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

This study explores the multispecies Lotka-Volterra population dynamics models, a captivating nonlinear mathematical framework with significant applications in natural sciences and environmental studies. The primary objective is to deliver precise solutions for these models using the New Iterative Method (NIM). Numerical simulations are conducted on three distinct types of nonlinear dynamic problems, comparing the accuracy of the NIM with that of the Perturbation Iteration Algorithm (PIA), existing exact solutions, and the traditional fourth-order Runge–Kutta method. A continuous step time of Δ = 0.001 was used for the Runge–Kutta method in all computations. Notably, the NIM's solutions for the nonlinear multispecies Lotka-Volterra models demonstrate very good accuracy, achieving convergence to the Runge–Kutta method's solutions within five iterations. The correctness of the NIM is found to be better than the other existing solutions. Its distinctive attribute lies in its computational efficiency, providing high accuracy without necessitating linearization, discretization, multipliers, or polynomials for nonlinear terms. This leads to simpler solution procedures while maintaining commendable accuracy. The findings underscore NIM's reliability and broad applicability in both linear and nonlinear models, highlighting its potential as an invaluable tool in numerical computation.

The Integration of machine learning and traditional image processing in dentistry has resulted in many applications like automatic teeth identification and numbering, caries, anomaly, disease detection, and dental treatment prediction. They have a broad scope in different applications observed in the dentistry literature review. This study reviews the literature on deep learning and dental radiograph analysis. We present an overview of machine learning algorithms in different areas of dentistry: tooth identification and numbering, Dental disease detection, and dental predictive treatment models. The methods under each area are briefly discussed. The dental radiograph data set required for performing experiments is summarized from the available literature. The study concludes by discussing new research opportunities and initiatives in this field. This paper offers a comprehensive overview of this innovative, challenging, and growing area in dentistry.

Blockchain technology and the Internet of Medical Things (IoMT) have garnered increased attention recently due to their growing application in effectively managing data security, storage, and transmission concerns within healthcare organizations. However, integrating various advancements, such as coordination, adaptivity, and automated responses, within the framework of blockchain-based IoMT has amplified its susceptibility to a range of attacks and vulnerabilities. Assessing and enhancing the resilience of blockchain-based IoMT is of utmost importance, particularly in anticipation of potential disruptions, to ensure its continuous and sustainable functionality. The stochastic nature of risks adds complexity to evaluating the resilience of blockchain-based IoMT, given that resilience in this domain may fluctuate over time. This study employs a dynamic Bayesian network (DBN) method to address the evolving characteristics of pertinent variables, capturing their temporal dependencies and demonstrating how the resilience capabilities of blockchain-based IoMT may evolve across different time intervals. Additionally, an information theory approach is adopted to mitigate uncertainty regarding the resilience performance of blockchain-based IoMT and its crucial subcomponents. This research showcases the effectiveness and adaptability of the DBN methodology in healthcare systems, offering insights for shaping appropriate and essential strategies for decision-makers to establish a highly resilient framework for blockchain-based IoMT.

Diphtheria is an infectious disease caused by a strain of Corynebacterium diphtheria and forms part of the childhood vaccine-preventable diseases. The Diphtheria vaccine is a component of one of the routine vaccines given to children thrice before their first birthday. The protection against diphtheria derived from the diphtheria vaccine in infancy wanes in later childhood, necessitating a booster dose to protect the child as they grow older. To determine the impact of a booster dose of the diphtheria vaccine amidst a contaminated environment, a diphtheria model that incorporates a vaccine booster and a contaminated environment is formulated. The reproduction number R0 is computed and used to prove the local and global stability of the disease-free equilibrium. Global sensitivity analysis is conducted via the application of Latin Hypercube Sampling (LHS) with a Partial Rank Correlation coefficient on the infected humans and the contaminated environment to deduce the most sensitive parameters of the dynamics of diphtheria disease. Then, the model is further extended based on the result of the global sensitivity analysis by introducing four time-dependent controls, disinfection, screening/treatment, booster vaccination, and hygiene practice, to form an optimal control model. The control model is analyzed using Pontryagin’s maximum principle. The numerical simulation shows that diphtheria disease will reduce drastically in the community if any control combination involves booster vaccination since the diphtheria vaccine in infancy wanes after ten years. In a situation where there are limited resources to implement all the controls simultaneously, it is recommended to implement any two of the combined controls: disinfection of the environment and administration of booster vaccination or screening/treatment of the asymptomatic infected and administration of booster vaccination. The study shows that the best combination is to disinfect the environment, screen/treat the asymptomatic infected humans, and administer booster vaccination to the community.

COVID-19 is a virus that can cause severe pneumonia, and the severity varies based on the patient's immune system. The rapid spread of the disease can be mitigated through automated detection, addressing the shortage of radiologists in medicine. This paper introduces the Modified-Inception V3 (MIn-V3) model, which utilizes feature fusion from the internal layers of Inception V3 to classify different diseases, including normal cases, COVID-19 positivity, viral pneumonia, and bacterial pneumonia. Additionally, transfer learning and fine-tuning techniques are applied to enhance accuracy. The performance of MIn-V3 is assessed by comparing it with pre-trained Deep Learning (DL) models, such as Inception-ResNet V2 (InRN-V2), Inception V3, and MobileNet V2. Experimental results demonstrate that the MIn-V3 model surpasses other pre-trained models with a classification accuracy of 96.33 %. Furthermore, integrating the MIn-V3 model into a mobile application enables rapid and accurate detection of COVID-19, thus playing a crucial role in advancing early diagnostics, which is essential for timely intervention and effective disease management.

Pneumonia is the leading infectious disease that threatens the lives of children under five and elders over 65. It is an infection that is commonly caused by Streptococcus pneumoniae. In this study, an age-structured (children and elders) model for pneumonia was formulated and analyzed to determine the impact of treatment and proper nutrition on the transmission dynamics of the disease in the two age groups. The effective reproduction number ($R_e$) was determined using the next-generation method. The disease-free equilibrium point was determined and found locally and globally asymptotically stable if $R_e<1$. Sensitivity analysis of the model parameters was performed using the normalized forward sensitivity index method, and the findings show that transmission rates are the most positive parameters to the effective reproduction number, while proper nutrition was the most negatively sensitive parameter. Additionally, numerical simulations were performed, and it was observed that the combination of proper nutrition and treatment was more effective in reducing the number of pneumonia-infected individuals. The study encourages the joint use of proper nutrition and treatment to control pneumonia transmission among children and elders, especially in the developing world, where economic constraints, infrastructure, and distribution challenges limit vaccine availability.

Androgen deprivation therapy (ADT) is frequently used to treat prostate cancer which is a widespread disease having a very low survival rate. A prolonged course of ADT can increase toxicity and drug resistance. This study proposes an adaptive therapy combining chemotherapy or immunotherapy with the discontinuation of hormone therapy to overcome these obstacles. The super-twisting sliding mode control (STSMC) algorithm is found to be one of the effective approach as an ADT model for obtaining suitable dosage adaptively. The primary objective is to rapidly reduce the number of cancer cells and the duration of drug exposure. The Takagi–Sugeno fuzzy controller-based active control algorithm is introduced, and it’s performance is compared with the STSMC algorithm. While maintaining global asymptotic stability, the Takagi–Sugeno fuzzy controller reduces the duration of therapy to six months. The controllers are implemented utilizing the linear matrix inequality (LMI) algorithm and the yet another LMI (YALMIP) toolset for MATLAB, and their efficacy is validated utilizing MATLAB and Simulink simulations. This study presents a novel approach to improve prostate cancer treatment outcomes by integrating nonlinear control algorithms and adaptive dosage strategies to reduce treatment duration and minimize drug exposure, thereby improving patient outcomes in prostate cancer management.

The recent outbreak of the novel coronavirus (COVID-19) pandemic has devastated many parts of the globe. Non-pharmaceutical interventions are the widely available measures to combat and control the COVID-19 pandemic. There is great concern over the rampant unaccounted cases of individuals skipping the border during this critical period in time. We develop a deterministic compartmental model to investigate the impact of escapees (individuals who evade mandatory quarantine) on the transmission dynamics of COVID-19. A suitable Lyapunov function has shown that the disease-free equilibrium is globally asymptotically stable, provided $R_0<1$. We performed a global sensitivity analysis using the Latin-hyper cube sampling method and partial rank correlation coefficients to determine the most influential model parameters on the short and long-term dynamics of the pandemic to minimize uncertainties associated with our variables and parameters. Results confirm a positive correlation between the number of escapees and the reported COVID-19 cases. It is shown that escapees are primarily responsible for the rapid increase in local transmissions. Also, the results from sensitivity analysis show that an increase in governmental role actions and a reduction in the illegal immigration rate will help to control and contain the disease spread.

A novel fractional derivative model with nine compartments is formulated to investigate the transmission dynamics of zika and dengue co-infection. The Atangana–Baleanu fractional derivative in the Caputo sense was employed. The conditions for a unique solution are identified, and the solutions’ positivity and boundedness are demonstrated. The disease-free equilibrium point (DFE) and basic reproduction number, R₀, were obtained. The DFE was shown to be locally asymptotically stable when the basic reproduction number is less than one. Zika-associated reproduction number, R_0z, and dengue-associated reproduction number, R_0d, were estimated to be 1.0144 and 1.1724, respectively. The system was shown to be generalized Ulam Hyers–Rassias stable, and the Adam–Bashforth method was used to provide its’ numerical solution. Sensitivity analysis using the Latin Hyper-cube Sampling (LHS) and Partial Rank Correlation Coefficient (PRCC) (|PRCC|> 0.45) with 200 runs was carried out using various variables as response functions per time. The most significant parameters were found to be zika human-to-human transmission rate, $\beta$ _hz1, vector death rate, $\mu$ _v, zika recovery rate, $\gamma$ _hz1 and dengue vector-to-human transmission rate, $\beta$ _hd. Real data from Espirito Santo in Brazil is used to validate the model and fit needed parameter values. Numerical simulations illustrated the impact of varying the fractional order derivative, recovery rates, transmission rates, and cross-enhancement parameters on the infected human compartments. The zika Human-to-human transmission rate, $\beta$ _hz1, was found to be a very significant parameter in the control of zika disease transmission. Increasing the vector death rate, $\mu$ _v, was more important in curbing dengue prevalence and incidence than the attainment of recovery from the dengue disease, and the absence of the zika Vector-to-human transmission rate, $\beta$ _hz3, was almost insignificant in the presence of the zika Human-to-human transmission rate, $\beta$ _hz1, for disease eradication. This study suggested control measures and strategies to decrease the dengue and zika human-to-human transmission rates.

The Centers for Medicare and Medicaid Services (CMS) provides annual reports of costs, charges, utilization, payment, penalty, payroll, and general institutional characteristics for thousands of Medicare-certified hospitals. However, beyond the small fraction of features offered in dated finalized public use files, the size and complexity of cost report data can make it difficult to use. To gain a greater breadth of up-to-date insights, hospitals and researchers must either pay for third party services or acquire the appropriate expertise. To democratize insights into cost report data, we first developed an open-source public repository of 6908 hospital-specific dataset, each containing 2843 labeled features and spanning years between 2010 and 2023. We then developed an open-source application for analyzing and downloading these data. Users can download and run the application locally or access it online (https://hcris-app.herokuapp.com/), and compare cost report features among hospitals and across time, explore relationships between features, and design new cost report variables. As examples of insights gained from our application, we present results from comparing Rush University Medical Center to 66 non-governmental acute care Illinois hospitals. We look forward to developing our open-source resources according to feedback from the healthcare community.