Improving Risk Stratification and Identifying High-Cost Members

Introduction

In a groundbreaking study, researchers have found that a risk prediction model using artificial intelligence (AI) can more accurately identify high-cost members in healthcare than traditional models. The study, conducted by a Medicaid accountable care organization, utilized AI to analyze multiple data sources, including claims data, demographics, social determinants of health (SDOH) data, and admission, discharge, and transfer (ADT) alerts. This article explores the avenues of which improving risk stratification contributes to healthcare.

Traditionally, risk stratification models have relied solely on demographic and claims information. However, this study demonstrated that incorporating AI and nontraditional data sources can significantly enhance the identification of high-cost members. The AI model, developed by Medical Home Network, consistently identified a higher proportion of the highest-spending members compared to the Chronic Illness and Disability Payment System (CDPS) model, which relied only on demographic and claims information.

To compare the models, researchers calculated mean, median, and total spending for members with the highest 5% of AI risk scores and compared these metrics with members identified by the CDPS model. The results showed that members deemed highest risk by the AI model had higher spending than those identified by the CDPS model.

Glancing at Risk Stratification

This innovative approach to risk stratification has significant implications for healthcare providers and payers. By accurately identifying high-cost members, healthcare organizations can allocate resources more effectively and develop targeted interventions to improve outcomes and reduce costs. Additionally, the incorporation of nontraditional data sources, such as SDOH and admission alerts, provides a more comprehensive understanding of patients’ health and social factors, enabling personalized and patient-centered care.

Discussing AI’s Reach in Healthcare

The use of AI in healthcare is not limited to risk stratification. AI is reconfiguring various aspects of healthcare, including diagnosis and treatment. For example, AI algorithms can analyze vast amounts of medical data, including electronic health records and medical images, to assist healthcare professionals in making accurate diagnoses and developing personalized treatment plans.

Furthermore, AI can help address healthcare disparities by ensuring equitable access to quality care. By analyzing large datasets, AI algorithms can identify patterns and trends that may be influenced by factors such as gender, race, or socioeconomic status. This information can inform policy and regulatory decisions to promote fairness and equality in healthcare.

Conclusion

As AI continues to advance, it is crucial for healthcare organizations to collaborate with AI consulting companies and firms specializing in artificial intelligence consulting. AI in healthcare improves risk stratification and identifies high-cost members, enhancing outcomes and reducing costs.