Why Artificial Intelligence is Critical to the Success of Value-Based Care

With all the recent buzz around generative artificial intelligence (AI) related to ChatGPT, it's reasonable to have mixed reactions to emerging technologies. However, many AI technologies — including optical character recognition, natural language processing and machine learning — are widely established and proven highly reliable in driving healthcare innovation for payers, providers and patients.

AI has enormous potential to accelerate value-based care models and is already critical for success in risk adjustment, quality improvement and member management programs. Employing AI-driven technology ensures accurate and timely compliance with industry regulations, mitigates audits and fines, and helps forecast accurate reimbursements.

The following are three key reasons AI is critical to the success of value-based care.

Reason 1: Managing the explosion of clinical data sets and ICD codes

There is enormous growth in clinical data driven by modern technologies, business processes, and research initiatives. And there are 73,000+ ICD codes with a daunting amount of information to understand.

With AI, we can solve this data dilemma in abstracting, processing, and coding for risk adjustment and quality improvement programs. AI technology is vital to processing, mining and analyzing massive data sets and reliably applying rules and logic to digest the data quickly and accurately.

These technologies also streamline workflows by prioritizing the next-most-valuable data per customizable rule sets. Automating, accelerating and improving clinical data coding and abstraction reduces errors, inefficiencies and program costs and ensures appropriate reimbursements while delivering improved outcomes.

Reason 2: Equipping providers with valuable information at the point of care

Data and process fragmentation contributes to administrative complexity and costs the U.S. healthcare system more than $265 billion annually in unnecessary spending.¹ Disjointed data across multiple records and a heavy reliance on retrospective claims data hinder population health management, care coordination and accurate value-based reimbursement. This means clinicians spend nearly twice as much time² doing manual, electronic health record (EHR)-related tasks as they spend with patients, leading to increased burnout. Clinician burnout already costs the U.S. healthcare system about $4.6 billion annually.³

Leveraging EHR-agnostic interoperability standards with AI can bring siloed data together in a longitudinal record, including structured and unstructured data from health information exchanges, all hospital and specialist EHRs, medications, and labs. Patient information can be packaged as a pre-encounter summary and shared directly with the provider before a patient visit to proactively close care gaps. Providers can add encounter data to the longitudinal record for concurrent and retrospective analysis. Making information available at the point of care is a game changer. It allows for prospective risk adjustment, eliminates reimbursement delays and increases the accuracy of risk adjustment factor scores. All of that improves revenue performance.

Reason 3: Navigating the 100,000+ nurse gap

Recent Department of Health and Human Services data projected the demand for registered nurses will hit more than 3.6 million by 2030. Given nurses' essential role in driving risk and quality programs, this workforce gap could have dire consequences for patient health.

The question is: "Would you rather have nurses providing direct patient care or reviewing medical records?" AI-enabled technology can serve as a virtual team member codifying documents, automating data abstraction and deriving meaning from medical records. Helping clinicians focus on higher-value work can improve productivity by 250% over manual processes, driving higher reimbursements and improved patient outcomes.

Investing in and adopting AI-driven technology is critical to realize the promise of value-based care and improving accuracy, efficiency, and outcomes for patients, payers, and providers.

This article originally appeared on Managed Healthcare Executive.

Reference

1. Shrank WH, Rogstad TL, Parekh N. Waste in the US Health Care System: Estimated Costs and Potential for Savings. JAMA. 2019;322(15):1501–1509. doi:10.1001/jama.2019.13978

2. J. Marc Overhage, David McCallie. Physician Time Spent Using the Electronic Health Record During Outpatient Encounters: A Descriptive Study. Ann Intern Med. 2020;172:169-174. doi:10.7326/M18-3684

3. Hartzband P, Groopman J. Physician burnout, interrupted. N Engl J Med. 2020;382(26):2485-2487. doi:10.1056/nejmp2003149