Despite the strides made in medical science, pancreatic cancer continues to be a threat, highlighting the urgent need for creative strategies to address this concern. Recently, a potential approach that has attracted significant attention is using machine learning in clinical decision-making. This research aims to analyze six machine learning algorithms, and an ensemble voting classifier, develop hybrid models for the early detection of pancreatic cancer based on several clinical characteristics and interpret their performance with Shapley Additive Explanations (SHAP). A publicly available dataset composed of 590 patient urine samples was utilized to develop six conventional models for the classification of cancerous from non-cancerous pancreatic cases through the analysis of specific attributes. An ensemble voting classifier was developed from the best-performed single models, which were later hybridized to form six novel hybrid models. The ensemble voting classifier outperformed all stand-alone models with an accuracy of 96.61% and a precision of 98.72%. The six novel hybrid models exhibited higher performance than single models with voting classifier random forest hybridized model outperforming others with an AUC of 99.05% (95% confidence interval (CI): 0.93-1.00) and an interpretation was given by SHAP showing top influential features in pancreatic cancer diagnosis that exhibited the greatest positive SHAP values. Employing rapid sophisticated models with high accuracy and precision holds significant promise in facilitating the effective detection of various diseases, including pancreatic cancer.

Aim: Annually, millions of people die from kidney diseases making it a serious public health concern. Patients with renal insufficiency have hemostatic defects that enhance their risk of thrombosis and bleeding. Evaluating the advantages and hazards of anticoagulant thromboprophylaxis is challenging.Material and Methods: By using the fuzzy preference ranking organization method for enrichment evaluation (fuzzy PROMETHEE) and fuzzy multi-criteria optimization and compromise solution (fuzzy VIKOR), which are analytical multi-criteria decision-making (MCDM) techniques, this study aims to analyze diverse types of anticoagulants; specifically, Vitamin K-Antagonist (warfarin) and direct oral anticoagulants namely; Dabigatran, Rivaroxaban, Apixaban, and Edoxaban, by considering various criteria.Results: Direct oral anticoagulants outperformed warfarin in terms of safety and effectiveness. Among all the analyzed anticoagulants, Apixaban was found to be the best-ranked anticoagulant with both fuzzy PROMETHEE and fuzzy VIKOR, with a net flow of 0.0064 and the lowest Qj value of 0.0000, respectively, compared with other alternatives depending on the selected criteria while warfarin was found to be the least ranked anticoagulant with a net flow of -0.0043 and the highest number of Qj being 1, respectively.Conclusion: The MCDM techniques used were effective, highly accurate, and sensitive in the comparison of anticoagulant therapy for venous thrombosis in renal insufficiency based on the chosen criteria. The proper use of a safe and effective anticoagulant will boost better performance not only in patients’ survival and well-being but also in the health care center.

Cancer continues to be a life-threatening case all over the world, as it is the most lethal health condition nowadays. Cervical cancer, in particular, is the fourth most prevalent cancer type in women, killing a huge number of patients yearly. Different measures have been taken to prevent, reduce, and treat this malignancy. Though surgery is among the treatments for cervical cancer, diverse complications arise from performing operations and they likely affect the results of surgery. These complications range from minor to major complications. It is very crucial for surgeons to know how to handle such situations before their occurrence. This study aims to assess some of the complications that may arise prior to, during, or post cervical cancer surgery. These are seizure, transient hematuria, wound infection, urinary infection, postoperative surgical hemorrhage, shock, and wound dehiscence. The chosen alternatives are to be analyzed and ranked using a multi-criteria decision-making (MCDM) model known as the fuzzy Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) depending on the selected criteria. Seizure ranked 1st with a net flow of 0.1165 while wound dehiscence ranked 8th with a net flow of -0.0670. Seizure is at low risk when compared to other alternatives due to high treatment types, low prevalence rate, high survival rate, and low mortality rate. Wound dehiscence was found to be at high risk due to its long recovery time and a high mortality rate in cervical cancer conditions when compared to the adjacent alternatives. The findings of this study will improve patient safety, and help surgeons in advancing their skills. To reduce surgical complications and standardize postoperative care, fuzzy PROMETHEE was found to be an effective model to support surgeons, and gynecologists in planning and performing surgeries by being aware of the consequences and any difficulties that may arise along the way.

Objective : Monkeypox, a disease caused by a deoxyribonucleic acid (DNA) based virus (MPXV) has posed global health challenges to the entire populace. MPXV is a zoonotic disease with public health concerns, rapid prevalence, and geographical spread resulting in swift preventive techniques, especially for vulnerable nations (population). Its incidence and global widespread have necessitated immediate intervention thus the use of vaccination. This study analyzed three globally recommended monkeypox vaccines, LC16m8, ACAM2000, and JYNNEOS, by assessing their safety and effectiveness in controlling monkeypox. Methods : Multi-criteria decision-making (MCDM) methods; the fuzzy Preference Ranking Organization Method for Enrichment Evaluations (fuzzy PROMETHEE) and the fuzzy Technique for Order Preference by Similarities to Ideal Solution (fuzzy TOPSIS), were applied for the evaluation of these vaccines considering 20 different criteria, mainly focusing on the route of administration, dosage, safety, adverse effects, affordability, and overall effectiveness of the vaccine. Results : LC16m8 ranked the most preferable vaccine from both MCDM methods with a net outranking flow of 0.4365 and Closeness coefficient value of 0.7916 (95% CI, 0.242-0.894). In terms of safety, both LC16m8 and JYNNEOS vaccines showed equal performance in their profiles mostly in vulnerable populations like human immunodeficiency virus-positive populations, pregnant women, and children, as well as cardiovascular disease patients. Conclusion : The MCDM models could be flexibly applied to other areas of public health as it has shown their reliability in assessing the monkeypox vaccines and can provide a decision guide for different health policy agencies.