A Dual-Part Theoretical Framework for AI in Complex Neurology Cases
Emily Koenig1, Tiffany Harmanian1, Rexhina Ago1, Alyssa Kim1, Matthew Dinh1
1A.T. Still University School of Osteopathic Medicine
Objective:

This study aims to develop and explore the implementation of a dual-part theoretical framework that integrates artificial intelligence (AI) with interdisciplinary medical approaches. The framework focuses on enhancing care for patients with complex neurological conditions, addressing both physiological and psychological needs.


Background:

The rapid advancement of AI in medical settings presents opportunities to alleviate pressures faced by healthcare systems and improve patient outcomes, particularly in complex cases. Despite AI's potential to streamline diagnostic processes, barriers such as resistance to change, financial constraints, access disparities, and compliance issues remain. This study proposes a framework that utilizes AI not only for diagnostic accuracy but also for holistic patient care, emphasizing interdisciplinary collaboration to address neurological and psychological health comprehensively.


Design/Methods:

The study involved an exploratory phase where patient data—including history, physical findings, lab results, imaging, and socioeconomic factors—was analyzed. This phase generated two key variables: patient identity and a treatment framework. The treatment phase employed an AI algorithm designed to recommend gold-standard treatments while addressing the psychological well-being of patients. The algorithm incorporated a NoSQL health database, allowing for seamless integration with healthcare systems. Additionally, barriers to AI implementation, such as HIPAA compliance and interoperability, were addressed. Disclosure: Components of this abstract utilized AI solely for the correction of spelling and grammatical errors.


Results:

The framework facilitated AI-driven treatment recommendations that aligned with current medical standards. Moreover, the model’s integration with psychological care offered an innovative approach to managing neurological conditions. The results also underscored the importance of human oversight to enhance the AI's performance and mitigate errors.


Conclusions:

The dual-part framework offers a promising avenue for improving outcomes in patients with complex neurological disorders. By incorporating both AI and interdisciplinary care, this model can enhance patient engagement, streamline treatment processes, and ultimately lead to more holistic care delivery in medical practice.


10.1212/WNL.0000000000211549
Disclaimer: Abstracts were not reviewed by Neurology® and do not reflect the views of Neurology® editors or staff.