Wirewalk Instituteof AI
hls-155 Basic Available

AI for Medical Billing and Coding Specialists: CPT, ICD-10-CM, HCPCS and Claim Edits

For working coders, billers and coding auditors who check, correct and defend what autonomous coding engines, CAC tools, claim scrubbers, denial scores and AI drafting tools produce, line by line against the official guidelines and edits.

Level
Basic
Study time
12 hours
Lessons
14 in 5 modules
Exam
20 questions

About this course

This course is built around one fictional composite organization, Brindlewood Health in Knoxville, Tennessee: two hospitals and a freestanding emergency department, a 212-provider physician group in Medicare Advantage risk contracts, an autonomous coding engine that has final-coded radiology and ED professional fees since June, and a CFO who wants it expanded on January 1, 2027, the day CPT 2027 takes effect. Each module solves one problem the coding and billing teams actually face: an engine that codes a suspected diagnosis as confirmed or bills the contrast study that was ordered rather than the one performed, a third of coders asking chatbots on their phones, a year-end HCC sweep paid on contingency, ambient-scribe notes that claim more than happened, AI-drafted queries that lead, a scrubber's Auto-apply toggle at month-end, a problem-list diagnosis offered to pass a coverage edit, a drug line whose discarded amount nobody documented, a denial score that would write off recoverable money, an appeal draft with an invented fact, and an audit whose pooled error rate hides the pattern that matters.

The rules are taught where they decide the case: the FY 2027 ICD-10-CM Official Guidelines (Sections IV.H, IV.K, II.H, I.B.14), whose adherence HIPAA requires; CPT 2027 and its Appendix S taxonomy for AI-enabled clinical services (codes named by number and described in Wirewalk's own words); HCPCS Level II; the quarterly NCCI edits and the Policy Manual's modifier and MUE indicators; the CMS JW and JZ discarded-drug modifier policy; the AHIMA/ACDIS compliant query practice brief; the HHS-OIG Medicare Advantage compliance program guidance of February 2026; the False Claims Act; the overpayment rules at 42 CFR 401.305 and 422.326; HIPAA minimum necessary and business associate rules; and the ABN. Real products (Solventum, CodaMetrix, Nym, Fathom, Waystar, Experian Health, and general assistants from Microsoft and Anthropic) are compared only by what their makers state. Every module ends in a Decision Lab, a 35-minute capstone simulation follows the whole case to February 1, and the capstone project is the coding quality packet a lead sends before an automation decision, offered as self-scored practice with a rubric and an answer key. Prior authorization and patient access stay at awareness depth (see hls-150); building models is hls-255. Status is as of October 2026. The course is educational, not legal, billing or coding-compliance advice, and no vendor endorses or is endorsed by it. It is not currently approved for AAPC or AHIMA continuing education credit (CEUs).

What you will be able to do

  • Validate AI-suggested ICD-10-CM, CPT and HCPCS codes and modifiers against the note or report for the setting (Sections IV.H, IV.K, II.H, I.B.14, and the procedure the report documents rather than the order), correcting or querying each and citing the deciding source with facts from the record only
  • Use an approved AI assistant for coding research with a minimum-necessary, de-identified question and record the official source and code-set version that confirms or refutes the answer
  • Classify AI-flagged HCC suspects and AI-supported E/M levels as supported, unsupported, query-needed or delete, and identify where a scribe-drafted note overstates the visit
  • Revise an LLM-drafted provider query or physician prompt so it passes a non-leading checklist from the AHIMA/ACDIS brief and avoids what the OIG names as a risk
  • Resolve NCCI PTP, MUE and coverage holds by removing a code, adding a modifier the indicator allows with its documentation sentence, checking the ABN, or holding for query, and reject unsupported AI suggestions
  • Triage a week of coding denials by group code, CARC, RARC and predictive score, route root causes, and correct an AI-drafted appeal so every statement traces to the record
  • Audit AI-coded output with a stratified sample and exact 95% intervals, recognize a payment-affecting pattern, and write the escalation that starts a timely overpayment investigation
  • Run a code-set and edit currency check on every tool for October 1, January 1 and each NCCI quarter, and decide whether an AI-enabled clinical service has its own CPT code

Syllabus

5 modules · 14 lessons · about 12 hours

Module 1: The Autonomous Queue: Checking What the Engine Codes

Validate an autonomous engine's suggestions against the note in outpatient and inpatient settings, and set the rule for which assistant coders may ask and how.
3 lessons
  1. Opening the Evidence: Validating Autonomous-Coding Suggestions Under Sections IV.H, IV.K and I.B.14
  2. The Inpatient Difference: Principal Diagnosis, Section II.H and the DRG Preview
  3. Asking a General-Purpose Assistant a Coding Question: Approved Tools, Minimum Necessary and the Official Source
  • Decision Lab · 12 minClear the Backlog by FridayDecide how fast to push an autonomous coding engine through an 11,300-encounter backlog when the vendor offers a shortcut, coders accept suggestions in 41 seconds, and a third of them ask chatbots on their phones.

Module 2: Diagnoses and Levels That Must Hold Up: HCC Suspects, Scribe Notes and Queries

Review AI suspect lists in both directions, score E/M on ambient-scribe notes, and fix AI-drafted queries that lead.
3 lessons
  1. Reviewing an AI Suspect List in Both Directions: Supported, Unsupported, Query-Needed and Delete
  2. Scoring E/M on an Ambient-Scribe Note: Medical Decision Making, Attested Time and What the Note Overstates
  3. Drafting a Provider Query With an LLM: Clinical Indicators, Answer Options and the Non-Leading Test
  • Decision Lab · 12 minThe Year-End SweepDecide how to capture 2026 risk-adjustment diagnoses before Plan A's deadline when the suspecting tool, a contingency vendor and a fast query button all point toward volume, and a plan's compliance letter arrives in December.

Module 3: Clean Claims Before They Go Out: Scrubber Edits, Modifiers and Medical Necessity

Resolve NCCI and coverage holds with AI explanations without bypassing an edit or adding a diagnosis the record does not give.
2 lessons
  1. Working a PTP or MUE Edit With an AI Explanation: Modifier Indicators, 59 and X Modifiers, and When to Remove the Code
  2. Medical Necessity at Charge Entry: Matching the Coverage Article, the ABN and the Diagnosis You May Not Add
  • Decision Lab · 12 minThe Auto-Apply ToggleClear a month-end hold queue when the scrubber offers to append its own modifiers and swap in covered diagnoses, then respond when the Medicare contractor and a commercial payer start asking about modifier use.

Module 4: The Denial Worklist: Triage, Root Cause and Appeals You Can Sign

Triage coding denials with a predictive score and correct AI-drafted appeals so nothing false reaches the payer.
2 lessons
  1. Triaging a Week of Coding Denials: Group Codes, CARCs, RARCs and a Predictive Overturn Score
  2. Correcting an AI-Drafted Appeal: Invented Facts, Wrong Citations and Minimum-Necessary Attachments
  • Decision Lab · 12 minTwo Hundred Twelve DenialsWork a week's coding-denial worklist when a predictive score calls 61 denials hopeless and a drafting tool can write 118 appeals overnight, then answer a payer medical director who found a false statement in one of them.

Module 5: Auditing the Machine and Keeping It Current

Audit auto-finalized work by stratum, act on the overpayment clock, check code-set and edit currency in every tool, code AI-enabled services, and assemble the capstone packet.
4 lessons
  1. Sampling Autonomously Coded Encounters: Error Rates, 95% Intervals and the 60-Day Overpayment Clock
  2. October 1, January 1 and Every Quarter: Code-Set and Edit Currency in Every Tool
  3. Coding AI-Enabled Clinical Services: CPT 2027 AI Codes, Appendix S and What the Report Must Show
  4. Capstone: The Coding Quality Packet
  • Decision Lab · 14 minEleven EncountersReport the first blind audit of auto-finalized work, decide how to contain a payment-affecting pattern, and recommend whether the engine expands on January 1 after a CPT 2027 dry run fails.
  • Capstone simulation · 35 minNinety Days to January 1Run Brindlewood's AI coding controls from the October 5 memo to February 1: build the ninety-day plan, keep coders checking, survive month-end and a payer's records request, act on the audit, settle the year-end sweep, prove CPT 2027 readiness and make the expansion recommendation.

Exam and certificate

The exam unlocks once you have completed every lesson and played each Decision Lab to an ending. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Solventum, CodaMetrix, Nym, Fathom, Waystar, Experian Health, Microsoft, or Anthropic. Product and company names are trademarks of their respective owners.

More in AI in Health and Life Sciences

All 21 courses in this track
hls-001 Free intro Available

AI in Health and Life Sciences: A Practical Introduction

A free introduction built on eight healthcare jobs: auditing an ambient-scribe note, answering a portal message from an AI draft, acting on a sepsis alert, reading a triage-flagged CT worklist, reviewing a prior-authorization request, checking AI-suggested codes, and triaging drug and device safety reports. Each lesson shows where AI helps, where it must not decide, and the rule that governs that exact task.

3 h · 8 lessons Free intro
hls-110 Basic Available

AI for Nursing and Care Team Professionals

Use a synthetic US care-team case to check AI drafts against source records, preserve nursing judgment and coordinate accountable follow-up. Build a practical evidence packet without patient data or a model account.

10 h · 18 lessons See price at checkout
hls-210 Intermediate Available

Building and Deploying AI in Healthcare Delivery

Evaluate clinical AI through a fictional US health-system case: procurement, source audits, silent validation, monitoring, privacy and integration. Produce a bounded evidence portfolio using synthetic materials and branching decisions.

16 h · 24 lessons See price at checkout