How Data Digitization helps Value-based Care Adoption
As the healthcare industry continues its evolution to value-based care, it becomes increasingly essential that payers and providers have comprehensive, accurate patient data to support these new models of care.
Data digitization – and integration of that data with structured and external data sets – can deliver a 360-degree view of the patient to provide actionable insights that enable payers and providers to reduce costs and improve care quality under value-based program contracts.
Top AI Interviews: AiThority Interview with James Rubin, Product Manager at Google
Adoption of value-based care has accelerated in recent years, and the trend is likely to continue as payers, employers, and government officials become more comfortable with these types of alternative payment models, according to a recent report from McKinsey. For example, the number of patients treated by physicians within the value-based care landscape could roughly double in the next five years, growing approximately 15% per year, according to the report.
Although the shift to value-based models is a positive step for the healthcare sector, these models alone will not transform the industry. Achieving that level of change will require numerous data digitization and infrastructure capabilities.
Realizing the full impact of value-based care through lower costs and higher quality largely depends on healthcare organizations’ ability to:
- Derive insights from patient data and external data sets to drive clinical decision-making
- Realize data interoperability to enable permissioned data-sharing
- Build longitudinal healthcare records that patients can supplement using their personal data to enhance clinical insights
- Create user-friendly, data-driven workflows for various entities in the healthcare ecosystem
- Adhere to interoperability standards for data-sharing
- Create a digital infrastructure that supports multi-stakeholder “network of networks” with different payment modalities
The many downsides of healthcare data
However, for many healthcare organizations, building the capabilities to take full advantage of the data needed to drive value-based arrangements remains a challenge. Much of this difficulty stems from the unique and messy nature of healthcare data, frequently affected by the following issues:
Unstructured data: A significant percentage – some industry estimates are as high as 80% – of healthcare data is unstructured, meaning that it is not in a form suitable for easy digital analysis. Unstructured health data may include images, audio, video, notes, charts, faxes, and freeform text. Because unstructured data is so rarely digitized and combined with other forms of data sets, it often offers minimal value to healthcare organizations, despite its wealth of useful and relevant information.
Lack of adherence to data standards: Healthcare-industry data standards (HL7, x12 EDI, FHIR, NCPDP, CCLF, CCDA) do exist for various patient data processing but they are not consistently adhered to in different organizations. Adding to the challenges, data standards are frequently nonexistent for many patient data sets, such as data from devices, wearables, and social determinants of health.
Insufficient use of external data: External data sets – such as those maintained by community-based organizations and government entities – can provide actionable insights for healthcare organizations to proactively address social determinants of health issues and other factors that affect access to care, particularly when combined with transactional and clinical data sets.
Lack of real-time data: In general, healthcare organizations are unable to access patients’ longitudinal health records across systems or payment information in real time. The result can be suboptimal point-of-care decision-making and delays in the revenue cycle.
Recommended: AiThority Interview with Ramsey Masri, Chief Executive Officer at Ceres Imaging
Inadequate infrastructure: Most healthcare organizations lack an information technology infrastructure that can support a network of networks model.
Data redundancy: Even within the same data set, data duplication errors are common.
Data digitization with AI and ML
Because patient data sets are so often fragmented across different systems, some need to be digitized and combined with structured and external data sets to deliver the 360-degree picture of patient health needed to guide decision-making in value-based arrangements.
In this regard, artificial intelligence (AI) and machine learning (ML) are essential to data digitization and reducing errors. AI and ML facilitate better automation of tasks and decision-making processes, and support bidirectional integration between information systems.
AI-based technologies such as natural language processing and computer vision are integral in driving the data digitization process, enabling the conversion of unstructured information from notes and images into structured data that can be used to inform care delivery and coordination. Similarly, ML algorithms can improve error-detection in billing and coding, leading to fewer claim denials.
Overall, these AI- and ML-based tools accelerate the processing of large data sets, helping to inform precise and comprehensive value-based risk forecasting and providing recommended actions to improve patient outcomes.
Health cloud data infrastructure: The final piece
A detailed longitudinal health record requires a robust data infrastructure. It is critical that a data engineering framework can deliver the following capabilities:
- Process standard (HL7, FHIR, etc.) and non-standard data sets
- Process external data sets
- Support unstructured data
- Implement a data digitization process that tags and merges this data with the rest of the data while using proper categorization
- Deploy an EMPI algorithm to tie disparate patient data records into a unified patient record
- Utilize APIs both to expose this data using DaaS (Data as a Service) and in the platform infrastructure through a Platform as a Service (PaaS)/Software as a Service (SaaS) model, running on a modern application stack that offers microservices
A data infrastructure that fulfills these requirements enables healthcare organizations to digitize data, synthesize different kinds of data sources, identify errors, and seamlessly integrate new data sources.
Successful data digitization is critical for the healthcare industry as it scales up value-based care capabilities. With accurate, holistic, up-to-date patient information at their fingertips, healthcare organizations are far better-equipped to fulfill the mission of these new care models – delivering better patient outcomes at lower costs.
Comments are closed.