Efficient prediction of drug-drug interaction using deep learning models

Trends in drug-drug interactions for new drug clinical trials in China over the past 10 years (2013-2022)

The number of drug-drug interaction (DDI) clinical trials in China has increased rapidly in recent years. The aim of this study was to summarize and analyze DDI clinical trials in China over the past 10 years. We conducted a cross-sectional study of DDI clinical trials registered in the Chinese Center for Drug Evaluation (CDE) from September 6, 2013 to December 31, 2022. All related registration information disclosed on the CDE website were summarized and analyzed. Although the number of DDI clinical trials conducted before 2017 was relatively low, it increased markedly after 2017. The average duration of DDI clinical trials was 85.83 ± 100.99 days from 2013 to 2019 and 107.16 ± 98.57 days from 2020 to 2022. The duration of rifampicin use was 5-19 days, and the investigational drug was administered after 5-14 days of rifampicin use. Itraconazole was administered for 4-17 days, and the investigational drug was administered after 3-10 days of itraconazole use. Clinical trials of drug-drug interactions have recently increased due to the development of new drugs and the updated policies regulating drug registration and marketing. Although the designs of clinical trials comply with the new guidelines, the duration of the administration of interacting drugs still varies widely. Optimizing protocol designs can shorten the implementation period of clinical trials and reduce the costs of drug marketing.

A novel deep sequential learning architecture for drug drug interaction prediction using DDINet

Drug drug Interactions (DDI) present considerable challenges in healthcare, often resulting in adverse effects or decreased therapeutic efficacy. This article proposes a novel deep sequential learning architecture called DDINet to predict and classify DDIs between pairs of drugs based on different mechanisms viz., Excretion, Absorption, Metabolism, and Excretion rate (higher serum level) etc. Chemical features such as Hall Smart, Amino Acid count and Carbon types are extracted from each drug (pairs) to apply as an input to the proposed model. Proposed DDINet incorporates attention mechanism and deep sequential learning architectures, such as Long Short-Term Memory and gated recurrent unit. It utilizes the Rcpi toolkit to extract biochemical features of drugs from their chemical composition in Simplified Molecular-Input Line-Entry System format. Experiments are conducted on publicly available DDI datasets from DrugBank and Kaggle. The model's efficacy in predicting and classifying DDIs is evaluated using various performance measures. The experimental results show that DDINet outperformed eight counterpart techniques achieving [Formula: see text] overall accuracy which is also statistically confirmed by Confidence Interval tests and paired t-tests. This architecture may act as an effective computational technique for drug drug interaction with respect to mechanism which may act as a complementary tool to reduce costly wet lab experiments for DDI prediction and classification.

Advanced AI and ML frameworks for transforming drug discovery and optimization: With innovative insights in polypharmacology, drug repurposing, combination therapy and nanomedicine

Artificial Intelligence (AI) and Machine Learning (ML) are transforming drug discovery by overcoming traditional challenges like high costs, time-consuming, and frequent failures. AI-driven approaches streamline key phases, including target identification, lead optimization, de novo drug design, and drug repurposing. Frameworks such as deep neural networks (DNNs), convolutional neural networks (CNNs), and deep reinforcement learning (DRL) models have shown promise in identifying drug targets, optimizing delivery systems, and accelerating drug repurposing. Generative adversarial networks (GANs) and variational autoencoders (VAEs) aid de novo drug design by creating novel drug-like compounds with desired properties. Case studies, such as DDR1 kinase inhibitors designed using generative models and CDK20 inhibitors developed via structure-based methods, highlight AI's ability to produce highly specific therapeutics. Models like SNF-CVAE and DeepDR further advance drug repurposing by uncovering new therapeutic applications for existing drugs. Advanced ML algorithms enhance precision in predicting drug efficacy, toxicity, and ADME-Tox properties, reducing development costs and improving drug-target interactions. AI also supports polypharmacology by optimizing multi-target drug interactions and enhances combination therapy through predictions of drug synergies and antagonisms. In nanomedicine, AI models like CURATE.AI and the Hartung algorithm optimize personalized treatments by predicting toxicological risks and real-time dosing adjustments with high accuracy. Despite its potential, challenges like data quality, model interpretability, and ethical concerns must be addressed. High-quality datasets, transparent models, and unbiased algorithms are essential for reliable AI applications. As AI continues to evolve, it is poised to revolutionize drug discovery and personalized medicine, advancing therapeutic development and patient care.

Enhancing drug discovery in schizophrenia: a deep learning approach for accurate drug-target interaction prediction - DrugSchizoNet

Drug discovery relies on the precise prognosis of drug-target interactions (DTI). Due to their ability to learn from raw data, deep learning (DL) methods have displayed outstanding performance over traditional approaches. However, challenges such as imbalanced data, noise, poor generalization, high cost, and time-consuming processes hinder progress in this field. To overcome the above challenges, we propose a DL-based model termed DrugSchizoNet for drug interaction (DI) prediction of Schizophrenia. Our model leverages drug-related data from the DrugBank and repoDB databases, employing three key preprocessing techniques. First, data cleaning eliminates duplicate or incomplete entries to ensure data integrity. Next, normalization is performed to enhance security and reduce costs associated with data acquisition. Finally, feature extraction is applied to improve the quality of input data. The three layers of the DrugSchizoNet model are the input, hidden and output layers. In the hidden layer, we employ dropout regularization to mitigate overfitting and improve generalization. The fully connected (FC) layer extracts relevant features, while the LSTM layer captures the sequential nature of DIs. In the output layer, our model provides confidence scores for potential DIs. To optimize the prediction accuracy, we utilize hyperparameter tuning through OB-MOA optimization. Experimental results demonstrate that DrugSchizoNet achieves a superior accuracy of 98.70%. The existing models, including CNN-RNN, DANN, CKA-MKL, DGAN, and CNN, across various evaluation metrics such as accuracy, recall, specificity, precision, F1 score, AUPR, and AUROC are compared with the proposed model. By effectively addressing the challenges of imbalanced data, noise, poor generalization, high cost and time-consuming processes, DrugSchizoNet offers a promising approach for accurate DTI prediction in Schizophrenia. Its superior performance demonstrates the potential of DL in advancing drug discovery and development processes.

DTI-MHAPR: optimized drug-target interaction prediction via PCA-enhanced features and heterogeneous graph attention networks

Drug-target interactions (DTIs) are pivotal in drug discovery and development, and their accurate identification can significantly expedite the process. Numerous DTI prediction methods have emerged, yet many fail to fully harness the feature information of drugs and targets or address the issue of feature redundancy. We aim to refine DTI prediction accuracy by eliminating redundant features and capitalizing on the node topological structure to enhance feature extraction. To achieve this, we introduce a PCA-augmented multi-layer heterogeneous graph-based network that concentrates on key features throughout the encoding-decoding phase. Our approach initiates with the construction of a heterogeneous graph from various similarity metrics, which is then encoded via a graph neural network. We concatenate and integrate the resultant representation vectors to merge multi-level information. Subsequently, principal component analysis is applied to distill the most informative features, with the random forest algorithm employed for the final decoding of the integrated data. Our method outperforms six baseline models in terms of accuracy, as demonstrated by extensive experimentation. Comprehensive ablation studies, visualization of results, and in-depth case analyses further validate our framework's efficacy and interpretability, providing a novel tool for drug discovery that integrates multimodal features.

Deep Drug Synergy Prediction Network Using Modified Triangular Mutation-Based Differential Evolution

Drug combination therapy is crucial in cancer treatment, but accurately predicting drug synergy remains a challenge due to the complexity of drug combinations. Machine learning and deep learning models have shown promise in drug combination prediction, but they suffer from issues such as gradient vanishing, overfitting, and parameter tuning. To address these problems, the deep drug synergy prediction network, named as EDNet is proposed that leverages a modified triangular mutation-based differential evolution algorithm. This algorithm evolves the initial connection weights and architecture-related attributes of the deep bidirectional mixture density network, improving its performance and addressing the aforementioned issues. EDNet automatically extracts relevant features and provides conditional probability distributions of output attributes. The performance of EDNet is evaluated over two well-known drug synergy datasets, NCI-ALMANAC and deep-synergy. The results demonstrate that EDNet outperforms the competing models. EDNet facilitates efficient drug interactions, enhancing the overall effectiveness of drug combinations for improved cancer treatment outcomes.

Accurate prediction of drug combination risk levels based on relational graph convolutional network and multi-head attention

BACKGROUND

Accurately identifying the risk level of drug combinations is of great significance in investigating the mechanisms of combination medication and adverse reactions. Most existing methods can only predict whether there is an interaction between two drugs, but cannot directly determine their accurate risk level.

METHODS

In this study, we propose a multi-class drug combination risk prediction model named AERGCN-DDI, utilizing a relational graph convolutional network with a multi-head attention mechanism. Drug-drug interaction events with varying risk levels are modeled as a heterogeneous information graph. Attribute features of drug nodes and links are learned based on compound chemical structure information. Finally, the AERGCN-DDI model is proposed to predict drug combination risk level based on heterogenous graph neural network and multi-head attention modules.

RESULTS

To evaluate the effectiveness of the proposed method, five-fold cross-validation and ablation study were conducted. Furthermore, we compared its predictive performance with baseline models and other state-of-the-art methods on two benchmark datasets. Empirical studies demonstrated the superior performances of AERGCN-DDI.

CONCLUSIONS

AERGCN-DDI emerges as a valuable tool for predicting the risk levels of drug combinations, thereby aiding in clinical medication decision-making, mitigating severe drug side effects, and enhancing patient clinical prognosis.

Developing an AI-based prediction model for anaphylactic shock from injection drugs using Japanese real-world data and chemical structure-based analysis

BACKGROUND

This study aims to develop an AI-based prediction model for injection drugs that cause anaphylactic shock using Japanese Real-World Data (JADER database) and chemical structure-based analysis.

METHODS

Data sourced from the JADER database included adverse drug reaction reports from April 2004 to December 2020. Only drugs with an adverse reaction named "anaphylactic shock" were selected for analysis. For model building, various models were constructed to predict anaphylactic shock-inducing drugs, such as logistic regression, LASSO, XGBoost, RF, SVM, and NNW. These models used chemical properties and structural similarities as feature variables. Dimension reduction was applied using principal component analysis. The dataset was split into training (80%) and validation (20%) sets. Six different models were trained and optimized through fivefold cross-validation.

RESULTS

From April 2004 to December 2020, 947 drugs with the adverse reaction name "anaphylactic shock" were extracted from the JADER database. 320 drugs were excluded due to analytical challenges, and another 400 were removed due to their administration route. 227 drugs were finalized as target medicines. For model validation, the performance of each model was evaluated based on metrics like AUCs of ROC curve, sensitivity, and specificity. Additionally, two ensemble models, constructed from the six models were assessed using bootstrap sampling. Interestingly, it was identified that mepivacaine structural similarity had the highest importance in the final model.

CONCLUSIONS

The study successfully developed an AI-based prediction model for anaphylactic shock inducing-injection drugs. The model would offer potential for drug safety evaluation and anaphylactic shock risk assessment.

G-K BertDTA: A graph representation learning and semantic embedding-based framework for drug-target affinity prediction

Developing new drugs is costly, time-consuming, and risky. Drug-target affinity (DTA), indicating the binding capability between drugs and target proteins, is a crucial indicator for drug development. Accurately predicting interaction strength between new drug-target pairs by analyzing previous experiments aids in screening potential drug molecules, repurposing them, and developing safe and effective medicines. Existing computational models for DTA prediction rely on strings or single-graph neural networks, lacking consideration of protein structure and molecular semantic information, leading to limited accuracy. Our experiments demonstrate that string-based methods may overlook protein conformations, causing a high root mean square error (RMSE) of 3.584 in affinity due to a lack of spatial context. Single graph networks also underperform on topology features, with a 6% lower confidence interval (CI) for activity classification. Absent semantic information also limits generalization across diverse compounds, resulting in 18% increment in RMSE and 5% in misclassifications within quantifications study, restricting potential drug discovery. To address these limitations, we propose G-K BertDTA, a novel framework for accurate DTA prediction incorporating protein features, molecular semantic features, and molecular structural information. In this proposed model, we represent drugs as graphs, with a GIN employed to learn the molecular topological information. For the extraction of protein structural features, we utilize a DenseNet architecture. A knowledge-based BERT semantic model is incorporated to obtain rich pre-trained semantic embeddings, thereby enhancing the feature information. We extensively evaluated our proposed approach on the publicly available benchmark datasets (i.e., KIBA and Davis), and experimental results demonstrate the promising performance of our method, which consistently outperforms previous state-of-the-art approaches. Code is available at https://github.com/AmbitYuki/G-K-BertDTA.

Predict lncRNA-drug associations based on graph neural network

LncRNAs are an essential type of non-coding RNAs, which have been reported to be involved in various human pathological conditions. Increasing evidence suggests that drugs can regulate lncRNAs expression, which makes it possible to develop lncRNAs as therapeutic targets. Thus, developing in-silico methods to predict lncRNA-drug associations (LDAs) is a critical step for developing lncRNA-based therapies. In this study, we predict LDAs by using graph convolutional networks (GCN) and graph attention networks (GAT) based on lncRNA and drug similarity networks. Results show that our proposed method achieves good performance (average AUCs > 0.92) on five datasets. In addition, case studies and KEGG functional enrichment analysis further prove that the model can effectively identify novel LDAs. On the whole, this study provides a deep learning-based framework for predicting novel LDAs, which will accelerate the lncRNA-targeted drug development process.

Multi-party collaborative drug discovery via federated learning

In the field of drug discovery and pharmacology research, precise and rapid prediction of drug-target binding affinity (DTA) and drug-drug interaction (DDI) are essential for drug efficacy and safety. However, pharmacological data are often distributed across different institutions. Moreover, due to concerns regarding data privacy and intellectual property, the sharing of pharmacological data is often restricted. It is difficult for institutions to achieve the desired performance by solely utilizing their data. This urgent challenge calls for a solution that not only enhances collaboration between multiple institutions to improve prediction accuracy but also safeguards data privacy. In this study, we propose a novel federated learning (FL) framework to advance the prediction of DTA and DDI, namely FL-DTA and FL-DDI. The proposed framework enables multiple institutions to collaboratively train a predictive model without the need to share their local data. Moreover, to ensure data privacy, we employ secure multi-party computation (MPC) during the federated learning model aggregation phase. We evaluated the proposed method on two DTA and one DDI benchmark datasets and compared them with centralized learning and local learning. The experimental results indicate that the proposed method performs closely to centralized learning, and significantly outperforms local learning. Moreover, the proposed framework ensures data security while promoting collaboration among institutions, thereby accelerating the drug discovery process.

Synergistic D-Amino Acids Based Antimicrobial Cocktails Formulated via High-Throughput Screening and Machine Learning

Antimicrobial resistance (AMR) from pathogenic bacterial biofilms has become a global health issue while developing novel antimicrobials is inefficient and costly. Combining existing multiple drugs with enhanced efficacy and/or reduced toxicity may be a promising approach to treat AMR. D-amino acids mixtures coupled with antibiotics can provide new therapies for drug-resistance infection with reduced toxicity by lower drug dosage requirements. However, iterative trial-and-error experiments are not tenable to prioritize credible drug formulations, owing to the extremely large number of possible combinations. Herein, a new avenue is provide to accelerate the exploration of desirable antimicrobial formulations via high-throughput screening and machine learning optimization. Such an intelligent method can navigate the large search space and rapidly identify the D-amino acid mixtures with the highest anti-biofilm efficiency and also the synergisms between D-amino acid mixtures and antibiotics. The optimized drug cocktails exhibit high antimicrobial efficacy while remaining non-toxic, which is demonstrated not only from in vitro assessments but also the first in vivo study using a lung infection mouse model.

Artificial Intelligence in Pediatrics: Learning to Walk Together

In this era of rapidly advancing technology, artificial intelligence (AI) has emerged as a transformative force, even being called the Fourth Industrial Revolution, along with gene editing and robotics. While it has undoubtedly become an increasingly important part of our daily lives, it must be recognized that it is not an additional tool, but rather a complex concept that poses a variety of challenges. AI, with considerable potential, has found its place in both medical care and clinical research. Within the vast field of pediatrics, it stands out as a particularly promising advancement. As pediatricians, we are indeed witnessing the impactful integration of AI-based applications into our daily clinical practice and research efforts. These tools are being used for simple to more complex tasks such as diagnosing clinically challenging conditions, predicting disease outcomes, creating treatment plans, educating both patients and healthcare professionals, and generating accurate medical records or scientific papers. In conclusion, the multifaceted applications of AI in pediatrics will increase efficiency and improve the quality of healthcare and research. However, there are certain risks and threats accompanying this advancement including the biases that may contribute to health disparities and, inaccuracies. Therefore, it is crucial to recognize and address the technical, ethical, and legal challenges as well as explore the benefits in both clinical and research fields.

Multimodal CNN-DDI: using multimodal CNN for drug to drug interaction associated events

Drug-to-drug interaction (DDIs) occurs when a patient consumes multiple drugs. Therefore, it is possible that any medication can influence other drugs' effectiveness. The drug-to-drug interactions are detected based on the interactions of chemical substructures, targets, pathways, and enzymes; therefore, machine learning (ML) and deep learning (DL) techniques are used to find the associated DDI events. The DL model, i.e., Convolutional Neural Network (CNN), is used to analyze the DDI. DDI is based on the 65 different drug-associated events, which is present in the drug bank database. Our model uses the inputs, which are chemical structures (i.e., smiles of drugs), enzymes, pathways, and the target of the drug. Therefore, for the multi-model CNN, we use several layers, activation functions, and features of drugs to achieve better accuracy as compared to traditional prediction algorithms. We perform different experiments on various hyperparameters. We have also carried out experiments on various iterations of drug features in different sets. Our Multi-Modal Convolutional Neural Network - Drug to Drug Interaction (MCNN-DDI) model achieved an accuracy of 90.00% and an AUPR of 94.78%. The results showed that a combination of the drug's features (i.e., chemical substructure, target, and enzyme) performs better in DDIs-associated events prediction than other features.

DiCleave: a deep learning model for predicting human Dicer cleavage sites

BACKGROUND

MicroRNAs (miRNAs) are a class of non-coding RNAs that play a pivotal role as gene expression regulators. These miRNAs are typically approximately 20 to 25 nucleotides long. The maturation of miRNAs requires Dicer cleavage at specific sites within the precursor miRNAs (pre-miRNAs). Recent advances in machine learning-based approaches for cleavage site prediction, such as PHDcleav and LBSizeCleav, have been reported. ReCGBM, a gradient boosting-based model, demonstrates superior performance compared with existing methods. Nonetheless, ReCGBM operates solely as a binary classifier despite the presence of two cleavage sites in a typical pre-miRNA. Previous approaches have focused on utilizing only a fraction of the structural information in pre-miRNAs, often overlooking comprehensive secondary structure information. There is a compelling need for the development of a novel model to address these limitations.

RESULTS

In this study, we developed a deep learning model for predicting the presence of a Dicer cleavage site within a pre-miRNA segment. This model was enhanced by an autoencoder that learned the secondary structure embeddings of pre-miRNA. Benchmarking experiments demonstrated that the performance of our model was comparable to that of ReCGBM in the binary classification tasks. In addition, our model excelled in multi-class classification tasks, making it a more versatile and practical solution than ReCGBM.

CONCLUSIONS

Our proposed model exhibited superior performance compared with the current state-of-the-art model, underscoring the effectiveness of a deep learning approach in predicting Dicer cleavage sites. Furthermore, our model could be trained using only sequence and secondary structure information. Its capacity to accommodate multi-class classification tasks has enhanced the practical utility of our model.

MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms

The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi‑type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.

PRID: Prediction Model Using RWR for Interactions between Drugs

Drug-drug interactions (DDI) occur because of the unexpected pharmacological effects of drug pairs. Although drug efficacy can be improved by taking two or more drugs in the short term, this may cause inevitable side effects. Currently, multiple drugs are prescribed based on the experience or knowledge of the clinician, and there is no standard database that can be referred to as safe co-prescriptions. Thus, accurately identifying DDI is critical for patient safety and treatment modalities. Many computational methods have been developed to predict DDIs based on chemical structures or biological features, such as target genes or functional mechanisms. However, some features are only available for certain drugs, and their pathological mechanisms cannot be fully employed to predict DDIs by considering the direct overlap of target genes. In this study, we propose a novel deep learning model to predict DDIs by utilizing chemical structure similarity and protein-protein interaction (PPI) information among drug-binding proteins, such as carriers, transporters, enzymes, and targets (CTET) proteins. We applied the random walk with restart (RWR) algorithm to propagate drug CTET proteins across a PPI network derived from the STRING database, which will lead to the successful incorporation of the hidden biological mechanisms between CTET proteins and disease-associated genes. We confirmed that the RWR propagation of CTET proteins helps predict DDIs by utilizing indirectly co-regulated biological mechanisms. Our method identified the known DDIs between clinically proven epilepsy drugs. Our results demonstrated the effectiveness of PRID in predicting DDIs in known drug combinations as well as unknown drug pairs. PRID could be helpful in identifying novel DDIs and associated pharmacological mechanisms to cause the DDIs.

MPFFPSDC: A multi-pooling feature fusion model for predicting synergistic drug combinations

Drug combination therapies are common practice in the treatment of cancer, but not all combinations result in synergy. As traditional screening approaches are restricted in their ability to uncover synergistic drug combinations, computer-aided medicine is becoming a increasingly prevalent in this field. In this work, a predictive model of potential interactions between drugs named MPFFPSDC is presented, which can maintain the symmetry of drug inputs and eliminate inconsistencies in predictive results caused by different drug inputting sequences or positions. The experimental results show that MPFFPSDC outperforms comparative models in major performance indicators and exhibits better generalization for independent data. Furthermore, the case study demonstrates that our model can capture molecular substructures that contribute to the synergistic effect of two drugs. These results indicate that MPFFPSDC not only offers strong predictive performance, but also has good model interpretability that may provide new insights for the study of drug interaction mechanisms and the development of new drugs.

Machine learning in metastatic cancer research: Potentials, possibilities, and prospects

Cancer has received extensive recognition for its high mortality rate, with metastatic cancer being the top cause of cancer-related deaths. Metastatic cancer involves the spread of the primary tumor to other body organs. As much as the early detection of cancer is essential, the timely detection of metastasis, the identification of biomarkers, and treatment choice are valuable for improving the quality of life for metastatic cancer patients. This study reviews the existing studies on classical machine learning (ML) and deep learning (DL) in metastatic cancer research. Since the majority of metastatic cancer research data are collected in the formats of PET/CT and MRI image data, deep learning techniques are heavily involved. However, its black-box nature and expensive computational cost are notable concerns. Furthermore, existing models could be overestimated for their generality due to the non-diverse population in clinical trial datasets. Therefore, research gaps are itemized; follow-up studies should be carried out on metastatic cancer using machine learning and deep learning tools with data in a symmetric manner.

DNN-PNN: A parallel deep neural network model to improve anticancer drug sensitivity

With the rapid development of deep learning techniques and large-scale genomics database, it is of great potential to apply deep learning to the prediction task of anticancer drug sensitivity, which can effectively improve the identification efficiency and accuracy of therapeutic biomarkers. In this study, we propose a parallel deep learning framework DNN-PNN, which integrates rich and heterogeneous information from gene expression and pharmaceutical chemical structure data. With the proposal of DNN-PNN, a new and more effective drug data representation strategy is introduced, that is, the correlation between features is represented by product, which alleviates the limitations of high-dimensional discrete data in deep learning. Furthermore, the framework is optimized to reduce the time complexity of the model. We conducted extensive experiments on the CCLE datasets to compare DNN-PNN with its variant DNN-FM representing the traditional feature correlation model, the component DNN or PNN alone, and the common machine learning models. It is found that DNN-PNN not only has high prediction accuracy, but also has significant advantages in stability and convergence speed.

Multisource Attention-Mechanism-Based Encoder-Decoder Model for Predicting Drug-Drug Interaction Events

Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.

Computer-Aided Multiclass Classification of Corn from Corn Images Integrating Deep Feature Extraction

Corn has great importance in terms of production in the field of agriculture and animal feed. Obtaining pure corn seeds in corn production is quite significant for seed quality. For this reason, the distinction of corn seeds that have numerous varieties plays an essential role in marketing. This study was conducted with 14,469 images of BT6470, Calipso, Es_Armandi, and Hiva types of corn licensed by BIOTEK. The classification of images was carried out in three stages. At the first stage, deep feature extraction of the four types of corn images was performed with the pretrained CNN model SqueezeNet 1000 deep features were obtained for each image. In the second stage, in order to reduce these features obtained from deep feature extraction with SqueezeNet, separate feature selection processes were performed with the Bat Optimization (BA), Whale Optimization (WOA), and Gray Wolf Optimization (GWO) algorithms among optimization algorithms. Finally, in the last stage, the features obtained from the first and second stages were classified by using the machine learning methods Decision Tree (DT), Naive Bayes (NB), multi-class Support Vector Machine (mSVM), k-Nearest Neighbor (KNN), and Neural Network (NN). In the classification processes of the features obtained in the first stage, the mSVM model has achieved the highest classification success with 89.40%. In the second stage, as a result of the classifications performed through the active features selected by using three types of feature selection algorithms (BA, WOA, GWO), the classification success obtained with the mSVM model was 88.82%, 88.72%, and 88.95%, respectively. The classification accuracies of the tested methods and the classification accuracies obtained in the first stage are close to each other in terms of classification success. However, with the algorithms used in feature selection, successful classification processes have been carried out with fewer features and in a shorter time. The results of the study, in which classification was carried out in the inexpensive, the objective, and the shorter time of processing for the corn types, present a different perspective in terms of classification performance.

Particle Swarm Optimization and Modular Multilevel Converter Communication in Electrical Applications with Machine Learning Algorithm

As a result of their natural capacity to recover harmonic current and reactive power from alternating current sources, power electronic devices utilized in conjunction with nonlinear loads have the potential to generate significant harmonic problems within the power system when employed in this way. When this occurs, voltage instability occurs, which must be avoided in order to maintain the consistency and dependability of the power system's power flow. With this approach, the series controller has been replaced by a multilevel modular controller in order to improve power handling capability and achieve higher modular levels with minimal distortions. The shunt compensator is the most effective way to achieve an extremely protected energy system as well as righteous steadiness in electric potential difference under a variety of load constraints. The DQ thesis is employed in this proposed converter to separate the harmonic components by establishing reference frame current, which is accomplished by machine learning techniques. As part of the constant mode operation, the PI controller contributes to maintaining the direct current-potential difference, which is given to the PWM generator. Optimization of the values of K p and K i is accomplished by the use of particle swarm optimization (PSO). The construction of this power system simulation model has been made feasible by the use of time-fluctuating characteristics modeling and the MATLAB programming environment. The new (unified power flow controller) UPFC research that has been made available is persuasive in its capacity to reduce distortions and watt-less power components while simultaneously enhancing efficiency and reducing costs.

Wearable Sensors with Internet of Things (IoT) and Vocabulary-Based Acoustic Signal Processing for Monitoring Children's Health

The brain is the most complex organ in the human body, and it is also the most complex organ in the whole biological system, making it the most complex organ on the planet. According to the findings of current studies, modern study that properly characterises the EEG data signal provides a clear classification accuracy of human activities which is distinct from previous research. Various brain wave patterns related to common activities such as sleeping, reading, and watching a movie may be found in the Electroencephalography (EEG) data that has been collected. As a consequence of these activities, we accumulate numerous sorts of emotion signals in our brains, including the Delta, Theta, and Alpha bands. These bands will provide different types of emotion signals in our brain as a result of these activities. As a consequence of the nonstationary nature of EEG recordings, time-frequency-domain techniques, on the other hand, are more likely to provide good findings. The ability to identify different neural rhythm scales using time-frequency representation has also been shown to be a legitimate EEG marker; this ability has also been demonstrated to be a powerful tool for investigating small-scale neural brain oscillations. This paper presents the first time that a frequency analysis of EEG dynamics has been undertaken. An augmenting decomposition consisting of the "Versatile Inspiring Wavelet Transform" and the "Adaptive Wavelet Transform" is used in conjunction with the EEG rhythms that were gathered to provide adequate temporal and spectral resolutions. Children's wearable sensors are being used to collect data from a number of sources, including the Internet. The signal is conveyed over the Internet of Things (IoT). Specifically, the suggested approach is assessed on two EEG datasets, one of which was obtained in a noisy (i.e., nonshielded) environment and the other was recorded in a shielded environment. The results illustrate the resilience of the proposed training strategy. Therefore, our method contributes to the identification of specific brain activity in children who are taking part in the research as a result of their participation. On the basis of several parameters such as filtering response, accuracy, precision, recall, and F-measure, the MATLAB simulation software was used to evaluate the performance of the proposed system.

Key Aggregation Cryptosystem and Double Encryption Method for Cloud-Based Intelligent Machine Learning Techniques-Based Health Monitoring Systems

Cloud technology is a business strategy that aims to provide the necessary material to customers depending on their needs. Individuals and cloud businesses alike have embraced the cloud storage service, which has become the most widely used service. The industries outsource their data to cloud storage space to relieve themselves of the load of dealing with redundant data contents. This must be protected to prevent the theft of personal belongings, and privacy must be improved as well. Different research projects have been suggested to ensure the safe management of the information included within the data content. The security of current research projects, on the contrary, still needs improvement. As a result, this method has been suggested to address the security concerns associated with cloud computing. The primary goal of this study effort is to offer a safe environment for cloud users while also increasing the profit of cloud resource providers by managing and securely delivering data contents to the cloud users. The bulk of sectors, including business, finance, military, and healthcare industry, do not store data in cloud-based storage systems. This technique is used to attract these kinds of customers. Increasing public acceptance, medical researchers are drawn to cloud computing because it allows them to store their study material in a centralized location and distribute and access it in a more flexible manner. They were collected from numerous individuals who were being evaluated for medical care at the time. Scalable and enhanced key aggregate cryptosystem is a protected data protection method that provides highly effective security in the healthcare industry. When parties interested in a dispute disagree on the outflow of sensitive information, this technique manages the disputes and ensures the data security deployment of a cloud-based intelligent health monitoring system for the parties involved. The encrypted data structure of medical and healthcare prescriptions is recorded as they move through the hands of patients and healthcare facilities, according to the technique recommended. The double encryption approach is used in order to raise the overall degree of security. An encryption class is created by referring to the Ciphertext ID during the encryption procedure. The keyholder is a master secret key that facilitates in the recovery of the secret keys of various monsters and creatures by acting as a conduit between them. It is transferred and stored as a single aggregate for the benefit of the patient or customer in order to make decryption more convenient and efficient. A safe connection between cloud-based intelligent health monitoring systems and healthcare organizations and their patients may be established via the use of a key aggregation cryptosystem and a double encryption approach, according to the researchers. Because of this, when compared to earlier techniques, the findings reveal that the research methodology provides high levels of security in terms of confidentiality and integrity, in addition to excellent scalability.

On the road to explainable AI in drug-drug interactions prediction: A systematic review

Over the past decade, polypharmacy instances have been common in multi-diseases treatment. However, unwanted drug-drug interactions (DDIs) that might cause unexpected adverse drug events (ADEs) in multiple regimens therapy remain a significant issue. Since artificial intelligence (AI) is ubiquitous today, many AI prediction models have been developed to predict DDIs to support clinicians in pharmacotherapy-related decisions. However, even though DDI prediction models have great potential for assisting physicians in polypharmacy decisions, there are still concerns regarding the reliability of AI models due to their black-box nature. Building AI models with explainable mechanisms can augment their transparency to address the above issue. Explainable AI (XAI) promotes safety and clarity by showing how decisions are made in AI models, especially in critical tasks like DDI predictions. In this review, a comprehensive overview of AI-based DDI prediction, including the publicly available source for AI-DDIs studies, the methods used in data manipulation and feature preprocessing, the XAI mechanisms to promote trust of AI, especially for critical tasks as DDIs prediction, the modeling methods, is provided. Limitations and the future directions of XAI in DDIs are also discussed.

Intelligent Wearable Devices Enabled Automatic Vehicle Detection and Tracking System with Video-Enabled UAV Networks Using Deep Convolutional Neural Network and IoT Surveillance

The discipline of computer vision is becoming more popular as a research subject. In a surveillance-based computer vision application, item identification and tracking are the core procedures. They consist of segmenting and tracking an object of interest from a sequence of video frames, and they are both performed using computer vision algorithms. In situations when the camera is fixed and the backdrop remains constant, it is possible to detect items in the background using more straightforward methods. Aerial surveillance, on the other hand, is characterized by the fact that the target, as well as the background and video camera, are all constantly moving. It is feasible to recognize targets in the video data captured by an unmanned aerial vehicle (UAV) using the mean shift tracking technique in combination with a deep convolutional neural network (DCNN). It is critical that the target detection algorithm maintains its accuracy even in the presence of changing lighting conditions, dynamic clutter, and changes in the scene environment. Even though there are several approaches for identifying moving objects in the video, background reduction is the one that is most often used. An adaptive background model is used to create a mean shift tracking technique, which is shown and implemented in this work. In this situation, the background model is provided and updated frame-by-frame, and therefore, the problem of occlusion is fully eliminated from the equation. The target tracking algorithm is fed the same video stream that was used for the target identification algorithm to work with. In MATLAB, the works are simulated, and their performance is evaluated using image-based and video-based metrics to establish how well they operate in the real world.

Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.

Medical Image Captioning Using Optimized Deep Learning Model

Medical image captioning provides the visual information of medical images in the form of natural language. It requires an efficient approach to understand and evaluate the similarity between visual and textual elements and to generate a sequence of output words. A novel show, attend, and tell model (ATM) is implemented, which considers a visual attention approach using an encoder-decoder model. But the show, attend, and tell model is sensitive to its initial parameters. Therefore, a Strength Pareto Evolutionary Algorithm-II (SPEA-II) is utilized to optimize the initial parameters of the ATM. Finally, experiments are considered using the benchmark data sets and competitive medical image captioning techniques. Performance analysis shows that the SPEA-II-based ATM performs significantly better as compared to the existing models.

Evolving Long Short-Term Memory Network-Based Text Classification

Recently, long short-term memory (LSTM) networks are extensively utilized for text classification. Compared to feed-forward neural networks, it has feedback connections, and thus, it has the ability to learn long-term dependencies. However, the LSTM networks suffer from the parameter tuning problem. Generally, initial and control parameters of LSTM are selected on a trial and error basis. Therefore, in this paper, an evolving LSTM (ELSTM) network is proposed. A multiobjective genetic algorithm (MOGA) is used to optimize the architecture and weights of LSTM. The proposed model is tested on a well-known factory reports dataset. Extensive analyses are performed to evaluate the performance of the proposed ELSTM network. From the comparative analysis, it is found that the LSTM network outperforms the competitive models.

Deep Ensemble Learning-Based Models for Diagnosis of COVID-19 from Chest CT Images

Novel coronavirus (COVID-19) has been endangering human health and life since 2019. The timely quarantine, diagnosis, and treatment of infected people are the most necessary and important work. The most widely used method of detecting COVID-19 is real-time polymerase chain reaction (RT-PCR). Along with RT-PCR, computed tomography (CT) has become a vital technique in diagnosing and managing COVID-19 patients. COVID-19 reveals a number of radiological signatures that can be easily recognized through chest CT. These signatures must be analyzed by radiologists. It is, however, an error-prone and time-consuming process. Deep Learning-based methods can be used to perform automatic chest CT analysis, which may shorten the analysis time. The aim of this study is to design a robust and rapid medical recognition system to identify positive cases in chest CT images using three Ensemble Learning-based models. There are several techniques in Deep Learning for developing a detection system. In this paper, we employed Transfer Learning. With this technique, we can apply the knowledge obtained from a pre-trained Convolutional Neural Network (CNN) to a different but related task. In order to ensure the robustness of the proposed system for identifying positive cases in chest CT images, we used two Ensemble Learning methods namely Stacking and Weighted Average Ensemble (WAE) to combine the performances of three fine-tuned Base-Learners (VGG19, ResNet50, and DenseNet201). For Stacking, we explored 2-Levels and 3-Levels Stacking. The three generated Ensemble Learning-based models were trained on two chest CT datasets. A variety of common evaluation measures (accuracy, recall, precision, and F1-score) are used to perform a comparative analysis of each method. The experimental results show that the WAE method provides the most reliable performance, achieving a high recall value which is a desirable outcome in medical applications as it poses a greater risk if a true infected patient is not identified.

Transfer learning with fine-tuned deep CNN ResNet50 model for classifying COVID-19 from chest X-ray images

COVID-19 cases are putting pressure on healthcare systems all around the world. Due to the lack of available testing kits, it is impractical for screening every patient with a respiratory ailment using traditional methods (RT-PCR). In addition, the tests have a high turn-around time and low sensitivity. Detecting suspected COVID-19 infections from the chest X-ray might help isolate high-risk people before the RT-PCR test. Most healthcare systems already have X-ray equipment, and because most current X-ray systems have already been computerized, there is no need to transfer the samples. The use of a chest X-ray to prioritize the selection of patients for subsequent RT-PCR testing is the motivation of this work. Transfer learning (TL) with fine-tuning on deep convolutional neural network-based ResNet50 model has been proposed in this work to classify COVID-19 patients from the COVID-19 Radiography Database. Ten distinct pre-trained weights, trained on varieties of large-scale datasets using various approaches such as supervised learning, self-supervised learning, and others, have been utilized in this work. Our proposed i N a t 2021 _ M i n i _ S w A V _ 1 k model, pre-trained on the iNat2021 Mini dataset using the SwAV algorithm, outperforms the other ResNet50 TL models. For COVID instances in the two-class (Covid and Normal) classification, our work achieved 99.17% validation accuracy, 99.95% train accuracy, 99.31% precision, 99.03% sensitivity, and 99.17% F1-score. Some domain-adapted ( I m a g e N e t _ C h e s t X - r a y 14 ) and in-domain (ChexPert, ChestX-ray14) models looked promising in medical image classification by scoring significantly higher than other models.

AMDE: a novel attention-mechanism-based multidimensional feature encoder for drug-drug interaction prediction

The properties of the drug may be altered by the combination, which may cause unexpected drug-drug interactions (DDIs). Prediction of DDIs provides combination strategies of drugs for systematic and effective treatment. In most of deep learning-based methods for predicting DDI, encoded information about the drugs is insufficient in some extent, which limits the performances of DDIs prediction. In this work, we propose a novel attention-mechanism-based multidimensional feature encoder for DDIs prediction, namely attention-based multidimensional feature encoder (AMDE). Specifically, in AMDE, we encode drug features from multiple dimensions, including information from both Simplified Molecular-Input Line-Entry System sequence and atomic graph of the drug. Data experiments are conducted on DDI data set selected from Drugbank, involving a total of 34 282 DDI relationships with 17 141 positive DDI samples and 17 141 negative samples. Experimental results show that our AMDE performs better than some state-of-the-art baseline methods, including Random Forest, One-Dimension Convolutional Neural Networks, DeepDrug, Long Short-Term Memory, Seq2seq, Deepconv, DeepDDI, Graph Attention Networks and Knowledge Graph Neural Networks. In practice, we select a set of 150 drugs with 3723 DDIs, which are never appeared in training, validation and test sets. AMDE performs well in DDIs prediction task, with AUROC and AUPRC 0.981 and 0.975. As well, we use Torasemide (DB00214) as an example and predict the most likely drug to interact with it. The top 15 scores all have been reported with clear interactions in literatures.

MDF-SA-DDI: predicting drug-drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism

One of the main problems with the joint use of multiple drugs is that it may cause adverse drug interactions and side effects that damage the body. Therefore, it is important to predict potential drug interactions. However, most of the available prediction methods can only predict whether two drugs interact or not, whereas few methods can predict interaction events between two drugs. Accurately predicting interaction events of two drugs is more useful for researchers to study the mechanism of the interaction of two drugs. In the present study, we propose a novel method, MDF-SA-DDI, which predicts drug-drug interaction (DDI) events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism. MDF-SA-DDI is mainly composed of two parts: multi-source drug fusion and multi-source feature fusion. First, we combine two drugs in four different ways and input the combined drug feature representation into four different drug fusion networks (Siamese network, convolutional neural network and two auto-encoders) to obtain the latent feature vectors of the drug pairs, in which the two auto-encoders have the same structure, and their main difference is the number of neurons in the input layer of the two auto-encoders. Then, we use transformer blocks that include self-attention mechanism to perform latent feature fusion. We conducted experiments on three different tasks with two datasets. On the small dataset, the area under the precision-recall-curve (AUPR) and F1 scores of our method on task 1 reached 0.9737 and 0.8878, respectively, which were better than the state-of-the-art method. On the large dataset, the AUPR and F1 scores of our method on task 1 reached 0.9773 and 0.9117, respectively. In task 2 and task 3 of two datasets, our method also achieved the same or better performance as the state-of-the-art method. More importantly, the case studies on five DDI events are conducted and achieved satisfactory performance. The source codes and data are available at https://github.com/ShenggengLin/MDF-SA-DDI.

Representation of molecules for drug response prediction

The rapid development of machine learning and deep learning algorithms in the recent decade has spurred an outburst of their applications in many research fields. In the chemistry domain, machine learning has been widely used to aid in drug screening, drug toxicity prediction, quantitative structure-activity relationship prediction, anti-cancer synergy score prediction, etc. This review is dedicated to the application of machine learning in drug response prediction. Specifically, we focus on molecular representations, which is a crucial element to the success of drug response prediction and other chemistry-related prediction tasks. We introduce three types of commonly used molecular representation methods, together with their implementation and application examples. This review will serve as a brief introduction of the broad field of molecular representations.

The usage of deep neural network improves distinguishing COVID-19 from other suspected viral pneumonia by clinicians on chest CT: a real-world study

OBJECTIVES

Based on the current clinical routine, we aimed to develop a novel deep learning model to distinguish coronavirus disease 2019 (COVID-19) pneumonia from other types of pneumonia and validate it with a real-world dataset (RWD).

METHODS

A total of 563 chest CT scans of 380 patients (227/380 were diagnosed with COVID-19 pneumonia) from 5 hospitals were collected to train our deep learning (DL) model. Lung regions were extracted by U-net, then transformed and fed to pre-trained ResNet-50-based IDANNet (Identification and Analysis of New covid-19 Net) to produce a diagnostic probability. Fivefold cross-validation was employed to validate the application of our model. Another 318 scans of 316 patients (243/316 were diagnosed with COVID-19 pneumonia) from 2 other hospitals were enrolled prospectively as the RWDs to testify our DL model's performance and compared it with that from 3 experienced radiologists.

RESULTS

A three-dimensional DL model was successfully established. The diagnostic threshold to differentiate COVID-19 and non-COVID-19 pneumonia was 0.685 with an AUC of 0.906 (95% CI: 0.886-0.913) in the internal validation group. In the RWD cohort, our model achieved an AUC of 0.868 (95% CI: 0.851-0.876) with the sensitivity of 0.811 and the specificity of 0.822, non-inferior to the performance of 3 experienced radiologists, suggesting promising clinical practical usage.

CONCLUSIONS

The established DL model was able to achieve accurate identification of COVID-19 pneumonia from other suspected ones in the real-world situation, which could become a reliable tool in clinical routine.

KEY POINTS

• In an internal validation set, our DL model achieved the best performance to differentiate COVID-19 from non-COVID-19 pneumonia with a sensitivity of 0.836, a specificity of 0.800, and an AUC of 0.906 (95% CI: 0.886-0.913) when the threshold was set at 0.685. • In the prospective RWD cohort, our DL diagnostic model achieved a sensitivity of 0.811, a specificity of 0.822, and AUC of 0.868 (95% CI: 0.851-0.876), non-inferior to the performance of 3 experienced radiologists. • The attention heatmaps were fully generated by the model without additional manual annotation and the attention regions were highly aligned with the ROIs acquired by human radiologists for diagnosis.

Efficient Automated Disease Diagnosis Using Machine Learning Models

Recently, many researchers have designed various automated diagnosis models using various supervised learning models. An early diagnosis of disease may control the death rate due to these diseases. In this paper, an efficient automated disease diagnosis model is designed using the machine learning models. In this paper, we have selected three critical diseases such as coronavirus, heart disease, and diabetes. In the proposed model, the data are entered into an android app, the analysis is then performed in a real-time database using a pretrained machine learning model which was trained on the same dataset and deployed in firebase, and finally, the disease detection result is shown in the android app. Logistic regression is used to carry out computation for prediction. Early detection can help in identifying the risk of coronavirus, heart disease, and diabetes. Comparative analysis indicates that the proposed model can help doctors to give timely medications for treatment.

A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records

Child physical abuse is a leading cause of traumatic injury and death in children. In 2017, child abuse was responsible for 1688 fatalities in the United States, of 3.5 million children referred to Child Protection Services and 674,000 substantiated victims. While large referral hospitals maintain teams trained in Child Abuse Pediatrics, smaller community hospitals often do not have such dedicated resources to evaluate patients for potential abuse. Moreover, identification of abuse has a low margin of error, as false positive identifications lead to unwarranted separations, while false negatives allow dangerous situations to continue. This context makes the consistent detection of and response to abuse difficult, particularly given subtle signs in young, non-verbal patients. Here, we describe the development of artificial intelligence algorithms that use unstructured free-text in the electronic medical record-including notes from physicians, nurses, and social workers-to identify children who are suspected victims of physical abuse. Importantly, only the notes from time of first encounter (e.g.: birth, routine visit, sickness) to the last record before child protection team involvement were used. This allowed us to develop an algorithm using only information available prior to referral to the specialized child protection team. The study was performed in a multi-center referral pediatric hospital on patients screened for abuse within five different locations between 2015 and 2019. Of 1123 patients, 867 records were available after data cleaning and processing, and 55% were abuse-positive as determined by a multi-disciplinary team of clinical professionals. These electronic medical records were encoded with three natural language processing (NLP) algorithms-Bag of Words (BOW), Word Embeddings (WE), and Rules-Based (RB)-and used to train multiple neural network architectures. The BOW and WE encodings utilize the full free-text, while RB selects crucial phrases as identified by physicians. The best architecture was selected by average classification accuracy for the best performing model from each train-test split of a cross-validation experiment. Natural language processing coupled with neural networks detected cases of likely child abuse using only information available to clinicians prior to child protection team referral with average accuracy of 0.90±0.02 and average area under the receiver operator characteristic curve (ROC-AUC) 0.93±0.02 for the best performing Bag of Words models. The best performing rules-based models achieved average accuracy of 0.77±0.04 and average ROC-AUC 0.81±0.05, while a Word Embeddings strategy was severely limited by lack of representative embeddings. Importantly, the best performing model had a false positive rate of 8%, as compared to rates of 20% or higher in previously reported studies. This artificial intelligence approach can help screen patients for whom an abuse concern exists and streamline the identification of patients who may benefit from referral to a child protection team. Furthermore, this approach could be applied to develop computer-aided-diagnosis platforms for the challenging and often intractable problem of reliably identifying pediatric patients suffering from physical abuse.

Cognitive load management in mobile learning systems: principles and theories

With the widespread adoption of mobile technologies, mobile-assisted learning is gaining lots of momentum. This new learning paradigm promotes education across different contexts, which is a key factor that contributes to enhancing learning irrespective of the conditions and location of the learner. Therefore, it creates an authentic learning setting whereby students can make meaningful connections to the real world while learning takes place. Previous research works in the field of mobile learning showed that improper design of learning elements is still present in mobile systems and consequently results in poor dynamic content adaptation. Some attempts to adapt learning contents with appropriate instructional design principles are conducted, but with moderate exploitation of smart technological assets in mobile learning systems and limited pedagogical reflections and cognitive factors. In this paper, a learning efficiency model chart is derived using important learning factors that can be considered to enhance mobile learning experiences. Some popular learning theories are analysed and compared with the proposed learning efficiency model chart. This investigation is considered to significantly reduce complexities that exist in mobile learning platforms and promote an enhanced mobile learning experience.

Deep Neural Network-Based Screening Model for COVID-19-Infected Patients Using Chest X-Ray Images

There are limited coronavirus disease 2019 (COVID-19) testing kits, therefore, development of other diagnosis approaches is desirable. The doctors generally utilize chest X-rays and Computed Tomography (CT) scans to diagnose pneumonia, lung inflammation, abscesses, and/or enlarged lymph nodes. Since COVID-19 attacks the epithelial cells that line our respiratory tract, therefore, X-ray images are utilized in this paper, to classify the patients with infected (COVID-19 [Formula: see text]ve) and uninfected (COVID-19 [Formula: see text]ve) lungs. Almost all hospitals have X-ray imaging machines, therefore, the chest X-ray images can be used to test for COVID-19 without utilizing any kind of dedicated test kits. However, the chest X-ray-based COVID-19 classification requires a radiology expert and significant time, which is precious when COVID-19 infection is increasing at a rapid rate. Therefore, the development of an automated analysis approach is desirable to save the medical professionals’ valuable time. In this paper, a deep convolutional neural network (CNN) approach is designed and implemented. Besides, the hyper-parameters of CNN are tuned using Multi-objective Adaptive Differential Evolution (MADE). Extensive experiments are performed by considering the benchmark COVID-19 dataset. Comparative analysis reveals that the proposed technique outperforms the competitive machine learning models in terms of various performance metrics.

Transfer Learning-Based Automatic Detection of Coronavirus Disease 2019 (COVID-19) from Chest X-ray Images

Background:

Coronavirus disease 2019 (COVID-19) is an emerging infectious disease and global health crisis. Although real-time reverse transcription polymerase chain reaction (RT-PCR) is known as the most widely laboratory method to detect the COVID-19 from respiratory specimens. It suffers from several main drawbacks such as time-consuming, high false-negative results, and limited availability. Therefore, the automatically detect of COVID-19 will be required.

Objective:

This study aimed to use an automated deep convolution neural network based pre-trained transfer models for detection of COVID-19 infection in chest X-rays.

Material and Methods:

In a retrospective study, we have applied Visual Geometry Group (VGG)-16, VGG-19, MobileNet, and InceptionResNetV2 pre-trained models for detection COVID-19 infection from 348 chest X-ray images.

Results:

Our proposed models have been trained and tested on a dataset which previously prepared. The all proposed models provide accuracy greater than 90.0%. The pre-trained MobileNet model provides the highest classification performance of automated COVID-19 classification with 99.1% accuracy in comparison with other three proposed models. The plotted area under curve (AUC) of receiver operating characteristics (ROC) of VGG16, VGG19, MobileNet, and InceptionResNetV2 models are 0.92, 0.91, 0.99, and 0.97, respectively.

Conclusion:

The all proposed models were able to perform binary classification with the accuracy more than 90.0% for COVID-19 diagnosis. Our data indicated that the MobileNet can be considered as a promising model to detect COVID-19 cases. In the future, by increasing the number of samples of COVID-19 chest X-rays to the training dataset, the accuracy and robustness of our proposed models increase further.

Infrared and visible image fusion method of dual NSCT and PCNN

To solve the problem that the details of fusion images are not retained well and the information of feature targets is incomplete, we proposed a new fusion method of infrared (IR) and visible (VI) image-IR and VI image fusion method of dual non-subsampled contourlet transform (NSCT) and pulse-coupled neural network (PCNN). The method makes full use of the flexible multi-resolution and multi-directional of NSCT, and the global coupling and pulse synchronization excitation characteristics of PCNN, effectively combining the features of IR image with the texture details of VI image. Experimental results show that the algorithm can combine IR and VI image features well. At the same time, the obtained fusion image can better display the texture information of image. The fusion performance in contrast, detail information and other aspects is better than the classical fusion algorithm, which has better visual effect and evaluation index.

Deep Transfer Learning Based Classification Model for COVID-19 Disease

The COVID-19 infection is increasing at a rapid rate, with the availability of limited number of testing kits. Therefore, the development of COVID-19 testing kits is still an open area of research. Recently, many studies have shown that chest Computed Tomography (CT) images can be used for COVID-19 testing, as chest CT images show a bilateral change in COVID-19 infected patients. However, the classification of COVID-19 patients from chest CT images is not an easy task as predicting the bilateral change is defined as an ill-posed problem. Therefore, in this paper, a deep transfer learning technique is used to classify COVID-19 infected patients. Additionally, a top-2 smooth loss function with cost-sensitive attributes is also utilized to handle noisy and imbalanced COVID-19 dataset kind of problems. Experimental results reveal that the proposed deep transfer learning-based COVID-19 classification model provides efficient results as compared to the other supervised learning models.