The Eastasouth Journal of Information System and Computer Science

Artificial Intelligence in Precision Medicine: Enhancing Chronic Disease Management and Genomic Drug Discovery through Predictive Modeling

Antu Roy — 2025-06-13

This paper explores the transformative role of Explainable Artificial Intelligence (XAI) in precision medicine, focusing on its application in chronic disease management and genomic drug discovery. Through two detailed workflow diagrams, the study highlights the integration of XAI within the clinical decision-making pipeline and biomedical research domains. Figure 1 illustrates a comprehensive process encompassing data acquisition, preprocessing, predictive modeling, and clinician feedback, all underpinned by XAI techniques such as SHAP, LIME, and attention mechanisms. This workflow enhances trust and transparency in AI-driven predictions, empowering clinicians to interpret and act on machine-generated insights. Figure 2 extends this understanding by mapping XAI applications to chronic disease monitoring and genomic analysis. In chronic care, XAI enables risk stratification and personalized interventions, while in genomic drug discovery, it facilitates the identification of potential targets through interpretable machine learning models. Together, these figures underscore XAI’s critical role in translating complex data into actionable healthcare outcomes. By promoting accountability, user trust, and informed decision-making, XAI emerges as a cornerstone for the ethical and effective deployment of artificial intelligence in precision medicine. The paper concludes that integrating explainability into AI models is not only a technical necessity but also a fundamental step toward safer, smarter, and more inclusive healthcare systems.

Accelerating Drug Discovery: The Role of Generative AI and Big Data Analytics

Ramchorn Gharami — 2025-06-19

Drug discovery has long been characterized by extensive timelines, high costs, and significant risks, often taking more than a decade and billions of dollars to bring a single drug to market. However, the convergence of generative artificial intelligence (AI) and big data analytics is fundamentally reshaping this landscape. This paper provides an in-depth analysis of generative AI especially models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and transformer-based architectures combined with vast biological and chemical datasets, is transforming molecular design, target identification, and compound optimization. Through a systematic review of literature, comparative model evaluation, and real-world case studies including AlphaFold, the paper explores the efficacy of these technologies in accelerating drug discovery. A hybrid methodology combining data mining, model testing, and bioinformatics simulation is employed. The results demonstrate significant improvements in candidate molecule generation, predictive modeling accuracy, and time-to-market for new drugs. Future challenges such as data interoperability, ethical considerations, and regulatory compliance are also discussed. The study concludes by highlighting the immense potential of AI and big data in ushering a new era of precision medicine and personalized therapeutics.

Analysis of Upstream Cloud Technology Acceptance at Pertamina Hulu Energi Regional 4

Ahmad Dzikra Fatahillah — 2025-08-08

This study aims to analyze the factors influencing the acceptance of Upstream Cloud technology at PT Pertamina Hulu Energi Regional 4. Upstream Cloud is part of the company's digital transformation strategy, expected to improve operational efficiency and competitiveness in the oil and gas industry. Using the Technology Acceptance Model (TAM) approach, this research examines the influence of Perceived Usefulness (PU), Perceived Ease of Use (PEOU), Confidence Level of Users (CL), and Cost Effectiveness (CE) on the level of technology acceptance within the organization. The research was conducted through a survey involving employees of PT Pertamina Hulu Energi Regional 4, with data analyzed using inferential statistical methods to determine the relationships and the magnitude of influence of each variable. The results indicate that PU has a positive and significant effect of 33.3%, PEOU of 9.2%, CL of 39.1%, and CE of 14.9% on technology acceptance. Simultaneously, these four variables contribute a total of 96.5% to the acceptance of Upstream Cloud technology. These findings have important strategic implications for the company, including the need to enhance user competence and confidence through technical training and mentoring, intensify communication regarding the tangible benefits of cloud technology, and strengthen technical support. Additionally, although PEOU has a relatively small influence, ensuring ease of use remains essential to minimize adoption barriers, particularly for non-technical users. Regular evaluations of the technology's effectiveness are also recommended to adapt to the dynamic operational needs and technological advancements in the oil and gas industry.

Using Image Similarity Metrics to Discriminate Between DALL-E Generated Art and Original Art

Avani Pandey — 2025-08-12

The rise of image-generating artificial intelligence (AI) tools like OpenAI’s DALL-E has changed the way art is made. It brings up important questions about originality, authorship, and ethical implications. I explore the originality of AI generated art through a quantitative similarity analysis using Bhattacharyya distance and Euclidean distance to measure color and structural similarity between AI outputs and their reference artworks. I analyze three distinct prompt variations—one including the artist’s name, another with a detailed description but no artist reference, and a third requesting a reinterpretation rather than replication of an original painting, namely the Mona Lisa. I find that AI generated images exhibit varying degrees of similarity depending on prompt specificity. The metrics found that mentioning the artist’s name in the prompt resulted in more similar outputs than when asked for a direct reinterpretation. Similarity metrics indicate that AI generated outputs tend to resemble each other more closely than they do the original painting, implying that AI models operate based on learned visual patterns rather than direct replication. The study emphasizes how important it is to have explicit ethical guidelines and legal frameworks to be able to regulate AI’s influence in the artistic domain.