Mohammad A. Shbool

Bio: Mohammad A. Shbool is an academic researcher from University of Jordan. The author has contributed to research in topics: Medicine & Supply chain. The author has an hindex of 3, co-authored 9 publications receiving 44 citations. Previous affiliations of Mohammad A. Shbool include University of Arkansas & Jordan University of Science and Technology.

Multi-criteria end milling parameters optimization of AISI D2 steel using genetic algorithm

Abstract: This paper focuses on using multi-criteria optimization approach in the end milling machining process of AISI D2 steel. It aims to minimize the cost caused by a poor surface roughness and the electrical energy consumption during machining. A multi-objective cost function was derived based on the energy consumption during machining, and the extra machining needed to improve the surface finish. Three machining parameters have been used to derive the cost function: feed, speed, and depth of cut. Regression analysis was used to model the surface roughness and energy consumption, and the cost function was optimized using a genetic algorithm. The optimal solutions for the feed and speed are found and presented in graphs as functions of extra machining and electrical energy cost. Machine operators can use these graphs to run the milling process under optimal conditions. It is found that the optimal values of the feed and speed decrease as the cost of extra machining increases and the optimal machining condition is achieved at a low value of depth of cut. The multi-criteria optimization approach can be applied to investigate the optimal machining parameters of conventional manufacturing processes such as turning, drilling, grinding, and advanced manufacturing processes such as electrical discharge machining.

An integrated multi-criteria decision-making framework for a medical device selection in the healthcare industry

Abstract: Medical devices used in healthcare organizations are costly, and the process of selecting these devices requires considering multiple criteria such as effectiveness and ease of use. Careful selecti...

Decision-Making Framework for Evaluating Physicians’ Preference Items Using Multi-Objective Decision Analysis Principles

Abstract: Physician preference items or PPIs are medical items recommended by physicians for use in medical procedures and other treatments. The recommendation of PPIs by individual physicians can cause the variety of item types that need to be managed within a health care supply chain to increase over time. To better manage the PPI selection process, healthcare organizations often select items through value analysis and discussion teams, which are highly subjective. To better control PPIs, this work uses multiple-objective decision analysis (MODA) to develop a structured quantitative framework for the PPI selection process. The established decision-making framework is based on the theory of multi-objective value analysis. It offers a structured and educated guide to decision-makers for improving value analysis outcomes, advocating sustainable healthcare management strategies. The model was tested and validated through two case studies on two different items in two hospitals in Jordan.

Computer Methods and Programs in Biomedicine

Abstract: Background and objective: Automatic detection and classification of the masses in mammograms are still a big challenge and play a crucial role to assist radiologists for accurate diagnosis. In this paper, we propose a novel Computer-Aided Diagnosis (CAD) system based on one of the regional deep learning techniques, a ROI-based Convolutional Neural Network (CNN) which is called You Only Look Once (YOLO). Although most previous studies only deal with classification of masses, our proposed YOLO-based CAD system can handle detection and classification simultaneously in one framework. Methods: The proposed CAD system contains four main stages: preprocessing of mammograms, feature extraction utilizing deep convolutional networks, mass detection with confidence, and finally mass classification using Fully Connected Neural Networks (FC-NNs). In this study, we utilized original 600 mammo- grams from Digital Database for Screening Mammography (DDSM) and their augmented mammograms of 2,400 with the information of the masses and their types in training and testing our CAD. The trained YOLO-based CAD system detects the masses and then classifies their types into benign or malignant. Results: Our results with five-fold cross validation tests show that the proposed CAD system detects the mass location with an overall accuracy of 99.7%. The system also distinguishes between benign and malignant lesions with an overall accuracy of 97%. Conclusions: Our proposed system even works on some challenging breast cancer cases where the masses exist over the pectoral muscles or dense regions.