diff --git a/backend/src/document-processor/services/aws-bedrock.service.ts b/backend/src/document-processor/services/aws-bedrock.service.ts
index 06b86921..6f75ef49 100644
--- a/backend/src/document-processor/services/aws-bedrock.service.ts
+++ b/backend/src/document-processor/services/aws-bedrock.service.ts
@@ -56,6 +56,18 @@ Look for and extract the following information:
 
 This document may be a lab report showing blood work or other test results, so please pay special attention to tables, numeric values, reference ranges, and medical terminology.
 
+IMPORTANT: Base your analysis on information from multiple trusted medical sources and authorities, including but not limited to:
+- Mayo Clinic
+- Cleveland Clinic
+- CDC (Centers for Disease Control and Prevention)
+- NIH (National Institutes of Health)
+- WHO (World Health Organization)
+- American Medical Association
+- American Heart Association
+- American Academy of Pediatrics
+- UpToDate
+- MedlinePlus
+
 Format the response as a JSON object with the following structure:
 {
   "title": string,
@@ -88,6 +100,7 @@ When extracting lab values:
 4. Set "isCritical" to true when the value indicates an urgent medical situation. Set it to false for values that are normal or only slightly abnormal.
 5. Include a "conclusion" field that provides a brief interpretation of what this value indicates about the patient's health
 6. Include a "suggestions" field that provides brief recommendations based on this value
+7. IMPORTANT: If reference ranges are missing from the document, add "reference-ranges-missing" to the missingInformation array in metadata, and use standard reference ranges from trusted medical sources to determine the status.
 
 EXTREMELY IMPORTANT FORMATTING INSTRUCTIONS:
 1. ABSOLUTELY DO NOT START YOUR RESPONSE WITH ANY TEXT. Begin immediately with the JSON object.
diff --git a/backend/src/document-processor/services/document-processor.service.ts b/backend/src/document-processor/services/document-processor.service.ts
index 6b80a17e..e51233c7 100644
--- a/backend/src/document-processor/services/document-processor.service.ts
+++ b/backend/src/document-processor/services/document-processor.service.ts
@@ -55,12 +55,31 @@ export class DocumentProcessorService {
       });
 
       // Step 2: Analyze extracted text using AWS Bedrock
-      const analysis = await this.bedrockService.analyzeMedicalDocument(
+      const initialAnalysis = await this.bedrockService.analyzeMedicalDocument(
         extractedText.rawText,
         userId,
       );
 
-      // Step 3: Generate simplified explanation using Perplexity
+      // Step 3: Review and verify analysis using Perplexity
+      this.logger.log('Reviewing medical analysis with Perplexity');
+      let analysis: MedicalDocumentAnalysis;
+
+      try {
+        const verifiedAnalysis = await this.perplexityService.reviewMedicalAnalysis(
+          initialAnalysis,
+          extractedText.rawText,
+        );
+        analysis = verifiedAnalysis;
+        this.logger.log('Analysis verified and possibly corrected by Perplexity');
+      } catch (reviewError) {
+        this.logger.error('Error reviewing analysis with Perplexity', {
+          error: reviewError instanceof Error ? reviewError.message : 'Unknown error',
+        });
+        // Fall back to initial analysis if review fails
+        analysis = initialAnalysis;
+      }
+
+      // Step 4: Generate simplified explanation using Perplexity
       let simplifiedExplanation: string | undefined;
 
       try {
diff --git a/backend/src/services/perplexity.service.ts b/backend/src/services/perplexity.service.ts
index 329bec8c..1d20b7e7 100644
--- a/backend/src/services/perplexity.service.ts
+++ b/backend/src/services/perplexity.service.ts
@@ -96,11 +96,7 @@ export class PerplexityService {
   }
 
   /**
-   * Sends a chat completion request to the Perplexity API
-   *
-   * @param messages Array of messages for the conversation
-   * @param options Additional options for the request
-   * @returns The chat completion response
+   * Queries the Perplexity AI API
    */
   async createChatCompletion(
     messages: PerplexityMessage[],
@@ -166,4 +162,69 @@ export class PerplexityService {
     const response = await this.createChatCompletion(messages);
     return response.choices[0].message.content.trim();
   }
+
+  /**
+   * Reviews and verifies a medical document analysis against trusted medical sources
+   *
+   * @param analysis The medical document analysis to review
+   * @param originalText The original text of the medical document
+   * @returns The corrected medical document analysis
+   */
+  async reviewMedicalAnalysis(analysis: any, originalText: string): Promise<any> {
+    this.logger.log('Reviewing medical document analysis with Perplexity');
+
+    const systemPrompt =
+      'You are an AI assistant specializing in medical information verification.\n' +
+      'Your task is to review a medical document analysis and verify it against trusted medical sources.\n' +
+      'You must ensure all information is accurate, especially lab value reference ranges and interpretations.\n' +
+      'Use authoritative medical sources like Mayo Clinic, Cleveland Clinic, CDC, NIH, WHO, and medical journals.\n';
+
+    const analysisJson = JSON.stringify(analysis, null, 2);
+
+    const userPrompt =
+      `Please review the following medical document analysis for accuracy and completeness. ` +
+      `Check if the lab value reference ranges, interpretations, and recommendations align with trusted medical sources. ` +
+      `Focus on these key aspects:\n` +
+      `1. Verify lab value reference ranges\n` +
+      `2. Confirm interpretations of abnormal values\n` +
+      `3. Validate medical conclusions and recommendations\n` +
+      `4. Ensure all lab values are correctly categorized\n\n` +
+      `If you find any discrepancies, provide corrections in your response by returning the corrected JSON directly.\n\n` +
+      `Medical Document Analysis:\n${analysisJson}\n\n` +
+      `Original Medical Document Text:\n${originalText}\n\n` +
+      `Return the corrected JSON analysis with the same structure, no preamble or explanation needed.`;
+
+    const messages: PerplexityMessage[] = [
+      { role: 'system', content: systemPrompt },
+      { role: 'user', content: userPrompt },
+    ];
+
+    try {
+      const response = await this.createChatCompletion(messages, {
+        temperature: 0.3, // Lower temperature for more accurate/factual responses
+        maxTokens: 4000, // Ensure there's enough space for the full corrected analysis
+      });
+
+      // Parse the response to get the corrected analysis
+      const responseText = response.choices[0].message.content.trim();
+
+      try {
+        // Try to parse as JSON - Perplexity should return the corrected JSON
+        const correctedAnalysis = JSON.parse(responseText);
+        return correctedAnalysis;
+      } catch (jsonParseError) {
+        // If parsing fails, log the error but return the original analysis
+        this.logger.error(
+          `Failed to parse Perplexity review response as JSON: ${jsonParseError instanceof Error ? jsonParseError.message : 'Unknown error'}`,
+        );
+        return analysis;
+      }
+    } catch (error) {
+      // If the API call fails, log the error but return the original analysis
+      this.logger.error(
+        `Error during medical analysis review: ${error instanceof Error ? error.message : 'Unknown error'}`,
+      );
+      return analysis;
+    }
+  }
 }