Browse publications by year: 2024

Fulltext Autologous Serum Therapy in Recalcitrant Chronic Spontaneous Urticaria: Experience from Three Dermatology Clinics in Malaysia

Ting Pao Lin I, Ghazali NI, Teo Y, Lai SL, Bakhtiar MF, Tang MM

Indian J Dermatol, 2024;69(5):406-410.
PMID: 39649968 DOI: 10.4103/ijd.ijd_172_24

Autohemotherapy is a commonly used treatment for recalcitrant chronic urticaria in some countries. Herein we report our experience using autologous serum therapy in eight patients with recalcitrant chronic spontaneous urticaria. Autologous serum therapy was initiated weekly for nine weeks followed by every fortnightly. Urticaria Activity Score (UAS) 7, Dermatology Life Quality Index (DLQI), and reduction of antihistamine usage were used to assess the treatment response. Eight patients (age range: 25-76 years old; four females and four males) had one to ten years of duration of recalcitrant chronic spontaneous urticaria. All failed to respond to high doses of second-generation antihistamines and five to immune-modulating agents. Three did not respond to omalizumab. At week nine, the reduction of UAS7 ranged from 76.2% to 100%. There was more than an 80% improvement in DLQI in all patients. The number of wheals seemed to be reduced first followed by pruritus. Three patients had stopped antihistamines by week eight of treatment. No adverse events were reported in all eight patients. Autologous serum therapy may serve as an alternative treatment for recalcitrant chronic spontaneous urticaria. Apart from the practicality, which requires frequent clinic visits, venipuncture, and centrifugation, it is cheap and effective with minimal adverse events.
Fulltext Effect of total knee arthroplasty on quadriceps and hamstring muscle recovery in individuals with knee osteoarthritis: A proposed systematic review and meta-analysis protocol

Shetty S, Gudi N, S EAR, Maiya GA, Kg MR, Vijayan S, et al.

MethodsX, 2024 Dec;13:103057.
PMID: 39650115 DOI: 10.1016/j.mex.2024.103057

Knee osteoarthritis is a prevalent degenerative joint disease leading to pain, stiffness, reduced mobility in the knee, and muscle weakness. Total knee arthroplasty (TKA) is typically the preferred surgical treatment option for moderate to severe osteoarthritis. A deeper understanding of quadriceps and hamstring muscle activation after TKA is needed to monitor patient prognosis postoperatively. This review aims to synthesize and summarize the available evidence on the effects of TKA on quadriceps and hamstring muscle recovery in individuals with knee osteoarthritis. Electronic databases such as PubMed, Scopus, Web of Science, CINAHL, EMBASE, and ProQuest Health & Medical Complete will be searched using relevant keywords related to knee osteoarthritis, total knee arthroplasty, surface electromyography and quadriceps and hamstring muscle recovery. Two reviewers will independently assess the related studies and extract data from the chosen articles. The Cochrane Risk of Bias Tool-1 and the Joanna Briggs critical appraisal checklist will be used to assess the methodological quality of the studies based on study design. Based on the relevance of the data and number of studies, a meta-analysis approach will be used to obtain a unified outcome. This review's findings will support clinical decision-making and offer direction for future researchers studying this patient population. Bullet points that outline the protocol•This proposed systematic review, and meta-analysis will summarize and synthesize literature on the effect of total knee arthroplasty (TKA) on quadriceps and hamstring muscle recovery in individuals with knee osteoarthritis.•This review offers important insights into knee muscle recovery following TKA, assisting orthopedic surgeons and rehabilitation professionals in improving their clinical decision-making.
Fulltext Implementing federated learning over VPN-based wireless backhaul networks for healthcare systems

Mahmood A, Hakim Azizul Z, Zakariah M, Brahim Belhaouari S, Altameem A, Ramli R, et al.

PeerJ Comput Sci, 2024;10:e2422.
PMID: 39650347 DOI: 10.7717/peerj-cs.2422

Federated learning (FL) is a popular method where edge devices work together to train machine learning models. This study introduces an efficient network for analyzing healthcare records. It uses VPN technology and applies a federated learning approach over a wireless backhaul network. The study compares different wireless backhaul channels, including terahertz (THz), E/V band (mmWave), and microwave, for their effectiveness. We looked closely at a suggested FL network that uses VPN technology over awireless backhaul network. We compared it with the standard method and found that using the FedAvg algorithm with Terahertz (THz) for communication gave the best accuracy. The time it took to reach a conclusion improved a lot, going from 55 seconds to an impressive 38 seconds. This emphasizes how having a faster communication link makes FL networks work much better. Furthermore, a three-step plan was executed to boost security, adopting a multi-layered method to safeguard the FL network and its confidential data. The first step involves integrating a private network into the current telecom infrastructure, establishing an initial layer of security. To enhance security further, licensed frequency channels are introduced, providing an extra layer of protection. The highest level of security is achieved by combining a private network with licensed frequency channels, complemented by an additional layer of security through VPN-based measures. This comprehensive strategy ensures the application of strong security protocols.
Fulltext A hybrid model integrating recurrent neural networks and the semi-supervised support vector machine for identification of early student dropout risk

Nguyen Thi Cam H, Sarlan A, Arshad NI

PeerJ Comput Sci, 2024;10:e2572.
PMID: 39650364 DOI: 10.7717/peerj-cs.2572

BACKGROUND: Student dropout rates are one of the major concerns of educational institutions because they affect the success and efficacy of them. In order to help students continue their learning and achieve a better future, there is a need to identify the risk of student dropout. However, it is challenging to accurately identify the student dropout risk in the preliminary stages considering the complexities associated with it. This research develops an efficient prediction model using machine learning (ML) and deep learning (DL) techniques for identifying student dropouts in both small and big educational datasets.
METHODS: A hybrid prediction model DeepS3VM is designed by integrating a Semi-supervised support vector machine (S3VM) model with a recurrent neural network (RNN) to capture sequential patterns in student dropout prediction. In addition, a personalized recommendation system (PRS) is developed to recommend personalized learning paths for students who are at risk of dropping out. The potential of the DeepS3VM is evaluated with respect to various evaluation metrics and the results are compared with various existing models such as Random Forest (RF), decision tree (DT), XGBoost, artificial neural network (ANN) and convolutional neural network (CNN).
RESULTS: The DeepS3VM model demonstrates outstanding accuracy at 92.54%, surpassing other current models. This confirms the model's effectiveness in precisely identifying the risk of student dropout. The dataset used for this analysis was obtained from the student management system of a private university in Vietnam and generated from an initial 243 records to a total of one hundred thousand records.
An automated AI-powered IoT algorithm with data processing and noise elimination for plant monitoring and actuating

Ali MAH, Moiduddin K, Nukman Y, Abd Razak B, Aboudaif MK, Thangaraj M

PeerJ Comput Sci, 2024;10:e2448.
PMID: 39650371 DOI: 10.7717/peerj-cs.2448

This article aims to develop a novel Artificial Intelligence-powered Internet of Things (AI-powered IoT) system that can automatically monitor the conditions of the plant (crop) and apply the necessary action without human interaction. The system can remotely send a report on the plant conditions to the farmers through IoT, enabling them for tracking the healthiness of plants. Chili plant has been selected to test the proposed AI-powered IoT monitoring and actuating system as it is so sensitive to the soil moisture, weather changes and can be attacked by several types of diseases. The structure of the proposed system is passed through five main stages, namely, AI-powered IoT system design, prototype fabrication, signal and image processing, noise elimination and proposed system testing. The prototype for monitoring is equipped with multiple sensors, namely, soil moisture, carbon dioxide (CO2) detector, temperature, and camera sensors, which are utilized to continuously monitor the conditions of the plant. Several signal and image processing operations have been applied on the acquired sensors data to prepare them for further post-processing stage. In the post processing step, a new AI based noise elimination algorithm has been introduced to eliminate the noise in the images and take the right actions which are performed using actuators such as pumps, fans to make the necessary actions. The experimental results show that the prototype is functioning well with the proposed AI-powered IoT algorithm, where the water pump, exhausted fan and pesticide pump are actuated when the sensors detect a low moisture level, high CO2 concentration level, and video processing-based pests' detection, respectively. The results also show that the algorithm is capable to detect the pests on the leaves with 75% successful rate.
Fulltext A novel deep neural network-based technique for network embedding

Benbatata S, Saoud B, Shayea I, Alsharabi N, Alhammadi A, Alferaidi A, et al.

PeerJ Comput Sci, 2024;10:e2489.
PMID: 39650372 DOI: 10.7717/peerj-cs.2489

In this paper, the graph segmentation (GSeg) method has been proposed. This solution is a novel graph neural network framework for network embedding that leverages the inherent characteristics of nodes and the underlying local network topology. The key innovation of GSeg lies in its encoder-decoder architecture, which is specifically designed to preserve the network's structural properties. The key contributions of GSeg are: (1) a novel graph neural network architecture that effectively captures local and global network structures, and (2) a robust node representation learning approach that achieves superior performance in various network analysis tasks. The methodology employed in our study involves the utilization of a graph neural network framework for the acquisition of node representations. The design leverages the inherent characteristics of nodes and the underlying local network topology. To enhance the architectural framework of encoder- decoder networks, the GSeg model is specifically devised to exhibit a structural resemblance to the SegNet model. The obtained empirical results on multiple benchmark datasets demonstrate that the GSeg outperforms existing state-of-the-art methods in terms of network structure preservation and prediction accuracy for downstream tasks. The proposed technique has potential utility across a range of practical applications in the real world.
Federated learning for millimeter-wave spectrum in 6G networks: applications, challenges, way forward and open research issues

Qamar F, Kazmi SHA, Siddiqui MUA, Hassan R, Zainol Ariffin KA

PeerJ Comput Sci, 2024;10:e2360.
PMID: 39650377 DOI: 10.7717/peerj-cs.2360

The emergence of 6G networks promises ultra-high data rates and unprecedented connectivity. However, the effective utilization of the millimeter-wave (mmWave) as a critical enabler of foreseen potential in 6G, poses significant challenges due to its unique propagation characteristics and security concerns. Deep learning (DL)/machine learning (ML) based approaches emerged as potential solutions; however, DL/ML contains centralization and data privacy issues. Therefore, federated learning (FL), an innovative decentralized DL/ML paradigm, offers a promising avenue to tackle these challenges by enabling collaborative model training across distributed devices while preserving data privacy. After a comprehensive exploration of FL enabled 6G networks, this review identifies the specific applications of mmWave communications in the context of FL enabled 6G networks. Thereby, this article discusses particular challenges faced in the adaption of FL enabled mmWave communication in 6G; including bandwidth consumption, power consumption and synchronization requirements. In view of the identified challenges, this study proposed a way forward called Federated Energy-Aware Dynamic Synchronization with Bandwidth-Optimization (FEADSBO). Moreover, this review highlights pertinent open research issues by synthesizing current advancements and research efforts. Through this review, we provide a roadmap to harness the synergies between FL and mmWave, offering insights to reshape the landscape of 6G networks.
Fulltext Federated learning-driven collaborative recommendation system for multi-modal art analysis and enhanced recommendations

Gong B, Mahsan IP, Xiao J

PeerJ Comput Sci, 2024;10:e2405.
PMID: 39650398 DOI: 10.7717/peerj-cs.2405

With the rapid development of artificial intelligence technology, recommendation systems have been widely applied in various fields. However, in the art field, art similarity search and recommendation systems face unique challenges, namely data privacy and copyright protection issues. To address these problems, this article proposes a cross-institutional artwork similarity search and recommendation system (AI-based Collaborative Recommendation System (AICRS) framework) that combines multimodal data fusion and federated learning. This system uses pre-trained convolutional neural networks (CNN) and Bidirectional Encoder Representation from Transformers (BERT) models to extract features from image and text data. It then uses a federated learning framework to train models locally at each participating institution and aggregate parameters to optimize the global model. Experimental results show that the AICRS framework achieves a final accuracy of 92.02% on the SemArt dataset, compared to 81.52% and 83.44% for traditional CNN and Long Short-Term Memory (LSTM) models, respectively. The final loss value of the AICRS framework is 0.1284, which is better than the 0.248 and 0.188 of CNN and LSTM models. The research results of this article not only provide an effective technical solution but also offer strong support for the recommendation and protection of artworks in practice.
Level up your coding: a systematic review of personalized, cognitive, and gamified learning in programming education

Ishaq K, Alvi A, Haq MIU, Rosdi F, Choudhry AN, Anjum A, et al.

PeerJ Comput Sci, 2024;10:e2310.
PMID: 39650413 DOI: 10.7717/peerj-cs.2310

Programming courses in computer science play a crucial role as they often serve as students' initial exposure to computer programming. Many university students find introductory courses overwhelming due to the vast amount of information they need to grasp. The traditional teacher-lecturer model used in university lecture halls frequently leads to low motivation and student participation. Personalized gamification, a pedagogical approach that blends gamification and personalized learning, offers a solution to this challenge. This approach integrates gaming elements and personalized learning strategies to motivate and engage students while addressing their individual learning needs and differences. A comprehensive literature review analyzes 101 studies based on research design, intervention, outcome measures, and quality assessment. The findings suggest that personalized gamification can enhance student cognition in programming courses by boosting motivation, engagement, and learning outcomes. However, the effectiveness of personalized gamification depends on various factors, including the types of gaming elements used, the level of personalization, and learner characteristics. This article offers insights into designing and implementing effective personalized gamification interventions in programming courses. The findings may inform educators and researchers in programming education about the potential benefits of personalized gamification and its implications for educational practice.
Fulltext Advanced neural network-based model for predicting court decisions on child custody

Abrar M, Salam A, Ullah F, Nadeem M, AlSalman H, Mukred M, et al.

PeerJ Comput Sci, 2024;10:e2293.
PMID: 39650418 DOI: 10.7717/peerj-cs.2293

Predicting court rulings has gained attention over the past years. The court rulings are among the most important documents in all legal systems, profoundly impacting the lives of the children in case of divorce or separation. It is evident from literature that Natural language processing (NLP) and machine learning (ML) are widely used in the prediction of court rulings. In general, the court decisions comprise several pages and require a lot of space. In addition, extracting valuable information and predicting legal decisions task is difficult. Moreover, the legal system's complexity and massive litigation make this problem more serious. Thus to solve this issue, we propose a new neural network-based model for predicting court decisions on child custody. Our proposed model efficiently performs an efficient search from a massive court decisions database and accurately identifies specific ones that especially deal with copyright claims. More specially, our proposed model performs a careful analysis of court decisions, especially on child custody, and pinpoints the plaintiff's custody request, the court's ruling, and the pivotal arguments. The working mechanism of our proposed model is performed in two phases. In the first phase, the isolation of pertinent sentences within the court ruling encapsulates the essence of the proceedings performed. In the second phase, these documents were annotated independently by using two legal professionals. In this phase, NLP and transformer-based models were employed and thus processed 3,000 annotated court rulings. We have used a massive dataset for the training and refining of our proposed model. The novelty of the proposed model is the integration of bidirectional encoder representations from transformers (BERT) and bidirectional long short-term memory (Bi_LSTM). The traditional methods are primarily based on support vector machines (SVM), and logistic regression. We have performed a comparison with the state-of-the-art model. The efficient results indicate that our proposed model efficiently navigates the complex terrain of legal language and court decision structures. The efficiency of the proposed model is measured in terms of the F1 score. The achieved results show that scores range from 0.66 to 0.93 and Kappa indices from 0.57 to 0.80 across the board. The performance is achieved at times surpassing the inter-annotator agreement, underscoring the model's adeptness at extracting and understanding nuanced legal concepts. The efficient results proved the potential of the proposed neural network model, particularly those based on transformers, to effectively discern and categorize key elements within legal texts, even amidst the intricacies of judicial language and the layered complexity of appellate rulings.
Fulltext DistilRoBiLSTMFuse: an efficient hybrid deep learning approach for sentiment analysis

Papia SK, Khan MA, Habib T, Rahman M, Islam MN

PeerJ Comput Sci, 2024;10:e2349.
PMID: 39650469 DOI: 10.7717/peerj-cs.2349

In today's modern society, social media has seamlessly integrated into our daily routines, providing a platform for individuals to express their opinions and emotions openly on the internet. Within this digital domain, sentiment analysis (SA) is a vital tool to understand the emotions conveyed in written text, whether positive, negative, or neutral. However, SA faces challenges such as dealing with diverse language, uneven data, and understanding complex sentences. This study proposes an effective approach for SA. For this, we introduce a hybrid architecture named DistilRoBiLSTMFuse, designed to extract deep contextual information from complex sentences and accurately identify sentiments. In this research, we evaluate our model's performance using two popular benchmark datasets: IMDb and Twitter USAirline sentiment. The raw text data are preprocessed, and this involves several steps, including: (1) implementing a comprehensive data cleaning protocol to remove noise and unnecessary information from the raw text, (2) preparing a custom list of stopwords to retain essential words while omitting common, non-informative words, and (3) applying Lemmatization to achieve consistency in text by reducing words to their base forms, enhancing the accuracy of text analysis. To address class imbalance, this study utilized oversampling, augmenting minority class samples to match the majority, thereby ensuring uniform representation across all categories. Considering the variability in preprocessing techniques across previous studies, our research initially explores the efficacy of seven distinct machine learning (ML) models paired with two commonly employed feature transformation methods: term frequency-inverse document frequency (TF-IDF) and bag of words (BoW). This approach allows for determining which combination yields optimal performance within these ML frameworks. In our study, the DistilRoBiLSTMFuse model is evaluated on two distinct datasets and consistently delivers outstanding performance, surpassing existing state-of-the-art approaches in each case. On the IMDb dataset, our model achieves 98.91% accuracy in training, 94.16% in validation, and 93.97% in testing. The Twitter USAirline Sentiment dataset reaches 99.42% accuracy in training, 98.52% in validation, and 98.33% in testing. The experimental results clearly demonstrate the effectiveness of our hybrid DistilRoBiLSTMFuse model in SA tasks. The code for this experimental analysis is publicly available and can be accessed via the following DOI: https://doi.org/10.5281/zenodo.13255008.
Fulltext An optimized BERT fine-tuned model using an artificial bee colony algorithm for automatic essay score prediction

Chassab RH, Zakaria LQ, Tiun S

PeerJ Comput Sci, 2024;10:e2191.
PMID: 39650476 DOI: 10.7717/peerj-cs.2191

BACKGROUND: The Automatic Essay Score (AES) prediction system is essential in education applications. The AES system uses various textural and grammatical features to investigate the exact score value for AES. The derived features are processed by various linear regressions and classifiers that require the learning pattern to improve the overall score.
ISSUES: Moreover, the classifiers face catastrophic forgetting problems, which maximizes computation complexity and reduce prediction accuracy. The forgetting problem can be resolved using the freezing mechanism; however, the mechanism can cause prediction errors.
METHOD: Therefore, this research proposes an optimized Bi-directional Encoder Representation from Transformation (BERT) by applying the Artificial Bee Colony algorithm (ABC) and Fine-Tuned Model (ABC-BERT-FTM) to solve the forgetting problem, which leads to higher prediction accuracy. Therefore, the ABC algorithm reduces the forgetting problem by selecting optimized network parameters.
RESULTS: Two AES datasets, ASAP and ETS, were used to evaluate the performance of the optimized BERT of the AES system, and a high accuracy of up to 98.5% was achieved. Thus, based on the result, we can conclude that optimizing the BERT with a suitable meta-heuristic algorithm, such as the ABC algorithm, can resolve the forgetting problem, eventually increasing the AES system's prediction accuracy.
Fulltext Advancing healthcare through multimodal data fusion: a comprehensive review of techniques and applications

Teoh JR, Dong J, Zuo X, Lai KW, Hasikin K, Wu X

PeerJ Comput Sci, 2024;10:e2298.
PMID: 39650483 DOI: 10.7717/peerj-cs.2298

With the increasing availability of diverse healthcare data sources, such as medical images and electronic health records, there is a growing need to effectively integrate and fuse this multimodal data for comprehensive analysis and decision-making. However, despite its potential, multimodal data fusion in healthcare remains limited. This review paper provides an overview of existing literature on multimodal data fusion in healthcare, covering 69 relevant works published between 2018 and 2024. It focuses on methodologies that integrate different data types to enhance medical analysis, including techniques for integrating medical images with structured and unstructured data, combining multiple image modalities, and other features. Additionally, the paper reviews various approaches to multimodal data fusion, such as early, intermediate, and late fusion methods, and examines the challenges and limitations associated with these techniques. The potential benefits and applications of multimodal data fusion in various diseases are highlighted, illustrating specific strategies employed in healthcare artificial intelligence (AI) model development. This research synthesizes existing information to facilitate progress in using multimodal data for improved medical diagnosis and treatment planning.
Fulltext A comprehensive review of sensor node deployment strategies for maximized coverage and energy efficiency in wireless sensor networks

P A, C N V, Cho J, Veerappampalayam Easwaramoorthy S

PeerJ Comput Sci, 2024;10:e2407.
PMID: 39650484 DOI: 10.7717/peerj-cs.2407

Wireless Sensor Networks (WSNs) have paved the way for a wide array of applications, forming the backbone of systems like smart cities. These systems support various functions, including healthcare, environmental monitoring, traffic management, and infrastructure monitoring. WSNs consist of multiple interconnected sensor nodes and a base station, creating a network whose performance is heavily influenced by the placement of sensor nodes. Proper deployment is crucial as it maximizes coverage and minimizes unnecessary energy consumption. Ensuring effective sensor node deployment for optimal coverage and energy efficiency remains a significant research gap in WSNs. This review article focuses on optimization strategies for WSN deployment, addressing key research questions related to coverage maximization and energy-efficient algorithms. A common limitation of existing single-objective algorithms is their focus on optimizing either coverage or energy efficiency, but not both. To address this, the article explores a dual-objective optimization approach, formulated as maximizing coverage Max ∑(i = 1) ^ N Ci and minimizing energy consumption Min ∑(i = 1) ^ N Ei for the sensor nodes, to balance both objectives. The review analyses recent algorithms for WSN deployment, evaluates their performance, and provides a comprehensive comparative analysis, offering directions for future research and making a unique contribution to the literature.
Fulltext Computational approach for counting of SISH amplification signals for HER2 status assessment

Rehman ZU, Ahmad Fauzi MF, Wan Ahmad WSHM, Abas FS, Cheah PL, Chiew SF, et al.

PeerJ Comput Sci, 2024;10:e2373.
PMID: 39650490 DOI: 10.7717/peerj-cs.2373

The human epidermal growth factor receptor 2 (HER2) gene is a critical biomarker for determining amplification status and targeting clinical therapies in breast cancer treatment. This study introduces a computer-aided method that automatically measures and scores HER2 gene status from invasive tissue regions of breast cancer using whole slide images (WSI) through silver in situ hybridization (SISH) staining. Image processing and deep learning techniques are employed to isolate untruncated and non-overlapping single nuclei from cancer regions. The Stardist deep learning model is fine-tuned on our HER2-SISH data to identify nuclei regions, followed by post-processing based on identified HER2 and CEP17 signals. Conventional thresholding techniques are used to segment HER2 and CEP17 signals. HER2 amplification status is determined by calculating the HER2-to-CEP17 signal ratio, in accordance with ASCO/CAP 2018 standards. The proposed method significantly reduces the effort and time required for quantification. Experimental results demonstrate a 0.91% correlation coefficient between pathologists manual enumeration and the proposed automatic SISH quantification approach. A one-sided paired t-test confirmed that the differences between the outcomes of the proposed method and the reference standard are statistically insignificant, with p-values exceeding 0.05. This study illustrates how deep learning can effectively automate HER2 status determination, demonstrating improvements over current manual methods and offering a robust, reproducible alternative for clinical practice.
Fulltext Automated programming approaches to enhance computer-aided translation accuracy

Zhao T, Alias MB

PeerJ Comput Sci, 2024;10:e2396.
PMID: 39650497 DOI: 10.7717/peerj-cs.2396

With the continued development of information technology and increased global cultural exchanges, translation has gained significant attention. Traditional manual translation relies heavily on dictionaries or personal experience, translating word by word. While this method ensures high translation quality, it is often too slow to meet the demands of today's fast-paced environment. Computer-assisted translation (CAT) addresses the issue of slow translation speed; however, the quality of CAT translations still requires rigorous evaluation. This study aims to answer the following questions: How do CAT systems that use automated programming fare compared to more conventional methods of human translation when translating English vocabulary? (2) How can CAT systems be improved to handle difficult English words, specialised terminology, and semantic subtleties? The working premise is that CAT systems that use automated programming techniques will outperform traditional methods in terms of translation accuracy. English vocabulary plays a crucial role in translation, as words can have different meanings depending on the context. CAT systems improve their translation accuracy by utilising specific automated programs and building a translation corpus through translation memory technology. This study compares the accuracy of English vocabulary translations produced by CAT based on automatic programming with those produced by traditional manual translation. Experimental results demonstrate that CAT based on automatic programming is 8% more accurate than traditional manual translation when dealing with complex English vocabulary sentences, professional jargon, English acronyms, and semantic nuances. Consequently, compared to conventional human translation, CAT can enhance the accuracy of English vocabulary translation, making it a valuable tool in the translation industry.
Fulltext Joint intent detection and slot filling with syntactic and semantic features using multichannel CNN-BiLSTM

Muhammad YI, Salim N, Zainal A

PeerJ Comput Sci, 2024;10:e2346.
PMID: 39650516 DOI: 10.7717/peerj-cs.2346

Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU). Enhancing the NLU tasks can lead to an accurate and efficient virtual assistant thereby reducing the need for human intervention and expanding their applicability in other domains. Traditionally, these tasks have been addressed individually, but recent studies have highlighted their interconnection, suggesting better results when solved together. Recent advances in natural language processing have shown that pretrained word embeddings can enhance text representation and improve the generalization capabilities of models. However, the challenge of poor generalization in joint learning models for intent detection and slot filling remains due to limited annotated datasets. Additionally, traditional models face difficulties in capturing both the semantic and syntactic nuances of language, which are vital for accurate intent detection and slot filling. This study proposes a hybridized text representation method using a multichannel convolutional neural network with three embedding channels: non-contextual embeddings for semantic information, part-of-speech (POS) tag embeddings for syntactic features, and contextual embeddings for deeper contextual understanding. Specifically, we utilized word2vec for non-contextual embeddings, one-hot vectors for POS tags, and bidirectional encoder representations from transformers (BERT) for contextual embeddings. These embeddings are processed through a convolutional layer and a shared bidirectional long short-term memory (BiLSTM) network, followed by two softmax functions for intent detection and slot filling. Experiments on the air travel information system (ATIS) and SNIPS datasets demonstrated that our model significantly outperformed the baseline models, achieving an intent accuracy of 97.90% and slot filling F1-score of 98.86% on the ATIS dataset, and an intent accuracy of 98.88% and slot filling F1-score of 97.07% on the SNIPS dataset. These results highlight the effectiveness of our proposed approach in advancing dialogue systems, and paving the way for more accurate and efficient natural language understanding in real-world applications.
Fulltext Navigating Diagnostic Complexities and Treatment Strategies of Moyamoya Syndrome: A Case Report

Kwan LL, Abdul Rashid AM, Md Noh MSF, Hoo FK, Inche Mat LN

Cureus, 2024 Nov;16(11):e73242.
PMID: 39650868 DOI: 10.7759/cureus.73242

Moyamoya syndrome (MMS) is characterized by progressive narrowing of intracranial arteries and the development of collateral vessel networks, often presenting with recurrent ischemic or hemorrhagic strokes. MMS poses significant challenges in diagnosis due to its overlapping symptoms with other cerebrovascular conditions. Treatment aims to improve cerebral blood flow, reduce symptom frequency, and prevent future strokes. Management requires a multidisciplinary approach, including medical optimization and potential surgical intervention. This case report discusses a 37-year-old woman with poorly controlled type 2 diabetes and hyperlipidemia who experienced multiple strokes before being diagnosed with MMS. Initial symptoms included intermittent headaches, hemiparesis, and slurred speech. The presence of underlying metabolic conditions led to an initial assumption of atherosclerosis as the primary cause of her strokes. This case underscores the diagnostic challenge of distinguishing MMS from more common vascular conditions, highlighting the need for careful evaluation when typical risk factors like atherosclerosis do not fully explain recurrent cerebrovascular events.
Fulltext External Laryngocele in an Adult: A Case Report

Tamilchelvan SK, Rozhan A, Kuppusamy S, Hamid Z

Cureus, 2024 Nov;16(11):e73234.
PMID: 39650892 DOI: 10.7759/cureus.73234

Laryngocele is a rare condition marked by an abnormal enlargement of the air-filled saccule of the laryngeal ventricle. This case report showcases a distinctive presentation of external laryngocele to assist clinicians in its diagnosis and management. A 43-year-old male, with a 20-year history of painless swelling on the right side of his neck, likened to the size of an orange, presented with a recent increment in size. He noticed a gurgling sound when pressing on the swelling but did not experience any hoarseness or difficulty swallowing. During the physical examination, it was observed that there was a swelling on the right side of the neck at level II that measured approximately 3 x 5 cm. This swelling seemed to increase when the Valsalva maneuver was performed. A computed tomography scan revealed a 5 x 3 cm air-filled lesion, indicative of an external laryngocele. Although surgical excision was advised, the patient decided not to proceed with treatment and did not attend follow-up appointments. Laryngocele mainly impacts men, especially those in their fifth and sixth decades of life and is linked to activities that raise laryngeal pressure. Diagnosis is mainly based on clinical evaluation, complemented by imaging techniques such as CT and MRI. Surgical excision remains the preferred treatment, with approaches differing, depending on the laryngocele subtype. This particular case highlights the infrequency of laryngocele, and how it may manifest as a swelling in the neck. It underscores the importance of clinicians being aware of this harmless condition, highlighting the significance of taking a detailed patient history and using suitable imaging for accurate diagnosis and effective management, especially to rule out any malignancies. This report adds to the current body of knowledge on laryngocele, offering valuable information on its clinical symptoms and treatment implications.
Fulltext The Utility and Limitations of Artificial Intelligence-Powered Chatbots in Healthcare

Hayat J, Lari M, AlHerz M, Lari A

Cureus, 2024 Nov;16(11):e73127.
PMID: 39650926 DOI: 10.7759/cureus.73127

At the intersection of artificial intelligence (AI) and healthcare, it is essential that clinicians grasp the ability of chatbots. AI-powered chatbots such as ChatGPT are being explored for their potential benefits by both individuals and institutions. The utility of ChatGPT (OpenAI) in various scenarios was explored through a series of recorded prompts and responses. In the clinical aspects, the chatbot facilitated tasks such as triage, patient consultation, diagnosis, and administrative responsibilities. Their capacity to translate and simplify intricate medical topics was also evaluated. For research purposes, the chatbots' abilities to suggest ideas, prepare protocols, assist in manuscript writing, guide statistical analyses, and recommend suitable journals were assessed. In the educational domain, chatbots were tested for simplifying complex subjects, reviewing procedural steps, generating clinical scenarios, and formulating multiple-choice questions. A comprehensive literature review was also conducted across Medline, Embase, and Web of Science. Chatbots, when optimally employed, can serve as invaluable resources in healthcare, spanning clinical, research, and educational domains. Their potential lies in enhancing efficiency, guiding decision-making, and facilitating patient care and education. However, their application requires a nuanced understanding and caution regarding their limitations.

External Links