AWS Security ChangesHomeSearch

AWS prescriptive-guidance documentation change

Service: prescriptive-guidance · 2026-07-10 · Documentation low

File: prescriptive-guidance/latest/rag-healthcare-use-cases/case-2.md

Summary

Updated image paths and simplified section titles (e.g., 'Predicting patient re-admission likelihood' to 'Predicting patient re-admission').

Security assessment

Changes are limited to image path corrections and title shortening. No references to security controls, vulnerabilities, or data protection measures were added or modified in the content.

Diff

diff --git a/prescriptive-guidance/latest/rag-healthcare-use-cases/case-2.md b/prescriptive-guidance/latest/rag-healthcare-use-cases/case-2.md
index 32e34ba8b..fceba25fe 100644
--- a//prescriptive-guidance/latest/rag-healthcare-use-cases/case-2.md
+++ b//prescriptive-guidance/latest/rag-healthcare-use-cases/case-2.md
@@ -32 +32 @@ The risk-scoring models quantify the inferences from the LLM into numerical scor
-![Using AWS services and an LLM to predict patient re-admission risk.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/predicting-readmission-risk.png)
+![Using AWS services and an LLM to predict patient re-admission risk.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/bcd24c08-658e-42e8-8880-38a42492de10.png)
@@ -47 +47 @@ Building this solution consists of the following steps:
-## Step 1: Predicting patient outcomes by using a medical knowledge graph
+## Step 1: Predicting patient outcomes
@@ -66 +66 @@ The following image shows the sequential steps involved in fine-tuning an LLM in
-![Fine-tuning an LLM in Amazon Bedrock by using a patient outcome prediction dataset.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/fine-tune-llm.png)
+![Fine-tuning an LLM in Amazon Bedrock by using a patient outcome prediction dataset.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/a4cc2509-4710-4a74-bbda-aa4ccea17da2.png)
@@ -89 +89 @@ The diagram shows the following workflow:
-## Step 2: Predicting patient behavior towards prescribed medications or treatments
+## Step 2: Predicting patient behavior
@@ -159 +159 @@ Fine-tuned LLMs can consume past prescription fulfillment data from the medical
-## Step 3: Predicting patient re-admission likelihood
+## Step 3: Predicting patient re-admission
@@ -244 +244 @@ You can process these time-series events to predict the re-admission likelihood
-## Step 4: Computing the hospital re-admission propensity score
+## Step 4: Computing the propensity score
@@ -271 +271 @@ The following diagram shows the workflow of a conversational AI agent that a cli
-![Proactive intervention by a clinician based on the re-admission risk of a patient.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/clinician-intervention.png)
+![Proactive intervention by a clinician based on the re-admission risk of a patient.](/images/prescriptive-guidance/latest/rag-healthcare-use-cases/images/guide-img/c2d53172-a932-4340-96f5-3132299b8691/images/893a3fe5-58fd-4afd-bc45-0e460802d836.png)