Hepatocellular carcinoma (HCC) is the primary liver cancer that occurs the most frequently. The risk of developing HCC is highest in those with chronic liver diseases, such as cirrhosis brought on by hepatitis B or C infection and the most common type of liver cancer. Knowledge-based interpretations are essential for understanding the HCC microarray dataset due to its nature, which includes high dimensions and hidden biological information in genes. When analyzing gene expression data with many genes and few samples, the main problem is to separate disease-related information from a vast quantity of redundant gene expression data and their noise. Clinicians are interested in identifying the specific genes responsible for HCC in individual patients. These responsible genes may differ between patients, leading to variability in gene selection. Moreover, ML approaches, such as classification algorithms, are similar to black boxes, and it is important to interpret the ML model outcomes. In this paper, we use a reliable pipeline to determine important genes for discovering HCC from microarray analysis. We eliminate redundant and unnecessary genes through gene selection using principal component analysis (PCA). Moreover, we detect responsible genes with the random forest algorithm through variable importance ranking calculated from the Gini index. Classification algorithms, such as random forest (RF), naïve Bayes classifier (NBC), logistic regression, and k-nearest neighbor (kNN) are used to classify HCC from responsible genes. However, classification algorithms produce outcomes based on selected genes for a large group of patients rather than for specific patients. Thus, we apply the local interpretable model-agnostic explanations (LIME) method to uncover the AI-generated forecasts as well as recommendations for patient-specific responsible genes. Moreover, we show our pathway analysis and a dendrogram of the pathway through hierarchical clustering of the responsible genes. There are 16 responsible genes found using the Gini index, and CCT3 and KPNA2 show the highest mean decrease in Gini values. Among four classification algorithms, random forest showed $96.53\%$ accuracy with a precision of $97.30\%$. Five-fold cross-validation was used in order to collect multiple estimates and assess the variability for the RF model with a mean ROC of $0.95\pm 0.2$. LIME outcomes were interpreted for two random patients with positive and negative effects. Therefore, we identified 16 responsible genes that can be used to improve HCC diagnosis or treatment. The proposed framework using machine-learning-classification algorithms with the LIME method can be applied to find responsible genes to diagnose and treat HCC patients.

Multifunctional materials have tremendous potential for engineering applications as they are able to convert mechanical to electromagnetic energy and vice-versa. One of the features of this class of materials is that they show significant hysteresis, which needs to be modeled correctly in order to maximize their application potential. A method of modeling multifunctional materials that exhibit the phenomenon of hysteresis and is compatible with the laws of thermodynamics was developed recently. The model is based on the Preisach hysteresis operator and its storage function and may be interpreted as a two-input, two-output neural net with elementary hysteresis operators as the neurons. The difficulty is that the parameters in the model appear in a non-linear fashion, and there are several constraints that must be satisfied by the parameters for thermodynamic compatibility. In this article, we present a novel methodology that uses the rate-independent memory evolution properties of the Preisach operator to split the parameter estimation problem into three numerically well-conditioned, linear least squares problems with constraints. The alternative direction method of multipliers (ADMM) algorithm and accelerated proximal gradient method are used to compute the Preisach weights. Numerical results are presented over data collected from experiments on a Galfenol sample. We show that the model is able to fit not only experimental data for strain and magnetization over a wide range of magnetic fields and stress but also able to predict the response for stress and magnetic fields not used in the parameter estimation.

The lack of conventional methods of estimating real-time infectious disease burden in granular regions inhibits timely and efficient public health response. Comprehensive data sources (e.g., state health department data) typically needed for such estimation are often limited due to 1) substantial delays in data reporting and 2) lack of geographic granularity in data provided to researchers. Leveraging real-time local health system data presents an opportunity to overcome these challenges. This study evaluates the effectiveness of machine learning and statistical approaches using local health system data to estimate current and previous COVID-19 hospitalizations in South Carolina. Random Forest models demonstrated consistently higher average median percent agreement accuracy compared to generalized linear mixed models for current weekly hospitalizations across 123 ZIP codes (72.29 %, IQR: 63.20-75.62 %) and 28 counties (76.43 %, IQR: 70.33-81.16 %) with sufficient health system coverage. To account for underrepresented populations in health systems, we combined Random Forest models with Classification and Regression Trees (CART) for imputation. The average median percent agreement was 61.02 % (IQR: 51.17-72.29 %) for all ZIP codes and 72.64 % (IQR: 66.13-77.69 %) for all counties. Median percent agreement for cumulative hospitalizations over the previous 6 months was 80.98 % (IQR: 68.99-89.66 %) for all ZIP codes and 81.17 % (IQR: 68.55-91.33 %) for all counties. These findings emphasize the effectiveness of utilizing real-time health system data to estimate infectious disease burden. Moreover, the methodologies developed in this study can be adapted to estimate hospitalizations for other diseases, offering a valuable tool for public health officials to respond swiftly and effectively to various health crises.

Since its discovery more than forty years ago, Terfenol-D has promised much but has not yet been fully exploited in applications.The main reason for this is that it shows significant hysteresis and other nonlinearities, such as saturation, which need to be modeled correctly in order to maximize the application potential. In this article, we focus on the characterization of a Terfenol-D sample with the intention of developing a predictive two-input (magnetic field and stress) and two-output (magnetic flux density and strain) model of magnetostriction that exhibits hysteresis and saturation and is compatible with the laws of thermodynamics. Compatibility with thermodynamics is essential to ensure that numerical simulations do not exhibit unphysical behavior. The model is based on the Preisach hysteresis operator and its storage function and may be interpreted as a two-input, two-output neural net with elementary hysteresis operators as the neurons. In order to estimate the parameters, it is necessary to collect data over a wide range of magnetic fields (-300 kA/m to 300 kA/m) and compressive stresses (up to 60 MPa). Using the rate-independent memory evolution properties of the Preisach operator, we split the parameter estimation problem into three numerically well-conditioned, linear least squares problems with constraints. We show that the model is able to fit experimental data for strain and magnetization over a wide range of magnetic fields and stress.

Objectives: Forecasting the effective reproductive number ( R _t ) and infection case counts is critical for guiding public health responses. We developed a machine learning and probabilistic forecasting framework to predict R _t and daily COVID-19 cases, respectively, across South Carolina counties, with the flexibility to generalize to other infectious diseases. Methods: We first estimated R _t using the EpiNow2 R package, which incorporates Bayesian time-series modeling and accounts for reporting delay and incubation period. These initial estimates were refined using spatial covariate-adjusted smoothing through the Integrated Nested Laplace Approximation (INLA). We then generated R _t forecasts using an ensemble of linear regression, random forest, and XGBoost models. Daily case forecasts were obtained by linking R _t trajectories with historical case data via a Poisson model. Results: This ensemble-based approach outperformed EpiNow2 across different forecast horizons (7-day, 14-day, and 21-day). In the first forecast period (November 11, 2020 – February 02, 2021), the ensemble achieved a median PA of 96.5% (IQR: 95.4% – 97.1%) for 7-day horizon R _t forecast, compared to 87.0% (IQR: 84.4% – 89.4%) from EpiNow2. In the second period (December 11, 2022 – March 04, 2023), the ensemble attained a 93.0% median PA for R _t forecast (IQR: 90.8% – 95.4%), while EpiNow2 reached 86.8% (IQR: 82.5% – 89.2%). Similar trends were observed for case forecasts, with the ensemble model demonstrating improved performance. Conclusion: This study presents a flexible forecasting framework that integrates Bayesian estimation, spatial smoothing, and ensemble machine learning to improve the accuracy of COVID-19 transmission and case forecasts. The approach enhances epidemic forecasting performance and offers scalable tools to support data-driven public health preparedness and response.