Healthcare supply chain optimization

Increase visibility to improve supply chain resilience and flexibility

The COVID-19 pandemic put unprecedented pressure on supply chains and emphasized the importance of effective supply chain planning. Before COVID, just-in-time inventory was pushed as the best inventory management method because it allows organizations to reduce expenses by decreasing the inventory on hand. However, as the pandemic demonstrated, while this method may save you money, it leaves you extremely vulnerable when disruptions and emergencies occur. At the same time, you don’t want to have too much inventory on hand, not only because of the maintenance costs but also because it increases waste as many products with an expiration date are disposed of before they can be used. One recent research report found that, on average, 13% of inventory stock for an operating room expires on the shelf (PDF).

While effective supply chain planning and inventory management is critical in every industry, it’s particularly crucial in healthcare, where supply chain disruptions can impact patient care, safety, and outcomes. To find the optimal approach and avoid having too much or too little inventory, the manufacturer and healthcare organization need to have visibility both upstream and downstream through the supply chain. Visibility into the entire process gives all parties in the supply chain the agility to leverage different source providers when disruptions occur.

To attain full visibility, healthcare organizations need to blend data from many external and internal sources. Organizations that struggle with data access, transparency, and data accuracy need to solve these challenges to move toward continuous supply chain planning and help ensure continuous operations.

Optimize your supply chain using all the right data

A voluminous amount of supply chain data is available today, and the amount grows exponentially every year. The problem many healthcare organizations face isn’t a lack of data, it’s the inability to understand the data and access the necessary data to develop meaningful insights.

In this use case, we’ll show you how Oracle Data Platform for healthcare can simplify the process of using advanced analytics and machine learning to insulate your supply chain from disruptive events while lowering costs and increasing patient safety.

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 two categories of data.

1. 1. Business Records is comprised of ERP, warehouse management system, inventory, materials and planning and scheduling and EPM.
2. 2. Technical input includes data from transportation management, telemetry data, logs and event stream sources.

The Ingest, Transform pillar comprises three capabilities.

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

All three capabilities connect unidirectionally into the serving data store, and cloud storage 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 use GraphStudio, Oracle Analytics Cloud, 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.

AI Services includes Oracle Digital assistant, OCI Language, Speech and Vision.

The serving data store, managed Hadoop, and object storage supply metadata to the OCI Data Catalog.

The Measure, Act pillar captures how the data analysis may be applied to support supply chain optimization. These outcomes are divided into two groups.

1. 1. The first group “People and Partners” includes continuous improvement and performance measurement, demand forecasting and inventory planning along with supply chain design and network optimization.
2. 2. The second group “Applications” includes get recall notifications, improve space and inventory management and use AI/ML to enhance operational processes.

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

There are three main options for injecting data into an architecture to build a flexible, open, and performant data platform.

• To start, we need to understand our overall inventory position. To do so, we use Oracle Cloud Infrastructure (OCI) GoldenGate to enable change data capture ingestion of near real-time warehouse inventory data from operational databases for all items that are stocked and the business units they’re associated with.
• We can now add relevant datasets, such as data from ERP systems, warehouse management systems, human resources systems, health management information systems, and enterprise performance management systems, to fully understand the supply chain and gain insight into its health. These datasets often comprise large volumes of often on-premises data, and in most cases, batch ingestion is typically most efficient. For application-to-application integrations (or integrations with other OCI services), Oracle Integration Cloud is a proven, top-class method that makes the process easy and cost-efficient.
• Bulk transfer services are used in situations where large volumes of data need to be moved to Oracle Cloud Infrastructure for the first time—for example, data from existing on-premises analytic repositories or other cloud sources. The specific bulk transfer service we’ll use will depend on the location of the data and the transfer frequency. For example, we may use OCI Data Transfer Service or OCI Data Transfer Appliance to load large volumes of on-premises data from historical planning or data warehouse repositories. When large volumes of data must be moved on an ongoing basis, we recommend using OCI FastConnect, which provides a high-bandwidth, dedicated private network connection between a customer’s data center and OCI.

Data persistence and processing is built on three (optionally four) components.

• Ingested raw data is stored in cloud storage. We’ll use OCI Data Flow for the batch processing of this now persisted data, such as ERP data, inventory data, telemetry data from devices and applications, logs, and product reference data. 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, this can be accomplished with Oracle Big Data Service as a managed Hadoop cluster.
• We have now created processed datasets that are ready to be persisted in optimized relational form for curation and query performance in the serving data store. This will enable us to quickly evaluate several valuable key performance indicators, such as inventory turns, supply expense as a percentage of net patient revenue, the percentage of items with identified substitutes, supplier fill rates, and the number of expired/wasted products as a percentage of the total purchased, to list only a few examples.

The ability to analyze, learn, and predict is built on four technologies.

• Analytics and visualization services deliver descriptive analytics (describes current trends with histograms and charts), predictive analytics (predicts future events, identifies trends, and determines the probability of uncertain outcomes), and prescriptive analytics (proposes suitable actions to support optimal decision-making), which can help healthcare organizations
  
  
  • Calculate the number of expired products as a percentage of on-hand products in their inventory
  • Use digital twins on the supply chain to perform risk-free what-if analysis
  • Determine supply expense as a percentage of net patient revenue
  • Understand what percentage of items have identified substitutes
• Alongside advanced analytics, machine learning models are developed, trained, and deployed. These models can be accessed via APIs, deployed within the serving data store, or embedded as part of a streaming analytics pipeline.
• When creating machine learning models, you have the flexibility to use OCI Data Science, the available OCI AI Services, or a combination of the two. The following are a few examples of OCI AI Services and how they can be used as part of a supply chain AI/ML pipeline:
  
  
  • OCI Anomaly Detection can help monitor supply chain performance metrics (for example, raw material inventory, production throughput, work in progress, transit times, and inventory turnover) in real time to identify and address disruptions. In a complex supply chain, the severity score of identified anomalies can help prioritize observed business disruptions for action.
  • OCI Forecasting can help forecast supply chain metrics, such as demand, supply, and resource capacity, to predict future performance so appropriate actions can be taken.
  • OCI Vision and Language can help understand documents, such as outgoing product quality reports and defect reports, to enrich supply chain data for analysis.
• 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.

Use automated intelligence to increase profitability and patient safety

Having a full view of the entire supply chain will allow healthcare organizations to answer many questions they’re unable to answer today—but to do so, they must have the right data platform. The platform should be flexible and able to handle all the necessary data types; open and able to easily connect to other clouds, on-premises data centers, or third-party organizations; and secure. With access to all the data, healthcare organizations will be able to accomplish many objectives, which may include

• Managing supplier risk while understanding patient demand and potential disruptive events—in-depth knowledge of the relationship between supplier risk and patient demand lays the foundation for greater operational effectiveness across the entire business operating model, facilitated by a centralized list of qualified and reliable suppliers
• Fortifying the healthcare supply chain to help increase patient safety while improving quality control and decreasing costs
• Increasing supply chain resilience by developing a deeper understanding of suppliers through data sharing
• Improving agility and making faster planning decisions and trade-offs, adjusting and monitoring plans as changes occur