Article
Computer Science, Artificial Intelligence
Mariam M. Hassan, Hoda M. O. Mokhtar
Summary: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that affects children. The complex nature of ASD research introduces challenges to communication and access to new discoveries among researchers. To bridge these gaps, researchers have created a comprehensive autism ontology that can support various applications.
EGYPTIAN INFORMATICS JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Asif Newaz, Sabiq Muhtadi, Farhan Shahriyar Haq
Summary: This paper presents an intelligent decision support system for cervical cancer diagnosis using risk factors from a publicly available dataset. A novel hybrid resampling technique is proposed to address class imbalance, while a Genetic Algorithm (GA) is applied to identify key risk factors. The combination of the two provides the best possible performance for cervical cancer diagnosis.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Oncology
Huiling Lai, Yunyun Guo, Liming Tian, Linxiang Wu, Xiaohui Li, Zunxian Yang, Shuqin Chen, Yufeng Ren, Shasha He, Weipeng He, Guofen Yang
Summary: This study provides a proteomic signature of circulating small extracellular vesicles in ovarian cancer, which can be used for screening and differential diagnosis of ovarian masses. It complements current clinical diagnostic measures and provides a valuable tool for gynecologists.
Article
Computer Science, Artificial Intelligence
Fang Liu, Jia-Wei Zhang, Zhang-Hua Luo
Summary: The paper proposes a sequential model for managing individual decision information, including the realization of additive complementary pairwise comparisons and the establishment of a real-time feedback mechanism to address irrational behavior. The weighted averaging operator is used for aggregating individual decision information in group decision making, and a method for reaching consensus in GDM is further proposed under the control of individual consistency degrees. Comparisons with existing models show that the sequential model has the ability to rationally manage individual decision information.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Grazia V. Aiosa, Maurizio Palesi, Francesca Sapuppo
Summary: This paper describes the implementation of a comprehensive clinical decision support system (CDSS) for predicting risk factors of comorbidities related to obesity and analyzing the indirect connections between these comorbidities and non-communicable diseases. The CDSS consists of ML predictive models, explainable artificial intelligence (XAI) model interpretation, and a graph-based representation. Multiple ML models are compared and the best-performing models for each disease are identified. The system provides risk factor prediction and model explanation for significant case studies, as well as a graph-based visualization of indirect disease co-occurrence.
Article
Integrative & Complementary Medicine
Nancy Allen Searson, Lynda G. Balneaves, Sally E. Thorne, Carolyn Gotay, Tracy L. O. Truant, Antony Porcino, Mary T. Kelly
Summary: The study showed that educating support persons through seminars can significantly increase their knowledge about complementary therapy and improve their confidence in decision-making. Most support persons indicated they would continue seeking information about complementary therapy online, and there was a significant decrease in decisional conflict while distress related to decisions remained unchanged.
JOURNAL OF ALTERNATIVE AND COMPLEMENTARY MEDICINE
(2021)
Article
Engineering, Electrical & Electronic
Jifeng Chu, Qiongyuan Wang, Yuyang Liu, Jianbin Pan, Huan Yuan, Aijun Yang, Xiaohua Wang, Mingzhe Rong
Summary: This study successfully detected SF6 decomposition products using a micro sensor array and gas chromatography-mass spectrometry. A recognition model based on SDAE was established to identify discharge faults in power equipment. This work provides a promising novel method for rapid on-site inspection of SF6-insulated power equipment.
IEEE TRANSACTIONS ON POWER DELIVERY
(2023)
Article
Computer Science, Artificial Intelligence
Kehui Song, Xianyi Zeng, Ying Zhang, Julien De Jonckheere, Xiaojie Yuan, Ludovic Koehl
Summary: This paper introduces an interpretable medical decision support system that integrates historical cases and expert opinions to establish a medical knowledge base for providing relevant recommendations. The system outperforms others in terms of specificity, sensitivity, and F-1 score, contributing to reliable support for diagnosis prediction.
KNOWLEDGE-BASED SYSTEMS
(2021)
Review
Computer Science, Artificial Intelligence
Nayab Khan, Chinyere Nwafor Okoli, Victory Ekpin, Kingsley Attai, Nwokoro Chukwudi, Humphrey Sabi, Christie Akwaowo, Joseph Osuji, Luis Benavente, Faith -Michael Uzoka
Summary: Medical decision support systems (MDSS) aim to improve patient care by simulating the cognitive process to arrive at valid clinical conclusions. Adoption and usage of MDSS have been slow due to lack of physician confidence and concerns about professional autonomy and physician-patient relationships. Future research should focus on implementing existing models and studying high burden diseases.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Carmela Comito, Deborah Falcone, Agostino Forestiero
Summary: This paper proposes a Clinical Decision Support System (CDS) framework that integrates heterogeneous health data from different sources. It utilizes machine learning and deep learning approaches, particularly a neural network model with word embedding, to predict patients' future health conditions and diagnose diseases accurately. Experimental results demonstrate the effectiveness and accuracy of this approach.
Article
Health Care Sciences & Services
Joao Moura, Ana Margarida Pisco Almeida, Fatima Roque, Adolfo Figueiras, Maria Teresa Herdeiro
Summary: The misuse of antibiotics leads to bacterial resistance and jeopardizes generational health globally. This study focused on designing and prevalidating a mobile app interface to assist in the diagnosis of upper respiratory problems by professionals in interface design and pharmacology experts. The resulting interface received positive feedback, leading to improvements and a validated new version.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Mathematics
Maria Villalba-Orero, Eugenio Roanes-Lozano
Summary: This research focuses on developing a decision support system based on clinical practice to assist in diagnosing and managing equine cardiac diseases. By organizing case data in logical mathematical form, it will improve the efficiency of equine clinicians and potentially enhance the level of healthcare for horses.
Article
Oncology
Marwa Obayya, Mashael S. Maashi, Nadhem Nemri, Heba Mohsen, Abdelwahed Motwakel, Azza Elneil Osman, Amani A. Alneil, Mohamed Ibrahim Alsaid
Summary: This study develops an arithmetic optimization algorithm with deep-learning-based histopathological breast cancer classification technique for healthcare decision making. The AOADL-HBCC technique employs noise removal based on median filtering (MF) and a contrast enhancement process. In addition, the presented AOADL-HBCC technique applies an AOA with a SqueezeNet model to derive feature vectors. Finally, a deep belief network (DBN) classifier with an Adamax hyperparameter optimizer is applied for the breast cancer classification process.
Article
Health Care Sciences & Services
Matt Sibbald, Sandra Monteiro, Jonathan Sherbino, Andrew LoGiudice, Charles Friedman, Geoffrey Norman
Summary: The study found that using EDS, whether early or late in the diagnostic process, increased the number of diagnostic hypotheses and the likelihood of the correct diagnosis appearing in the differential. Early use primarily increased the number of diagnostic hypotheses, while late use increased the likelihood of the correct diagnosis being present in the differential regardless of experience level.
BMJ QUALITY & SAFETY
(2022)
Review
Oncology
Teesta Mukherjee, Omid Pournik, Sarah N. Lim Choi N. Keung, Theodoros N. N. Arvanitis
Summary: Brain tumours are abnormal growths of cells in the human brain. Clinical decision support systems (CDSSs) have played an important role in the diagnosis and treatment of brain tumours. This study systematically identifies different types of CDSSs used in brain tumour diagnosis and prognosis through medical imaging.
Article
Oncology
Phyllis S. Y. Chong, Jing Yuan Chooi, Julia S. L. Lim, Sabrina Hui Min Toh, Tuan Zea Tan, Wee-Joo Chng
Summary: The study highlights the crucial role of NSD2 in t(4;14) multiple myeloma, revealing a novel, SWI/SNF-independent interaction between NSD2 and SMARCA2 for chromatin remodeling and transcriptional regulation of oncogenes. Targeting the bromodomain of SMARCA2 with BET inhibitor PFI-3 disrupts the NSD2-SMARCA2 complex, inhibiting the viability of t(4;14) myeloma cells and reducing tumor growth in vivo, suggesting a potential therapeutic strategy for this type of cancer.
Article
Medicine, Research & Experimental
Michal M. Hoppe, Patrick Jaynes, Joanna D. Wardyn, Sai Srinivas Upadhyayula, Tuan Zea Tan, Stefanus Lie, Diana G. Z. Lim, Brendan N. K. Pang, Sherlly Lim, Joe Yeong, Anthony Karnezis, Derek S. Chiu, Samuel Leung, David G. Huntsman, Anna S. Sedukhina, Ko Sato, Monique D. Topp, Clare L. Scott, Hyungwon Choi, Naina R. Patel, Robert Brown, Stan B. Kaye, Jason J. Pitt, David S. P. Tan, Anand D. Jeyasekharan
Summary: The study showed that high RAD51 expression in epithelial ovarian cancer is associated with shorter progression-free and overall survival, as well as platinum resistance, especially in HR-proficient cancers. RAD51 overexpression may also modify the expression of immune-regulatory pathways and result in exclusion of cytotoxic T cells in situ.
EMBO MOLECULAR MEDICINE
(2021)
Article
Oncology
Malina Xiao, Meriem Hasmim, Audrey Lequeux, Kris Van Moer, Tuan Zea Tan, Christine Gilles, Brett G. Hollier, Jean Paul Thiery, Guy Berchem, Bassam Janji, Muhammad Zaeem Noman
Summary: This study highlights the importance of CMTM6 and CMTM7 in regulating PD-L1 expression in aggressive breast cancer cells. Activating EMT process in breast cancer cells upregulates CMTM6, which is essential for cell surface expression of PD-L1. Dual targeting CMTM6 and CMTM7 can decrease PD-L1 surface expression, suggesting potential therapeutic benefits in highly aggressive breast cancer patients.
Article
Computer Science, Artificial Intelligence
W. H. Chai, S. S. Ho, H. C. Quek
Summary: A fast parallelable Jacobi iteration type optimization method is proposed for non-smooth convex composite optimization, which integrates both first and second-order techniques to boost convergence speed. Experimental results show that the proposed method converges significantly better than existing methods.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Information Systems
Woon Huei Chai, Shen-Shyang Ho, Hiok Chai Quek
Summary: This paper studies the recovery probability of the state-of-the-art sparse recovery method YALL1 and provides a generalization of a theoretical work based on a special case of YALL1 optimization problem. The results show that not only the special case but also some other cases of YALL1 optimization problem can recover any sufficiently sparse coefficient vector under certain conditions. The trade-off parameter in YALL1 allows the recovery probability to be optimally tuned. Experimental results demonstrate the superiority of YALL1 optimization problem with primal augmented Lagrangian optimization technique in terms of speed.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Qing Yang Eddy Lim, Qi Cao, Chai Quek
Summary: This study introduces Reinforcement Learning and dynamic portfolio rebalancing to enhance portfolio management efficiency, adapting portfolios dynamically to market trends, risks, and returns. After evaluating and comparing three constructed financial portfolios, it was found that the RL agent for gradual portfolio rebalancing with the LSTM model outperformed other methods, improving returns by 27.9-93.4% compared to full rebalancing methods.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Jeow Li Huan, Arif Ahmed Sekh, Chai Quek, Dilip K. Prasad
Summary: This paper investigates text classification methods by using deep models and recurrent neural networks to extract features and represent documents as semantic vector sequences for classification. The addition of sentiment information improves accuracy, outperforming classical techniques in experiments.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Yue Hu, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek, Quanjun Yin
Summary: This paper proposes a neural network model called STEM-COVID to identify asymptomatic COVID-19 cases (ACCs) using contact tracing data. The model incorporates adaptive resonance theory and weighted evidence pooling to achieve high accuracy and efficiency in identifying ACCs. It also demonstrates robustness against noisy data and breakthrough infections after vaccination.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Xie Chen, Deepu Rajan, Dilip K. Prasad, Chai Quek
Summary: This paper investigates the benefits of using a deep learning model as a fuzzy implication operator in a neuro-fuzzy system for learning and explaining predictions of both steady-state and dynamically changing data. The results show that this approach improves the model performance and enhances the interpretability of the reasoning process.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek
Summary: Hierarchical reinforcement learning is an approach to decompose goals into subgoals for long-horizon goal-reaching tasks. End-to-end HRL methods use a hierarchy of policies to search useful subgoals directly in a continuous subgoal space. LIDOSS, an integrated subgoal discovery heuristic, reduces the search space of the higher-level policy by focusing on subgoals with a higher probability of occurrence in state-transition trajectories leading to the goal.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Leon Lai Xiang Yeo, Qi Cao, Chai Quek
Summary: This article introduces two trading indicators: the optimized fMACDH indicator and the fMACDH-fRSI indicator. These two indicators are optimized using a genetic algorithm, and the optimized fMACDH indicator is used to propose two rule-based portfolio rebalancing algorithms: Tactical Buy and Hold (TBH) and Rule-Based Business Cycle (RBBC). The experiments show consistent and encouraging performances of these algorithms in dynamic portfolio rebalancing.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yizhang Wang, Di Wang, You Zhou, Xiaofeng Zhang, Chai Quek
Summary: The VDPC algorithm is proposed to address the limitation of DPC in identifying clusters with variational density. It systematically performs the clustering task on datasets with different density distributions by identifying representatives, constructing initial clusters, and using a unified clustering framework.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan, Chai Quek
Summary: This article proposes a novel subgoal graph-based planning method called LSGVP, which addresses the challenge of learning to reach long-horizon goals in spatial traversal tasks for autonomous agents. LSGVP uses a subgoal discovery heuristic based on cumulative reward and automatically prunes the learned subgoal graph to remove erroneous connections. It achieves higher cumulative positive rewards and goal-reaching success rates compared to other subgoal sampling or discovery heuristics.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Xinjing Song, Di Wang, Chai Quek, Ah-Hwee Tan, Yanjiang Wang
Summary: This paper proposes a cognitive model called STEM-ADL, which encodes event sequences to predict the type and starting time of daily self-care activities. Experimental results demonstrate that STEM-ADL outperforms other models and is suitable for real-life healthcare applications.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wai-Cheong Lincoln Lew, Di Wang, Kai Keng Ang, Joo-Hwee Lim, Chai Quek, Ah-Hwee Tan
Summary: This article proposes a video summarization model (EVES) based on EEG and video emotion data, which utilizes multimodal deep reinforcement learning architecture to learn visual interestingness for better video summaries. The experimental results show that EVES outperforms unsupervised models and narrows the performance gap with supervised models. EVES receives higher ratings in content coherency and emotion-evoking content.
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Qianghua Liu, Yu Tian, Tianshu Zhou, Kewei Lyu, Ran Xin, Yong Shang, Ying Liu, Jingjing Ren, Jingsong Li
Summary: This study proposes a few-shot disease diagnosis decision making model based on a model-agnostic meta-learning algorithm (FSDD-MAML). It significantly improves the diagnostic process in primary health care and helps general practitioners diagnose few-shot diseases more accurately.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)
Article
Computer Science, Artificial Intelligence
Balazs Borsos, Corinne G. Allaart, Aart van Halteren
Summary: The study demonstrates the feasibility of predicting functional outcomes for ischemic stroke patients and the usability of multimodal deep learning architectures for this purpose.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)
Article
Computer Science, Artificial Intelligence
Abdelmoniem Helmy, Radwa Nassar, Nagy Ramdan
Summary: This study utilizes machine learning models to detect depression symptoms in Arabic and English texts, and provides manually and automatically annotated tweet corpora. The study also develops an application that can detect tweets with depression symptoms and predict depression trends.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2024)