E-norms and AI in clinical neurophysiology

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Biostatistics

Background:

• The e-norms method is a technique for deriving normative data from patient studies.
• Traditional e-norms plateau identification relies on visual inspection using an Excel Macro.
• Automating this process can improve efficiency and accuracy in data analysis.

Purpose of the Study:

• To describe the use of Artificial Intelligence (AI) to automate the e-norms method.
• To develop a Python script using OpenAI's ChatGPT for e-norms plateau identification.
• To compare AI-automated e-norms derivation with traditional methods.

Main Methods:

• Utilized OpenAI's ChatGPT to generate a Python script.
• The script automates the identification of the e-norms plateau, crucial for determining normal values.
• The automated method was applied to mixed datasets containing normal and abnormal patient data.

Main Results:

• E-norms normal values derived using the AI-automated Python script favorably compared with those obtained via the traditional visual e-norms plateau identification method.
• The AI-driven automation demonstrated comparable accuracy to the established Excel Macro approach.
• The study confirmed the feasibility of automating a key step in normative data derivation.

Conclusions:

• OpenAI's ChatGPT can be used to develop Python scripts for automating e-norms normal value collection.
• Users with minimal programming or statistical expertise can successfully develop these automation tools.
• AI offers a viable solution for streamlining the derivation of normative data in clinical studies.