Superior Recall Research Articles

Revolutionizing cardiovascular disease classification through machine learning and statistical methods.

Cardiovascular diseases (CVDs) include abnormal conditions of the heart, diseased blood vessels, structural problems of the heart, and blood clots. Traditionally, CVD has been diagnosed by clinical experts, physicians, and medical specialists, which is expensive, time-consuming, and requires expert intervention. On the other hand, cost-effective digital diagnosis of CVD is now possible because of the emergence of machine learning (ML) and statistical techniques. In this research, extensive studies were carried out to classify CVD via 19 promising ML models. To evaluate the performance and rank the ML models for CVD classification, two benchmark CVD datasets are considered from well-known sources, such as Kaggle and the UCI repository. The results are analysed considering individual datasets and their combination to assess the efficiency and reliability of ML models on the basis of various performance measures, such as precision, kappa, accuracy, recall, and the F1 score. Since some of the ML models are stochastic, we repeated the simulation 50 times for each dataset using each model and applied nonparametric statistical tests to draw decisive conclusions. The nonparametric Friedman - Nemenyi hypothesis test suggests that the Extra Tree Classifier provides statistically superior accuracy and precision compared with all other models. However, the Extreme Gradient Boost (XGBoost) classifier provides statistically superior recall, kappa, and F1 scores compared with those of all the other models. Additionally, the XGBRF classifier achieves a statistically second-best rank in terms of the recall measures.

Abstract A037: Improved liquid biopsy assay performance using novel highly accurate sequencing-by-binding (SBB) technology

Abstract Liquid biopsy is revolutionizing the field of early cancer detection research through non-invasive detection of tumor DNA in the blood. However, existing liquid biopsy assays are limited in their sensitivity for ctDNA detection at low variant allele frequencies (VAFs), with most relying on extreme sequencing depth and computational error correction to separate the true ctDNA signal from background errors. This limitation is particularly problematic in the area of early cancer detection and minimal residual disease monitoring, in which expected ctDNA allele frequencies are extremely low. Novel strategies are therefore needed to help improve liquid biopsy assay sensitivity and reduce per-sample sequencing requirements. Here we describe PacBio’s application of the Onso short-read sequencing system to enable detection of ctDNA at low VAFs using the SeraCare Complete ctDNA Mutation Mix reference standard. The Onso system makes use of a novel sequencing by binding (SBB) method to achieve 10- to 100-fold greater quality scores, with ≥90% of reads at Q40 or above. We performed targeted capture and sequencing of libraries prepared from the SeraCare reference mix diluted into WT human DNA at the following VAFs: 0.00% (WT), 0.05%, 0.10%, and 0.25%, and compared the sensitivity at each VAF for SBB compared to a competitor method using sequencing by synthesis (SBS) at varying sequencing depths. At equivalent sequencing depth (12,000X) we observed superior recall for low frequency variants (VAF = 0.05%, 0.1%) in the reference sample for Onso compared to SBS. Furthermore, SBB was able to achieve comparable sensitivity results to SBS using four- fold less sequencing (6,000X vs. 24,000X), and without the use of computational error correction. Combining SBB with error correction methods boosted sensitivity even further, suggesting an additive value for these technologies. Comparison of false positive variant calls in the WT samples showed a dramatic decrease in false positives for Onso (n=2) compared to SBS (n=49) across 10 subsampling replicates, and observed allele frequencies for Onso were closer to the expected values. In conclusion, Onso achieved superior sensitivity for ctDNA detection at compared to SBS at equivalent sequencing depths, and achieved similar performance with four- fold less sequencing and without the use of error correction. This improvement was due in part to the reduction in false positive variant calling in the WT sample, which lowers the limit of detection to maximize variant detection while maintaining high specificity. Taken together, our results demonstrate the potential of SBB to improve upon existing methods of liquid biopsy and better enable research on early cancer detection and minimal residual disease. Citation Format: Alexandra Sockell, Dan Nasko, Young Kim, Kristi Kim, Jonas Korlach. Improved liquid biopsy assay performance using novel highly accurate sequencing-by-binding (SBB) technology [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A037.

Optimizing SMS Spam Detection Using Machine Learning: A Comparative Analysis of Ensemble and Traditional Classifiers

With the rapid rise of mobile communication, Short Message Service (SMS) has become an essential platform for transmitting information. However, the growing volume of unsolicited and harmful spam messages presents significant challenges for both users and mobile network operators. This study explores the effectiveness of various machine learning models, including Random Forest, Gradient Boosting, AdaBoost, Support Vector Machine (SVM), Logistic Regression, and an Ensemble Voting Classifier, in detecting SMS spam. A dataset containing 5,572 SMS messages, labeled as either spam or ham (legitimate), was used to evaluate these models. Hyperparameter tuning was performed on each model to optimize accuracy, and the models were assessed using metrics such as precision, recall, F1-score, and accuracy. The results indicated that the SVM and Ensemble Voting Classifier achieved the highest performance, with accuracies of 0.9857 and 0.9848, respectively. Both models demonstrated superior recall for spam messages, making them highly effective for real-world spam detection systems. While Random Forest, Gradient Boosting, and AdaBoost also performed well, their slightly lower recall for spam suggests that they may misclassify some spam as legitimate messages. The study highlights the effectiveness of machine learning models in addressing the SMS spam problem, particularly when using ensemble methods. Future research should focus on addressing class imbalance and exploring deep learning approaches to further enhance model performance. These findings offer valuable insights for developing more accurate and scalable SMS spam detection systems.

Multi-Layer Perceptron and Radial Basis Function Networks in Predictive Modeling of Churn for Mobile Telecommunications Based on Usage Patterns

Customer retention is a key priority for mobile telecommunications companies, as acquiring new customers is significantly more costly than retaining existing ones. A major challenge in this field is predicting customer churn—users discontinuing services. Traditional predictive models such as rule-based systems often struggle with the complex, non-linear nature of customer behavior. To address this, we propose the use of deep learning techniques, specifically multi-layer perceptron (MLP) and radial basis function (RBF) networks, to improve the accuracy of churn predictions. However, while neural networks excel in predictive performance, they are often criticized for being “black-box” models, lacking interpretability. A real-world data set is considered, which originally contained information about 15,000 randomly selected clients. Various network structures and configurations are analyzed. The obtained results are compared with results generated using fuzzy rule-based and rough-set rule-based systems. The MLP model achieved an almost perfect accuracy of 0.999 with an F-measure of 0.989, outperforming traditional methods such as fuzzy rule-based and rough-set systems. Although the RBF model slightly lagged in accuracy, it demonstrated a superior recall of 0.993, indicating better identification of potential churners. These results demonstrate that neural network models significantly enhance predictive performance in churn modeling. The interpretability of the model is also discussed since it bears significance in real applications. Our contribution lies in showing that deep learning methods significantly enhance churn prediction accuracy, though the challenge of model interpretability remains a critical area for future work.

Circadian Rhythms in Conditioned Threat Extinction Reflect Time-of-Day Differences in Ventromedial Prefrontal Cortex Neural Processing.

Circadian rhythms in conditioned threat extinction emerge from a tissue-level circadian timekeeper, or local clock, in the ventromedial prefrontal cortex (vmPFC). Yet it remains unclear how this local clock contributes to extinction-dependent adaptations. Here we used single-unit and local field potential analyses to interrogate neural activity in the male rat vmPFC during repeated extinction sessions at different times of day. In association with superior recall of a remote extinction memory during the circadian active phase, vmPFC putative principal neurons exhibited phasic firing that was amplified for cue presentations and diminished at transitions in freezing behavior. Coupling of vmPFC gamma amplitude to the phase of low-frequency oscillations was greater during freezing than mobility, and this difference was augmented during the active phase, highlighting a time-of-day dependence in the organization of freezing- versus mobility-associated cell assemblies. Additionally, a greater proportion of vmPFC neurons were phase-locked to low-frequency oscillations during the active phase, consistent with heightened neural excitability at this time of day. Our results suggest that daily fluctuations in vmPFC excitability precipitate enhanced neural recruitment into extinction-based cell assemblies during the active phase, providing a potential mechanism by which the vmPFC local clock modulates circuit and behavioral plasticity during conditioned threat extinction.

Detection and Classification of Cannabis Seeds Using RetinaNet and Faster R-CNN

The rapid growth of the cannabis industry necessitates accurate and efficient methods for detecting and classifying cannabis seed varieties, which is crucial for quality control, regulatory compliance, and genetic research. This study presents a deep learning approach to automate the detection and classification of 17 different cannabis seed varieties, addressing the limitations of manual inspection processes. Leveraging a unique dataset of 3319 high-resolution seed images, we employ self-supervised bounding box annotation using the Grounding DINO model. Our research evaluates two prominent object detection models, Faster R-CNN and RetinaNet, with different backbone architectures (ResNet50, ResNet101, and ResNeXt101). Extensive experiments reveal that RetinaNet with a ResNet101 backbone achieves the highest strict mean average precision (mAP) of 0.9458 at IoU 0.5–0.95. At the same time, Faster R-CNN with ResNet50 excels at the relaxed 0.5 IoU threshold (0.9428 mAP) and maintains superior recall. Notably, the ResNeXt101 backbone, despite its complexity, shows slightly lower performance across most metrics than ResNet architectures. In terms of inference speed, the Faster R-CNN with a ResNeXt101 backbone demonstrates the fastest processing at 17.5 frames per second. This comprehensive evaluation, including performance-speed trade-offs and per-class detection analysis, highlights the potential of deep learning for automating cannabis seed analysis. Our findings address challenges in seed purity, consistency, and regulatory adherence within the cannabis agricultural domain, paving the way for improved productivity and quality control in the industry.

VolcanoSV enables accurate and robust structural variant calling in diploid genomes from single-molecule long read sequencing

Structural variants (SVs) significantly contribute to human genome diversity and play a crucial role in precision medicine. Although advancements in single-molecule long-read sequencing offer a groundbreaking resource for SV detection, identifying SV breakpoints and sequences accurately and robustly remains challenging. We introduce VolcanoSV, an innovative hybrid SV detection pipeline that utilizes both a reference genome and local de novo assembly to generate a phased diploid assembly. VolcanoSV uses phased SNPs and unique k-mer similarity analysis, enabling precise haplotype-resolved SV discovery. VolcanoSV is adept at constructing comprehensive genetic maps encompassing SNPs, small indels, and all types of SVs, making it well-suited for human genomics studies. Our extensive experiments demonstrate that VolcanoSV surpasses state-of-the-art assembly-based tools in the detection of insertion and deletion SVs, exhibiting superior recall, precision, F1 scores, and genotype accuracy across a diverse range of datasets, including low-coverage (10x) datasets. VolcanoSV outperforms assembly-based tools in the identification of complex SVs, including translocations, duplications, and inversions, in both simulated and real cancer data. Moreover, VolcanoSV is robust to various evaluation parameters and accurately identifies breakpoints and SV sequences.

In-Game Advertising: Role of Virtual Reality and Persuasion Knowledge

ABSTRACT This experimental research examines the effect of brand placement (prominent or subtle) and use of technology (2D or head-mounted-display (HMD) VR) in in-game advertising (IGA) on brand recall and how persuasion knowledge moderates this relationship. Results showed that for a prominent brand placement, a 2D game resulted in higher brand recall than an HMD VR game. Players with high persuasion knowledge, showed superior recall for the embedded brands in two game conditions: a prominent placed 2D game and a prominent placed HMDVR game. However, insignificant results were found for a subtle brand placement-2D game and a subtle placement-HMD VR game irrespective of whether the player has high or low persuasion knowledge. Further the study provides strong theoretical and managerial implications and avenues for future research in the gamified-advertising context.

SwinYOLOv7: Robust ship detection in complex synthetic aperture radar images

Using satellite-based SAR (Synthetic Aperture Radar) imagery to detect and track ships is a formidable challenge. However, accurate analysis is hampered by inherent difficulties such as obscured edges, multiple targets, varying dimensions and complex backgrounds. These factors contribute to a poor signal-to-noise ratio. Various artificial intelligence models have been developed to improve these problems, especially with YOLO-based models. To overcome the above challenges and achieve robust performance, this study presents a model called SwinYOLOv7, a novel fusion of the YOLOv7 framework with the Features Pyramid Network and the Swin Transformer using ground-breaking anchor-free detection algorithms. This innovative method aims to increase the accuracy of vessel detection while reducing the impact of background clutter. The proposed model improved by YOLOv7 examined three different datasets in detail: SRSDD-v1.0, HRSID, and SSDD to optimize the performance of the model. The training process was consistently verified using superior recall, precision, and F1-score values, which can be easily compared with previous studies. The results show that the model using the Swin Transformer attention mechanism and using an image size of 640×640 achieves the highest accuracy of 96.59%. Alternative attention mechanisms, including the Squeeze-and-Excitation Network (SEnet), the Convolutional Block Attention Module (CBAM), Channel Attention (CA) and Efficient Channel Attention (ECA), deliver poorer accuracy rates. The combination of YOLOv7 and Swin Transformer yielded encouraging results that enabled the proposed model to outperform the current benchmarking models. Therefore, the proposed model provides a compelling solution to ensure accurate vessel identification in complex search and rescue scenarios.

Enhanced Vision Transformer and Transfer Learning Approach to Improve Rice Disease Recognition

In the evolving landscape of agricultural technology, recognizing rice diseases through computational models is a critical challenge, predominantly addressed through Convolutional Neural Networks (CNN). However, the localized feature extraction of CNNs often falls short in complex scenarios, necessitating a shift towards models capable of global contextual understanding. Enter the Vision Transformer (ViT), a paradigm-shifting deep learning model that leverages a self-attention mechanism to transcend the limitations of CNNs by capturing image features in a comprehensive global context. This research embarks on an ambitious journey to refine and adapt the ViT Base(B) transfer learning model for the nuanced task of rice disease recognition. Through meticulous reconfiguration, layer augmentation, and hyperparameter tuning, the study tests the model's prowess across both balanced and imbalanced datasets, revealing its remarkable ability to outperform traditional CNN models, including VGG, MobileNet, and EfficientNet. The proposed ViT model not only achieved superior recall (0.9792), precision (0.9815), specificity (0.9938), f1-score (0.9791), and accuracy (0.9792) on challenging datasets but also established a new benchmark in rice disease recognition, underscoring its potential as a transformative tool in the agricultural domain. This work not only showcases the ViT model's superior performance and stability across diverse tasks and datasets but also illuminates its potential to revolutionize rice disease recognition, setting the stage for future explorations in agricultural AI applications.

Machine learning based detection of T–wave alternans in real ambulatory conditions

Background and objectiveT-wave alternans (TWA) is a fluctuation in the repolarization morphology of the ECG. It is associated with cardiac instability and sudden cardiac death risk. Diverse methods have been proposed for TWA analysis. However, TWA detection in ambulatory settings remains a challenge due to the absence of standardized evaluation metrics and detection thresholds. MethodsIn this work we use traditional TWA analysis signal processing-based methods for feature extraction, and two machine learning (ML) methods, namely, K–nearest–neighbor (KNN) and random forest (RF), for TWA detection, addressing hyper–parameter tuning and feature selection. The final goal is the detection in ambulatory recordings of short, non-sustained and sparse TWA events. ResultsWe train ML methods to detect a wide variety of alternant voltage from 20 to 100 μV, i.e., ranging from non–visible micro–alternans to TWA of higher amplitudes, to recognize a wide range in concordance to risk stratification. In classification, RF outperforms significantly the recall in comparison with the signal processing methods, at the expense of a small lost in precision. Despite ambulatory detection stands for an imbalanced category context, the trained ML systems always outperform signal processing methods. ConclusionsWe propose a comprehensive integration of multiple variables inspired by TWA signal processing methods to fed learning-based methods. ML models consistently outperform the best signal processing methods, yielding superior recall scores.

Personalized learning paths recommendation system with collaborative filtering and content-based approaches

Recommender systems have undergone a transformative evolution, reshaping user interactions across diverse domains. Notably, the emphasis on personalized learning paths has grown significantly in education. This research paper delves into the performance evaluation of User-based Collaborative Filtering and Content-based recommendation techniques to develop innovative recommender systems explicitly tailored to Information Systems students. By integrating the primary dataset collection rooted within the Knowledge - Skill - Attitude framework for students in the Faculty of Information Systems at the University of Economics and Law, this study assesses how effectively these two separate models develop personalized recommendation systems. Furthermore, the empirical evaluation of two distinct models, the Collaborative Filtering and Content-Based approach, across key metrics such as Precision, Recall, and F1-Score, provides a comprehensive view of their effectiveness in generating a Recommendation System for the University of Economics and Law. Findings reveal that the Collaborative Filtering approach excels in Precision, achieving a perfect score. At the same time, the Content-based technique demonstrates superior recall capabilities, suggesting its potential to cater to diverse educational needs. This paper also highlights the transformative role of recommendation systems in higher education, particularly in enhancing student engagement through personalized learning experiences and aligning curricula with industry requirements. Recognizing the limitations inherent in deploying either model independently, future research should propose a hybrid approach that combines the strengths of both Collaborative Filtering and Content-based methods, aiming to mitigate the existing drawbacks of the distinct model. The findings provide actionable insights for students, universities, and businesses to enhance educational content and career development tools and pave the way for future research on hybrid recommendation methodologies, which promise a more tailored and efficient learning experience for learners.

Comparative Performance Evaluation of One-Stage and Two-Stage Object Detectors for Screw Head Detection and Classification in Disassembly Processes

The process of manually detecting and removing screws during disassembly can be time-consuming and demanding. Automated systems utilizing imaging and deep learning can rapidly and accurately identify screws based on features like head shape and size. Different deep learning methods have varying screw detection capabilities. Choosing the right method significantly impacts system effectiveness, robustness and efficiency. Several generic deep learning architectures have been proposed to address this problem. However, there is little guidance on their suitability for specific scenarios. This paper aims to provide qualified guidance for selecting suitable deep learning methods for screw head detection. The proposed approach involves researching existing object detection methods and choosing two representatives – one employing a one-stage approach, the other using two-stage. These selected methods will be implemented identically and their performance evaluated via rigorous analysis and comparison. The dataset comprises synthetic and real images of 6 screw types across 3 products. YOLOv5 was selected for one-stage detectors, Faster R-CNN for two-stage. Results show the one-stage YOLOv5 generally outperforms Faster R-CNN in precision, recall, speed and training times, while Faster R-CNN delivered superior recall with smaller training datasets.

Human memory for real-world solid objects is not predicted by responses to image displays.

In experimental psychology and neuroscience, computerized image stimuli are typically used as artificial proxies for real-world objects to understand brain and behavior. Here, in a series of five experiments (n = 165), we studied human memory for objects presented as tangible solids versus computerized images. We found that recall for solids was superior to images, both immediately after learning, and after a 24-hr delay. A "realness advantage" was also evident relative to three-dimensional (3-D) stereoscopic images, and when solids were viewed monocularly, arguing against explanations based on the presence of binocular depth cues in the stimulus. Critically, memory for solids was modulated by physical distance, with superior recall for objects positioned within versus outside of observers' reach, whereas recall for images was unaffected by distance. We conclude that solids are processed quantitatively and qualitatively differently in episodic memory than are images, suggesting caution in assuming that artifice can always substitute for reality. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

An Automated Fire Code Compliance Checking Jointly Using Building Information Models and Natural Language Processing

Fire checking is indispensable for guaranteeing the fire safety of buildings as it reviews the compliance of the building with fire codes and regulations. Automated Compliance Checking (ACC) systems that check building data utilizing Building Information Modeling (BIM) against fire codes have emerged as an active field of research. Substantial efforts have focused on analyzing the properties of the building components. However, the analysis of the spatial geometric relationships of building components has received inadequate attention. The present study proposes a novel ACC system leveraging Natural Language Processing (NLP) techniques to review the spatial geometric relationships of building components in BIM models. First, a framework for a BIM-based ACC system is delineated and decomposes ACC into three constituent subtasks: building model parsing, code knowledge translation, and compliance check result reporting. Second, an approach for structured processing of spatial geometric stipulations in fire codes using NLP is presented to review the geometric relationships between components in building models. Finally, the system’s performance is assessed by testing fire code compliance across various building types utilizing BIM models. The empirical findings demonstrate that the system achieves superior recall compared with the manually formulated gold standard, with the ACC system enabling quick, accurate, and comprehensive automated compliance checking.

Which modality results in superior recall for students: Handwriting, typing, or drawing?

One of the most common interests among cognitive psychologists is establishing ways to enhance human learning. An additional layer of complexity has been brought on by the rapid evolution of technology. Specifically, examining if the mechanisms involved in typing differ from those involved in handwriting. The literature concerning the implications of encoding modality on memory have been inconclusive. This present research examined whether encoding modality resulted in performance differences for word recall. Wammes et al.’s (2016) drawing versus handwriting methodology was utilized with the addition of a typing condition. The results replicated the drawing effect, whereby drawn words were better recalled than handwritten ones. Overall, the evidence did not suggest that the mechanisms involved in handwriting led to better free recall than those involved in typing. However, if the pen is indeed mightier than the keyboard (Mueller & Oppenheimer, 2014), then the effect is not explained by visual attention or sensorimotor action differences between modalities. Implications for education are discussed.

Multi-vendor evaluation of artificial intelligence as an independent reader for double reading in breast cancer screening on 275,900 mammograms

BackgroundDouble reading (DR) in screening mammography increases cancer detection and lowers recall rates, but has sustainability challenges due to workforce shortages. Artificial intelligence (AI) as an independent reader (IR) in DR may provide a cost-effective solution with the potential to improve screening performance. Evidence for AI to generalise across different patient populations, screening programmes and equipment vendors, however, is still lacking.MethodsThis retrospective study simulated DR with AI as an IR, using data representative of real-world deployments (275,900 cases, 177,882 participants) from four mammography equipment vendors, seven screening sites, and two countries. Non-inferiority and superiority were assessed for relevant screening metrics.ResultsDR with AI, compared with human DR, showed at least non-inferior recall rate, cancer detection rate, sensitivity, specificity and positive predictive value (PPV) for each mammography vendor and site, and superior recall rate, specificity, and PPV for some. The simulation indicates that using AI would have increased arbitration rate (3.3% to 12.3%), but could have reduced human workload by 30.0% to 44.8%.ConclusionsAI has potential as an IR in the DR workflow across different screening programmes, mammography equipment and geographies, substantially reducing human reader workload while maintaining or improving standard of care.Trial registrationISRCTN18056078 (20/03/2019; retrospectively registered).

Do we remember when to better recall what? Repetition benefits are probably not due to explicit temporal context memory

A number of temporal context-based theories of the spacing effect assume that temporal context is retrieved during repetitions, allowing better memory on a later test. Since associations in memory are often bidirectional, if we can use temporal context to recall an item, perhaps we can also use the item to explicitly recall its temporal context. If so, explicit memory-for-when during study would be a good predictor of later recall for repeated items. Experiment 1 appeared to be consistent with our predictions; items with memory-for-when during List 2 showed superior recall accuracy on a final free recall test. However, the effect was primarily driven by better memory-for-when in the primacy region. Experiment 2 used an incidental learning procedure during List 1 to reduce this confound since the primacy region is greatly attenuated in incidental learning. While the benefits of having memory-for-when persisted in Experiment 2, they were again attributable solely to the first few items on the list. The results suggest that explicit temporal context information is unlikely to underlie the benefits of spaced repetition. Either temporal context information is strengthened implicitly, our measures of context failed to capture the type of context used in spacing, or other mechanisms entirely produce the benefits of repetition.

Art of using music-product congruence and lyrics in radio-ads

PurposeThis research aims to exhibit the impacts of vocal music vs instrumental music on ad-recall from the perspectives of attention and elaboration.Design/methodology/approachA 2 music-product congruence (congruence vs incongruence) × 2 music lyrics (lyrics vs no lyrics) between-subject measures design is used. 180 management students participated in the study. A 2 × 2 between-subjects ANOVA is used to test the hypotheses.FindingsResults showed that the instrumental rendition of an ad-song prompted higher ad-recall over the vocal variant. The instrumental rendition provoked the subjects to create the verses or lyrics in their minds, prompting superior recall. Further, it was found that a music-product congruent ad resulted into higher ad-recall than an incongruent ad. Moreover, for a congruent ad condition, the instrumental version of ad-song resulted into higher ad-recall than the vocal version of ad-song. On the other hand, for an incongruent ad condition, the instrumental version as well as the vocal version of ad-song resulted into same level of ad-recall.Research limitations/implicationsThe study offers important implications for marketers and advertisers in terms of effective ad-designing and execution considering lyrics and music-product congruence as important factors in the context of radio advertising.Originality/valueSince very little research has been done focusing on the combined effect of music lyrics and music-product congruence relationship on ad-recall from attention and elaboration perspectives, this paper scores as a pioneering study of its kind in India.

In-depth analysis of SARS-CoV-2-specific T cells reveals diverse differentiation hierarchies in vaccinated individuals.

SARS-CoV-2 vaccines pose as the most effective approach for mitigating the COVID-19 pandemic. High-degree efficacy of SARS-CoV-2 vaccines in clinical trials indicates that vaccination invariably induces an adaptive immune response. However, the emergence of breakthrough infections in vaccinated individuals suggests that the breadth and magnitude of vaccine-induced adaptive immune response may vary. We assessed vaccine-induced SARS-CoV-2 T cell response in 21 vaccinated individuals and found that SARS-CoV-2–specific T cells, which were mainly CD4+ T cells, were invariably detected in all individuals but the response was varied. We then investigated differentiation states and cytokine profiles to identify immune features associated with superior recall function and longevity. We identified SARS-CoV-2–specific CD4+ T cells were polyfunctional and produced high levels of IL-2, which could be associated with superior longevity. Based on the breadth and magnitude of vaccine-induced SARS-CoV-2 response, we identified 2 distinct response groups: individuals with high abundance versus low abundance of SARS-CoV-2–specific T cells. The fractions of TNF-α– and IL-2–producing SARS-CoV-2 T cells were the main determinants distinguishing high versus low responders. Last, we identified that the majority of vaccine-induced SARS-CoV-2 T cells were reactive against non-mutated regions of mutant S-protein, suggesting that vaccine-induced SARS-CoV-2 T cells could provide continued protection against emerging variants of concern.