Enhancing Risk Adjustment using NLP
Independence Blue Cross (IBC) is a healthcare payer serving 200K Medicare Advantage members. Part of its service is to maintain a risk score for family members, and to submit reimbursement claims to CMS (Centers for Medicare and Medicaid Services). It does this by reviewing members’ medical charts. IBC receives 125K charts per year, with charts ranging from 40 – 100 pages, and typically received by fax. The existing system relied on experienced nurses reviewing PDFs of the charts and flagging covered, eligible conditions, and IBC wanted to move to a more efficient automated and digital system using NLP.<
The result for IBC is an I2E NLP-based system that is 25 – 50% faster in processing the medical charts, and that helps nurses identify conditions they might have previously missed. IBC is using I2E in other areas including analyzing transcribed call center notes to look for conditions such as colon and breast cancer, and in population health, assessing social determinants of health such as loneliness and lack of mobility. IBC sees NLP becoming a core capability with the payer community.