Gen AI Narrative

Summary

Narrative generation using OCI Gen AI service

Description

In this release, Argus Safety introduces a Gen AI-powered narrative generation feature. This feature auto-generates narratives from the structured data available in a case, making this process efficient with highly natural, accurate and complete narratives. Hence, minimal manual user intervention is required. This feature is available for case processing in the Analysis tab as well as for medical reviews in the Medical Review screen of the case form.

Configuration changes

A new profile switch, Enable Narrative Generation using Gen AI, is introduced under Argus Console > System Management (Common Profile Switches) > Case Processing. You can enable or disable the Gen AI feature using this switch.

Case Form changes

A new Generative (AI) button is added for the Narrative field in the case form. This button is available for the Argus Global user. When you click this button, a new dialog appears with the existing narrative text (if any) adjacent to the system generated output using the Gen AI service for comparison. You can substitute the entire existing narrative with the system-generated text by clicking the Replace button, or manually copy specific sections of the system-generated text and paste them into the existing narrative.

This dialog also allows you to provide feedback for the system-generated output, which will help us improve the quality of the Gen AI service.

Note:

The narrative generated using Gen AI is for evaluation purposes only. Hence, it is disabled by default.

When to enable this feature

To make sure the narratives generated via this feature meet your quality standards, Oracle recommends you perform thorough testing and evaluation with your real-world data to assess its performance in the test environment. This will help you understand how the feature works and identify any areas for improvement. You can compare our AI results with your own quality standards.

How it works

Raise a ticket with Oracle Support to get the following information to proceed further with testing and evaluation:

• Guidelines on what to expect.
• Key metrics to measure performance.
• Tips for debugging.
• Model Card details, including the model's intended use, performance, limitations, and AI governance.

What next?

When the results generated via Gen AI are validated and meet your expectations, the product team will work with you on the next steps to deploy this feature for product usage.

We will also provide a formal validation pack when the feature is fully released to make sure it meets all regulations and is based on the real-world performance data. We are committed to working with you to make sure our AI feature generate optimal suggestions.