Optimization in the Context of COVID-19 Prediction and Control: A Literature Review

Overcoming bias in estimating epidemiological parameters with realistic history-dependent disease spread dynamics

Epidemiological parameters such as the reproduction number, latent period, and infectious period provide crucial information about the spread of infectious diseases and directly inform intervention strategies. These parameters have generally been estimated by mathematical models that involve an unrealistic assumption of history-independent dynamics for simplicity. This assumes that the chance of becoming infectious during the latent period or recovering during the infectious period remains constant, whereas in reality, these chances vary over time. Here, we find that conventional approaches with this assumption cause serious bias in epidemiological parameter estimation. To address this bias, we developed a Bayesian inference method by adopting more realistic history-dependent disease dynamics. Our method more accurately and precisely estimates the reproduction number than the conventional approaches solely from confirmed cases data, which are easy to obtain through testing. It also revealed how the infectious period distribution changed throughout the COVID-19 pandemic during 2020 in South Korea. We also provide a user-friendly package, IONISE, that automates this method.

Deep learning in public health: Comparative predictive models for COVID-19 case forecasting

The COVID-19 pandemic has had a significant impact on both the United Arab Emirates (UAE) and Malaysia, emphasizing the importance of developing accurate and reliable forecasting mechanisms to guide public health responses and policies. In this study, we compared several cutting-edge deep learning models, including Long Short-Term Memory (LSTM), bidirectional LSTM, Convolutional Neural Networks (CNN), hybrid CNN-LSTM, Multilayer Perceptron's, and Recurrent Neural Networks (RNN), to project COVID-19 cases in the aforementioned regions. These models were calibrated and evaluated using a comprehensive dataset that includes confirmed case counts, demographic data, and relevant socioeconomic factors. To enhance the performance of these models, Bayesian optimization techniques were employed. Subsequently, the models were re-evaluated to compare their effectiveness. Analytic approaches, both predictive and retrospective in nature, were used to interpret the data. Our primary objective was to determine the most effective model for predicting COVID-19 cases in the United Arab Emirates (UAE) and Malaysia. The findings indicate that the selected deep learning algorithms were proficient in forecasting COVID-19 cases, although their efficacy varied across different models. After a thorough evaluation, the model architectures most suitable for the specific conditions in the UAE and Malaysia were identified. Our study contributes significantly to the ongoing efforts to combat the COVID-19 pandemic, providing crucial insights into the application of sophisticated deep learning algorithms for the precise and timely forecasting of COVID-19 cases. These insights hold substantial value for shaping public health strategies, enabling authorities to develop targeted and evidence-based interventions to manage the virus spread and its impact on the populations of the UAE and Malaysia. The study confirms the usefulness of deep learning methodologies in efficiently processing complex datasets and generating reliable projections, a skill of great importance in healthcare and professional settings.

TGRA-P: Task-driven model predicts 90-day mortality from ICU clinical notes on mechanical ventilation

BACKGROUND

With the outbreak and spread of COVID-19 worldwide, limited ventilators fail to meet the surging demand for mechanical ventilation in the ICU. Clinical models based on structured data that have been proposed to rationalize ventilator allocation often suffer from poor ductility due to fixed fields and laborious normalization processes. The advent of pre-trained models and downstream fine-tuning methods allows for learning large amounts of unstructured clinical text for different tasks. But the hardware requirements of large-scale pre-trained models and purposeless networks downstream have led to a lack of promotion in the clinical domain.

OBJECTIVE

In this study, an innovative architecture of a task-driven predictive model is proposed and a Task-driven Gated Recurrent Attention Pool model (TGRA-P) is developed based on the architecture. TGRA-P predicts early mortality risk from patients' clinical notes on mechanical ventilation in the ICU, which is used to assist clinicians in diagnosis and decision-making.

METHODS

Specifically, a Task-Specific Embedding Module is proposed to fine-tune the embedding with task labels and save it as static files for downstream calls. It serves the task better and prevents GPU overload. The Gated Recurrent Attention Unit (GRA) is proposed to further enhance the dependency of the information preceding and following the text sequence with fewer parameters. In addition, we propose a Residual Max Pool (RMP) to avoid ignoring words in common text classification tasks by incorporating all word-level features of the notes for prediction. Finally, we use a fully connected decoding network as a classifier to predict the mortality risk.

RESULT

The proposed model shows very promising results with an AUROC of 0.8245±0.0096, an AUPRC of 0.7532±0.0115, an accuracy of 0.7422±0.0028 and F1-score of 0.6612±0.0059 for 90-day mortality prediction using clinical notes of ICU mechanically ventilated patients on the MIMIC-III dataset, all of which are better than previous studies. Moreover, the superiority of the proposed model in comparison with other baseline models is also statistically validated through the calculated Cohen's d effect sizes.

CONCLUSION

The experimental results show that TGRA-P based on the innovative task-driven prognostic architecture obtains state-of-the-art performance. In future work, we will build upon the provided code and investigate its applicability to different datasets. The model balances performance and efficiency, not only reducing the cost of early mortality risk prediction but also assisting physicians in making timely clinical interventions and decisions. By incorporating textual records that are challenging for clinicians to utilize, the model serves as a valuable complement to physicians' judgment, enhancing their decision-making process.

Bayesian monitoring of COVID-19 in Sweden

In an effort to provide regional decision support for the public healthcare, we design a data-driven compartment-based model of COVID-19 in Sweden. From national hospital statistics we derive parameter priors, and we develop linear filtering techniques to drive the simulations given data in the form of daily healthcare demands. We additionally propose a posterior marginal estimator which provides for an improved temporal resolution of the reproduction number estimate as well as supports robustness checks via a parametric bootstrap procedure. From our computational approach we obtain a Bayesian model of predictive value which provides important insight into the progression of the disease, including estimates of the effective reproduction number, the infection fatality rate, and the regional-level immunity. We successfully validate our posterior model against several different sources, including outputs from extensive screening programs. Since our required data in comparison is easy and non-sensitive to collect, we argue that our approach is particularly promising as a tool to support monitoring and decisions within public health. Significance: Using public data from Swedish patient registries we develop a national-scale computational model of COVID-19. The parametrized model produces valuable weekly predictions of healthcare demands at the regional level and validates well against several different sources. We also obtain critical epidemiological insights into the disease progression, including, e.g., reproduction number, immunity and disease fatality estimates. The success of the model hinges on our novel use of filtering techniques which allows us to design an accurate data-driven procedure using data exclusively from healthcare demands, i.e., our approach does not rely on public testing and is therefore very cost-effective.

A data-driven optimization model to response to COVID-19 pandemic: a case study

COVID-19 is a highly prevalent disease that has led to numerous predicaments for healthcare systems worldwide. Owing to the significant influx of patients and limited resources of health services, there have been several limitations associated with patients' hospitalization. These limitations can cause an increment in the COVID-19-related mortality due to the lack of appropriate medical services. They can also elevate the risk of infection in the rest of the population. The present study aims to investigate a two-phase approach to designing a supply chain network for hospitalizing patients in the existing and temporary hospitals, efficiently distributing medications and medical items needed by patients, and managing the waste created in hospitals. Since the number of future patients is uncertain, in the first phase, trained Artificial Neural Networks with historical data forecast the number of patients in future periods and generate scenarios. Through the use of the K-Means method, these scenarios are reduced. In the second phase, a multi-objective, multi-period, data-driven two-stage stochastic programming is developed using the acquired scenarios in the previous phase concerning the uncertainty and disruption in facilities. The objectives of the proposed model include maximizing the minimum allocation-to-demand ratio, minimizing the total risk of disease spread, and minimizing the total transportation time. Furthermore, a real case study is investigated in Tehran, the capital of Iran. The results showed that the areas with the highest population density and no facilities near them have been selected for the location of temporary facilities. Among temporary facilities, temporary hospitals can allocate up to 2.6% of the total demand, which puts pressure on the existing hospitals to be removed. Furthermore, the results indicated that the allocation-to-demand ratio can remain at an ideal level when disruptions occur by considering temporary facilities. Our analyses focus on: (1) Examining demand forecasting error and generated scenarios in the first phase, (2) exploring the impact of demand parameters on the allocation-to-demand ratio, total time and total risk, (3) investigating the strategy of utilizing temporary hospitals to address sudden changes in demand, (4) evaluating the effect of disruption to facilities on the supply chain network.

Systematic review of MCDM approach applied to the medical case studies of COVID-19: trends, bibliographic analysis, challenges, motivations, recommendations, and future directions

When COVID-19 spread in China in December 2019, thousands of studies have focused on this pandemic. Each presents a unique perspective that reflects the pandemic's main scientific disciplines. For example, social scientists are concerned with reducing the psychological impact on the human mental state especially during lockdown periods. Computer scientists focus on establishing fast and accurate computerized tools to assist in diagnosing, preventing, and recovering from the disease. Medical scientists and doctors, or the frontliners, are the main heroes who received, treated, and worked with the millions of cases at the expense of their own health. Some of them have continued to work even at the expense of their lives. All these studies enforce the multidisciplinary work where scientists from different academic disciplines (social, environmental, technological, etc.) join forces to produce research for beneficial outcomes during the crisis. One of the many branches is computer science along with its various technologies, including artificial intelligence, Internet of Things, big data, decision support systems (DSS), and many more. Among the most notable DSS utilization is those related to multicriterion decision making (MCDM), which is applied in various applications and across many contexts, including business, social, technological and medical. Owing to its importance in developing proper decision regimens and prevention strategies with precise judgment, it is deemed a noteworthy topic of extensive exploration, especially in the context of COVID-19-related medical applications. The present study is a comprehensive review of COVID-19-related medical case studies with MCDM using a systematic review protocol. PRISMA methodology is utilized to obtain a final set of (n = 35) articles from four major scientific databases (ScienceDirect, IEEE Xplore, Scopus, and Web of Science). The final set of articles is categorized into taxonomy comprising five groups: (1) diagnosis (n = 6), (2) safety (n = 11), (3) hospital (n = 8), (4) treatment (n = 4), and (5) review (n = 3). A bibliographic analysis is also presented on the basis of annual scientific production, country scientific production, co-occurrence, and co-authorship. A comprehensive discussion is also presented to discuss the main challenges, motivations, and recommendations in using MCDM research in COVID-19-related medial case studies. Lastly, we identify critical research gaps with their corresponding solutions and detailed methodologies to serve as a guide for future directions. In conclusion, MCDM can be utilized in the medical field effectively to optimize the resources and make the best choices particularly during pandemics and natural disasters.

Optimizing COVID-19 vaccine allocation considering the target population

Vaccine allocation strategy for COVID-19 is an emerging and important issue that affects the efficiency and control of virus spread. In order to improve the fairness and efficiency of vaccine distribution, this paper studies the optimization of vaccine distribution under the condition of limited number of vaccines. We pay attention to the target population before distributing vaccines, including attitude toward the vaccination, priority groups for vaccination, and vaccination priority policy. Furthermore, we consider inventory and budget indexes to maximize the precise scheduling of vaccine resources. A mixed-integer programming model is developed for vaccine distribution considering the target population from the viewpoint of fairness and efficiency. Finally, a case study is provided to verify the model and provide insights for vaccine distribution.

Development of a Smartphone-Based Expert System for COVID-19 Risk Prediction at Early Stage

COVID-19 has imposed many challenges and barriers on traditional healthcare systems due to the high risk of being infected by the coronavirus. Modern electronic devices like smartphones with information technology can play an essential role in handling the current pandemic by contributing to different telemedical services. This study has focused on determining the presence of this virus by employing smartphone technology, as it is available to a large number of people. A publicly available COVID-19 dataset consisting of 33 features has been utilized to develop the aimed model, which can be collected from an in-house facility. The chosen dataset has 2.82% positive and 97.18% negative samples, demonstrating a high imbalance of class populations. The Adaptive Synthetic (ADASYN) has been applied to overcome the class imbalance problem with imbalanced data. Ten optimal features are chosen from the given 33 features, employing two different feature selection algorithms, such as K Best and recursive feature elimination methods. Mainly, three classification schemes, Random Forest (RF), eXtreme Gradient Boosting (XGB), and Support Vector Machine (SVM), have been applied for the ablation studies, where the accuracy from the XGB, RF, and SVM classifiers achieved 97.91%, 97.81%, and 73.37%, respectively. As the XGB algorithm confers the best results, it has been implemented in designing the Android operating system base and web applications. By analyzing 10 users’ questionnaires, the developed expert system can predict the presence of COVID-19 in the human body of the primary suspect. The preprocessed data and codes are available on the GitHub repository.

Study on the Localization of Fangcang Shelter Hospitals During Pandemic Outbreaks

In the event of pandemic, it is essential for government authority to implement responses to control the pandemic and protect people's health with rapidity and efficicency. In this study, we first develop an evaluation framework consisting of the entropy weight method (EWM) and the technique for order preference by similarity to ideal solution (TOPSIS) to identify the preliminary selection of Fangcang shelter hospitals; next, we consider the timeliness of isolation and treatment of patients with different degrees of severity of the infectious disease, with the referral to and triage in Fangcang shelter hospitals characterized and two optimization models developed. The computational results of Model 1 and Model 2 are compared and analyzed. A case study in Xuzhou, Jiangsu Province, China, is used to demonstrate the real-life applicability of the proposed models. The two-stage localization method gives decision-makers more options in case of emergencies and can effectively designate the location. This article may give recommendations of and new insights into parameter settings in isolation hospital for governments and public health managers.

Spatialized epidemiological forecasting applied to Covid-19 pandemic at departmental scale in France

In this paper, we present a spatialized extension of a SIR model that accounts for undetected infections and recoveries as well as the load on hospital services. The spatialized compartmental model we introduce is governed by a set of partial differential equations (PDEs) defined on a spatial domain with complex boundary. We propose to solve the set of PDEs defining our model by using a meshless numerical method based on a finite difference scheme in which the spatial operators are approximated by using radial basis functions. Such an approach is reputed as flexible for solving problems on complex domains. Then we calibrate our model on the French department of Isère during the first period of lockdown, using daily reports of hospital occupancy in France. Our methodology allows to simulate the spread of Covid-19 pandemic at a departmental level, and for each compartment. However, the simulation cost prevents from online short-term forecast. Therefore, we propose to rely on reduced order modeling to compute short-term forecasts of infection number. The strategy consists in learning a time-dependent reduced order model with few compartments from a collection of evaluations of our spatialized detailed model, varying initial conditions and parameter values. A set of reduced bases is learnt in an offline phase while the projection on each reduced basis and the selection of the best projection is performed online, allowing short-term forecast of the global number of infected individuals in the department. The original approach proposed in this paper is generic and could be adapted to model and simulate other dynamics described by a model with spatially distributed parameters of the type diffusion-reaction on complex domains. Also, the time-dependent model reduction techniques we introduced could be leveraged to compute control strategies related to such dynamics.

Modeling the Impact of the Imperfect Vaccination of the COVID-19 with Optimal Containment Strategy

Since the beginning of the COVID-19 pandemic, vaccination has been the main strategy to contain the spread of the coronavirus. However, with the administration of many types of vaccines and the constant mutation of viruses, the issue of how effective these vaccines are in protecting the population is raised. This work aimed to present a mathematical model that investigates the imperfect vaccine and finds the additional measures needed to help reduce the burden of disease. We determine the R0 threshold of disease spread and use stability analysis to determine the condition that will result in disease eradication. We also fitted our model to COVID-19 data from Morocco to estimate the parameters of the model. The sensitivity analysis of the basic reproduction number, with respect to the parameters of the model, is simulated for the four possible scenarios of the disease progress. Finally, we investigate the optimal containment measures that could be implemented with vaccination. To illustrate our results, we perform the numerical simulations of optimal control.

Solving Patient Allocation Problem during an Epidemic Dengue Fever Outbreak by Mathematical Modelling

Dengue fever is a mosquito-borne disease that has rapidly spread throughout the last few decades. Most preventive mechanisms to deal with the disease focus on the eradication of the vector mosquito and vaccination campaigns. However, appropriate mechanisms of response are indispensable to face the consequent events when an outbreak takes place. This study applied single and multiple objective linear programming models to optimize the allocation of patients and additional resources during an epidemic dengue fever outbreak, minimizing the summation of the distance travelled by all patients. An empirical study was set in Ciudad del Este, Paraguay. Data provided by a privately run health insurance cooperative was used to verify the applicability of the models in this study. The results can be used by analysts and decision makers to solve patient allocation problems for providing essential medical care during an epidemic dengue fever outbreak.