Article
Biochemical Research Methods
Elham Nazari, Ghazaleh Pourali, Majid Khazaei, Alireza Asadnia, Mohammad Dashtiahangar, Reza Mohit, Mina Maftooh, Mohammadreza Nassiri, Seyed Mahdi Hassanian, Majid Ghayour-Mobarhan, Gordon A. A. Ferns, Soodabeh Shahidsales, Amir Avan
Summary: This study utilized bioinformatics to analyze RNA-sequencing data of patients with stomach adenocarcinoma (STAD), identifying 61 differentially expressed genes (DEGs) and key dysregulated genes associated with STAD. The study also suggested that ASPA gene may serve as a prognostic marker for STAD patients, but further functional investigations are needed to explore the value of emerging markers.
CURRENT BIOINFORMATICS
(2023)
Review
Computer Science, Artificial Intelligence
Rajvir Kaur, Jeewani Anupama Ginige, Oliver Obst
Summary: The manual process of assigning clinical codes to free-text clinical narratives is expensive, time-consuming, and error-prone. Researchers have explored the use of Natural Language Processing (NLP), machine learning, and deep learning methods to automate this process and improve accuracy and efficiency. This systematic literature review analyzes automated clinical coding systems that utilize NLP, machine learning, and deep learning methods to assign International Classification of Diseases (ICD) codes to discharge summaries. The review identifies datasets, techniques, and trends in performance evaluation metrics. Efforts are needed to improve code prediction accuracy and access to large-scale de-identified clinical corpora.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Environmental Sciences
Zhihao Wang, Alexander Brenning
Summary: Using active learning with uncertainty sampling can reduce the time and cost needed by experts under limited data conditions, improve model performance, and is particularly suitable for emergency response settings and landslide susceptibility modeling.
Review
Computer Science, Information Systems
Rasheed Ahmad, Izzat Alsmadi
Summary: As IoT applications continue to expand, attacks on them are growing rapidly, with recent research trends emphasizing the development of models that integrate big data and machine learning technologies for better security.
INTERNET OF THINGS
(2021)
Article
Biochemistry & Molecular Biology
Wei Sheng, Runbin Sun, Ran Zhang, Peng Xu, Youmei Wang, Hui Xu, Jiye Aa, Guangji Wang, Yuan Xie
Summary: The study conducted metabolomics research on methamphetamine-exposed mice, revealing that the metabolic patterns caused by methamphetamine varied over time, with different characteristics in serum and urine metabolomics. The random forest model proved to be the best for predicting exposure time, and a potential biomarker set helped identify methamphetamine exposure.
Review
Automation & Control Systems
Jalaj Pachouly, Swati Ahirrao, Ketan Kotecha, Ganeshsree Selvachandran, Ajith Abraham
Summary: Delivering high-quality software products requires coordination from different teams. Software defects can lead to costly consequences for businesses. Conducting a comprehensive survey and analysis on software defect prediction can provide valuable insights for researchers to develop prediction tools.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Multidisciplinary Sciences
Hui Yuan Tan, Zhi Yun Goh, Kar-Hoe Loh, Amy Yee-Hui Then, Hasmahzaiti Omar, Siow-Wee Chang
Summary: The study aimed to develop an automated identification model for cephalopod species based on beak images. Deep features extracted from the images were found to accurately highlight morphometric differences, with lower beaks showing more significant differences than upper beaks. Future work should focus on including more cephalopod species and increasing sample size to enhance the accuracy and comprehensiveness of the developed model.
Review
Computer Science, Information Systems
Isam Kareem Thajeel, Khairulmizam Samsudin, Shaiful Jahari Hashim, Fazirulhisyam Hashim
Summary: This article provides a review of recent advances in machine learning and deep learning for XSS attack detection. The analysis and taxonomy of existing ML/DL approaches reveal that the preprocessing of XSS data significantly affects the performance and detection models. The limitations of current ML/DL-based XSS attack detection mechanisms are highlighted, and future trends are identified.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Review
Construction & Building Technology
Georgios-Fotios Angelis, Christos Timplalexis, Stelios Krinidis, Dimosthenis Ioannidis, Dimitrios Tzovaras
Summary: The paper critically examines the non-intrusive load monitoring (NILM) problem by reviewing the experimental framework of both legacy and state-of-the-art studies. It presents widely used NILM datasets, analyzes feature engineering approaches, and discusses the evolution of learning methods. Performance evaluation methods, limitations of NILM, and future research directions are also discussed.
ENERGY AND BUILDINGS
(2022)
Article
Computer Science, Artificial Intelligence
Sushil Kumar Maurya, Dinesh Singh, Ashish Kumar Maurya
Summary: This article discusses the impact of online reviews on consumer purchase decisions and seller market strategies, as well as the challenges and methods of deceptive opinion spam detection.
APPLIED INTELLIGENCE
(2023)
Article
Mechanics
G. Maitrejean, A. Samson, D. C. D. Roux, N. El-Kissi
Summary: The understanding of the flowing properties of fluids and their rheological properties is crucial for both research and industry. Rheometers, devices developed to determine the complex rheological properties of fluids, have been used extensively. This paper aims to identify the rheological properties of a fluid ejected using continuous inkjet printing process by comparing its morphology to a dataset of known fluid jet morphologies and properties. The study shows that using a large dataset and a neural network, the viscosity of the fluid can be accurately identified with an average error of less than 1%.
Article
Biochemical Research Methods
Yuxuan Pang, Lantian Yao, Jhih-Hua Jhong, Zhuo Wang, Tzong-Yi Lee
Summary: Through the AVPIden model, multiple descriptors are utilized to accurately demonstrate peptide properties and explainable machine learning strategies based on Shapley value are adopted to show how the descriptors impact antiviral activities. The evaluation performance of the model indicates its ability to predict antivirus activities and their potential functions against six virus families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight kinds of virus (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV). AVPIden provides an option for strengthening the development of AVPs with a computer-aided method, and it has been deployed at http://awi.cuhk.edu.cn/AVPIden/.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Computer Science, Information Systems
Nikhil Kumar Singh, Manish Khare, Harikrishna B. Jethva
Summary: Person re-identification is an application of video surveillance that aims to identify individuals across non-overlapping camera views. It has become popular in the field of Computer Vision and Image processing due to its potential for enhancing safety and security. This paper discusses the challenges involved in person re-identification, such as lighting variations, different poses, blurring effects, and background changes. It also explores various approaches and techniques, including temporal, spatial, feature, distance metric, machine learning, and automation methods, to provide a comprehensive understanding of person re-identification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Review
Computer Science, Interdisciplinary Applications
Anna Procopio, Giuseppe Cesarelli, Leandro Donisi, Alessio Merola, Francesco Amato, Carlo Cosentino
Summary: Mechanistic-based models (MMs) and Machine Learning (ML) techniques are often used separately to investigate biological systems. This review investigates the combination of MMs and ML in systems biology research and highlights the great potential of this hybrid approach at both micro and macro biological scales.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2023)
Review
Computer Science, Information Systems
Shagun Sharma, Kalpna Guleria
Summary: According to the World Health Organization, there were 2.5 million deaths reported due to pneumonia in 2019, with 14% of them occurring in children aged 0-5. Diagnosing pneumonia is crucial to prevent the failure of bodily functions due to the high mortality rate. Machine and deep learning techniques can be used for pneumonia prediction, and deep learning is preferred for its better performance outcomes and automatic feature extraction. This systematic literature review comprehensively discusses various techniques for detecting pneumonia using deep learning, including convolutional neural networks, pre-trained models, and ensemble models. It provides a detailed illustration of the architecture and working process of these models, evaluates their effectiveness in solving medical challenges, and identifies research gaps and potential solutions.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Correction
Health Care Sciences & Services
George Karystianis, Armita Adily, Peter Schofield, Lee Knight, Clara Galdon, David Greenberg, Louisa Jorm, Goran Nenadic, Tony Butler
JOURNAL OF MEDICAL INTERNET RESEARCH
(2019)
Article
Health Care Sciences & Services
George Karystianis, Armita Adily, Peter W. Schofield, David Greenberg, Louisa Jorm, Goran Nenadic, Tony Butler
JOURNAL OF MEDICAL INTERNET RESEARCH
(2019)
Article
Computer Science, Information Systems
Hui Yang, Peter A. Bath
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2020)
Article
Health Care Sciences & Services
Kerina H. Jones, Elizabeth M. Ford, Nathan Lea, Lucy J. Griffiths, Lamiece Hassan, Sharon Heys, Emma Squires, Goran Nenadic
JOURNAL OF MEDICAL INTERNET RESEARCH
(2020)
Article
Health Care Sciences & Services
George Karystianis, Annabeth Simpson, Armita Adily, Peter Schofield, David Greenberg, Handan Wand, Goran Nenadic, Tony Butler
JOURNAL OF MEDICAL INTERNET RESEARCH
(2020)
Article
Public, Environmental & Occupational Health
Alexander Bulcock, Lamiece Hassan, Sally Giles, Caroline Sanders, Goran Nenadic, Stephen Campbell, Will Dixon
Summary: Participants in the study demonstrated low awareness of pharmacovigilance methods and ADR reporting, but showed willingness to share health-related social media data with researchers and regulators. However, they were cautious about the use of automated text mining methods to detect and report ADRs.
Article
Health Care Sciences & Services
Lamiece Hassan, Goran Nenadic, Mary Patricia Tully
Summary: This study analyzed all publicly available posts on the Twitter platform containing the hashtag #datasaveslives between September 1, 2016, and August 31, 2017. The research found that this hashtag-based social media campaign effectively encouraged a wide audience of stakeholders to disseminate positive examples of health research, supporting community building and bridging practices within and between interdisciplinary sectors.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2021)
Article
Medical Informatics
Ghada Alfattni, Maksim Belousov, Niels Peek, Goran Nenadic
Summary: This study evaluates the feasibility of using NLP and deep learning approaches for extracting drug information from clinical free-text notes and presents an extensive error analysis. Results show that deep learning methods can achieve high accuracy and exhibit different strengths in handling various relations.
JMIR MEDICAL INFORMATICS
(2021)
Article
Public, Environmental & Occupational Health
Meghna Jani, Belay Birlie Yimer, David Selby, Mark Lunt, Goran Nenadic, William G. Dixon
Summary: This study aimed to examine the impact of incorporating narrative prescribing instructions and subsequent drug preparation assumptions on adverse event rates, using a worked example of opioids and fracture risk. The results showed that assumptions made during the drug preparation process, especially for those with variability in prescription instructions, can impact subsequent risk estimates.
PHARMACOEPIDEMIOLOGY AND DRUG SAFETY
(2023)
Article
Medicine, Research & Experimental
George Karystianis, Wilson Lukmanjaya, Paul Simpson, Peter Schofield, Natasha Ginnivan, Goran Nenadic, Marina van Leeuwen, Iain Buchan, Tony Butler
Summary: This study examines the lead authors' affiliations in the field of epidemiological criminology to determine the countries and organizations responsible for the published research. It also explores the relationship between research outputs and the overall standard of a country's justice system.
INTERACTIVE JOURNAL OF MEDICAL RESEARCH
(2022)
Article
Health Care Sciences & Services
George Karystianis, Rina Carines Cabral, Armita Adily, Wilson Lukmanjaya, Peter Schofield, Iain Buchan, Goran Nenadic, Tony Butler
Summary: This study explores the concordance between mental illness mentions in police event narratives and mental health diagnoses from hospital records in the context of domestic violence. The findings suggest that accessing the rich information contained in police text narratives can enhance current surveillance systems for reporting and understanding domestic violence, and additional insights can be gained through linkage to other health and welfare data collections.
JMIR FORMATIVE RESEARCH
(2022)
Article
Medical Informatics
Natalie K. Fitzpatrick, Richard Dobson, Angus Roberts, Kerina Jones, Anoop Shah, Goran Nenadic, Elizabeth Ford
Summary: This study aimed to gather stakeholder views on the creation of a consented, donated databank of clinical free text for NLP research. All stakeholders were strongly in favor of the databank and saw great value in creating an environment for testing and training NLP tools to improve accuracy.
JMIR MEDICAL INFORMATICS
(2023)
Article
Health Care Sciences & Services
George Karystianis, Paul Simpson, Wilson Lukmanjaya, Natasha Ginnivan, Goran Nenadic, Iain Buchan, Tony Butler
Summary: The field of epidemiological criminology aims to study the intersection between public health and justice systems. This study examines the gaps between published research outputs in epidemiological criminology and the research priorities identified by prison stakeholders.
JMIR FORMATIVE RESEARCH
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Nikola Milosevic, Dimitar Marinov, Abdullah Gok, Goran Nenadic
NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS (NLDB 2019)
(2019)
Review
Medical Informatics
Irena Spasic, Goran Nenadic
JMIR MEDICAL INFORMATICS
(2020)