Here is the report of published academic papers written by Marquette faculty and staff and submitted to the Office of Marketing and Communication for November 2026. These papers have appeared in print or been presented recently.
The AI Detective: Safeguarding Academic Integrity in Dental Education
Dr. Mohamed Ibrahim, clinical professor of surgical and diagnostic sciences | American Association of Endodontists (Eye on Education)
Abstract: The study, published in the International Endodontic Journal, describes a Siamese neural network designed to compare preoperative and postoperative radiographs and identify inconsistencies that may suggest radiograph substitution during preclinical endodontic assessments. The model achieved an overall accuracy of approximately 89% and demonstrates the potential for AI to support fair, objective, and scalable assessment practices in dental education. A U.S. patent application has also been filed for the technology, and external validation with additional institutions is underway to assess its broader applicability across dental education settings.
Belonging and involvement in the college environment among underrepresented prelicensure nursing students – A mixed methods study
Dr. Maria Y. Peña, Dr. Amber Young-Brice, Dr. Kristin Haglund, Dr. Terrie Garcia, and Dr. derria byrd | Journal of Professional Nursing (Volume 67)
Abstract: A representative nursing workforce is essential for promoting optimal health and delivering culturally responsive care. While holistic review has increased enrollment of students with underrepresented ethnic and cultural social identities, less is known about how students experience belonging and involvement after enrollment. This study explored how prelicensure nursing students with underrepresented ethnic and cultural social identities perceive the influence of the college environment on sense of belonging and likelihood of involvement in historically predominantly White institutions.
Simulation-based strategies co-designed with young adults for sickle cell disease self-management
Dr. Dora L. Clayton-Jones, Dr. Sylvia Pena, Dr. Kristin Haglund, Dr. Abir K. Bekhet, Dr. Lee Za Ong, Dr. Anne M. Costello, Grainne Kilroy Ferlmann | Western Journal of Nursing Research (Volume 48, Issue 11)
Abstract: Young adults living with sickle cell disease (SCD) face complex self-management challenges during care-seeking. Developmentally appropriate, experiential interventions remain limited. Interventions to prepare young adults for emotionally charged real-world situations such as emergency department encounters, peer communication, and independent decision-making are needed. To describe the co-design of a simulation-based self-management intervention for young adults living with SCD and conduct evaluation of 6 intervention implementation parameters: necessity, acceptability, feasibility, safety, fidelity, and preliminary effectiveness.
Integrating multi-omics data through deep learning with applications to autism risk gene prioritization
Dr. Shengtong Han, assistant professor of biostatistics; and Dr. Wenhui Sheng, research assistant professor | Briefings in Bioinformatics (Volume 27, Issue 5)
Abstract: This paper presents a newly developed novel deep learning tool, called Deep-MOTIFs to integrate multi-omics data to prioritize disease associated risk genes. In particular, we applied Deep-MOTIFs to autism study and rank all the genes genome-wide by Deep-MOTIFs scores, and the top genes are enriched in well-known ASD-related biological terms, including autistic behavior, synaptic signaling, synapse, chromatin organization, etc.
AI-bioinformatics synergy for precision medicine in brain diseases: integrating radiomics and multi-omics data
Dr. Bekir Altas, clinical assistant professor of biomedical sciences | Briefings in Bioinformatics (Volume 27, Issue 5)
Abstract: The convergence of artificial intelligence (AI) and bioinformatics is reshaping the landscape of precision medicine in brain diseases, particularly in neurological diseases and brain tumors. Despite advances in both fields, the combined application of radiomics and multi-omics fusion remains underutilized, even though integrative frameworks are essential for addressing the complexity and heterogeneity of imaging and molecular data. This review examines how integrative AI-bioinformatics frameworks enable the fusion of radiomics with genomics, transcriptomics, proteomics, and other omics modalities to more comprehensively model disease complexity.
AI-bioinformatics synergy for precision medicine in brain diseases: integrating radiomics and multi-omics data
Dr. Sam Omidi, research assistant professor of community dental sciences | Bioengineering (Volume 10, Issue 13)
Abstract: The advent of generative artificial intelligence (AI), particularly large language models (LLMs) and deep generative networks, is transforming the landscape of Alzheimer’s disease and related dementia (ADRD) research and care. This narrative review aims to synthesize current applications of generative AI in ADRD research and care, highlight ethical and implementation challenges, and propose strategies for responsible integration into clinical practice. We conducted a narrative review of literature, regulatory documents, program reports, and relevant sources published between 2016 and 2026, with a specific focus on cognitive screening, synthetic data generation, digital twin modeling, and caregiver support.
Evaluating shared gene prioritization for type 2 diabetes and FinnGen R10 chronic periodontitis
Dr. Sam Omidi, research assistant professor of community dental sciences | Archives of Oral Biology (Volume 192)
Abstract: While clinicians have long observed that type 2 diabetes and chronic gum disease (periodontitis) often strike the same individuals, our genomic analysis of large-scale biobanks uncovered no shared inherited DNA risk factors. Evaluating over 19,000 protein-coding genes revealed not a single gene that met statistical thresholds for both conditions simultaneously. Furthermore, machine learning models tasked with identifying shared risk pathways performed no better than random chance. These results indicate that the interplay between diabetes and oral disease is an acquired consequence of sustained inflammation, elevated blood sugar, and bacterial shifts in the mouth—not an inherited genetic trait.
Battling the Bottleneck: Evaluating Autism Diagnostic Training in Primary Care
Dr. Norah L. Johnson, Dr. Amy Van Hecke, Dr. Maharaj Singh | Journal of Autism and Developmental Disorders (Volume 56, Issue 12)
Abstract: The purpose of this study was to evaluate training that helped primary care providers in Wisconsin learn to identify and diagnose autism in young children ages 24–36 months using the STAT (Screening Tool for Autism in Toddlers and Young Children). The training was followed by a year-long learning community where providers discussed patient cases and shared knowledge during monthly meetings. Researchers assessed providers’ knowledge, attitudes, screening practices, and confidence before and after the training. Before the training, providers reported limited use of tools specifically designed to screen for and diagnose autism. Among the 11 providers with both pre- and post-training data, confidence improved in identifying signs of autism, distinguishing autism from other developmental conditions, making diagnoses, and discussing results with families, while improvements in referrals and connecting families with mental health services were more limited. These findings suggest that training primary care providers to recognize and diagnose autism in young children may help reduce delays in diagnosis and improve access to early intervention services.
If you have recently published a paper, or if you have one coming out, we would like to feature your publication in an upcoming Faculty in Print feature. More information on the submission process is available online.
