AI Revenue Cycle Management: The Guide to Denials, Coding and Automation

Denial Log Analysis Template: CARC and RARC Columns, Prompts and a Worked Example

Hathr.AI built this denial log analysis template for revenue cycle teams that have a spreadsheet of denials and want an AI assistant to find what repeats. It is part of the AI revenue cycle management guide and the companion to the denial analysis workflow. It gives you the columns to export, five prompts to run, and a worked example on a synthetic log whose right answers we computed with a script, so you can check any tool's output against them.

Key takeaways

  • A useful denial log needs about a dozen columns. The two most important are the claim adjustment reason code (CARC) and the payer; the rest decide whether you can find a root cause.
  • Run the five prompts in order: group, trace, compare periods, rank by dollars, then draft the owner and the fix. Each builds on the last.
  • Every AI answer about counts and dollars should be checked against the source rows. The synthetic example below shows what a correct answer looks like.
  • Hathr.AI analyzes .xlsx and .csv files under a BAA accepted at signup, so real denial logs can be uploaded without stripping identifiers first.
  • The template finds patterns. A person decides which denials to appeal and signs every appeal.

What goes in a denial log analysis template?

The template is a spreadsheet with one row per denied claim line and the columns below. Most clearinghouses and billing systems export all of them. The 835 electronic remittance advice is the standard source for CARC, group code and RARC; if you cannot get them from a report, ask your clearinghouse for an 835 export converted to a spreadsheet.

ColumnWhat goes in itWhere it comes from
claim_idYour internal claim numberPractice management or billing system
payerPayer name or IDClaim or 835
service_dateDate of serviceClaim
denial_dateDate of the remittance that denied it835 or payer portal
group_codeCO, PR, OA or PI835 (CAS segment)
carcClaim adjustment reason code835 (CAS segment)
rarcRemittance advice remark code, if any835 (LQ segment) or remit report
cpt_hcpcsProcedure code, with modifiers in a separate columnClaim
locationBilling location or rendering sitePractice management system
rendering_npiRendering providerClaim
billedBilled amount for the denied lineClaim
paidPaid amount, if any835
appeal_statusNone, filed, won, lost or written offYour appeals log

Do not include patient name or date of birth unless you need them. The analysis does not. If you do upload them, a BAA must be in place first (HHS, Business Associates guidance). Hathr.AI accepts its BAA electronically at signup on the web app.

Which five prompts find the pattern?

Run them in order in one conversation. Each prompt names the columns it expects, so rename your headers to match or tell the assistant what your headers mean.

Prompt 1: Group

Analyze this denial log. Group denials by CARC, then give for each: the count, the share of all denials, and the total billed amount. Sort by count, and show the top 10.

Prompt 2: Trace

For the top 5 CARCs, show which payer, CPT family and location combinations account for most of the denials. Give counts, and say what share of that CARC each combination represents.

Prompt 3: Compare periods

Compare the last 90 days with the 90 days before. List the CARCs whose counts changed by more than 25%, and for each, show where the change is concentrated.

Prompt 4: Rank by dollars

Rank CARCs by total billed amount instead of count. Flag any code that is a small share of denials but a large share of dollars.

Prompt 5: Owner and fix

For each of the five biggest patterns, propose one owner (registration, scheduling, coding, billing or clinical) and one process change that would prevent it. Mark each as a hypothesis for staff to confirm.

What does a correct answer look like? A worked example

Hathr.AI built a synthetic log of 1,240 denied claim lines over 12 months (October 2025 to September 2026) with $1,136,585 in billed amount, four payers, three locations and four procedure families. The data is invented. Hathr.AI planted three patterns in it and computed the correct counts with a script, so the first prompt should return something close to this:

CARCDenialsShare of denialsBilled amountNotes
CO-4 (modifier inconsistent or missing)30024.2%$199,578Most frequent code; low dollars per claim
CO-197 (precertification or authorization absent)22418.1%$168,26187 of the 224 are one payer and imaging codes
CO-16 (claim lacks information)21817.6%$122,87679 in the last 90 days against 38 in the 90 days before; 43 of the 79 come from the East location
CO-50 (not medically necessary)19115.4%$395,29535% of all billed dollars; 95 are surgery codes worth $363,959
CO-29 (timely filing)12910.4%$126,72177 of the 129 come from the South location
CO-97 (included in another service)957.7%$56,322Likely modifier or bundling issue
CO-18 (duplicate claim)836.7%$67,532Check resubmission habits

Hathr.AI can run these prompts on your own export; the medical billing and RCM page shows how a billing team gets started.

In Hathr.AI's example, the second prompt should surface the first planted pattern: authorization denials (CO-197) concentrate in one payer and imaging codes, which account for 87 of the 224. That points to an authorization check at scheduling for that payer, not to appeals. The third prompt should surface the second: CO-16 denials rose from 38 to 79 between the two 90-day windows, and 43 of the 79 come from one location, which suggests a registration or claim-form problem there that started in the last quarter. Hathr.AI's fourth prompt should surface the final pattern: CO-50 is a modest share of denials but a large share of billed dollars, almost all of it in surgery codes. Those are the few cases where appeals may be worth the effort, if the chart supports medical necessity.

Note what the AI does not know. It cannot tell you whether the East location changed its intake form in July. That is a question for a person, and it is why Hathr.AI's fifth prompt asks for hypotheses, not conclusions.

Which denial patterns usually belong to which team?

A denial code is a symptom, and the owner of the cause is rarely the billing office. This mapping is Hathr.AI's starting point for the conversation, not a rule; confirm each pattern with the team before you assign work.

PatternLikely ownerFirst question to ask
Authorization absent (CO-197)Scheduling and authorization staffIs the authorization check done before the visit, and for which payers?
Missing information (CO-16)Registration and charge entryDid a form, field or template change on the date the count rose?
Timely filing (CO-29)Billing office and the location managerWhere do claims wait before they are submitted?
Not medically necessary (CO-50)Clinical documentation and the physicianDoes the chart support the service against the payer policy?
Modifier or bundling (CO-4, CO-97)CodingWhich code pairs repeat, and which modifiers are missing?

What are the common mistakes with a denial log?

  • Analyzing only the first denial. If a claim is denied, resubmitted and denied again, count the first denial for rate and the later ones for rework, so the two do not mix. HFMA's Claim Integrity Task Force counts only the first denial on a claim in its initial denial rate.
  • Mixing denial and rejection. A rejection never reached adjudication and does not appear in the 835. Keep rejections in a separate log.
  • Trusting a pattern from small groups. Under a few dozen rows, read the claims yourself.
  • Skipping the dollar view. The most frequent denial code is not always the most expensive one, as the example shows.

How do you check the AI's counts?

A model that reads a spreadsheet can still miscount. Use the same three checks on every result:

  1. Total check. The group counts must add up to the row count of the file. In the example above they sum to 1,240.
  2. Spot check. Filter the spreadsheet for the top group and compare the count the assistant gave. A pivot table takes a minute.
  3. Trace check. For one claim the assistant cites as an example, open the row and confirm the payer, code and date.

If any check fails, say so in the conversation and ask the assistant to recompute. If it fails again, do the count in the spreadsheet. Hathr.AI analyzes and summarizes your data; it does not replace a reconciliation.

What should you do with the results?

Take the owner and fix from the fifth prompt to the people who own the process, with the counts and a sample of rows. Re-run the same five prompts monthly on the new export and compare the group table to the previous month. If a pattern shrinks after a change, you have the proof; if not, the cause lay elsewhere. For appeals, score each denial group on expected recovery against the cost of the appeal using your own overturn history, and have a person approve every submission; the denial analysis workflow shows how.

How do you start?

The web app costs $47 per user per month (as of October 2026), with a 7-day free trial and no seat minimums; see Hathr.AI pricing. Start a 7-day free trial, upload last quarter's denial log as a .xlsx or .csv file, and run Prompt 1. Teams of 10 or more can book a demo; the Hathr.AI Enterprise BAA can be signed in under 24 hours.

Frequently asked questions

What columns does a denial log need?
At minimum: payer, CARC, group code, service and denial dates, procedure code, location and billed amount. Add RARC, rendering provider, paid amount and appeal status when you can. Hathr.AI analyzes the file as a spreadsheet, so extra columns do not hurt and missing ones limit which questions you can ask.

Can I upload a spreadsheet with patient identifiers?
Only to a vendor that has signed a BAA with you. Hathr.AI accepts its BAA at signup and analyzes .xlsx and .csv files under it, so you do not have to strip identifiers first. Leave out name and date of birth anyway when the analysis does not need them.

Do I need an 835 file to start?
No. A spreadsheet export from your billing system or clearinghouse with the columns above is enough. The 835 is the standard source for CARC and RARC, so ask your clearinghouse for an 835 report in spreadsheet form if your billing system does not export them.

How big a file can I upload?
Hathr.AI handles 90+ files and 100,000+ pages in a single workflow. If you want to check results in smaller pieces, split very large exports by month or payer, then compare the totals to the full file.

Will the AI decide which denials to appeal?
No. Hathr.AI finds patterns and drafts text, and a biller or physician decides what to appeal and signs every appeal. Score groups on expected recovery against your own appeal cost and overturn history, and treat any group without history as a guess.

Category
Implementation Guides
Written by
Sam Hart headshot - Founder at Hathr.ai
Sam Hart
Date Published:
2026-10-27

Our Youtube Videos

Hathr.AI is the fastest, safest way to handle sensitive medical records with HIPAA-compliant artificial intelligence. In this demo, watch how you can:✅ Summarize a patient’s medical record  ✅ Generate an AI-assisted treatment plan  ✅ Write a letter to the patient in plain English  ✅ Suggest CPT billing codes  ✅ Draft an insurance appeal for a denied claim  ✅ Evaluate the case for potential malpractice — all in under 5 minutes.The only AI tool hosted in AWS GovCloud and Powered by Claude 4.0 Sonnet, Hathr.AI is trusted by hundreds of practices that need speed, security, and compliance.Learn more: hathr.ai  For healthcare teams: hathr.ai/healthcare  Reach out to learn more: contact@hathr.ai‍

#HIPAACompliantAI#ArtificialIntelligenceInMedicine#HealthcareAI#MedicalBillingAI#AIForDoctors#HIPAAAI#MedicalRecords#AIInHealthcare

Description

‍

As Hathr.AI, we are dedicated to providing a private, secure, and HIPAA-compliant AI solution that prioritizes your data privacy while delivering cutting-edge technology for enterprises and healthcare professionals alike.

In this video, we’ll dive deep into the growing concerns around data privacy with AI tools—especially in light of recent revelations about Microsoft’s Word and Excel AI features. These new features have raised alarm over data scraping practices, where user data could be used without clear consent, leaving individuals and organizations exposed to potential privacy breaches. What makes this especially concerning is the "opt-in by default" design, which could lead to unintended data sharing.

In contrast, Hathr.AI ensures that your data stays yours. With a firm commitment to HIPAA compliance, we take the protection of sensitive healthcare data to the highest level. Our platform is built with the understanding that privacy is not an afterthought but a fundamental pillar of our design. We don’t collect, store, or sell user data, and we employ state-of-the-art encryption, secure access protocols, and clear user consent processes to keep you in full control.

We’ll also touch on why Hathr.AI, powered by advanced LLM (Large Language Models) like Claude AI, offers a secure and private alternative for businesses looking to leverage AI technology without compromising sensitive information. While some AI tools may collect or expose data through ambiguous or hard-to-find opt-out settings, Hathr.AI puts transparency and security at the forefront, offering peace of mind in an era of increasing digital vulnerability.

If you’re concerned about your privacy or looking for a HIPAA-compliant AI solution that respects your data, Hathr.AI provides the robust security, transparency, and ethical design that you need.

Key Points:

  • HIPAA Compliant AI: Built for healthcare professionals, ensuring compliance with privacy regulations.
  • Privacy-first: No data scraping, no data selling, full user control over information.
  • Claude AI: Secure, powerful LLM tools for advanced capabilities without compromising security.
  • Data Transparency: Say goodbye to hidden opt-in/opt-out toggles—Hathr.AI gives you clear, easy-to-understand privacy settings.

Tune in to learn how Hathr.AI ensures your AI tools remain private, secure, and trustworthy, while still delivering the performance and accuracy you need to thrive in a fast-evolving digital landscape.

Don't forget to like, comment, and subscribe for more insights on secure AI solutions and how to protect your organization from emerging privacy risks!

Description

‍

Discover how Hathr AI's advanced AI tools transform federal acquisition processes with unparalleled security and efficiency. Designed for government professionals, this video showcases Hathr AI’s capabilities, including secure AI data analysis, HIPAA-compliant tools, and AWS GovCloud integration, to help streamline decision-making and document management. Perfect for agencies seeking private, compliant, and powerful AI solutions, Hathr.AI delivers tools tailored for healthcare and government needs.
‍

Key Topics Covered:

AI-driven data analysis for governmentHIPAA-compliant, secure AI tools for federal agencies

Private deployment options with AWS GovCloud

Learn more about Hathr AI’s secure, high-performance solutions at hathr.ai and transform your agency’s acquisition process with cutting-edge AI.

Description

‍

Discover how Hathr.AI simplifies NSF grant evaluations with advanced AI-driven compliance and proposal review tools. This video showcases Hathr.AI’s capability to streamline grant compliance checks, enhance accuracy, and save time for evaluators and applicants alike. Ideal for research institutions, government agencies, and proposal writers, Hathr.AI offers secure, HIPAA-compliant AI solutions tailored to meet the complex requirements of NSF and other grant processes.Highlights:AI-powered compliance checks for NSF grant proposalsFast, accurate, and secure evaluations with Hathr.AITailored solutions for research, government, and healthcareOptimize your grant proposal process with Hathr.AI's private, secure AI tools. Learn more at hathr.ai and transform how you handle grant evaluations and compliance.

Description

‍

Join Hathr.AI at the Defense Information Systems Agency (DISA) Technical Exchange Meeting to explore innovative AI solutions tailored for federal and defense applications. In this session, we highlight Hathr.AI's secure, private AI tools designed for efficient data handling, HIPAA compliance, and seamless integration within government systems, including AWS GovCloud. Perfect for agencies seeking reliable AI for data analysis, document summarization, and secure decision-making, Hathr.AI provides cutting-edge technology for defense and healthcare needs.Highlights:AI tools for federal and defense data managementSecure, HIPAA-compliant AI solutions with AWS GovCloudEnhancing operational efficiency with private AI deploymentsDiscover how Hathr.AI's solutions empower government and defense agencies to stay at the forefront of innovation. Visit https://hathr.ai to learn more about our services.

Blog and articles

Latest insights and trends

AI Healthcare solutions with Hathr.AI
HIPAA Compliant AI

AI Healthcare Solutions: How a HIPAA Compliant LLM can Revolutionize your practice

Learn how HIPAA compliant AI healthcare solutions can revolutionize your practice. Hathr AI offers secure, HIPAA & NIST-certified tools that automate billing, enhance diagnostics, and improve patient care while ensuring complete data privacy and compliance.
deepseek-ai-is-dangerous-for-healthcare
Security & Compliance

DeepSeek AI: Interesting Methods, Dangerous Product

Analysis of DeepSeek AI's computational efficiency innovations and why its security risks, censorship issues, and compliance concerns make it unsuitable for healthcare, government, and other regulated industries in the United States.
Challenges Finding Compliant AI
Security & Compliance

Challenges Finding Compliant AI: ChatGPT is Watching You

This blog post explores the recent discovery of AI-powered surveillance by Chinese intelligence using ChatGPT, highlighting the vulnerabilities of commercial AI tools in terms of security, privacy, and compliance. It discusses the implications for regulated industries and offers guidance on implementing secure, HIPAA-compliant AI solutions like Hathr.AI to safeguard operations without compromising functionality.
HIPAA Compliant AI

Low-Code HIPAA Compliant AI: Hathr.AI Integrates with Pipedream.com to Deliver HIPAA-Compliant AI Integration

Hathr.AI partners with Pipedream.com to offer HIPAA-compliant AI integrations, transforming healthcare automation with secure, low-code solutions. This collaboration empowers healthcare providers and developers to create compliant workflows, enhancing efficiency and patient outcomes while maintaining robust data security.