22.1 CAC, NLP and AI: Context, Oversight and Performance

AHIMA Certified Documentation Integrity Practitioner CDIP

Track your progress as you read

Finished sections get a check mark.

1 Chapter 1: Authoritative Coding Resources & Conventions

1.1 Official Coding Resources: Scope, Authority & Research 1.2 General Coding Conventions, Punctuation & Instructional Notes 1.3 Chapter-Specific and Setting-Specific Coding Guidelines

2 Chapter 2: Principal & Secondary Diagnosis Determination

2.1 UHDDS Definitions & Principal Diagnosis Selection 2.2 Two or More Diagnoses Equally Meeting Criteria 2.3 Secondary Diagnosis Reporting Standards & POA Status

3 Chapter 3: Procedure Coding & Sequencing Standards

3.1 ICD-10-PCS Root Operations & Inpatient Procedure Coding 3.2 Principal Procedure Selection & Surgical Sequencing 3.3 Applying Official References to Ambiguous Records

4 Chapter 4: Inpatient Prospective Payment & DRG Grouping

4.1 MS-DRG Logic, CC/MCC Exclusions & Severity Levels 4.2 Working vs. Final DRG Assignment & Optimization vs. Maximization 4.3 CDI-Coding Reconciliation & Annual Regulatory Updates

5 Chapter 5: Enterprise CDI Promotion & Program Value

5.1 Articulating CDI Value to C-Suite & Hospital Leadership 5.2 Organizational Models, Inpatient/Outpatient Scope & Staffing 5.3 Cross-Functional Collaboration: HIM, Quality & Case Management

6 Chapter 6: Cross-Functional Alignment & Improvement Projects

6.1 Partnering with Nursing, Pharmacy & Allied Health Professionals 6.2 Documentation Improvement Project Identification & Scoping 6.3 Executing, Piloting & Measuring CDI Project Outcomes

7 Chapter 7: Physician Champion Engagement & Clinical Advocacy

7.1 Selection, Role & Credibility of the CDI Physician Champion 7.2 Peer-to-Peer Engagement, Coaching & Overcoming Resistance 7.3 Developing Standard CDI Operational Policies & Procedures

8 Chapter 8: Compliant Policy Architecture & Query Governance

8.1 AHIMA/ACDIS Practice Brief Standards in Policy Construction 8.2 Medical Record Integration of Provider Query Responses 8.3 Policies for Electronic, Paper, and Verbal Query Communications

9 Chapter 9: Query Escalation & Professional Communication

9.1 Chain of Command & Protocols for Unanswered Queries 9.2 Conflict Resolution & Professional Feedback Mechanisms 9.3 Assessing Stakeholder Learning Needs & Specialty Curricula

10 Chapter 10: Educational Delivery & Broader Healthcare Impacts

10.1 Delivery Methods: Microlearning, Case Studies & Grand Rounds 10.2 Documentation Impacts on Clinical Research & Epidemiology 10.3 Documentation Impacts on Case Management, LOS & Reimbursement

11 Chapter 11: Clinical Record Synthesis & Encounter Trajectory

11.1 Synthesizing Provider Notes, Consults & Progress Trajectory 11.2 Interpreting Diagnostic Imaging, Pathology & Labs 11.3 Resolving Conflicting, Ambiguous & Copy-Forward Entries

12 Chapter 12: Advanced Clinical Concepts & Review Prioritization

12.1 Pharmacotherapy, Clinical Trajectories & Disease Correlations 12.2 Inpatient Review Prioritization: High-Risk & High-Volume 12.3 Payer Prioritization, Length of Stay & Re-Review Cadence

13 Chapter 13: Clinical Indicator Mapping & Gap Recognition

13.1 Systematic Identification of Documentation Gaps 13.2 Sepsis Definitions, SEP-1, and Coding 13.3 AKI Criteria, Tubular Injury, and CKD Staging

14 Chapter 14: Diagnostic Precision in High-Impact Conditions

14.1 Respiratory Failure: Acuity, Evidence, and Sequencing 14.2 Heart Failure Phenotype, Acuity, and Hypertensive Combinations 14.3 Encephalopathy, Delirium, and Acute Cognitive Change

15 Chapter 15: Clinical Validation & Complication Discrepancies

15.1 Malnutrition Assessment, Severity, and Provider Documentation 15.2 Principles of a Compliant, Nonleading Query 15.3 Open-Ended, Multiple-Choice, and Yes/No Queries

16 Chapter 16: Query Mechanics & Direct Provider Collaboration

16.1 Electronic Query Systems, Templates, and Technology Oversight 16.2 Collaborating With the Appropriate Query Recipient 16.3 Capturing and Clarifying Query Responses

17 Chapter 17: Quality Indicators & Post-Discharge Clarification

17.1 Present on Admission Clarification and Selected HAC Rules 17.2 Clarifying Acuity, Cause, Site and Severity 17.3 Post-Discharge Query Opportunities and Limits 17.4 Managing Post-Discharge Query Workflows

18 Chapter 18: CDI Operational Dashboards & Quality Auditing

18.1 Departmental Metrics: Definitions, Calculations and Dashboard Use 18.2 Internal CDI Quality Audits and Reviewer Calibration 18.3 Query Trends: Understanding the Process and Provider Experience

19 Chapter 19: Benchmarking, Productivity & Data-Driven Workflow

19.1 Provider Documentation Benchmarking 19.2 External Benchmarking: CMI, Severity, Mortality and Length of Stay 19.3 Evaluating CDI Professional Performance 19.4 Using Data to Design CDI Workflow and Staffing

20 Chapter 20: Ethical CDI Standards & Regulatory Frameworks

20.1 Applying AHIMA Ethics to CDI Decisions 20.2 Responding to Financial Pressure and Upcoding Risks 20.3 Maintaining Competence and Professional Integrity

21 Chapter 21: Regulatory Compliance & Enforcement Landscapes

21.1 False Claims, Overpayments and Referral Laws 21.2 Regulatory Agencies, Review Contractors and Appeals 21.3 EHR Templates, Copied Text and Record Integrity

22 Chapter 22: Technology Risks & Second-Level Review Protocols

22.1 CAC, NLP and AI: Context, Oversight and Performance 22.2 Selecting Cases for Second-Level Review 22.3 Conducting and Closing a Second-Level Review

23 Chapter 23: Clinical Validation Queries & Risk Mitigation

23.1 Clinical Validation and Coding Clarification 23.2 Clinical Validation Queries and Denial Evidence 23.3 Detecting Leading, Biased and Unsupported Queries

24 Chapter 24: Noncompliant Query Remediation & Query Lifecycle Management

24.1 Query Remediation and Corrective Action 24.2 Query Timeframes, Aging and Measurement 24.3 Query Records, Retention and Evidence Preservation

22.1 CAC, NLP and AI: Context, Oversight and Performance

Key Takeaways Explain This Topic AI

An extracted concept, software suggestion, provider diagnosis and reportable code are separate stages requiring the applicable professional review.

Preserve negation, uncertainty, time and the person experiencing the condition; historical or family mentions alone do not establish a new acute diagnosis.

Confabulation, automation bias and performance disparities are different risks. Verify actual evidence and avoid assuming that a vendor score or approval click resolves them.

The 2026 query brief allows pre-delivery review or ongoing structured auditing; automated delivery retains organizational accountability and requires regular structured auditing.

Precision is TP/(TP+FP), recall is TP/(TP+FN), and false-positive rate is FP/(FP+TN). An audit of flags alone cannot determine recall.

Last updated: October 2026

CAC, NLP and AI: Context, Oversight and Performance

Computer-assisted coding (CAC) can propose codes or identify text for review. Natural language processing (NLP) can identify concepts and their context in narrative records. Generative AI can draft summaries or query language. These functions overlap in some products, but they are not a mandatory sequence of technological “generations.” Evaluate the actual intended use, inputs, output and workflow of the local tool.

An extracted phrase, a proposed diagnosis and a reportable code are different things. Finding the word “stroke” in a chart does not establish that the patient has a current acute infarction. The responsible professionals still must apply the clinical, documentation, query and coding requirements appropriate to the task.

Read beyond the extracted concept

Clinical NLP must preserve context. The original ConText research illustrates why negation, time and the person experiencing a condition matter; it does not establish the performance of every contemporary product. ConText primary study, introduction and algorithm description

• Illustrative source wording Information a reviewer must preserve
• “Denies chest pain” The symptom is negated in this statement
• “Father had a stroke” The condition refers to a family member
• “Stroke in 2019, no residual deficits” A historical event is not automatically a new acute event
• “Return if fever develops” A conditional future event is not a current finding

“Pneumonia considered; further evaluation pending” The statement expresses uncertainty at this point in the course

These examples are reading exercises, not automatic coding instructions. A clinical report may use “history” to describe a condition that remains relevant, and reportability depends on the complete encounter and applicable rules. Similarly, inpatient uncertain-diagnosis rules apply to specified discharge documentation and settings; an early differential or a software label cannot be substituted for those requirements. FY2027 ICD-10-CM guidelines, Sections III.C and IV

Worked review: An automated summary converts “mother had diabetes” into “patient has diabetes.” Locate the original sentence, verify the person and encounter, correct the output through the authorized workflow and report the attribution defect for investigation. A provider-facing query for a new patient diagnosis cannot be justified by the family-history sentence alone. Review any separate current evidence before deciding whether a different clarification is warranted.

Recognize different failure mechanisms

Extraction or mapping error: The tool may lose a negative modifier, confuse the source person, attach the wrong date or map a nonspecific term to an unsupported specific concept. Check the original text rather than trusting the highlighted keyword.

Confabulation: A generated summary may introduce a finding, relationship or citation absent from its inputs. Plausible prose is not evidence. Verify clinical observations against the actual health record and verify cited guidance against its source. NIST identifies confidently erroneous content as a generative-AI risk, including in consequential healthcare uses. NIST Generative AI Profile, §2.2

Automation bias: A person may defer to the output without evaluating it. A nominal approval click provides little protection if the reviewer cannot inspect the source or lacks the time, training and authority needed to challenge the result. Conversely, rejecting a useful tool solely because it is automated also avoids evaluating its actual performance. NIST Generative AI Profile, §2.7

Directional design or performance disparities: A system can overproduce a favored diagnosis or perform differently across note types, services, languages or populations. Investigate the actual outputs and configuration. Do not assume every vendor intentionally tunes software to upcode or that one aggregate score represents every group. NIST distinguishes harmful bias and performance disparities from other AI risks. NIST Generative AI Profile, §2.6

An abnormal laboratory value or medication can be a review trigger without establishing a diagnosis. For example, albumin alone is not an accepted nutrition-status marker for diagnosing malnutrition. A high provider agreement rate with albumin-triggered queries does not validate that premise. Check the clinical evidence and query construction; agreement, clinical support and code accuracy are separate outcomes. ASPEN position paper on visceral proteins

Apply query standards to the function

The 2026 AHIMA/ACDIS brief covers technology-generated prompts, nudges and advisories when they function as patient-specific documentation queries. A vendor label does not exempt the communication. It distinguishes passive reference information from a communication directing consideration of a specific patient diagnosis or documentation option.

The brief calls for organizational vetting, query and compliance involvement, training and ongoing monitoring. Human oversight may occur before delivery or through ongoing structured auditing . Automated delivery without pre-delivery review is therefore not categorically prohibited by the brief. It requires structured regular auditing and continued organizational accountability. Local policy may choose a stricter review process based on risk.

Evaluate relevant, traceable indicators, neutral wording and supported response options, including a way to give an alternate explanation. Test the provider-visible title and interface as well as the body. Review selection, drafting and delivery controls together; a compliant template can still be populated with the wrong patient's data. 2026 compliant-query guidance, §XI

Measure a defined task

First define the unit and reference standard. A “positive” could mean that a particular record contains a legitimate opportunity for review under specified criteria. It does not mean that a diagnosis has been established or that a provider must answer yes. Use qualified independent review and resolve disagreements in the reference labels.

For an illustrative audit of 100 records , suppose reviewers classify 30 as containing the defined opportunity. The tool flags 40 records, of which 24 are true opportunities:

• Reference review Tool flags Tool does not flag Total
• Opportunity present 24 true positives 6 false negatives 30
• Opportunity absent 16 false positives 54 true negatives 70
• Total 40 60 100

Precision: true positives / all positive flags = 24 / (24 + 16) = 60% . How many flagged records actually have the defined opportunity?

Recall or sensitivity: true positives / all actual positives = 24 / (24 + 6) = 80% . How many actual opportunities did the tool find?

False-positive rate: false positives / all actual negatives = 16 / (16 + 54), approximately 22.9% . How often did it flag records without the opportunity?

The 40% of flags that are false positives is not the false-positive rate; it uses a different denominator. An audit limited to flagged records can estimate precision but cannot determine recall without examining a suitable set of unflagged records. A provider agreement rate answers neither question.

These numbers describe this illustrative task and sample. They do not prove that 60% precision is acceptable, establish a contractual target or measure every dimension of query compliance. Assess both missed problems and unnecessary prompts, account for the sampling design and uncertainty, and compare relevant subgroups. NIST's framework is voluntary risk-management guidance, not a federal requirement for an 85% CDI precision threshold or a universal quarterly audit schedule. NIST AI Risk Management Framework

Monitor the deployed workflow

Assign owners for clinical content, coding rules, query compliance, technical operation and privacy/security. Establish the intended setting, permitted data, version, evaluation method and response to defects. Confirm that authorized users can inspect meaningful source evidence and report problems. Use approved systems for PHI; do not paste records into an unapproved consumer AI service merely to obtain a second opinion.

Reassess performance after relevant changes such as a model update, new note template, data-interface change or coding-year transition. A local decline may reflect changed inputs, reference labels or workflow as well as model behavior. Investigate before changing thresholds. Keep records sufficient for the organization's audit, retention and incident-response obligations; “permanent logging of every suggestion” is not a universal retention rule.

If an output is defective, address the immediate communication and determine the affected scope with authorized owners. Some problems require a template fix; others require a system pause, broader case review or incident response. Do not assume that a signature or vendor assurance makes the issue harmless. Equally, an inaccurate suggestion alone does not establish all FCA elements or automatically trigger a per-claim penalty; use the conduct and legal analysis taught in Section 21.1. 2026 query guidance, §XI ; NIST Generative AI Profile, §§2.4 and 3