Medical claims review is imperative for health insurers to determine medical necessity and quality of care. Apart from this, a detailed analysis of the claims also helps identify insurance fraud and abuse. The review process itself is time- and labor-intensive and must be performed by skilled, trained and experienced professionals. The reviewer has to find out whether the claim has been accurately paid, is in keeping with the payer’s policy, and compliant with applicable regulations. If the claim is a complex one, it may take more time to be processed. The entire process can be stressful for payers and the attorneys who represent them, especially because most payers are required to pay claims within fifteen or thirty days from the date of receipt. To facilitate medical record analysis, advanced technology such as artificial intelligence or AI is being used to review the medical records and claims quickly and effectively.
Contact Managed Outsource Solutions (MOS) for Value-added Medical Claims Review!
Challenges Involved in Medical Claims Review
- Unorganized medical records
- Inconsistent document layout
- Varying medical terminology
- Duplicate entries
- Erratic coding
It could be very difficult to perform manual reviews on all the claims because of the large-volume medical records involved. Therefore, there could be challenges in identifying erroneous payments and in adjudicating claims. Another major concern is in ensuring that the documentation is complete, and that all conducted procedures are correctly documented and supports medical necessity. The documentation should also follow applicable regulations and policies.
AI and Other Advanced Technology to Facilitate Medical Record Review
AI technology including NLP (Natural Language Processing) is used for reviewing medical records and claims. Advanced artificial intelligence models help speed up claims processing while maintaining compliance. Here are some of the things that machine learning-driven models can perform.
- Review large-volume claims quickly and efficiently
- Assign risk scores to remaining claims. This enables manual intervention to be focused strategically.
- Automatically document findings and provide guidance to medical record reviewers with pertinent evidence regarding adherence to clinical policies.
- Scan the medical records and extract important evidence from radiology reports, lab results, medical history, physicians’ notes and others. By applying clinical policy against the extracted data, AI models help with quick and informed decision-making.
- Automation of the medical record review process ensures consistency and reduces the risk of non-compliance with medical standards and applicable regulations.
The manual medical claims review and medical record review processes can be made more efficient and consistent with advanced technology models. However, human participation cannot be completely avoided. AI models can review a greater number of medical records and better focus the reviews. Importantly, healthcare provider calls associated with medical necessity and authorization can be considerably reduced. AI for medical record review can integrate with the clients’ current processes.
Application Areas of Advanced Technology
- HEDIS Quality Measures: Natural language processing models facilitates identifying supporting evidence for hybrid HEDIS measures. With such advanced technology, it is easier to extract key facts contained in unstructured text documents. There is no need to review the documents multiple times and consequently incur high costs. NLP processes can be applied through the reporting year, which in turn helps identify and close care gaps immediately.
- Extract SDoH details or Social Determinants of Health: These include severity of the disease and lifestyle choices. NLP can be used to extract these data from the medical records and provide complete details of each plan member.
- Risk Adjustment for Medicare Advantage: Advanced technology models help in identifying specific disease comorbidities in association with chronic diseases such as heart failure and diabetes. Many key details may not be captured in the EHR fields and these can be obtained from a review of the clinical notes. Such information is important for long-term conditions such as multiple sclerosis, chronic hepatitis, diabetes, heart failure, chronic obstructive pulmonary disease. Medical record review helps show the audit trail and proof of various face-to-face encounters and their dates.
- Clinical review and medical necessity: Tedious medical record analysis can be simplified with NLP technology that can more easily identify supporting evidence in the medical chart for the treatments provided, medical devices used and so on. The medical records can be easily scanned and the relevant criteria extracted efficiently.
Health insurers rely on accurate medical record review and medical claim review to ensure appropriate reimbursement for various medical procedures and treatments. Advanced technology can reduce the stress and inefficiency associated with manually reviewing vast amounts of unstructured medical data and related high costs. To gain vital member insights from the medical records, payers are increasingly evaluating and using various technology options. Medical record review teams for health plans also utilize advanced technology to quickly search huge data sets and obtain results ranked in the order of relevance. This helps them locate the information needed to make a coding or clinical determination.