An explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions

Using a clinical narrative-aware pre-trained language model for predicting emergency department patient disposition and unscheduled return visits

The increasing prevalence of overcrowding in Emergency Departments (EDs) threatens the effective delivery of urgent healthcare. Mitigation strategies include the deployment of monitoring systems capable of tracking and managing patient disposition to facilitate appropriate and timely care, which subsequently reduces patient revisits, optimizes resource allocation, and enhances patient outcomes. This study used ∼ 250,000 emergency department visit records from Taipei Medical University-Shuang Ho Hospital to develop a natural language processing model using BlueBERT, a biomedical domain-specific pre-trained language model, to predict patient disposition status and unplanned readmissions. Data preprocessing and the integration of both structured and unstructured data were central to our approach. Compared to other models, BlueBERT outperformed due to its pre-training on a diverse range of medical literature, enabling it to better comprehend the specialized terminology, relationships, and context present in ED data. We found that translating Chinese-English clinical narratives into English and textualizing numerical data into categorical representations significantly improved the prediction of patient disposition (AUROC = 0.9014) and 72-hour unscheduled return visits (AUROC = 0.6475). The study concludes that the BlueBERT-based model demonstrated superior prediction capabilities, surpassing the performance of prior patient disposition predictive models, thus offering promising applications in the realm of ED clinical practice.

Predicting economic resilience of territories in Italy during the COVID-19 first lockdown

This paper aims to predict the economic resilience to crises of territories based on local pre-existing socioeconomic characteristics. Specifically, we consider the case of Italian municipalities during the first wave of the COVID-19 pandemic, leveraging a large-scale dataset of cardholders performing transactions in Point-of-Sales. Based on a set of machine learning classifiers, we show that network-based measures and variables related to the social, economic, demographic and environmental dimensions are relevant predictors of the economic resilience of Italian municipalities to the crisis. In particular, we find accurate classification performance both in balanced and un-balanced scenarios, as well as in the case we restrict the analysis to specific geographical areas. Our analysis predicts that territories with larger income per capita, soil consumption, concentration of real estate activities and commuting network centrality in terms of closeness and Pagerank constitute the set of most affected areas, experiencing the strongest reduction of economic activities during the COVID-19 pandemic. Overall, we provide an application of an early-warning system able to provide timely evidence to policymakers about the detrimental effects generated by natural disasters and severe crisis episodes, thus contributing to optimize public decision support systems.

Risk Factors Associated with COVID-19 Lethality: A Machine Learning Approach Using Mexico Database

Identifying risk factors associated with COVID-19 lethality is crucial in combating the ongoing pandemic. In this study, we developed lethality predictive models for each epidemiological wave and for the overall dataset using the Extreme Gradient Boosting technique and analyzed them using Shapley values to determine the contribution levels of various features, including demographics, comorbidities, medical units, and recent medical information from confirmed COVID-19 cases in Mexico between February 23, 2020, and April 15, 2022. The results showed that pneumonia and advanced age were the most important factors predicting patient death in all cohorts. Additionally, the medical unit where the patient received care acted as a risk or protective factor. IMSS medical units were identified as high-risk factors in all cohorts, except in wave four, while SSA medical units generally were moderate protective factors. We also found that intubation was a high-risk factor in the first epidemiological wave and a moderate-risk factor in the following waves. Female gender was a protective factor of moderate-high importance in all cohorts, while being between 18 and 29 years old was a moderate protective factor and being between 50 and 59 years old was a moderate risk factor. Additionally, diabetes (all cohorts), obesity (third wave), and hypertension (fourth wave) were identified as moderate risk factors. Finally, residing in municipalities with the lowest Human Development Index level represented a moderate risk factor. In conclusion, this study identified several significant risk factors associated with COVID-19 lethality in Mexico, which could aid policymakers in developing targeted interventions to reduce mortality rates.

An augmented Snake Optimizer for diseases and COVID-19 diagnosis

Feature Selection (FS) techniques extract the most recognizable features for improving the performance of classification methods for medical applications. In this paper, two intelligent wrapper FS approaches based on a new metaheuristic algorithm named the Snake Optimizer (SO) are introduced. The binary SO, called BSO, is built based on an S-shape transform function to handle the binary discrete values in the FS domain. To improve the exploration of the search space by BSO, three evolutionary crossover operators (i.e., one-point crossover, two-point crossover, and uniform crossover) are incorporated and controlled by a switch probability. The two newly developed FS algorithms, BSO and BSO-CV, are implemented and assessed on a real-world COVID-19 dataset and 23 disease benchmark datasets. According to the experimental results, the improved BSO-CV significantly outperformed the standard BSO in terms of accuracy and running time in 17 datasets. Furthermore, it shrinks the COVID-19 dataset's dimension by 89% as opposed to the BSO's 79%. Moreover, the adopted operator on BSO-CV improved the balance between exploitation and exploration capabilities in the standard BSO, particularly in searching and converging toward optimal solutions. The BSO-CV was compared against the most recent wrapper-based FS methods; namely, the hyperlearning binary dragonfly algorithm (HLBDA), the binary moth flame optimization with Lévy flight (LBMFO-V3), the coronavirus herd immunity optimizer with greedy crossover operator (CHIO-GC), as well as four filter methods with an accuracy of more than 90% in most benchmark datasets. These optimistic results reveal the great potential of BSO-CV in reliably searching the feature space.

Combating Covid-19 using machine learning and deep learning: Applications, challenges, and future perspectives

COVID-19, a worldwide pandemic that has affected many people and thousands of individuals have died due to COVID-19, during the last two years. Due to the benefits of Artificial Intelligence (AI) in X-ray image interpretation, sound analysis, diagnosis, patient monitoring, and CT image identification, it has been further researched in the area of medical science during the period of COVID-19. This study has assessed the performance and investigated different machine learning (ML), deep learning (DL), and combinations of various ML, DL, and AI approaches that have been employed in recent studies with diverse data formats to combat the problems that have arisen due to the COVID-19 pandemic. Finally, this study shows the comparison among the stand-alone ML and DL-based research works regarding the COVID-19 issues with the combinations of ML, DL, and AI-based research works. After in-depth analysis and comparison, this study responds to the proposed research questions and presents the future research directions in this context. This review work will guide different research groups to develop viable applications based on ML, DL, and AI models, and will also guide healthcare institutes, researchers, and governments by showing them how these techniques can ease the process of tackling the COVID-19.

Predictive models for COVID-19 detection using routine blood tests and machine learning

The problem of accurate, fast, and inexpensive COVID-19 tests has been urgent till now. Standard COVID-19 tests need high-cost reagents and specialized laboratories with high safety requirements, are time-consuming. Data of routine blood tests as a base of SARS-CoV-2 invasion detection allows using the most practical medicine facilities. But blood tests give general information about a patient’s state, which is not directly associated with COVID-19. COVID-19-specific features should be selected from the list of standard blood characteristics, and decision-making software based on appropriate clinical data should be created. This review describes the abilities to develop predictive models for COVID-19 detection using routine blood tests and machine learning.

Predictive modeling for COVID-19 readmission risk using machine learning algorithms

Introduction

The COVID-19 pandemic overwhelmed healthcare systems with severe shortages in hospital resources such as ICU beds, specialized doctors, and respiratory ventilators. In this situation, reducing COVID-19 readmissions could potentially maintain hospital capacity. By employing machine learning (ML), we can predict the likelihood of COVID-19 readmission risk, which can assist in the optimal allocation of restricted resources to seriously ill patients.

Methods

In this retrospective single-center study, the data of 1225 COVID-19 patients discharged between January 9, 2020, and October 20, 2021 were analyzed. First, the most important predictors were selected using the horse herd optimization algorithms. Then, three classical ML algorithms, including decision tree, support vector machine, and k-nearest neighbors, and a hybrid algorithm, namely water wave optimization (WWO) as a precise metaheuristic evolutionary algorithm combined with a neural network were used to construct predictive models for COVID-19 readmission. Finally, the performance of prediction models was measured, and the best-performing one was identified.

Results

The ML algorithms were trained using 17 validated features. Among the four selected ML algorithms, the WWO had the best average performance in tenfold cross-validation (accuracy: 0.9705, precision: 0.9729, recall: 0.9869, specificity: 0.9259, F-measure: 0.9795).

Conclusions

Our findings show that the WWO algorithm predicts the risk of readmission of COVID-19 patients more accurately than other ML algorithms. The models developed herein can inform frontline clinicians and healthcare policymakers to manage and optimally allocate limited hospital resources to seriously ill COVID-19 patients.