The concept behind risk adjustment is simple: the federal government provides more financial support to health insurers when a patient has more severe medical conditions, ensuring that beneficiaries receive the necessary care.
At the heart of risk adjustment are Hierarchical Condition Categories (HCCs), which are diagnosis codes used to determine a patient's risk adjustment factor (RAF) score. This score takes into account the patient's specific conditions, as well as other factors such as Medicaid eligibility, gender, and age/disability status.
For Medicare Advantage plans, the monthly capitated payment received for each enrolled member is adjusted based on their RAF score. This adjustment allows reimbursements to accurately reflect the expected cost of caring for each patient based on their health profile. In essence, the RAF adjustment process ensures that physicians' payments align with the severity and complexity of their patient population. This system ensures that healthcare financing supports the real healthcare needs of the population, benefiting both patients and providers.
Specialty providers often offer services in fields like cardiology, nephrology, oncology, and immunology, etc. depending on the needs of their patients. Coding for chronic medical conditions can be difficult, but it is necessary to ensure accurate RAF scores.
For instance, a patient visiting a nephrologist might have high blood pressure or morbid obesity, which could be linked to high sugar levels and potentially trigger diabetes. To receive accurate reimbursements, the specialty provider must include and report codes for each condition to CMS. In this scenario, the patient's chart may include codes related to hyperglycemia, hypertension, such as CKD with heart failure, and more based on the diagnosis.
Due to the increasing importance of HCC coding, relying solely on medical coders for 100% accuracy is no longer justifiable. Why? There are over 60,000 ICD-10 codes and 9,500 ICD-10-CM codes mapped to HCCs across 79 categories, making the potential for errors evident. This is why the healthcare industry as a whole is shifting towards automated or partially automated coding systems to comply with the annual risk adjustment process.
To optimize complex care consumption at affordable costs, CMS is testing various specialty-focused care models. For example, nephrology practices can participate in the CKCC (Comprehensive Kidney Care Contracting) model, while oncology practices can focus on the EOM (Enhanced Oncology Model), among others, to receive better reimbursements based on the value and quality of care provided to patients.
A common requirement in all CMS models is the consistent collection and reporting of quality data that accurately reflects the severity of medical conditions. This data plays a crucial role in assessing risk across populations for accurate reimbursements. Based on our experience working with leading health systems, here are two proven strategies for specialty providers to capture accurate RAF scores:
Increasing primary care touch points can significantly reduce hospital visits when specialty providers prioritize preventive care. This can be achieved through various approaches, such as annual wellness visits or appointments with social workers. The more primary care touch points there are, the greater the opportunity to accurately capture diagnoses and map them to HCC codes.
Coding is a collaborative effort that involves not just physicians and clinicians, but also coders, certified medical assistants, nurses, and other team members in contact with the patient. While only physicians and clinicians can make diagnoses, the entire care team plays a crucial role in ensuring that these diagnoses are appropriately documented with supporting documentation.
In a Medicaid program for risk adjustment, many health plans are still on retrospective risk adjustment programs which requires loads of manual administrative tasks in form of medical record reviews. Going forward, it becomes crucial for health plans to prospectively engage both patients and providers in proactive management, treatment, assessment, and accurate coding of their conditions on an ongoing basis.
With prospective and concurrent risk adjustment at the point of care, physicians get real-time access to data to enhance patient monitoring, diagnostics, treatment plans, and coding, resulting in improved gap closure.
By identify coding gaps during outpatient visits with an EHR-integrated interface, providers can drive point-of-care prospective review gap closure, thereby improving care delivery by leveraging technology to close HCC coding gaps.
Innovaccer’s physician engagement solution, InNote is revolutionizing the risk adjustment process by actively involving physicians at the point of care. This platform integrates seamlessly with any browser-accessible EHR and utilizes third-party data sources to provide physicians with real-time, comprehensive clinical information. Not only does it streamline the EHR experience, but it also proactively alerts physicians to gaps in patient care through simultaneous API calls.
By directly involving physicians, InNote enhances the effectiveness of closing these gaps, particularly in coding and quality improvement. This ultimately leads to improved patient outcomes and overall quality of care. Additionally, its versatility in displaying care insights makes it a valuable tool for healthcare organizations looking to enhance their risk adjustment efforts.
Innovaccer's Suspect Coder Assistant, powered by advanced AI analytics, performs continuous retrospective analysis of historical data to identify missed and questionable codes. It suggests coding opportunities based on claims data and clinical markers, helping providers avoid incorrect data submission, audits, repayments to CMS, penalties, and other legal consequences related to improper coding. This assistant seamlessly integrates with providers' population health management, analytics, and physician engagement solutions to provide point-of-care coding support.
By utilizing Innovaccer's Suspect Coder Assistant, healthcare organizations can benefit from a potential 10% increase in coding accuracy, thanks to improved capture of dropped and suspect codes. This solution can also lead to a 20% decrease in physician coding time at the point of care and reduce total coding time by 30% through automation.
Backed by Innovaccer's Best-in-KLAS data & analytics platform, Suspect Coder Assistant leverages unified patient records, Machine Learning (ML), and Natural Language Processing (NLP) to analyze unstructured data and identify additional suspect conditions or diagnoses, ensuring comprehensive risk capture. Moreover, the solution can be customized to align with unique organizational goals and priorities.
To discover how InNote and Suspect Coder Assistant can optimize coding accuracy and enhance financial performance, schedule a demo with our experts.