A Scopus Dataset for Systematic and AI-Based Analysis of AI Research in Leukemia

This dataset provides a structured research corpus of 2,338 peer-reviewed publications addressing the application of artificial intelligence (AI) in leukemia research. The dataset was retrieved from the Scopus database and served as the primary data source for the paper titled “A Systematic, Scalable, and Interpretable Mapping of Artificial Intelligence Research in Leukemia Using a Hybrid Machine Learning and Qualitative Framework”.

The dataset covers publications from 1990 to 2024 and was collected using a targeted Scopus query combining leukemia-related terms with artificial intelligence, machine learning, deep learning, reinforcement learning, and self-supervised learning concepts. A PRISMA-guided screening process was applied to ensure thematic relevance, remove duplicates, and exclude records without abstracts or explicit references to both leukemia and AI-related methodologies.

Each record contains curated publication metadata, including authors, author full names, author identifiers, publication year, DOI, Abstract, author keywords, and Scopus index keywords. These fields support a wide range of downstream analyses using PEARL [1], including AI-assisted semantic modeling, unsupervised clustering, thematic parameter discovery, qualitative synthesis, and cross-domain research mapping, rather than being limited to citation or bibliometric analysis alone.

The dataset enables large-scale, reproducible exploration of how AI methods, data modalities, and clinical objectives intersect across diagnostic, prognostic, therapeutic, genetic, and methodological dimensions of leukemia research. By sharing this dataset publicly, the authors aim to support transparency, methodological reuse, and further AI-driven knowledge discovery in leukemia and related biomedical research domains. We have applied this approach across various fields and sectors, including AI explainability and governance [1], [2], [3], energy [4], education [5], healthcare [6]–[8], transportation [9], [10], labor markets [11], [12], tourism [13], service industries [14], and others.

Categories:
Artificial Intelligence; Leukemia; Machine Learning; Deep Learning; AI-Based Literature Analysis; Systematic Review; Hematologic Oncology; Semantic Analysis; Research Mapping

References:
[1] doi: 10.2139/ssrn.6009614.
[2] doi: 10.3389/FNINF.2024.1472653/BIBTEX.
[3] doi: 10.2139/SSRN.5086713.
[4] doi: 10.3389/FENRG.2023.1071291.
[5] doi: 10.3389/FRSC.2022.871171/BIBTEX.
[6] doi: 10.3390/SU14063313.
[7] doi: 10.3390/TOXICS11030287.
[8] doi: 10.3390/app10041398.
[9] doi: 10.3390/SU14095711.
[10] doi: 10.3390/s21092993.
[11] doi: 10.3390/JOURNALMEDIA4010010.
[12] doi: 10.1177/00368504231213788.
[13] doi: 10.3390/SU15054166.
[14] doi: 10.3390/SU152216003.