Design of an artificial neural network to predict mortality among COVID-19 patients

Utilizing machine learning to predict hospital admissions for pediatric COVID-19 patients (PrepCOVID-Machine)

The COVID-19 pandemic has burdened healthcare systems globally. To curb high hospital admission rates, only patients with genuine medical needs are admitted. However, machine learning (ML) models to predict COVID-19 hospitalization in Asian children are lacking. This study aimed to develop and validate ML models to predict pediatric COVID-19 hospitalization. We collected secondary data with 2200 patients and 65 variables from Malaysian aged 0 to 12 with COVID-19 between 1st February 2020 and 31st March 2022. The sample was partitioned into training, internal, and external validation groups. Recursive Feature Elimination (RFE) was employed for feature selection, and we trained seven supervised classifiers. Grid Search was used to optimize the hyperparameters of each algorithm. The study analyzed 1988 children and 30 study variables after data were processed. The RFE algorithm selected 12 highly predicted variables for COVID-19 hospitalization, including age, male sex, fever, cough, rhinorrhea, shortness of breath, vomiting, diarrhea, seizures, body temperature, chest indrawing, and abnormal breath sounds. With external validation, Adaptive Boosting was the highest-performing classifier (AUROC = 0.95) to predict COVID-19 hospital admission in children. We validated AdaBoost as the best to predict COVID-19 hospitalization among children. This model may assist front-line clinicians in making medical disposition decisions.

Prediction the prognosis of the poisoned patients undergoing hemodialysis using machine learning algorithms

BACKGROUND

Hemodialysis is a life-saving treatment used to eliminate toxins and metabolites from the body during poisoning. Despite its effectiveness, there needs to be more research on this method precisely, with most studies focusing on specific poisoning. This study aims to bridge the existing knowledge gap by developing a machine-learning prediction model for forecasting the prognosis of the poisoned patient undergoing hemodialysis.

METHODS

Using a registry database from 2016 to 2022, this study conducted a retrospective cohort study at Loghman Hakim Hospital. First, the relief feature selection algorithm was used to identify the most important variables influencing the prognosis of poisoned patients undergoing hemodialysis. Second, four machine learning algorithms, including extreme gradient boosting (XGBoost), histgradient boosting (HGB), k-nearest neighbors (KNN), and adaptive boosting (AdaBoost), were trained to construct predictive models for predicting the prognosis of poisoned patients undergoing hemodialysis. Finally, the performance of paired feature selection and machine learning (ML) algorithm were evaluated to select the best models using five evaluation metrics including accuracy, sensitivity, specificity the area under the curve (AUC), and f1-score.

RESULT

The study comprised 980 patients in total. The experimental results showed that ten variables had a significant influence on prognosis outcomes including age, intubation, acidity (PH), previous medical history, bicarbonate (HCO3), Glasgow coma scale (GCS), intensive care unit (ICU) admission, acute kidney injury, and potassium. Out of the four models evaluated, the HGB classifier stood out with superior results on the test dataset. It achieved an impressive mean classification accuracy of 94.8%, a mean specificity of 93.5 a mean sensitivity of 94%, a mean F-score of 89.2%, and a mean receiver operating characteristic (ROC) of 92%.

CONCLUSION

ML-based predictive models can predict the prognosis of poisoned patients undergoing hemodialysis with high performance. The developed ML models demonstrate valuable potential for providing frontline clinicians with data-driven, evidence-based tools to guide time-sensitive prognosis evaluations and care decisions for poisoned patients in need of hemodialysis. Further large-scale multi-center studies are warranted to validate the efficacy of these models across diverse populations.

Machine learning approach to evaluate TdP risk of drugs using cardiac electrophysiological model including inter-individual variability

Introduction: Predicting ventricular arrhythmia Torsade de Pointes (TdP) caused by drug-induced cardiotoxicity is essential in drug development. Several studies used single biomarkers such as qNet and Repolarization Abnormality (RA) in a single cardiac cell model to evaluate TdP risk. However, a single biomarker may not encompass the full range of factors contributing to TdP risk, leading to divergent TdP risk prediction outcomes, mainly when evaluated using unseen data. We addressed this issue by utilizing multi-in silico features from a population of human ventricular cell models that could capture a representation of the underlying mechanisms contributing to TdP risk to provide a more reliable assessment of drug-induced cardiotoxicity. Method: We generated a virtual population of human ventricular cell models using a modified O'Hara-Rudy model, allowing inter-individual variation. IC 50 and Hill coefficients from 67 drugs were used as input to simulate drug effects on cardiac cells. Fourteen features (dVm dt repol , dVm dt max , Vm peak , Vm resting , APD tri , APD 90 , APD 50 , Ca peak , Ca diastole , Ca tri , CaD 90 , CaD 50 , qNet, qInward) could be generated from the simulation and used as input to several machine learning models, including k-nearest neighbor (KNN), Random Forest (RF), XGBoost, and Artificial Neural Networks (ANN). Optimization of the machine learning model was performed using a grid search to select the best parameter of the proposed model. We applied five-fold cross-validation while training the model with 42 drugs and evaluated the model's performance with test data from 25 drugs. Result: The proposed ANN model showed the highest performance in predicting the TdP risk of drugs by providing an accuracy of 0.923 (0.908-0.937), sensitivity of 0.926 (0.909-0.942), specificity of 0.921 (0.906-0.935), and AUC score of 0.964 (0.954-0.975). Discussion and conclusion: According to the performance results, combining the electrophysiological model including inter-individual variation and optimization of machine learning showed good generalization ability when evaluated using the unseen dataset and produced a reliable drug-induced TdP risk prediction system.

Research on the application and effect of flipped-classroom combined with TBL teaching model in WeChat-platform-based biochemical teaching under the trend of COVID-19

BACKGROUND

Biochemistry is a core subject in clinical medical education. The traditional classroom teaching model led by teachers is often limited to the knowledge transfer of teachers and the passive acceptance of students. It lacks interactive and efficient teaching methods and is not enough to meet the learning needs and educational goals of modern students. The combination of WeChat public platform, flipped classroom and TBL teaching model is closer to the needs of real life and workplace, helping students to cultivate comprehensive literacy and the ability to solve practical problems. At the same time, this teaching model has yet to be used in biochemistry courses.

OBJECTIVE

To explore the influence of the mixed teaching model of flipped classroom and combining TBL based on WeChat public platform upon undergraduates in biochemistry.

METHODS

Using the mixed research method of quasi-experimental research design and descriptive qualitative research, 68 students were selected into the traditional and the blended teaching groups. Among them, the blended teaching group adopts the blended teaching model of flipped classroom combined with TBL based on the WeChat platform to learn biochemical courses. In this study, an independent sample t-test was intended to analyze the differences in final scores, a chi-square test was served to analyze the differences in satisfaction questionnaires, and thematic analysis was used to analyze semi-structured interview data.

RESULTS

Compared with the traditional teaching model, the mixed teaching model significantly improved students' final exam scores (P < 0.05). The teaching satisfaction of the mixed teaching group was also higher than that of the traditional teaching group with statistical significance (P < 0.05). The results of the interviews with eight students were summarized into three topics: (1) Stimulating interest in learning; (2) Improving the ability of autonomous learning; (3) Recommendations for improvement.

CONCLUSIONS

The combination of the WeChat platform and flipped classroom with TBL has a positive effect on improving medical students' autonomous learning ability and problem-solving ability. The research shows that the teaching mode of flipped classroom combined with TBL based on the WeChat platform is effective and feasible.

Multimodal deep learning for COVID-19 prognosis prediction in the emergency department: a bi-centric study

Predicting clinical deterioration in COVID-19 patients remains a challenging task in the Emergency Department (ED). To address this aim, we developed an artificial neural network using textual (e.g. patient history) and tabular (e.g. laboratory values) data from ED electronic medical reports. The predicted outcomes were 30-day mortality and ICU admission. We included consecutive patients from Humanitas Research Hospital and San Raffaele Hospital in the Milan area between February 20 and May 5, 2020. We included 1296 COVID-19 patients. Textual predictors consisted of patient history, physical exam, and radiological reports. Tabular predictors included age, creatinine, C-reactive protein, hemoglobin, and platelet count. TensorFlow tabular-textual model performance indices were compared to those of models implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular fastai and XGBoost models, with AUC 0.87 ± 0.02, F1 score 0.62 ± 0.10 and an MCC 0.52 ± 0.04 (p < 0.32). As for ICU admission, the combined model MCC was superior (p < 0.024) to the tabular models. Our results suggest that a combined textual and tabular model can effectively predict COVID-19 prognosis which may assist ED physicians in their decision-making process.

COVID-19 vaccine rejection causes based on Twitter people’s opinions analysis using deep learning

According to the World Health Organization, vaccine hesitancy was one of the ten major threats to global health in 2019, including the COVID-19 vaccine. The availability of vaccines does not always mean utilization. This is because, people have less confidence in vaccines, which resulted in vaccination hesitancy and developing global decline in vaccine intake and has caused viral disease outbreaks worldwide. Therefore, there is a need to understand people's perceptions about the COVID-19 vaccine to help the manufacturing companies of the vaccine to improve their marketing strategy based on the rejection causes. In this paper, we used multi-class Sentiment Analysis to classify people's opinions from extracted tweets about COVID-19 vaccines, using firstly different Machine Learning (ML) classifiers such as Logistic Regression (LR), Stochastic Gradient Descent, Support Vector Machine, K-Nearest Neighbors, Decision Tree (DT), Multinomial Naïve Bayes, Random Forest and Gradient Boosting and secondly various Deep Learning (DL) models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), RNN-LSTM and RNN-GRU. Then, we investigated the analysis of the negative tweets to identify the causes of rejection using the Latent Dirichlet Allocation (LDA) technique. Finally, we classified these negative tweets according to the rejection causes for all the vaccines using the same selected ML and DL models. The result of SA showed that DT gives the best performance with an accuracy of 92.26% and for DL models, GRU achieved 96.83%. Then, we identified five causes: Lack of safety, Side effect, Production problem, Fake news and Misinformation, and Cost. Furthermore, for the classification of the negative tweets according to the identified rejection causes, the LR achieved the best result with an accuracy of 89.97%. For DL models, the LSTM model showed the best result with an accuracy of 91.66%.

Prognostic models in COVID-19 infection that predict severity: a systematic review

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

The predictive model for COVID-19 pandemic plastic pollution by using deep learning method

Pandemic plastics (e.g., masks, gloves, aprons, and sanitizer bottles) are global consequences of COVID-19 pandemic-infected waste, which has increased significantly throughout the world. These hazardous wastes play an important role in environmental pollution and indirectly spread COVID-19. Predicting the environmental impacts of these wastes can be used to provide situational management, conduct control procedures, and reduce the COVID-19 effects. In this regard, the presented study attempted to provide a deep learning-based predictive model for forecasting the expansion of the pandemic plastic in the megacities of Iran. As a methodology, a database was gathered from February 27, 2020, to October 10, 2021, for COVID-19 spread and personal protective equipment usage in this period. The dataset was trained and validated using training (80%) and testing (20%) datasets by a deep neural network (DNN) procedure to forecast pandemic plastic pollution. Performance of the DNN-based model is controlled by the confusion matrix, receiver operating characteristic (ROC) curve, and justified by the k-nearest neighbours, decision tree, random forests, support vector machines, Gaussian naïve Bayes, logistic regression, and multilayer perceptron methods. According to the comparative modelling results, the DNN-based model was found to predict more accurately than other methods and have a significant predominance over others with a lower errors rate (MSE = 0.024, RMSE = 0.027, MAPE = 0.025). The ROC curve analysis results (overall accuracy) indicate the DNN model (AUC = 0.929) had the highest score among others.

Generalizable machine learning approach for COVID-19 mortality risk prediction using on-admission clinical and laboratory features

We aimed to propose a mortality risk prediction model using on-admission clinical and laboratory predictors. We used a dataset of confirmed COVID-19 patients admitted to three general hospitals in Tehran. Clinical and laboratory values were gathered on admission. Six different machine learning models and two feature selection methods were used to assess the risk of in-hospital mortality. The proposed model was selected using the area under the receiver operator curve (AUC). Furthermore, a dataset from an additional hospital was used for external validation. 5320 hospitalized COVID-19 patients were enrolled in the study, with a mortality rate of 17.24% (N = 917). Among 82 features, ten laboratories and 27 clinical features were selected by LASSO. All methods showed acceptable performance (AUC > 80%), except for K-nearest neighbor. Our proposed deep neural network on features selected by LASSO showed AUC scores of 83.4% and 82.8% in internal and external validation, respectively. Furthermore, our imputer worked efficiently when two out of ten laboratory parameters were missing (AUC = 81.8%). We worked intimately with healthcare professionals to provide a tool that can solve real-world needs. Our model confirmed the potential of machine learning methods for use in clinical practice as a decision-support system.

Authentication of Covid-19 Vaccines Using Synchronous Fluorescence Spectroscopy

The present study demonstrates the potential of synchronous fluorescence spectroscopy and multivariate data analysis for authentication of COVID-19 vaccines from various manufacturers. Synchronous scanning fluorescence spectra were recorded for DNA-based and mRNA-based vaccines obtained through the NHS Central Liverpool Primary Care Network. Fluorescence spectra of DNA and DNA-based vaccines as well as RNA and RNA-based vaccines were identical to one another. The application of principal component analysis (PCA), PCA-Gaussian Mixture Models (PCA-GMM)) and Self-Organising Maps (SOM) methods to the fluorescence spectra of vaccines is discussed. The PCA is applied to extract the characteristic variables of fluorescence spectra by analysing the major attributes. The results indicated that the first three principal components (PCs) can account for 99.5% of the total variance in the data. The PC scores plot showed two distinct clusters corresponding to the DNA-based vaccines and mRNA-based vaccines respectively. PCA-GMM clustering complemented the PCA clusters by further classifying the mRNA-based vaccines and the GMM clusters revealed three mRNA-based vaccines that were not clustered with the other vaccines. SOM complemented both PCA and PCA-GMM and proved effective with multivariate data without the need for dimensions reduction. The findings showed that fluorescence spectroscopy combined with machine learning algorithms (PCA, PCA-GMM and SOM) is a useful technique for vaccination verification and has the benefits of simplicity, speed and reliability.

Clinical decision support system for quality of life among the elderly: an approach using artificial neural network

Background

Due to advancements in medicine and the elderly population’s growth with various disabilities, attention to QoL among this age group is crucial. Early prediction of the QoL among the elderly by multiple care providers leads to decreased physical and mental disorders and increased social and environmental participation among them by considering all factors affecting it. So far, it is not designed the prediction system for QoL in this regard. Therefore, this study aimed to develop the CDSS based on ANN as an ML technique by considering the physical, psychiatric, and social factors.

Methods

In this developmental and applied study, we investigated the 980 cases associated with pleasant and unpleasant elderlies QoL cases. We used the BLR and simple correlation coefficient methods to attain the essential factors affecting the QoL among the elderly. Then three BP configurations, including CF-BP, FF-BP, and E-BP, were compared to get the best model for predicting the QoL.

Results

Based on the BLR, the 13 factors were considered the best factors affecting the elderly’s QoL at P < 0.05. Comparing all ANN configurations showed that the CF-BP with the 13-16-1 structure with sensitivity = 0.95, specificity  =  0.97, accuracy = 0.96, F-Score = 0.96, PPV = 0.95, and NPV = 0.97 gained the best performance for QoL among the elderly.

Conclusion

The results of this study showed that the designed CDSS based on the CFBP could be considered an efficient tool for increasing the QoL among the elderly.