Artificial Intelligence as a Decision Making Tool in Neurology

Rambam Health Care Campus

Status: Active, not recruiting

Conditions: Emergency Department Visit; Neurological Diseases or Conditions; Medical Reporting; Clinical Decision-making

Treatments: Other: Retrospective Data Extraction of 10,000 Neurology ER Cases; Other: Artificial Intelligence

Study type: Observational

Funder types: Other

Identifiers

NCT06902675

0026-24RMB

Details and patient eligibility

About

Background: The establishment of neuroinformatics as a distinct field has enabled the integration of computational biology and informatics to improve neurological research. This interdisciplinary approach enhances the capacity to integrate diverse datasets, unravel complex neural networks, and develop computational models that can improve clinical management. The investigators aim to evaluate whether an artificial-intelligence-based tool is effective in non-English-speaking regions.

Hypothesis: Integrating a language model-based clinical assistance system within the neurology ward will significantly enhance the efficiency and accuracy of patient care by leveraging neuroinformatics principles. The investigators hypothesize that combining natural language processing and data analytics will improve diagnostic and treatment processes.

Full description

Research Design:

A pre-post-intervention design will be used, measuring outcomes before and after the implementation of a neuroinformatics-driven clinical assistance system. Changes in diagnostic accuracy, treatment decisions, and workflow efficiency will be quantified.

Workflow:

1. A neurologist evaluates each patient, and the patient signs informed consent.
2. A medical student manually uploads de-identified clinical information to a secure interface.
3. Data are analyzed by a large language model (LLM) system through a hospital-approved application.
4. A senior physician must approve any decision based on the LLM's recommendation.
5. For half of the prospectively enrolled participants, the LLM's recommendation is presented to the resident.

Retrospective Data:

1. The investigators will extract data from 10,000 patients who were evaluated by a neurologist in the Emergency Department.
2. Clinical information (without patient identifiers) will be uploaded to a secure, hospital-approved LLM with a security key.
3. The model's output will be compared with actual clinical decisions and patient outcomes (e.g., mortality, discharge status).

Enrollment: 1,000 estimated patients

Sex: All

Ages: 18 to 120 years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Informed consent

Exclusion criteria

• Unable to give informed consent

Trial design

1,000 participants in 3 patient groups

Evaluation With AI

Description:

* Description: Participants in this arm receive an LLM-based recommendation that is presented to the resident (after senior physician approval) given by random selection (control versus study) 1:1. * Intervention: Artificial Intelligence as a Decision-Making Tool * Intervention Description: The large language model (LLM) provides clinical suggestions regarding diagnosis or management. The final decision remains at the discretion of the attending physician.

Treatment:

Other: Artificial Intelligence

Evaluation Without AI

Description:

* Description: Participants in this arm receive standard clinical care without access to an AI-based recommendation given by random selection (control versus study) 1:1 to the neurological resident. * Intervention: No Intervention * Intervention Description: Standard of care only. No AI tool is provided to the resident.

Retrospective Cohort

Description:

* Description: Clinical data from 10,000 patients previously evaluated by neurologists in the Emergency Department are extracted and analyzed retrospectively. * Intervention: Data Extraction and Analysis * Intervention Description: De-identified data are uploaded into the LLM for retrospective analysis. Model outputs are then compared to actual patient outcomes and standard-of-care decisions.

Treatment:

Other: Retrospective Data Extraction of 10,000 Neurology ER Cases