Hepatitis B is a potentially deadly liver infection caused by the hepatitis B virus. It is a serious public health problem globally. Substantial efforts have been made to apply machine learning in detecting the virus. However, the application of model interpretability is limited in the existing literature. Model interpretability makes it easier for humans to understand and trust the machine-learning model. Therefore, in this study, we used SHapley Additive exPlanations (SHAP), a game-based theoretical approach to explain and visualize the predictions of machine learning models applied for hepatitis B diagnosis. The algorithms used in building the models include decision tree, logistic regression, support vector machines, random forest, adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost), and they achieved balanced accuracies of 75%, 82%, 75%, 86%, 92%, and 90%, respectively. Meanwhile, the SHAP values showed that bilirubin is the most significant feature contributing to a higher mortality rate. Consequently, older patients are more likely to die with elevated bilirubin levels. The outcome of this study can aid health practitioners and health policymakers in explaining the result of machine learning models for health-related problems.

In recent years, machine learning (ML) has become a pivotal tool for predicting and diagnosing thyroid disease. While many studies have explored the use of individual ML models for thyroid disease detection, the accuracy and robustness of these single-model approaches are often constrained by data imbalance and inherent model biases. This study introduces a filter-based feature selection and stacking-based ensemble ML framework, tailored specifically for thyroid disease detection. This framework capitalizes on the collective strengths of multiple base models by aggregating their predictions, aiming to surpass the predictive performance of individual models. Such an approach can also reduce screening time and costs considering few clinical attributes are used for diagnosis. Through extensive experiments conducted on a clinical thyroid disease dataset, our filter-based feature selection approach and the ensemble learning method demonstrated superior discriminative ability, reflected by an improved receiver operating characteristic - area under the curve (ROC-AUC) scores of 99.9% for the analysis. Our proposed framework sheds light on the complementary strengths of different base models, fostering a deeper understanding of their joint predictive performance. Our findings underscore the potential of ensemble strategies to significantly improve the efficacy of ML-based detection of thyroid diseases, marking a shift from reliance on single models to more robust, collective approaches.

In the present study, we propose and analyze an epidemic mathematical model for malaria dynamics, considering multiple recurrent phenomena: relapse, reinfection, and recrudescence. A limitation in hospital bed capacity, which can affect the treatment rate, is modeled using a saturated treatment function. The qualitative behavior of the model, covering the existence and stability criteria of the endemic equilibrium, is investigated rigorously. The concept of the basic reproduction number of the proposed model is obtained using the concept of the next-generation matrix. We find that the malaria-free equilibrium point is locally asymptotically stable if the basic reproduction number is less than one and unstable if it is larger than one. Our observation on the malaria-endemic equilibrium of the proposed model shows possible multiple endemic equilibria when the basic reproduction number is larger or smaller than one. Hence, we conclude that a condition of a basic reproduction number less than one is not sufficient to guarantee the extinction of malaria from the population. To test our model in a real-life situation, we fit our model parameters using the monthly incidence data from districts in Central Sumba, Indonesia called Wee Luri, which were collected from the Wee Luri Health Center. Using the first twenty months’ data from Wee Luri district, we show that our model can fit the data with a confidence interval of 95%. Both analytical and numerical experiments show that a limitation in hospital bed capacity and reinfection can trigger a more substantial possibility of the appearance of backward bifurcation. On the other hand, we find that an increase in relapse can reduce the chance of the appearance of backward bifurcation. A non-trivial result appears in that a higher probability of recrudescence (treatment failure) does not always result in the appearance of backward bifurcation. From the global sensitivity analysis using a combination of Latin hypercube sampling and partial rank correlation coefficient, we found that the initial infection rate in humans and the mosquito infection rate are the most influential parameters in determining the increase in total new human infections. We expand our model as an optimal control problem by including three types of malaria interventions, namely the use of bed net, hospitalization, and fumigation as a time-dependent variable. Using the Pontryagin maximum principle, we characterize our optimal control problem. Results from our cost-effectiveness analysis suggest that hospitalization only is the most cost-effective strategy required to control malaria disease.

Pneumonia is a dangerous disease that can lead to death without proper treatment. It is caused by a bacterial infection that leads to the inflammation of the air sacs in human lungs and potentially results in a lung abscess if not properly untreated. Here in this article we introduced a novel mathematical model to investigate the potential impact of Pneumonia treatments on disease transmission dynamics. The model is then validated against data from Jakarta City, Indonesia. In the model, the infection stage in infected individuals is categorized into three stages: the Exposed, Congestion and Hepatization, and the Resolution stage. Mathematical analysis shows that the disease-free equilibrium is always locally asymptotically stable when the basic reproduction number is less than one and unstable when larger than one. The endemic equilibrium only exists when the basic reproduction number is larger than one. Our proposed model always exhibits a forward bifurcation when the basic reproduction number is equal to one, which indicates local stability of the endemic equilibrium when the basic reproduction number is larger than one but close to one. A global sensitivity analysis shows that the infection parameter is the most influential parameter in determining the size of the total infected individual in the endemic equilibrium point. Furthermore, we also found that the hospitalization and the acceleration of the treatment duration can be used to control the level of endemic size. An optimal control problem was constructed from the earlier model and analyzed using the Pontryagin Maximum Principle. We find that the implementation of treatment in the earlier stage of infected individuals is needed to avoid a more significant outbreak of Pneumonia in a long-term intervention.

The COVID-19 pandemic has ravaged global health and national economies worldwide. Testing and isolation are effective control strategies to mitigate the transmission of COVID-19, especially in the early stage of the disease outbreak. In this paper, we develop a deterministic model to investigate the impact of testing and compliance with isolation on the transmission of COVID-19. We derive the control reproduction number ${\mathcal{R}}_C$, which gives the threshold for disease elimination or prevalence. Using data from New York State in the early stage of the disease outbreak, we estimate ${\mathcal{R}}_C=7.989$. Both elasticity and sensitivity analyses show that testing and compliance with isolation are significant in reducing ${\mathcal{R}}_C$ and disease prevalence. Simulation reveals that only high testing volume combined with a large proportion of individuals complying with isolation have great impact on mitigating the transmission. The testing starting date is also crucial: the earlier testing is implemented, the more impact it has on reducing the infection. The results obtained here would also be helpful in developing guidelines of early control strategies for pandemics similar to COVID-19.

The COVID-19 pandemic has ravaged almost every part of the world, causing severe loss of life and economic damage to the world economy. This study proposes a mathematical model of SARS-COV-2 by considering the high-risk population. We establish the local and global stability of the model based on a threshold. The local and global sensitivity analysis is conducted to predict the epidemiological parameters responsible for driving the infection. Using the Pontryagin maximum principle and optimal control theory, we included four time-dependent controls to assess the impact of five different strategies on our model. Results from numerical simulation of the model with controls show that the number of infections decreased. Finally, the cost-effectiveness analysis shows the most effective strategy with the lowest intervention cost.