Healthcare analytics (New York, N.Y.)最新文献

Diabetic retinopathy (DR) is a severe global issue causing blindness if untreated, affecting millions worldwide and worsening over time. Addressing this growing concern necessitates early and accurate DR identification. This study introduces a novel approach to DR detection, combining machine learning algorithms with deep feature extraction techniques. A hybrid model is proposed by stacking predictions from diverse classifiers, such as Decision Trees, Random Forests, Support Vector Machines (SVMs), and more. Three deep learning models – MobileNetV2, DenseNet121, and InceptionResNetV2 – are employed as feature extractors from retinal images. Each classifier undergoes hyperparameter tuning for optimal performance. Using the APTOS 2019 Blindness Detection dataset, including preprocessing techniques like data augmentation and standardization, this hybrid model demonstrates promising accuracy in multi-class (95.50%) and binary classification (98.36%). Notably, DenseNet121 outperforms others. The results suggest the effectiveness of this hybrid technique in early diabetic retinopathy detection, holding significant promise for improved medical intervention.

Listeriosis is a food-borne disease that mainly affects pregnant women and newborns. We propose and analyze a deterministic model of Listeriosis by considering three groups of individuals: newborns, pregnant women, and others. Mathematical analysis of the model is performed, and equilibrium points are determined. The model has three equilibria, namely, the disease-free equilibrium, the bacteria-free equilibrium, and the endemic equilibrium. We use Castillo-Chavez theorem to establish the global stability of the disease-free equilibrium when the basic reproduction number is less than 1. The local asymptotic stability of the bacteria-free, and endemic equilibria are also established using the sign of the eigenvalues of the Jacobian matrix. We use the non-standard finite difference scheme and carried numerical simulations to confirm the theoretical results. We further show the impact of specific parameters on the dynamics of infectious individuals and observe that intervention is required in all the sub-populations by reducing the contact rate and vertical transmission to mininmize the number of infectious.

Diabetes poses a global health challenge, demanding continuous monitoring and expert care for effective management. Conventional monitoring methods lack real-time insights and secure data-sharing capabilities, necessitating innovative solutions that leverage emerging technologies. Existing centralized monitoring systems often entail risks such as data breaches and single points of failure, emphasizing the necessity for a secure, decentralized approach that integrates the Internet of Things (IoT), blockchain, and machine learning for efficient and secure diabetes management. This paper introduces a decentralized, blockchain-based framework for remote diabetes monitoring, IoT sensors, machine learning models, and decentralized applications (DApps). The proposed framework comprises five layers: the IoT Sensor Layer, which collects real-time health data from patients; the Blockchain Layer, leveraging smart contracts on the Ethereum blockchain for secure data sharing and transactions; the machine learning Layer, analyzing patient data to detect diabetes; and the DApps Layer, facilitating interactions between patients, doctors, and hospitals. For intelligent decision-making regarding diabetes based on data collected from different sensors, nine machine learning algorithms, including logistic regression, K-nearest neighbors (KNN), support vector machine (SVM), Decision Tree, Random Forest, AdaBoost, stochastic gradient boosting (SGD), and Naive Bayes, were trained and tested on the PIMA dataset. Based on the performance evaluation parameters such as accuracy, recall, F1-score, and the area under the curve (AUC), it was found that the AdaBoost model achieved the highest predictive accuracy of 92.64%, followed by the Decision Tree with an accuracy of 92.21% in diabetes classification.

Lumpy skin disease (LSD) is an economically significant viral disease of cattle caused by the lumpy disease virus (LSDV) which is primarily spread mechanically by blood feeding vectors such as particular species in flies, mosquitoes and ticks. Despite efforts to control its spread, LSD has been expanding geographically, posing challenges for effective control measures. This study develops a Susceptible–Exposed–Infectious–Recovered–Susceptible (SEIRS) model that incorporates cattle and vector populations to investigate LSD transmission dynamics. The model considers the waning rate of natural active immunity in recovered cattle, disease-induced mortality, and the biting rate. Using a standard dynamical system approach, we conducted a qualitative analysis of the model, defining the invariant region, establishing conditions for solution positivity, computing the basic reproduction number, and examining the stability of disease-free and endemic equilibria. We employ a non-linear least squares method for model calibration, fitting it to a synthetic dataset. We subsequently test it with actual infectious cases data. Results from the calibration and testing phases demonstrate the model’s validity and reliability for diverse settings. Local and global sensitivity analyses were conducted to determine the model’s robustness to parameter values. The biting rate emerged as the most significant parameter, followed by the probabilities of infection from either population and the recovery rate. Additionally, the waning rate of LSD infection-induced immunity gained positive significance in LSD prevalence from the beginning of the infectious period onward. Simulation results suggest reducing the biting rate as the most effective LSD control measure, which can be achieved by applying vector repellents in cattle farms/herds, thereby mitigating the disease’s prevalence in both cattle and vector populations and reducing the chances of infection from either population. Furthermore, measures aiming to boost LSD infection-induced immunity upon recovery are recommended to preserve the immune systems of the cattle population.

Intensive Care Unit (ICU) capacity can be significantly affected by disease outbreaks, epidemics, and pandemics, impeding the operational efficiency of healthcare systems and compromising patient care. This paper presents a multi-stage optimization approach to planning the location and distribution of ICU beds to increase accessibility and reduce mortality caused by a shortage of beds in a geographic region during epidemic events. Using a Brazilian state monthly hospital admissions due to Covid-19 from October 2020 to April 2021, we show the amount and the allocation of extra ICU beds that could reduce mortality, minimize patient travel and transportation, and increase accessibility while considering budget limitations. Our findings show coverage for 21 previously underserved municipalities, providing extra ICU beds for 69 municipalities, ranging from 880 to 1670 beds across seven months. On average, patients are displaced 56% less and access ICUs within 17 ± 2.3 kilometres (CI 95%). The strategy contributes to public health planning and the equitable allocation of hospital resources among the population.

Data augmentation involves artificially expanding a dataset by applying various transformations to the existing data. Recent developments in deep learning have advanced data augmentation, enabling more complex transformations. Especially vital in the medical domain, deep learning-based data augmentation improves model robustness by generating realistic variations in medical images, enhancing diagnostic and predictive task performance. Therefore, to assist researchers and experts in their pursuits, there is a need for an extensive and informative study that covers the latest advancements in the growing domain of deep learning-based data augmentation in medical imaging. There is a gap in the literature regarding recent advancements in deep learning-based data augmentation. This study explores the diverse applications of data augmentation in medical imaging and analyzes recent research in these areas to address this gap. The study also explores popular datasets and evaluation metrics to improve understanding. Subsequently, the study provides a short discussion of conventional data augmentation techniques along with a detailed discussion on applying deep learning algorithms in data augmentation. The study further analyzes the results and experimental details from recent state-of-the-art research to understand the advancements and progress of deep learning-based data augmentation in medical imaging. Finally, the study discusses various challenges and proposes future research directions to address these concerns. This systematic review offers a thorough overview of deep learning-based data augmentation in medical imaging, covering application domains, models, results analysis, challenges, and research directions. It provides a valuable resource for multidisciplinary studies and researchers making decisions based on recent analytics.

Tuberculosis is a pressing global health concern, particularly pervasive in many developing nations. This study investigates the influence of treatment failure on tuberculosis control strategies, incorporating vaccination interventions using a deterministic compartmental epidemiological model. Mathematical analysis unveils disease-free and endemic equilibrium points, with the control reproduction number determined using next-generation methods. Identifying endemic equilibrium points and determining the control reproduction number provide essential metrics for assessing the effectiveness of control strategies and guiding policy decisions. The model exhibits a backward bifurcation phenomenon, leading to multiple endemic equilibria despite a reproduction number below one due to reinfection. Sensitivity analysis using Latin Hypercube Sampling/Partial Rank Correlation Coefficient elucidates parameter impacts on the control reproduction number. Vaccination efficacy is crucial for quality and validity, with superior quality and longer validity yielding more significant effects. While reinfection may not directly affect the reproduction number, its influence is pivotal in determining tuberculosis persistence or extinction. This study underscores the intricate interplay of factors in tuberculosis control strategies, providing insights vital for effective interventions and policy formulation.

Population aging is a global challenge, leading to increased demand for health care and social services for the elderly. Home Health Care (HHC) is a vital solution to serve this segment of the population. Given the increasing demand for HHC, it is essential to coordinate and regulate caregiver allocation efficiently. This is crucial for both budget-optimized planning and ensuring the delivery of high-quality care. This research addresses a fundamental question in home health agencies (HHAs): “How can caregiver allocation be optimized, especially when caregivers prefer flexibility in their visit sequences?”. While earlier studies proposed rigid visiting sequences, our study introduces a decision support framework that allocates caregivers through a hybrid method that considers the flexibility in visiting sequences and aims to reduce travel mileage, increase the number of visits per planning period, and maintain the continuity of care – a critical metric for patient satisfaction. Utilizing data from an HHA in Tennessee, United States, our approach led to an impressive reduction in average travel mileage (up to 42%, depending on discipline) without imposing restrictions on caregivers. Furthermore, the proposed framework is used for caregivers’ supply analysis to provide valuable insights into caregiver resource management.