Archives

  • Journal of Computing and Engineering - JCE
    Vol. 2 No. 2 (2026)

    A Review of Artificial Intelligence Application in Healthcare Sectors

    Nur Rachman Dzakiyullah1 Muhammad Fahrul Aditya2

    1Faculty of Science, Engineering and Technology, Department of Information System, Universitas Alma Ata, Yogyakarta, Indonesia, nurrachmandzakiyullah@almaata.ac.id, ORCID 0000-0001-8124-1655

    2Faculty of Science, Engineering and Technology, Department of Information System, Universitas Alma Ata, Yogyakarta, Indonesia, m032510014@student.utem.edu.my, ORCID 0000-0003-0287-7685

    Abstract

    Artificial Intelligence (AI) is no longer an experimental method for computation, but has become a game-changer in the present day medical field. In the past decade, machine learning (ML), deep learning (DL), and now large language models (LLMs) have found their way into most medical specialties, ranging from radiology and oncology to cardiology, neurology, and hepatology. A literature review was conducted to collate peer-reviewed research articles, published from 2020 to 2025, on the evolution, application fields, methodological trends, ethical issues, and unanswered questions about the use of AI in medicine. Using more than hundred primary studies and umbrella reviews, the review reveals that the primary data sources are diagnostic imaging, electronic health records (EHRs), and biomarker analytics, with the rapid growth of multimodal foundation models and agentic clinical workflows emerging in the landscape.

    Keywords: Artificial Intelligence, healthcare, healthcare system, literature review.

  • Journal of Computing and Engineering - JCE
    Vol. 2 No. 1 (2026)

    Can ChatGPT answer Pregnant Women Questions?

    Aseel Abdulameer Mohammed1

    1College of Medicine, University of Kufa, Aseela.albubaqer@uokufa.edu.iq, ORCID 0009-0002-9389-0868

    Abstract

    OpenAI has developed ChatGPT which is considered as one of the famous artificial intelligence tools. It provides a significant advancement and particularly noted in order to create a speaking conversations with human. This review paper shows the use of ChatGPT in women care in their pregnancy time. ChatGPT provides available and sympathetic information and replies to any questions about childbirth, pregnancy and woman care. The reliability and accuracy of ChatGPT’s answers is important to be checked.  It also helps to support decision making in pregnancy clinical problems but it recently lacks the precision and appropriate answers without doctor oversight. Moreover, it provides technical accurate information, proper medical answers with lacks of references.  However, it is not always giving correct answers.  very few studies have been done on this area and most of them in English. This research attented to ask ChatGPT in Arabic. We choose five of the common questions that always be asked by pregnant ladies in their booking visit and compare the answers of ChatGPT with the answers of three famous obstetrician doctors in Iraq in order to see the similarities or differences.

    Keywords: Artificial intelligence, AI, pregnancy questions, pregnant woman, early pregnancy.


    Artificial Intelligence in Big Data: A Literature Review

    Eman Yahya Maarof1

    1Facility of Computer Studies, Arab Open University, Saudi Arabia, e.maarof@arabou.edu.sa, ORCID 0009-0003-8456-9826

    Abstract

    This Artificial Intelligence (AI) and Big Data combination has revolutionized data-driven decision-making in almost all the scientific and industrial fields. Over the last six years, from 2020 to 2026, the field witnessed an unprecedented degree of change, as deep learning became more mature, transformer architectures and large language models emerged and became more popular, federated learning and edge learning began to gain farming, and privacy and algorithmic accountability became stricter. This paper is a systematic review of the literature in Scopus and Web of Science following PRISMA 2020 guidelines. After deduping records, two stage screening and quality checking with Kitchenham & Charters criteria, 138 Primary studies were selected from a pool of 4182 records. The objective of this research is to bring together the evidence for the four research questions. Results indicate the deep-learning family continues to be the top applied family (46.4% of studies), but the field is on a structural shift with the transformer- and LLM-based approaches rising from less than 3.0% in 2020, to more than 28% in 2025, and with federated-learning slightly more than 9% jumping to roughly tripled in the same timeframe. Application areas and domains are still largely dominated by the areas of healthcare, IoT/smart cities, and finance, while scalability, privacy, explainability, data quality, and energy efficiency remain among the most frequently cited open problems. The paper ends with a research agenda consisting of six points, most of them focusing on trustworthy, sustainable, and human-centric AI for Big Data.

    Keywords: Artificial Intelligence, Big Data, Deep learning, Federated learning, Large language models, Edge AI, Literature review.

  • Journal of Computing and Engineering - JCE
    Vol. 1 No. 2 (2025)

    Black-Box Machine Learning versus White-Box Methods: A Mapping Literature Review

    Mohammed Ghazi Naji Al-Nussairi 1

    1Department of Computer Science, University of Oviedo, Oviedo, Spain, UO298481@uniovi.es, ORCID 0009-0005-7568-3541

    Abstract

    The rapid proliferation of machine learning (ML) and deep learning (DL) methods across scientific and industrial domains has intensified the debate between predictive performance and model interpretability. Black-box models, including deep neural networks, ensemble methods, and support vector machines, offer state-of-the-art accuracy but operate with limited transparency. White-box models, encompassing linear programming, interpretable ML, and rule-based systems, prioritize explainability, auditability, and constraint satisfaction. This systematic literature review synthesizes findings from 50 peer-reviewed articles published between 2015 and 2025, retrieved from IEEE Xplore, Scopus, and Web of Science. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, this review compares black-box and white-box approaches across six dimensions: predictive performance, interpretability, computational efficiency, scalability, robustness, and domain applicability. Results reveal a persistent accuracy–interpretability trade-off, an emerging convergence through explainable artificial intelligence (XAI) methods, and growing hybrid architectures that blend both paradigms. This review identifies critical research gaps and provides a structured roadmap for future investigation.

    Keywords: Black-box models, deep learning, explainable AI, interpretable machine learning, machine learning, optimization, literature review, white-box models, XAI.

  • Journal of Computing and Engineering - JCE
    Vol. 1 No. 1 (2025)

    Electronic Information Sharing Influence Factors in the Higher Education Sector

    Mohammed Abdulamer Mohammed1, Huda Ibrahim2

    1College of Computer Sciences & Information Technology, University of Hilla, Babylon, Iraq, mhmd@hilla-unc.edu.iq, 6433, ORCID 0000-0002-6430-3882

    2Department.of Information System, School of Computing, Universiti Utara Malaysia, Kedah, Malaysia, huda753@uum.edu.my, ORCID 0009-0004-2799-3046

    Abstract

    Information sharing is one of the important aspects that improve the quality of businesses. Furthermore, with the advances in information and communication technology, electronic information sharing is increasingly needed to support decision making as well as the education sector in Iraq. In supporting the decision making process in public universities in Iraq, the Ministry of Higher Education and Scientific Research (MOHESR) has allowed the practice of decentralisation. This situation provides universities academic freedom. However, Iraqi public universities have limited resources to support information sharing that can enable them to make their own decisions. The limitation of electronic information sharing especially between universities and MOHESR is considered a significant gap in increasing information. The main objective of this study is to propose a theoretical model of electronic information sharing between public universities and MOHESR. Technological, environmental and organisational factors have been identified as influential in increasing participation in electronic information sharing between them. The model could contribute much to the ministry and the public universities by guiding them in planning as well as in strategizing the enhancement of infrastructure, policies and human development through an increase in electronic information sharing that could empower their decision making skills.

    Keywords: Information sharing, Electronic information sharing, Public universities, Minister of higher education, Theoretical framework.