Document Processing · Fraud Detection
Elevance Health needed to find fraud, waste, and abuse in very large volumes of claims, payment, contract, and medical-record data so it could detect billing errors, suspicious coding patterns, and improper payments earlier while controlling healthcare costs and protecting program integrity.
Reported impact
Elevance Health says AI helps investigators identify issues earlier in the claims process, speeds audits and medical-record review, improves the efficiency of fraud, waste, and abuse investigations, and supports cost control and healthcare program integrity.
Elevance Health describes an in-house AI-assisted payment integrity workflow that combines predictive AI, AI-driven lead identification, and human review inside Carelon’s Payment Integrity operation. The process starts with claims and payment data, which models analyze to determine whether services were billed and paid appropriately and to surface unusual coding or charging patterns relative to peers or local norms. Supporting AI-powered programs also summarize thousands of pages of medical records and align formatting across care provider contract data and medical claims so auditors can review suspected irregularities faster. The outputs are not used autonomously: investigators, auditors, and the Special Investigations Unit review flagged leads, interpret whether anomalies stem from mistakes, contract differences, regulations, or intentional upcoding, and then decide on education, recovery, termination, or other follow-up actions.
Claims and payment data are analyzed by predictive AI models to flag unusual billing patterns, while AI-powered programs process medical records and normalize care provider contract and claims formats. These outputs flow to Payment Integrity investigators, auditors, and the Special Investigations Unit, who review the evidence, determine whether fraud, waste, or abuse is occurring, and take follow-up action.
"AI gives us the ability to see patterns humans might not on their own, but it’s our people who bring context and clarity."
"Increasingly, this work pairs the human expertise of Elevance Health associates ... with AI-driven lead identification or predictive AI."
"The process often begins with models that analyze claims and payment data to ensure services have been billed and paid for appropriately."
"These programs can summarize thousands of pages of medical records, for example, or align formatting for care provider contract data and medical claims to support any required human review of irregular payment patterns."
"Within a clinical auditing unit in Carelon’s Payment Integrity division, for example, one program has helped cut associates’ medical record review time in half — from an average of 40 minutes to 20 minutes — across an annualized volume of nearly 23,000 reviews."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample Jul 28, 2026 Novartis Novartis R&D needs to turn large volumes of scientific, clinical, operational, and real-world data into faster, higher-quality decisions across drug discovery and development, reducing cycle times, surfacing safety… less than 10 percent of drug candidates historically reach the market AI models · AI-enhanced analytics · Generative AI In-house Sample Est. · Jun 25, 2025 Merck Merck needed to remove complexity and manual effort from the clinical trial process, where medical writers spent months reviewing thousands of pages of clinical data to produce regulatory-quality clinical study reports. Reduced the time to create a fully human reviewed CSR first draft from an average of 180 hours to 80 hours advanced table pre-processing · gen AI authoring · large language models (LLMs) In-house Sample Jun 19, 2025 Sanofi Sanofi needed to replace siloed, manual manufacturing and supply workflows with a connected, data-driven operating model that could improve medicine quality and safety, prevent supply disruptions, speed product… 3,500 annual Product Quality Reports Modulus · advanced analytics · generative AI 