Improve value-based care with performance monitoring

Accurately measure the impact of your value-based care strategy

The healthcare industry has been in a constant state of transformation since the 1970s. In 2001, the Institute of Medicine released “Crossing the Quality Chasm” and the Triple Aim, which sought to address the improvement of population health, patient experience, and quality outcomes, as well as reduce the per capita cost of healthcare. Since then, there has been a seismic shift in the way healthcare is delivered. Rather than focusing on volume-driven activities that reward more visits, more procedures, and more admissions, the healthcare industry has moved toward a value-based system of integrated care, which recognizes patient-centered activities, optimizes resources, and improves outcomes for both the patient’s health and the organization’s financial position.

To promote a value-based model, healthcare organizations can’t simply rely on clinical systems to identify and mitigate cost inefficiencies. They need visibility across the entire enterprise to perform the kind of balanced analysis that will help them identify opportunities for improvement by weighing and adjusting for factors such as reimbursement models, quality, outcomes, resource utilization, and cost. However, many healthcare organizations find it challenging to achieve this level of visibility, and the inability to integrate clinical data from electronic medical and health records with nonclinical and unstructured data is one of the key obstacles preventing them from fully embracing value-based care.

Overcoming this inability must be a priority for healthcare organizations, and fortunately technology can help. A modern data platform allows healthcare providers to collect the necessary data, evaluate and report on that data using a combination of high-end analytics and artificial intelligence, and use that data to identify potential problems—either within a specific episode of care or in a broader aspect of the business—as well as opportunities.

Simplify the development of KPIs

As healthcare organizations deploy initiatives to support patient-centered care, it’s vital for them to build lower-cost delivery models and identify ways to reduce fixed costs, improve the quality of care, and address social determinants of health. Once these initiatives have been implemented, healthcare organizations must evaluate their effectiveness based on several key performance indicators (KPIs), such as patient-reported outcomes and readmission rates. At the same time, those working within the organization not only need access to all the relevant data, but they also need to be able to understand that data, interpret it, and act accordingly.

Oracle Data Platform delivers all the capabilities healthcare organizations need to successfully capture and act on all the available data while providing automated features to simplify the process.

This image shows how Oracle Data Platform for healthcare can be used to support value-based care with performance monitoring. The platform includes the following five pillars:

1. 1.Data Sources, Discovery
2. 2.Ingest, Transform
3. 3. Persist, Curate, Create
4. 4. Analyze, Learn, Predict
5. 5. Measure, Act

The Data Sources, Discovery pillar includes four categories of data.

1. 1. Applications is comprised of patient administrative records.
2. 2. Health records include generic and condition-specific questionnaires and clinical data, such as data from EHRs, EMRs, and healthcare pathways.
3. 3. Third-party data comprises patient-reported outcomes.
4. 4.Technical input includes data from EMR and ePrescribing systems.

The Ingest, Transform pillar comprises four capabilities.

1. 1. Bulk transfer uses OCI FastConnect, OCI Data Transfer, MFT, and OCI CLI.
2. 2. Batch ingestion uses OCI Data Integration, Oracle Data Integrator, and Data Studio.
3. 3. Change data capture uses OCI GoldenGate and Oracle Data Integrator.
4. 4. Streaming ingest uses Kafka Connect.

All four capabilities connect unidirectionally into the serving data store, cloud storage, and transactional data store within the Persist, Curate, Create pillar.

The Persist, Curate, Create pillar comprises five capabilities.

1. 1. The serving data store uses Autonomous Data Warehouse, Exadata Cloud Service, and Exadata Cloud@Customer.
2. 2. Managed Hadoop uses Oracle Big Data Service.
3. 3.Cloud storage uses OCI Object Storage.
4. 4. Batch processing uses OCI Data Flow.
5. 5. Governance uses OCI Data Catalog.

These capabilities are connected within the pillar. Cloud storage is unidirectionally connected to the serving data store and managed Hadoop; it is also bidirectionally connected to batch processing.

Managed Hadoop is unidirectionally connected to the serving data store.

Two capabilities connect into the Analyze, Learn, Predict pillar: The serving data store connects to both the analytics and visualization capability and the data products, APIs capability. Cloud storage connects to the machine learning capability.

The Analyze, Learn, Predict pillar comprises three capabilities.

1. 1. Analytics and visualization uses Oracle Analytics Cloud, GraphStudio, and ISVs.
2. 2. Data products, APIs uses OCI API Gateway and OCI Functions.
3. 3. Machine learning uses OCI Data Science, Oracle Machine Learning, and ML Notebooks.
4. 4. The data products, APIs capability is unidirectionally connected to the machine learning capability.
5. 5. The serving data store and object storage supply metadata to the OCI Data Catalog.

The Measure, Act pillar captures how the data analysis may be applied to support a value-based care delivery model and monitor performance.

1. The first group includes monitoring the allocation and use of resources and evaluating outcomes and cohorts based on patient risk and treatment protocol, peer comparisons and international benchmarking, and cost reporting.
2. The second group includes patient outcome predictions.

The three central pillars—Ingest, Transform; Persist, Curate, Create; and Analyze, Learn, Predict—are supported by infrastructure, network, security, and IAM.

The architecture for Oracle Data Platform for healthcare gives organizations the ability to capture, store, manage, and gain insights from data collected from patient-reported outcomes, patient administrative records, and many other data sources to help them achieve their goal of moving to a value-based healthcare system.

• To start our process, we need to understand everything we can about the patient. To do so, we use OCI GoldenGate to enable change data capture ingestion of near real-time operational data, such as patient administrative records and healthcare pathways, from different health management systems.
• We can now add datasets that enrich what we already know about the patient and help us understand why they are being evaluated and what has been prescribed. These datasets often comprise large volumes of data, and in most cases, batch ingestion is typically the most efficient ingestion method. This is also the most efficient way to consume data from different electronic health record providers, such as Epic and Oracle
• We can also use streaming ingestion to ingest streaming data, such as ePrescriptions and, depending on the provider, even electronic health records. Additionally, in this use case, we intend to analyze and rapidly respond to patient sentiment by analyzing social media messages, responses to first-party posts, and trending messages. Social media (application) messages/events will be ingested and stored in cloud storage to be used later to help us fully understand the patient’s experience.
• Optionally, if there is a high volume of on-premises historical data, it may be wise to use a bulk transfer process to upload historical patient-reported outcomes, patient-reported experience measures, and outcome-based contract terms with insurers.

Data persistence and processing is built on four components.

• Ingested raw data is stored in cloud storage. For the batch processing of this now persisted data, such as ePrescriptions, electronic health record data, completed questionnaires, patient-reported outcomes, and social media data, we will use OCI Data Flow. These processed datasets are returned to cloud storage for onward persistence, curation, and analysis and ultimately for loading in optimized form to the serving data store. Alternatively, depending on architectural preference and the desire to use open source options, this can be accomplished with Oracle Big Data Service as a managed Hadoop cluster.
• We have now created processed datasets ready to be persisted in optimized relational form for curation and query performance in the serving data store. This will enable us to identify and return key performance indicators, such as the readmission rate, patient outcomes, the claims processing rate, and the claim denial rate.

The ability to analyze, learn, and predict relies on two technologies.

• Analytics and visualization services deliver several categories of analytics. Descriptive analytics describes current trends with histograms and charts and, as an example, can provide information on outcomes, such as five-year survival rates, repeat operations, unplanned admissions, and deviations from treatment plans. Diagnostic analytics aims to explain why certain events occurred and what the factors were that triggered them. For example, you can use diagnostic analytics to understand the possible reasons behind a deviation from the standard amount of time it takes for a patient to go from referral to their first clinic visit for a specific area of the country or why there has been an increase in nursing days per patient for a specific condition. Prescriptive analytics proposes suitable actions to support optimal decision-making. For instance, you can use prescriptive analytics to suggest procedural and clinical adjustments that could lead to improvements in quality-of-life reported outcomes (such as improved functioning or decreased pain levels).
• Alongside advanced analytics, machine learning models are developed, trained, and deployed. These models can be accessed via APIs or deployed within the serving data store.
• Our curated, tested, and high-quality data and models can have governance rules and policies applied and can be exposed as a data product (API) within a data mesh architecture for distribution across the healthcare organization.

The benefits of value-based care

Understanding how well their value-based care initiatives are performing is the key to a healthcare organization’s ability to evolve and adapt their strategies to achieve continued success. A successfully deployed and evaluated value-based care strategy will provide healthcare organizations with many benefits and enhanced capabilities that will ultimately advantage their patients, staff, and clinicians, as well as their bottom line. Examples include

• Efficiently collecting and applying information from patients themselves to learn how well the health service is treating them
• Adopting an equitable, sustainable, and transparent approach to resource utilization to achieve better patient outcomes and experiences
• More effectively combating overdiagnosis, over-prescription, poor allocation of resources, and the introduction of inadequately evidenced treatments
• Identifying unwarranted variations associated with the overuse or underuse of health technologies and care
• Limiting antimicrobial resistance
• Combating the opioid addiction crisis