Charan Kumari

Pancreatic cancer, characterized by its high mortality rate and scarce treatment options, poses a formidable challenge in the field of oncology. Now, we live in a reality that requires immediate progress in diagnostic and prognostic methodologies to find pancreatic cancer early and understand its stage. This study deals with the pressing requirement for better diagnostic tools by evaluating and deciding the suitable machine learning (ML) algorithms for detecting pancreatic cancer at an early stage. This work uses a publicly available dataset with 590 urine samples which included control, benign hepatobiliary disease as well as Pancreatic Ductal Adenocarcinoma (PDAC) samples. The primary objectives of the research included developing a predictive model based on clinical data, examining various machine learning (ML) algorithms for their diagnostic precision, and improving the early detection rates for pancreatic cancer. The study assessed the efficacy of a broad array of ML algorithms in forecasting outcomes associated with pancreatic cancer. This analysis systematically explored Random Forest, Support Vector Machine, Decision Trees, K-Nearest Neighbours, XGBoost, ADABoost, CatBoost, and GradientBoost. The assessment focused on standard performance metrics such as accuracy, precision (also known as positive predicted value or PPV), recall (sometimes called sensitivity or true positive rate), F1-score, and support. Notably, CatBoost achieved the highest accuracy of 75%, outperforming other models such as Random Forest (74%) and XGBoost (74%), demonstrating its superior classification performance in distinguishing between pancreatic cancer, benign conditions, and non-cancerous cases. In addition to performance evaluation, this study integrates SHAP (Shapley Additive Explanations) analysis to enhance model interpretability, ensuring transparency in feature contributions. SHAP analysis revealed that Plasma CA19-9, LYVE1, and TFF1 were the most influential biomarkers across all classifications, reinforcing their diagnostic significance. This research emphasizes the critical importance of early detection, model interpretability, and clinical applicability, demonstrating that ML algorithms, particularly CatBoost, not only enhance diagnostic precision but also provide explainable predictions that support real-world medical decision-making.

Chronic Kidney Disease (CKD) is considered a leading cause of high morbidity and mortality. Therefore, it needs early detection to allow timely intervention aimed at the enhancement of the patient outcome. The current study presents a Transparent CKD ML which combines the predictive power of efficient ML methods with the eXplainable AI techniques for transparent interpretibility of the prediction. This study has conducted an in-depth performance evaluation of the predictive power of the following eight machine learning algorithms: Logistic Regression, K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, CatBoost, XGBoost, and AdaBoost on the 'Chronic Kidney Disease' dataset provided by UCI Machine Learning Repository. As a further study on algorithm performance, performance measures of accuracy, precision, recall, and F1 score were calculated; it was determined that Logistic Regression, Random Forest, and AdaBoost were performing very well and achieved 100% score in all metrics. This study further combined the ML models with eXplainable AI (XAI) techniques to increase the transparency of the models. SHapley Additive exPlanations (SHAP) an XAI technique was used to provide critical insights into the causality that dictates the predictions of CKD. Thus, this combination ensures the best performance of the model, increasing the trust in AI within clinical practice. The present study, therefore, unleashes the transformational potential of AI technologies in radically renovating the management of CKD and improving patient outcomes across the world.

Risks associated with delivery of a software project and the effort spent on managing these risks are well researched topics. Very few have included this extra effort termed as risk exposure of a project, in the software effort estimate of a project. This research proposes to improve the accuracy of software effort estimates by integrating the risk exposure with the initial effort estimate of the project. A function to calculate integrated effort estimates has been defined and evolutionary algorithms ABC, PSO and GLBPSO have been used to optimize the MMRE. The approach has been tested on two datasets collected from industry, one for waterfall projects, another for agile projects. For both the datasets, integrated effort estimates were more accurate on account of MMRE, standardized accuracy, effect size and R2, than the initial effort estimates. Evolutionary algorithms also gave the optimum weight values at which the MMRE was optimal for both the datasets. These weight values determine the contribution of risk associated with each project cost factor in the risk exposure of the project. Integrated effort estimates have been found to be more accurate, reliable, and comprehensive than the initial effort estimates. Application of evolutionary algorithms help in reducing any bias in the integrated effort estimates.