Feature Importance Analysis and Machine Learning for Alzheimer's Disease Early Detection: Feature Fusion of the Hippocampus, Entorhinal Cortex, and Standardized Uptake Value Ratio.

Introduction: Alzheimer's disease (AD) is a progressive neurological disorder characterized by mild memory loss and ranks as a leading cause of mortality in the USA, accounting for approximately 120,000 deaths per year. It is also the primary form of dementia. Early detection is critical for timely intervention as the neurodegenerative process often starts 15-20 years before cognitive symptoms manifest. This study focuses on determining feature importance in AD classification using fused texture features from 3D magnetic resonance imaging hippocampal and entorhinal cortex and standardized uptake value ratio (SUVR) derived from positron emission tomography (PET) images. Methods: To achieve this objective, we employed four distinct classifiers (Linear Support Vector Classification, Linear Discriminant Analysis, Logistic Regression, and Logistic Regression Classifier with Stochastic Gradient Descent Learning). These classifiers were used to derive both average and top-ranked importance scores for each feature based on their outputs. Our framework is designed to distinguish between two classes, AD-negative (or mild cognitive impairment stable [MCIs]) and AD-positive (or MCI conversion [MCIc]), using a probabilistic neural network classifier and the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results: The findings from the feature importance highlight the crucial role of the GLCM texture features extracted from the hippocampus and entorhinal cortex, demonstrating their superior performance compared to the volume and SUVR. GLCM texture AD classification achieved approximately 90% sensitivity in identifying MCIc cases while maintaining low false positives (below 30%) when fused with other features. Moreover, the receiver operating characteristic curves validate the GLCMs' superior performance in distinguishing between MCIs and MCIc. Additionally, fusing different types of features improved classification performance compared to relying solely on any single feature category. Conclusion: Our study emphasizes the pivotal role of GLCM texture features in early Alzheimer's detection.

Design of an automated staff scheduling system for an independent pharmacy.

BACKGROUND: In service industries, employee salaries and wages often constitute the largest portion of the costs to the company. This is very true in the case of an independent pharmacy, which employs pharmacists and pharmacy technicians. Thus, for pharmacies to cost effectively meet the increasing demand for pharmaceuticals, it is crucial that pharmacy managers efficiently allocate the pharmacy staff's time. METHOD: Through a case study, this paper demonstrates the use of an Excel VBA based on a mathematical model to schedule the staff of an independent pharmacy. The whole year data was used in this study. After collection of whole year's data, the number of prescriptions to be filled for each day by hour of hour of the day were sourced and classified. RESULTS: It is indicated that the pharmacy employees' time could be more efficiently assigned to meet the demand of the pharmacy. The benefit of modeling the pharmacy employees at this pharmacy is based on the data (the number of total prescriptions filled on Friday in March) with the following results; 12 h shifts are covered where one employee must be between 04:00-16:00, two employees between 06:00-18:00, one employee between 07:00-19:00 and one employee between 15:00-03:00. CONCLUSION: In this study a basic model was presented that can be used schedule pharmacy employees in an independent pharmacy and solved by Excel VBA. This model can be further extended to meet the needs of a specific pharmacy.

Modeling nurse-patient assignments considering patient acuity and travel distance metrics.

Balancing workload among nurses on a hospital unit is important for the satisfaction and safety of nurses and patients. To balance nurse workloads, direct patient care activities, indirect patient care activities, and non-patient care activities that occur throughout a shift must be considered. The layout of a hospital unit and the location of a nurse's assigned patients relative to other resources on the unit are also important factors in achieving workload balance. In most hospitals, a unit charge nurse is responsible for the shift assignment of patients to nurses based on experience and past practices. The nurse-patient assignment process is also often a manual process in which the charge nurse must sort through multiple decision criteria in a limited amount of time. In this paper, a methodology for the construction of balanced nurse-patient workload assignments is proposed. Through the illustration of this methodology new scoring metrics are developed using measures currently available on, or from, the hospital unit. It was demonstrated that the complex scheduling problem can be captured. While the methodology was illustrated for a scheduling problem commonly encountered on a hospital unit, the approach can be adapted to other workforce scheduling problems in which measures of workload are required and composed of elements imposed by the work environment, variability within the required tasks, and a measurable perception of the relative intensity of the work elements.