 9 \%}$ in all performance metrics used. These findings emphasize its proficiency in precisely identifying and categorizing pancreatic cancer. This program aims to alleviate the tremendous workload of healthcare systems caused by the large number of medical images analyzed by medical professionals. It specifically can assist radiologists and other specialists in detecting pancreatic tumors by offering a faster and more accurate technique.

Childbirth is a life-giving procedure whereby a whole individual is given an existence though at some points there may be a loss of infants along the journey. Maternal morbidity and death continue to be global issues despite improvements in contemporary obstetrics. This study aims at evaluating vaginal birth, emergency cesarean, elective cesarean, vaginal birth after C-section, vacuum extraction, and forceps delivery techniques considering the selected criteria which are the requirement of medical indication, patient preparation, the use of prophylactic antibiotics, infection rate, mortality rate, safety, prenatal hemorrhage, post-partum hemorrhage, laceration, use of general anesthesia, birth trauma, organ injury, dystocia, fetal distress, time of the procedure, cost, recovery, and the formation of long term scars using fuzzy Preference Ranking Organization Method for Enrichment Evaluations (fuzzy PROMETHEE); a multi-criteria decision-making (MCDM) model. The results of this study showed that vaginal birth was the first preferable ranked technique with a net outranking flow of 0.0773 and forceps delivery, vacuum extraction, vaginal birth after c-section, and emergency cesarean followed, with a net flow of $0.0195,0.0123$, $-0.0129,-0.0422$, respectively. The elective cesarean method was found to be the least preferable technique ranking sixth with a net flow of $\mathbf{- 0 . 0 5 4 0}$. Fuzzy PROMETHEE showed high effectiveness and accuracy in the ranking system. This method will support midwives, obstetricians, and mothers in deciding and weighing the risks associated with possible delivery approaches.

The uncontrollable growth of healthy cells in or around the vulva is known as vulva cancer. The most known risk factor for this type of cancer is the infection of the Human papillomavirus (HPV). Vulva cancer is most likely misdiagnosed as an inflammatory condition that leads to late treatment thus increasing the mortality rate of this type of cancer. Therefore, the current study examines the diagnosis and treatment techniques of vulva cancer considering a list of selected criteria using fuzzy Preference Ranking for Organization Method of Enrichment Evaluation (fuzzy PROMETHEE). The chosen diagnostic alternatives are cystoscopy, colposcopy, biopsy, Positron Emission Tomography (PET), Computed Tomography (CT) scan, and Magnetic Resonance Imaging (MRI) whereas the therapeutic alternatives are lymph node biopsy, vulvectomy, wide local excision, chemotherapy, radiation therapy, immunotherapy, and targeted therapy. In the ranking of the diagnostic methods, punch biopsy ranked first with a net flow of 0.2548 whereas CT scan ranked sixth with a net flow of ${- 0. 2 0 3 6}$. Furthermore, the treatment ranking resulted in lymph node biopsy as the first treatment alternative with a net flow of 0.5466 and immunotherapy as the seventh alternative with a net flow of $-{0}.5388$. The fuzzy PROMETHEE algorithm showed high effectiveness and precision in ranking the proposed alternatives. Thus, the results of this study will assist gynecologists and oncologists in making the appropriate decision for the early detection and treatment of vulva cancer.

The rise of health/medical informatics has created new opportunities for diagnosing different diseases. This is due to its cost-effectiveness and reliable ability to provide clear and understandable information that specialists and policymakers can use. This study aims at screening and predicting clinical lung cancer using a combination of socio-demographic and clinical input factors by implementing hybridized-novel paradigms integrated with multi-model single techniques. Four distinct multimodal single approaches combined with three hybridized novel paradigms were applied to predict lung cancer in a clinical setting. Both the quantitative and graphical performance of the individual methods demonstrate the superior capability of the Gaussian process regression (GPR) model compared to the other three models: Least-square boost (L-Boost), Step-wise-linear regression (SWLR), and Support Vector Regression (SVR). As a result of the inadequate performance and decreased effectiveness of individual procedures, three hybridized novel paradigms were introduced, namely; Stepwise-linear regression- Gaussian process regression (SWLR-GPR), Stepwise-linear regression- Least-square boost (SWLR-L-BOOST) and Stepwise-linear regression- Support Vector Regression (SWLR-SVR) to enhance the predictive abilities of individual methodologies in the clinical prediction of lung cancer by using regression methods. The comparative examination of the hybridized paradigms revealed that SWLR-GPR outperforms all other hybridized paradigms and single approaches in predicting lung cancer. Based on the results of this research and the efficacy of the suggested algorithms, this methodology may be used as a reliable method by medical professionals and policymakers for predicting Lung cancer.