Degradation branching in systems with inter-dependent units is a common phenomenon in many real-life applications, particularly in biomechanical and healthcare systems. In such processes, the degradation of one unit may initiate spontaneously or be triggered by the degradation of the adjacent units, leading to spatially correlated failure behaviors. This paper develops a general stochastic degradation branching model that characterizes both the inter-dependency of degradation initiation times and the inter-dependency of degradation growth rates among units. Analytical formulations are derived for the probabilistic properties of the branching process, including the probability distribution of degradation of the system that has specific combination of degraded components, the overall system degradation, along with system reliability. The model is validated using longitudinal cervical spine degeneration data, demonstrating its ability to capture spontaneous and propagation-induced degradation patterns among vertebrae. Beyond theoretical modeling, the proposed framework provides clinically and socially relevant insights: it supports individualized degeneration risk assessment, optimization of surgical and rehabilitation timing, and evidence-based healthcare resource allocation, while also offering a quantitative basis for medical insurance policy design by estimating population-level degeneration trajectories. This unified stochastic framework thus strengthens the translational linkage between reliability theory, precision medicine, and healthcare management.

The use of electronic health record (EHR) tabular data for clustering has garnered global attention for its potential to uncover meaningful clusters, improve patient care and advance healthcare research. Applications of EHR data extend beyond healthcare to include financial modeling, fraud detection, differential diagnosis and rare disease identification. However, critical challenges persist, including privacy concerns, limited access to real EHR data, underexplored generative methods and inadequate validation frameworks. This study aims to generate and validate synthetic EHR tabular data and demonstrate its utility in clustering, addressing existing gaps in privacy, data quality and validation. Advanced deep learning architectures, including Generative Adversarial Networks (GANs), were developed to generate high-quality synthetic datasets. We implemented robust validation frameworks that incorporate fidelity, utility and privacy-preserving mechanisms. Dirichlet Process Mixture Models (DPMMs) used synthetic data to group similar items and measured the differences between real and synthetic data distributions by estimating divergence. GANs effectively replicated complex datasets while balancing fidelity, utility and privacy. Validation confirmed the robustness of DPMMs in identifying latent structures. Cluster analysis revealed significant multimorbidity patterns, facilitating personalized treatment strategies, resource allocation and preventive care. This study demonstrates the transformative potential of synthetic EHR data in clustering, advancing healthcare delivery, planning and research.

The incidence of Valley Fever can be predicted using a Poisson regression model, which links the expected incidence count to influential covariates with model coefficients. In real-world practice, the estimated model coefficients are sensitive to the inevitable measurement errors in the covariates, which are usually manifested as classical errors and/or Berkson errors. While conventional methods have separately addressed each type of error, the joint consideration of both, referred to as mixture measurement error in this article, is currently absent from the existing literature, leaving model coefficient estimators with significant biases. This article presents a measurement-error tolerant Poisson regression to mitigate the impacts of the mixture measurement error in covariates of health-care data analysis. An error-structureadapted quasi-likelihood estimation method is proposed to enhance the accuracy of model estimation. The effectiveness of the proposed method is demonstrated through a numerical case study built upon a Valley Fever investigation, validating its improved estimation accuracy and robustness.

Waning immunity to the SARS-CoV-2 virus and the inevitability of viral mutations necessitate a large-scale periodic revaccination program. Rapid mass vaccination may quickly suppress an epidemic, but it may have an unintended downstream effect of creating a surge in population susceptibility later when vaccinated people lose their immunity all at the same time. To test this hypothesis, we conducted a simulation study comparing pulse vaccination, the repeated administration of “booster” vaccines in large pulses occurring at fixed intervals, and constant vaccination, the continuous administration of booster vaccines at a slower, constant pace. We showed that constant vaccination can maintain population susceptibility and therefore incident deaths at a constant, manageable level; while pulse vaccination can induce large recurrent epidemics. The advantage of constant vaccination is only realized, however, in a post-pandemic scenario when a high level of population immunity has already been attained through a combination of vaccination and natural infection. At the beginning of a novel pandemic, aggressive vaccination is recommended to prioritize immediate protection over long-term protection. In a counterfactual analysis, we showed that prematurely switching to constant vaccination would have significantly increased the disease burden during the Delta variant wave in August 2021.

Machine learning has shown great promise for integrating multi-modality neuroimaging datasets to predict the risk of progression/conversion to Alzheimer’s Disease (AD) for individuals with Mild Cognitive Impairment (MCI). Most existing work aims to classify MCI patients into converters versus non-converters using a pre-defined timeframe. The limitation is a lack of granularity in differentiating MCI patients who convert at different paces. Progression pace prediction has important clinical values, which allow from more personalized interventional strategies, better preparation of patients and their caregivers, and facilitation of patient selection in clinical trials. We proposed a novel ADPacer model which formulated the pace prediction into an ordinal learning problem with a unique capability of leveraging training samples with label ambiguity to augment the training set. This capability differentiates ADPacer from existing ordinal learning algorithms. We applied ADPacer to MCI patient cohorts from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarker & Lifestyle Flagship Study of Aging (AIBL), and demonstrated the superior performance of ADPacer compared to existing ordinal learning algorithms. We also integrated the SHapley Additive exPlanations (SHAP) method with ADPacer to assess the contributions from different modalities to the model prediction. The findings are consistent with the AD literature.

Electronic health records (EHRs) and other computerized systems facilitate the timely exchange of patients’ health information between providers across different departments and organizations. This study investigates the types and trends of electronic information exchange between doctors and the factors that impact electronic information exchange. We used data from the National Electronic Health Records Survey. Logistic regression models were run to explore the predictors of doctors’ satisfaction with EHRs for information exchange. The models were adjusted to practice type and size and clinical specialty. A total of 1,524 physicians completed cross-sectional questionnaires. Low satisfaction with EHRs was correlated with the inability of providers to exchange information electronically and with difficulty in clinical care documentation. We found that doctors who perceived EHRs to improve their practices’ quality, efficiency, and care coordination were more satisfied with EHRs. They also preferred EHR systems that help them reduce errors (odds ratio (OR) = 2.69, p = 0.008) and prevent duplicate test orderings (OR = 2.33, p = 0.023). Furthermore, factors such as difficulty integrating information into the system, use problems, and time consumption negatively impacted doctors’ perception of EHR use. Doctors’ satisfaction with EHR use was associated with meaningful functionality, namely the ability to enhance care coordination, the ability to improve information availability and quality, work environment and logistic factors, and design characteristics. Improving the design of EHR systems is essential but may not be sufficient for successful and efficient electronic information exchange between doctors. Usability more broadly with data management including external data should be prioritized.

The global extent of COVID-19 mutations and the consequent depletion of hospital resources highlighted the necessity of effective computer-assisted medical diagnosis. COVID-19 detection mediated by deep learning models can help diagnose this highly contagious disease and lower infectivity and mortality rates. Computed tomography (CT) is the preferred imaging modality for building automatic COVID-19 screening and diagnosis models. It is well-known that the training set size significantly impacts the performance and generalization of deep learning models. However, accessing a large dataset of CT scan images from an emerging disease like COVID-19 is challenging. Therefore, data efficiency becomes a significant factor in choosing a learning model. To this end, we present a multi-task learning approach, namely, a mask-guided attention (MGA) classifier, to improve the generalization and data efficiency of COVID-19 classification on lung CT scan images. The novelty of this method is compensating for the scarcity of data by employing more supervision with lesion masks, increasing the sensitivity of the model to COVID-19 manifestations, and helping both generalization and classification performance. Our proposed model achieves better overall performance than the single-task (without MGA module) baseline and state-of-the-art models, as measured by various popular metrics.

Wrist-worn wearables, with sensors to measure physiological responses such as heart rate variability (HRV) and electrodermal activity (EDA), have been increasing and have the potential to be used for continuous monitoring. These devices have been used to detect responses in workers’ physical and cognitive demands; however, the accuracy of wrist wearables for distinguishing these demands is unknown, especially since many every day and work activities frequently require motion. The objective of this study was to evaluate the effectiveness of a wrist-worn wearable in measuring physiological changes during different demand conditions. Participants (n = 20 college students) completed a multi-factor laboratory study that considered task (cognitive/physical), difficulty (easy/hard), and motion (motion/no motion). N-back tasks and stationary bike tasks were used to represent cognitive and physical demands, respectively. Metrics of HRV and EDA were measured using reference-standard devices and a validated wrist-wearable. Significant differences between task, motion, and difficulty were observed from HRV measurements from the reference-standard and wrist-worn devices. Wrist wearables are sensitive to detecting workplace demands and may be used as an alternative to reference-standard sensors for continuous health and activity monitoring for worker health and wellness. Findings in this study can provide guidelines on task and conditions that affect the use and interpretation of wrist-worn devices for measuring cognitive and physical demands in healthcare systems. HIGHLIGHTS Applications for noninvasive, wrist-worn sensors can be used for continuous health and exercise monitoring HRV and EDA metrics obtained from wrist-worn device are sensitivity in detecting changes in task, difficulty, and motion HRV metric from wrist-worn device had agreement with reference-standard device Wrist-wearables has potential for ubiquitous health monitoring of individuals

We designed a model for hospital selection and patient transport in the emergency medical system. The model integrates the criterium of insurance coverage, seldom used in the literature and the usual criteria such as care capacities, congestion and proximity, typical of countries with mixed health systems (public-private). In addition, the model considered the travel and waiting times in emergency departments as performance measures in different time slots and days of the week. We developed and implemented a prototype in the Python programming language connecting to web services from Google Maps API (Directions, Maps JavaScript) to support the decision-making process in real-time and tested its performance. This research study validated the model with actual data from events managed by the emergency medical system in a Colombian city. We used Monte Carlo simulation to predict the current and proposed models’ travel and transfer time (travel time + waiting time). The simulation results indicate that the proposed model, which considers insurance coverage, emergency departments capacities, congestion and proximity, has a lower probability of putting at risk the lives of critically ill patients. In addition, non-critical patient satisfaction increases as wait times decrease.