AttGRU-HMSI: enhancing heart disease diagnosis using hybrid deep learning approach.

Heart disease is a major global cause of mortality and a major public health problem for a large number of individuals. A major issue raised by regular clinical data analysis is the recognition of cardiovascular illnesses, including heart attacks and coronary artery disease, even though early identification of heart disease can save many lives. Accurate forecasting and decision assistance may be achieved in an effective manner with machine learning (ML). Big Data, or the vast amounts of data generated by the health sector, may assist models used to make diagnostic choices by revealing hidden information or intricate patterns. This paper uses a hybrid deep learning algorithm to describe a large data analysis and visualization approach for heart disease detection. The proposed approach is intended for use with big data systems, such as Apache Hadoop. An extensive medical data collection is first subjected to an improved k-means clustering (IKC) method to remove outliers, and the remaining class distribution is then balanced using the synthetic minority over-sampling technique (SMOTE). The next step is to forecast the disease using a bio-inspired hybrid mutation-based swarm intelligence (HMSI) with an attention-based gated recurrent unit network (AttGRU) model after recursive feature elimination (RFE) has determined which features are most important. In our implementation, we compare four machine learning algorithms: SAE + ANN (sparse autoencoder + artificial neural network), LR (logistic regression), KNN (K-nearest neighbour), and naïve Bayes. The experiment results indicate that a 95.42% accuracy rate for the hybrid model's suggested heart disease prediction is attained, which effectively outperforms and overcomes the prescribed research gap in mentioned related work.

Time series prediction of insect pests in tea gardens.

BACKGROUND: Tea-garden pest control is crucial to ensure tea quality. In this context, the time-series prediction of insect pests in tea gardens is very important. Deep-learning-based time-series prediction techniques are advancing rapidly but research into their use in tea-garden pest prediction is limited. The current study investigates the time-series prediction of whitefly populations in the Tea Expo Garden, Jurong City, Jiangsu Province, China, employing three deep-learning algorithms, namely Informer, the Long Short-Term Memory (LSTM) network, and LSTM-Attention. RESULTS: The comparative analysis of the three deep-learning algorithms revealed optimal results for LSTM-Attention, with an average root mean square error (RMSE) of 2.84 and average mean absolute error (MAE) of 2.52 for 7 days' prediction length, respectively. For a prediction length of 3 days, LSTM achieved the best performance, with an average RMSE of 2.60 and an average MAE of 2.24. CONCLUSION: These findings suggest that different prediction lengths influence model performance in tea garden pest time series prediction. Deep learning could be applied satisfactorily to predict time series of insect pests in tea gardens based on LSTM-Attention. Thus, this study provides a theoretical basis for the research on the time series of pest and disease infestations in tea plants. © 2024 Society of Chemical Industry.

Enhanced detection of acrylamide using a versatile solid-state upconversion sensor through spectral and visual analysis.

Acrylamide (AM) generally forms in high-temperature processes and has been classified as a potential carcinogen. In this study, we put forward a maneuverable solid-state luminescence sensor using polydimethylsiloxane (PDMS) as the matrix coupled with upconversion nanoparticles as the indicator. The core-shell upconversion nanoparticles emitting cyan light were uniformly encapsulated in PDMS. Then it was further modified with complementary DNA of AM aptamer. The nanocrystalline fluorescein isothiocyanate isomer (FITC), coupled with AM aptamer, was attached to the surface of PDMS. FITC effectively quenched the upconversion luminescence through fluorescence resonance energy transfer (FRET). The introduction of AM resulted in preferentially bound to aptamer caused the separation of the quencher and the donor, and led to luminescence recovery. The developed sensor was applied for both spectral and visual monitoring, demonstrating a detection limit (LOD) of 1.00 nM and 1.07 nM, respectively. Importantly, in the actual foodstuffs detection, there is no obvious difference between the results of this study and the standard method, which indicates the developed method has good accuracy. Therefore, this solid-state sensor has the potential for on-site detection using a smartphone device and an Android application.

CARDPSoML: Comparative approach to analyze and predict cardiovascular disease based on medical report data and feature fusion approach.

Background and Aims: Diabetes patients are at high risk for cardiovascular disease (CVD), which makes early identification and prompt management essential. To diagnose CVD in diabetic patients, this work attempts to provide a feature-fusion strategy employing supervised learning classifiers. Methods: Preprocessing patient data is part of the method, and it includes important characteristics connected to diabetes including insulin resistance and blood glucose levels. Principal component analysis and wavelet transformations are two examples of feature extraction techniques that are used to extract pertinent characteristics. The supervised learning classifiers, such as neural networks, decision trees, and support vector machines, are then trained and assessed using these characteristics. Results: Based on the area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy, these classifiers' performance is closely evaluated. The assessment findings show that the classifiers have a good accuracy and area under the receiver operating characteristic curve value, suggesting that the suggested strategy may be useful in diagnosing CVD in patients with diabetes. Conclusion: The recommended method shows potential as a useful tool for developing clinical decision support systems and for the early detection of CVD in diabetes patients. To further improve diagnostic skills, future research projects may examine the use of bigger and more varied datasets as well as different machine learning approaches. Using an organized strategy is a crucial first step in tackling the serious problem of CVD in people with diabetes.

An augmentation aided concise CNN based architecture for COVID-19 diagnosis in real time.

Over 6.5 million people around the world have lost their lives due to the highly contagious COVID 19 virus. The virus increases the danger of fatal health effects by damaging the lungs severely. The only method to reduce mortality and contain the spread of this disease is by promptly detecting it. Recently, deep learning has become one of the most prominent approaches to CAD, helping surgeons make more informed decisions. But deep learning models are computation hungry and devices with TPUs and GPUs are needed to run these models. The current focus of machine learning research is on developing models that can be deployed on mobile and edge devices. To this end, this research aims to develop a concise convolutional neural network-based computer-aided diagnostic system for detecting the COVID 19 virus in X-ray images, which may be deployed on devices with limited processing resources, such as mobile phones and tablets. The proposed architecture aspires to use the image enhancement in first phase and data augmentation in the second phase for image pre-processing, additionally hyperparameters are also optimized to obtain the optimal parameter settings in the third phase that provide the best results. The experimental analysis has provided empirical evidence of the impact of image enhancement, data augmentation, and hyperparameter tuning on the proposed convolutional neural network model, which increased accuracy from 94 to 98%. Results from the evaluation show that the suggested method gives an accuracy of 98%, which is better than popular transfer learning models like Xception, Resnet50, and Inception.

NeuroNet19: an explainable deep neural network model for the classification of brain tumors using magnetic resonance imaging data.

Brain tumors (BTs) are one of the deadliest diseases that can significantly shorten a person's life. In recent years, deep learning has become increasingly popular for detecting and classifying BTs. In this paper, we propose a deep neural network architecture called NeuroNet19. It utilizes VGG19 as its backbone and incorporates a novel module named the Inverted Pyramid Pooling Module (iPPM). The iPPM captures multi-scale feature maps, ensuring the extraction of both local and global image contexts. This enhances the feature maps produced by the backbone, regardless of the spatial positioning or size of the tumors. To ensure the model's transparency and accountability, we employ Explainable AI. Specifically, we use Local Interpretable Model-Agnostic Explanations (LIME), which highlights the features or areas focused on while predicting individual images. NeuroNet19 is trained on four classes of BTs: glioma, meningioma, no tumor, and pituitary tumors. It is tested on a public dataset containing 7023 images. Our research demonstrates that NeuroNet19 achieves the highest accuracy at 99.3%, with precision, recall, and F1 scores at 99.2% and a Cohen Kappa coefficient (CKC) of 99%.

Recent advances in rare earth ion-doped upconversion nanomaterials: From design to their applications in food safety analysis.

The misuse of chemicals in agricultural systems and food production leads to an increase in contaminants in food, which ultimately has adverse effects on human health. This situation has prompted a demand for sophisticated detection technologies with rapid and sensitive features, as concerns over food safety and quality have grown around the globe. The rare earth ion-doped upconversion nanoparticle (UCNP)-based sensor has emerged as an innovative and promising approach for detecting and analyzing food contaminants due to its superior photophysical properties, including low autofluorescence background, deep penetration of light, low toxicity, and minimal photodamage to the biological samples. The aim of this review was to discuss an outline of the applications of UCNPs to detect contaminants in food matrices, with particular attention on the determination of heavy metals, pesticides, pathogenic bacteria, mycotoxins, and antibiotics. The review briefly discusses the mechanism of upconversion (UC) luminescence, the synthesis, modification, functionality of UCNPs, as well as the detection principles for the design of UC biosensors. Furthermore, because current UCNP research on food safety detection is still at an early stage, this review identifies several bottlenecks that must be overcome in UCNPs and discusses the future prospects for its application in the field of food analysis.

Comparison of Si-GA-PLS and Si-CARS-PLS build algorithms for quantitation of total polyphenols in black tea using the spectral analytical system.

BACKGROUND: The objective of the current study was to compare two machine learning approaches for the quantification of total polyphenols by choosing the optimal spectral intervals utilizing the synergy interval partial least squares (Si-PLS) model. To increase the resilience of built models, the genetic algorithm (GA) and competitive adaptive reweighted sampling (CARS) were applied to a subset of variables. RESULTS: The collected spectral data were divided into 19 sub-interval selections totaling 246 variables, yielding the lowest root mean square error of cross-validation (RMSECV). The performance of the model was evaluated using the correlation coefficient for calibration (RC ), prediction (RP ), RMSECV, root mean square error of prediction (RMSEP) and residual predictive deviation (RPD) value. The Si-GA-PLS model produced the following results: PCs = 9; RC = 0.915; RMSECV = 1.39; RP = 0.8878; RMSEP = 1.62; and RPD = 2.32. The performance of the Si-CARS-PLS model was noted to be best at PCs = 10, while RC = 0.9723, RMSECV = 0.81, RP = 0.9114, RMSEP = 1.45 and RPD = 2.59. CONCLUSION: The build model's prediction ability was amended in the order PLS < Si-PLS < CARS-PLS when full spectroscopic data were used and Si-PLS < Si-GA-PLS < Si-CARS-PLS when interval selection was performed with the Si-PLS model. Finally, the developed method was successfully used to quantify total polyphenols in tea. © 2023 Society of Chemical Industry.

Fusion-based strategy of CSA and mobile NIR for the quantification of free fatty acid in wheat varieties coupled with chemometrics.

The use of sensor fusion, a novel method of combining artificial senses, has become increasingly popular in the assessment of food quality. This study employed a combination of the colorimetric sensor array (CSA) and mobile near-infrared (NIR) spectroscopy to predict free fatty acids in wheat flour. In conjunction with a partial least squares model, Low- and mid-level fusion strategies were used for quantification. Accordingly, performance of the built model was evaluated based on higher correlation coefficients between calibration and prediction (RC and RP), lower root mean square error of prediction (RMSEP), and a higher residual predictive deviation (RPD). The mid-level fusion coupled PLS model produced superior data fusion findings, with RC = 0.8793, RMSECV = 7.91 mg/100 g, RP = 0.8747, RMSEP = 6.99 mg/100 g, and RPD = 2.27. The findings of the study suggest that the NIR-CSA fusion approach could be effectively applied to the prediction of free fatty acids in wheat flour.

Ultrasensitive fluorescence sensor for Hg2+ in food based on three-dimensional upconversion nanoclusters and aptamer-modulated thymine-Hg2+-thymine strategy.

Mercury (Hg2+) is a potentially toxic heavy metal ion found to be drastically deleterious to humans. Herein, an ultrasensitive fluorescence sensor was developed using three-dimensional upconversion nanoclusters (EBSUCNPs) and aptamer-modulated thymine-Hg2+-thymine strategy. The EBSUCNPs were used as the energy donors, the PDANPs served as the acceptors, and the aptamer was applied as an identification tag for Hg2+. Due to the energy transfer effect, the fluorescence of EBSUCNPs can be effectively quenched by Polydopamine nanoparticles (PDANPs). In the existence of Hg2+, T (thymine)-rich aptamers between EBSUCNPs and PDANPs were hybridized with Hg2+ to yield thymine-Hg2+-thymine and folded back to hairpin structure, causing PDANPs to detach from the EBSUCNPS and the recovery of fluorescence. Under optimum conditions, the linear sensing range of Hg2+ was 0.5-20 µg/L, and the detection limit was 0.28 µg/L. Furthermore, it exhibited excellent selectivity and anti-interference, which made it an ideal method for identifying Hg2+ in spiked samples.

Ultrasensitive hairpin mediated upconversion fluorescence biosensor for Staphylococcus aureus detection in foods and waters exploiting g-C3N4-assisted catalysis.

A novel g-C3N4 nanosheets (g-C3N4 NSs)-assisted upconversion fluorescent aptasensor was proposed for Staphylococcus aureus (S. aureus) detection by adopting hybridization chain reaction (HCR) as a sensitizer. Two hairpin (H1 and H2) structured DNA probes were engineered predicated on the partial complementary sequence (cDNA) of S. aureus aptamer and modified on the exterior of the upconversion nanoparticles (UCNPs), respectively. The presence of S. aureus initiated the HCR system and activated H1 and H2 probes to form a double-helix away from the g-C3N4 NSs vicinity. This led to the decrease in peroxidase-like activity (PA) of the g-C3N4 NSs and corresponding fluorescence recovery proportional to the concentration of S. aureus (10-106 cfu mL-1). The method was applied to real food samples with acceptable recoveries (91.1-101.6%) and further validated by traditional plate counting method (p > 0.05).

Competitive Ratiometric Aptasensing with Core-Internal Standard-Shell Structure Based on Surface-Enhanced Raman Scattering.

Reproducibility and stability are important indicators for the evaluation of quantitative sensing methods based on surface-enhanced Raman scattering (SERS) technology. Developing a SERS substrate with self-calibration capabilities is vital for effectively quantifying targets. In this work, a competitive ratiometric SERS aptasensor was developed. 4-Aminothiophenol as an internal standard (IS) was embedded in the substrate followed by gradually loading with the aptamer and methylene blue functionalizing of the complementary sequences of the aptamer (MB-cDNA). Recognition and binding of the target to the aptamer resulted in the shedding of MB-cDNA after magnetic separation reducing the SERS signal of MB, allowing for the ratiometric determination of the target based on the constant intensity from the IS. For the selective detection of okadaic acid (OA), a good negative correlation was achieved between the SERS ratiometric intensity and OA concentration in the range of 0.5-100 ng/mL. The magnetic separation strategy effectively simplifies the production steps of the aptasensor, and the ratiometric strategy effectively improved the reproducibility and stability of the OA sensing. This ratiometric aptasensor has been successfully employed to detect OA in food and environmental samples and is expected to be extended to detect other targets.

Recent advances of nanomaterial-based optical sensor for the detection of benzimidazole fungicides in food: a review.

The abuse of pesticides in agricultural land during pre- and post-harvest causes an increase of residue in agricultural products and pollution in the environment, which ultimately affects human health. Hence, it is crucially important to develop an effective detection method to quantify the trace amount of residue in food and water. However, with the rapid development of nanotechnology and considering the exclusive properties of nanomaterials, optical, and their integrated system have gained exclusive interest for accurately sensing of pesticides in food and agricultural samples to ensure food safety thanks to their unique benefit of high sensitivity, low detection limit, good selectivity and so on and making them a trending hotspot. This review focuses on recent progress in the past five years on nanomaterial-based optical, such as colorimetric, fluorescence, surface-enhanced Raman scattering (SERS), and their integrated system for the monitoring of benzimidazole fungicide (including, carbendazim, thiabendazole, and thiophanate-methyl) residue in food and water samples. This review firstly provides a brief introduction to mentioned techniques, detection mechanism, applied nanomaterials, label-free detection, target-specific detection, etc. then their specific application. Finally, challenges and perspectives in the respective field are discussed.

Recent advancement in nano-optical strategies for detection of pathogenic bacteria and their metabolites in food safety.

Pathogenic bacteria and their metabolites are the leading risk factor in food safety and are one of the major threats to human health because of the capability of triggering diseases with high morbidity and mortality. Nano-optical sensors for bacteria sensing have been greatly explored with the emergence of nanotechnology and artificial intelligence. In addition, with the rapid development of cross fusion technology, other technologies integrated nano-optical sensors show great potential in bacterial and their metabolites sensing. This review focus on nano-optical strategies for bacteria and their metabolites sensing in the field of food safety; based on surface-enhanced Raman scattering (SERS), fluorescence, and colorimetric biosensors, and their integration with the microfluidic platform, electrochemical platform, and nucleic acid amplification platform in the recent three years. Compared with the traditional techniques, nano optical-based sensors have greatly improved the sensitivity with reduced detection time and cost. However, challenges remain for the simple fabrication of biosensors and their practical application in complex matrices. Thus, bringing out improvements or novelty in the pretreatment methods will be a trend in the upcoming future.

An upconversion biosensor based on DNA hybridization and DNA-templated silver nanoclusters for the determination of acrylamide.

Acrylamide is widely present in many fried and baked foods, that has been proved as potentially carcinogenic to humans. In this work, a novel biosensor using core-shell upconversion nanoparticles (CSUCNPs) with aptamer as recognized element was designed for the determination of acrylamide. The principle of this work was based on the fluorescence resonance energy transfer (FRET) process from CSUCNPs to silver nanoclusters (AgNCs). Whereas the binding between acrylamide and the aptamer disturbed the DNA structure and inhibited the synthesis of AgNCs, which induced a higher fluorescence intensity. Under the optimal conditions, a low limit of detection (LOD) was calculated as 1.13 nM in the range of 1-105 nM. This biosensor was further applied in the spiked food samples to validate the applicability that recoveries were at the range of 78.52-117.09% with a relative standard deviation of 1.54-10.46%. The approach was compared with the standard HPLC method in great agreement (P ＞ 0.05).

A target-responsive release SERS sensor for sensitive detection of tetracycline using aptamer-gated HP-UiO-66-NH2 nanochannel strategy.

In this study, a target-responsive release Surface-enhanced Raman scattering (SERS) sensor was developed for sensitive detection of tetracycline (TTC) using aptamer-gated HP-UiO-66-NH2 nanochannel strategy. The hierarchically porous zirconium-based metal-organic frameworks (HP-UiO-66-NH2 MOFs) with high surface areas and the conjugated π-electron system were first synthesized and served as the nanocontainers. The methylene blue (MB) and gold nanoparticles (AuNPs) were then loaded in the pores of HP-UiO-66-NH2 as the signal probes and capping agent, respectively. Thereafter, aptamer was assembled on the surface of HP-UiO-66-NH2 based on the π-π stacking interaction. In the presence of TTC, the aptamer "molecular gate" was opened, resulting in the "cargo release" of MB and AuNPs. Hence, the amount of TTC could be determined by monitoring the change of SERS intensity of the supernatant. Under the optimal conditions, a good linear correlation between SERS intensity (886 cm-1) and TTC concentration was observed with the concentration from 0.01 to 10000 ng/mL, resulting in a relatively low detection limit of 0.01 ng/mL. Moreover, this method showed a promising practical application in spiked real samples (milk and pork) with recoveries of 93.23-108.79%, which confirmed its great potential in antibiotic detection.

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

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

Simultaneous determination of benzimidazole fungicides in food using signal optimized label-free HAu/Ag NS-SERS sensor.

Extensively employed pesticide in agriculture causes residue in food products that would threaten public health safety. The surface-enhanced Raman scattering (SERS) signal reliant on double sensing of carbendazim and thiabendazole in a single step is achieved without the aid of any bio-recognition element. A label-free anisotropic bimetallic hollow Au/Ag nanostars (HAu/Ag NS) SERS substrate was synthesized with numerous hot spots for Raman molecule through a galvanic displacement-free deposition. The individual and mixed analyte calibration results were compared based on the identified peak at 1224 (carbendazim) and 778 (thiabendazole) cm-1 and exhibited insignificant differences. The sensor could detect carbendazim and thiabendazole up to 4.28 × 10-4 and 6.04 × 10-4 µg·g-1 or µg·mL-1 in both individual and mixture of their extract. The recovery for accuracy and precision analysis was 91.54-98.26 % in rice and water. Finally, validation results were achieved satisfactorily (p > 0.05) with HPLC.

Catalytic hairpin activated gold-magnetic/gold-core-silver-shell rapid self-assembly for ultrasensitive Staphylococcus aureus sensing via PDMS-based SERS platform.

Staphylococcus aureus (S. aureus) has been identified as a marker of food contamination, closely associated with human health. This work designs a sensitive and rapid bio-detection strategy for S. aureus based on hybridization chain reaction-assisted surface enhanced Raman scattering (HCR-assisted-SERS) signal amplification. In this approach, the interaction between the aptamer (Apt) and its partial complementary DNA strands (cDNA) fabricated on the surface of gold-assisted magnetic nanoparticles (Au-MNPs) and the subsequent detachment of the cDNA results in the activation of the HCR process. In the HCR, a pair of hairpin structured DNA probes (H1 and H2) with sticky ends self-assembles to form a long DNA polymer. Subsequently, the output and amplification of the SERS signal were performed by conjugating 4-ATP modified Au@Ag NPs with the obtained DNA polymer via a specific Ag-S bond, and further collected through a self-administered polydimethylsiloxane (PDMS) cone-shaped support array. The precise quantification of S. aureus was performed in the concentration range of 28 to 2.8 × 106 cfu/mL, achieving a detection limit of 0.25 cfu/mL. This strategy was further applied to S. aureus detection in spiked milk samples with good recoveries (91-102%) and the relative standard deviation (4.35-8.41%). The sensing platform also showed satisfactory validation results (p > 0.05) using the traditional plate counting method. The proposed HCR-assisted SERS probe can be extended to other foodborne pathogenic bacteria types via engineering appropriate Apt and DNA initiators, thus, inspiring widespread applications in food safety and biomedical research.

A solid-phase capture probe based on upconvertion nanoparticles and inner filter effect for the determination of ampicillin in food.

Ampicillin (AMP) is commonly used to treat diseases caused by bacterial infections as a veterinary drug. However, the abuse of AMP can lead to residues in food and ultimately cause harm to humans. Thus, it is significant to construct a reliable system for AMP detection. Here, we developed an inner filter effect system based on a solid-phase capture probe and the catalysis of platinum nanoparticles (PtNPs) for AMP determination in food. In the presence of AMP, PDMS captured AMP then combined with aptamer-functionalized PtNPs, which catalyzed the oxidation of 3,3',5,5'-tetramethylbenzidine, resulting in upconversion fluorescence quenching. The results showed the fluorescence intensity of upconversion nanoparticles was related to AMP concentration (0.5-100 ng·mL-1) with an LOD of 0.32 ng·mL-1, which made quantification of AMP possible. The method also achieved a satisfactory recovery rate (96.89-112.92%) and can be used for AMP detection in food samples with selectivity and sensitivity.