Enterprise Insight in Today’s Consolidated Enterprise

As health systems acquire or partner with previously independent facilities to form Consolidated Enterprises, and implement a Shared Electronic Medical Record (EMR) system, they often consolidate legacy diagnostic imaging IT systems to a shared solution. Facilities, data centers, identity management, networking equipment, interface engines, and other IT infrastructure and communications components are also often consolidated and managed centrally. Often, a program to capture and manage clinical imaging records follows.

Whether the health system deploys a Vendor Neutral Archive (VNA), an Enterprise PACS, or a combination of both, some investment is made to reduce the overall number of imaging IT systems installed and the number of interfaces to maintain. An enterprise-wide radiation dose monitoring solution may also be implemented.

While much has been written on strategies to achieve this type of shared, integrated, enterprise-wide imaging IT solution, there are several other opportunities for improvement beyond this vision.

In addition to imaging and information record management systems, enterprise-wide solutions for system monitoring, audit record management, and data analytics can also provide significant value.

Systems Monitoring

Organizations often have some form of enterprise-level host monitoring solution, which provides basic information on the operational status of the computers, operating systems and (sometimes) databases. However, even when the hosts are operating normally, there are many conditions that can cause a solution or workflow to be impeded.

In imaging, there are many transaction dependencies that, if they are not all working as expected, can cause workflow to be delayed or disabled. Often, troubleshooting these workflow issues can be a challenge, especially in a high-transaction enterprise.

Having a solution that monitors all the involved systems and the transactions between them can help detect, prevent, and correct workflow issues.

Audit Record Management

Many jurisdictions have laws and regulations that require a comprehensive audit trail to be made available on demand. Typically, this audit trail provides a time-stamped record of all accesses and changes to a patient’s record, including their medical images, indexed by the users and systems involved.

Generating this audit trail from the myriad of logs in each involved system, each with its own record format and schema, can be a costly manual effort.

The Audit Trail and Node Authentication integration profile (ATNA), part of Integrating the Healthcare Enterprise (IHE), provides a framework for publishing, storing, and indexing audit records from different systems. It defines triggering events, along with a record format, and communication protocol.

Enterprises are encouraged to look for systems that support the appropriate actors in the ATNA integration profiles during procurement of new IT systems and equipment. Implementing an Audit Record Repository with tools that make audit trail generation easy is also important.

Data Analytics

Capturing and analyzing operational data is key to identifying issues and trends. As each system generates logs in different formats and using different methods, it often takes significant effort to normalize data records to get reliable analytics reports.

Periodic (for example, daily, weekly, or monthly) reports, common in imaging departments for decades, are often not considered enough in today’s on-demand, real-time world. Interactive dashboards that allow stakeholders to examine the data through different “lenses”, by changing the query parameters, are increasingly being implemented.

Getting reliable analytics results using data from both information (for example, the EMR and RIS) and imaging (for example, modalities, PACS, VNA, and Viewers) systems often requires significant effort, tools to extract/transform/load (ETL) the data, and a deep understanding of the “meaning” of the data.

Enterprise Insight

Implementing solutions that continuously and efficiently manage the health of your systems, the records accessed, and operational metrics are important aspects in today’s Consolidated Enterprise. Evaluating any new system as to their ability to integrate with, and provide information to, these systems is recommended.

The Case for Vendor Neutral Artificial Intelligence (VNAi) Solutions in Imaging

Defining VNAi

Lessons Learned from Vendor Neutral Archive (VNA) Solutions

For well over a decade, VNA solutions have been available to provide a shared multi-department, multi-facility repository and integration point for healthcare enterprises. Organizations employing these systems, often in conjunction with an enterprise-wide Electronic Medical Record (EMR) system, typically benefit from a reduction in complexity, compared to managing disparate archives for each site and department. These organizations can invest their IT dollars in ensuring that the system is fast and provides maximum uptime, using on-premises or cloud deployments. And it can act as a central, managed broker for interoperability with other enterprises.

The ability to standardize on the format, metadata structure, quality of data (completeness and consistency of data across records, driven by organizational policy), and interfaces for storage, discovery, and access of records is much more feasible with a single, centrally-managed system. Ensuring adherence to healthcare IT standards, such as HL7 and DICOM, for all imaging records across the enterprise is possible with a shared repository that has mature data analytics capabilities and Quality Control (QC) tools.

What is a Vendor Neutral Artificial Intelligence (VNAi) Solution?

The same benefits of centralization and standardization of interfaces and data structures that VNA solutions provide are applicable to Artificial Intelligence (AI) solutions. This is not to say that a VNAi solution must also be a VNA (though it could be), just that they are both intended to be open and shared resources that provide services to several connected systems.

Without a shared, centrally managed solution, healthcare enterprises run the risk of deploying a multitude of vendor-proprietary systems, each with a narrow set of functions. Each of these systems would require integration with data sources and consumer systems, user interfaces to configure and support it, and potentially varying platforms to operate on.

Do we want to repeat the historic challenges and costs associated with managing disparate image archives when implementing AI capabilities in an enterprise?

Characteristics of a Good VNAi Solution

The following capabilities are important for a VNAi solution.

Interfaces

Flexible, well-documented, and supported interfaces for both imaging and clinical data are required. Standards should be supported, where they exist. Where standards do not exist, good design principles, such as the use of REST APIs and support for IT security best practices, should be adhered to.

Note: Connections to, or inclusion of, other sub-processes—such as Optical Character Recognition (OCR) and Natural Language Processing (NLP)—may be necessary to extract and preprocess unstructured data before use by AI algorithms.

Data Format Support

The data both coming in and going out will vary and a VNAi will need to support all kinds of data formats (including multimedia ones) with the ability to process this data for use in its algorithms. The more the VNAi can perform data parsing and preprocessing, the less each algorithm will need to deal with this.

Note: It may be required to have a method to anonymize some inbound and/or outbound data, based on configurable rules.

Processor Plug-in Framework

To provide consistent and reliable services to algorithms, which could be written in different programming languages or run on different hosts, the VNAi needs a well-documented, tested, and supported framework for plugging in algorithms for use by connected systems. Methods to manage the state of a plug-in—from test, production, and disabled, as well as revision controls—will be valuable.

Quality Control (QC) Tools

Automated and manual correction of data inputs and outputs will be required to address inaccurate or incomplete data sets.

Logging

Capturing the logic and variables used in AI processes will be important to retrospectively assess their success and to identify data generated by processes that prove over time to be flawed.

Data Analytics

For both business stakeholders (people) and connected applications (software), the ability to use data to measure success and predict outcomes will be essential.

Data Persistence Rules

Much like other data processing applications that rely on data as input, the VNAi will need to have configurable rules that determine how long defined sets of data are persisted, and when they are purged.

Performance

The VNAi will need to be able to quickly process large data sets at peak loads, even with highly complex algorithms. Dynamically assigning IT resources (compute, network, storage, etc.) within minutes, not hours or days, may be necessary.

Deployment Flexibility

Some organizations will want their VNAi in the cloud, others will want it on-premises. Perhaps some organizations want a hybrid approach, where learning and testing is on-premises, but production processing is done in the cloud.

High Availability (HA) and Business Continuity (BC) and System Monitoring

Like any critical system, uptime is important. The ability for the VNAi to be deployed in an HA/BC configuration will be essential.

Multi-tenant Data Segmentation and Access Controls

A shared VNAi reduces the effort to build and maintain the system, but its use and access to the data it provides will require data access controls to ensure that data is accessed only by authorized parties and systems.

Cost Sharing

Though this is not a technical characteristic, the VNAi solution likely requires the ability to share the system build and operating costs among participating organizations. Methods to identify usage of specific functions and algorithms to allocate licensing revenues would be very helpful.

Effective Technical Support

A VNAi can be a complex ecosystem with variable uses and data inputs and outputs. If the system is actively learning, how it behaves on one day may be different than on another. Supporting such a system will require developer-level profile support staff in many cases.

Conclusion

Without some form of VNAi (such the one described here), we risk choosing between monolithic, single-vendor platforms, or a myriad of different applications, each with their own vendor agreements, hosting and interface requirements, and management tools.

Special thanks to @kinsonho for his wisdom in reviewing this post prior to publication.

SIIM 2018 Annual Meeting: A Preview

SIIM18 graphic
Gaylord National Resort, National Harbor, MD

The SIIM 2018 Annual Meeting in Washington D.C. is just around the corner (May 31 to June 2). I look forward to seeing many friends, sharing ideas, and learning. I will be involved in number of sessions this year. Here is a preview.

Preparing for a Successful RFP and Contract with Vendors

Thursday, May 31 | 9:45 am – 10:45 am | Annapolis 1

In this roundtable session, participants will discuss how to best prepare for, develop, and issue an RFP, as well as how to analyze and grade the responses. We will also discuss how to best prepare for, and support, contract negotiations with a vendor.

Debate: Enterprise PACS vs. Vendor Neutral Archive (VNA): Choose Wisely

Friday, June 1 | 9:45 am – 10:45 am | Cherry Blossom Ballroom

Depending on your organization’s goals and scale of enterprise, the options available to you for an image archive can vary. In this debate-style session, we will explore the merits of using a Vendor Neutral Archive (VNA) vs. an archive provided as part of an Enterprise PACS. I am moderating the session.

Imaging IT Financials – Learn from the Masters

Saturday, June 2 | 12:45 pm – 2:45 pm | Baltimore 3/4/5

Participants that sign up for this learning lab (limited seats available) will work hands-on with experts to learn how to perform clear and compelling financial analysis. Two lab exercises—one focused on assessing cloud-based vs. on-premises image archive storage, and another on the IT investment required for rolling out the enterprise imaging solution to a newly acquired facility—will be worked on in teams. Each team will share their work with the other near the end of the session. Lab assistants will be on-hand to assist. Participants must bring a laptop or tablet with Microsoft Excel installed.

 

MIIT 2018 – May 4, 2018

In just less than a month from today on Friday May 4, 2018 (Star Wars day!), the annual MIIT (Medical Imaging Informatics and Teleradiology) conference will once again be held at the beautiful Liuna Station in Hamilton, Ontario, Canada.

This year’s theme is Connecting Imaging and Information in the Era of AI and the program features several distinguished speakers from Canada and the U.S.

Talks will cover EMR implementation, Radiology Outreach, the link between Quality and Informatics, Highly Automated Radiology (using AI), an update on IHE, and a comparison of PACS+VNA vs. Regional PACS. It will also have a panel on the impact of EMRs and AI on Radiology and a talk on AI by a speaker from IBM Watson Health.

Register Today!

MIIT Badge

Revenue Revolution in Radiology

I have been reading a lot recently about trends in healthcare and imaging around costs and revenues. There seems to be a perfect storm of changes in the market that will have a fundamental impact on diagnostic imaging service providers. I find this topic interesting because, unless you understand how the money is moving, you won’t understand why things are happening. Here is a summary of what I have discovered.

Medicare Reimbursement Cuts

This one is obvious. If you lower the amount of money paid for something, your revenues will go down (unless volume goes up proportionally). Here is an infographic from MITA on the cuts made since 2006.

Fewer Medical Imaging Exams being Ordered

Here is an article from MITA on the decline of the total number of CT exams being done in the U.S. Here is another one citing data published by the American College of Radiology (ACR). It states: “…physicians are calling for less, not more, imaging tests.” This shows a measurable reduction in the volume of exams performed in the U.S. And here is an article indicating a steady decrease in imaging studies being ordered for patients in the ED, following a steady increase up to 2007.

Image Sharing

The sharing of patients’ clinical records across facilities is a key part of Accountable Care, and is generally a good thing for patient care. So is sharing imaging records. With reliable options now available on the market, sites within a local referral area are rapidly launching or signing up to services to share images. The clinical benefits of comparing new imaging exams with priors are well understood, but this practice will often result in avoiding the need to perform a repeat exam. This benefits the patient (less radiation and anxiety and delay), and the operations of the receiving organization (less schedule disruption, less costs due to CD importation). The other impact, of course, is that the receiving organization loses some revenue from that avoided repeat exam. This will result in a reduction in volume of exams performed.

Adoption of Clinical Decision Support

Starting on January 1, 2017, imaging exams will require the use of Clinical Decision Support (CDS) to ensure that physicians are following Appropriate Use Criteria (AUC). In addition to clinical evidence, factors such as relative radiation level and cost of the exam are used to determine what is appropriate. All things being equal, the lower cost exam is likely to be recommended. The adoption of CDS may result in a reduction in volume of exams performed, or a recommendation to a lower cost (profit) exam.

Preauthorization Requirements

In some insurance plans, preauthorization is required before certain exam types can be ordered (even when CDS is used, in some cases). This may require a consultation with a radiologist or Radiology Benefits Management (RBM) company. Here is an article from 2011 on the use of preauthorization and CDS. The larger the burden on the ordering physician, the less likely they are to order the exam, which may result in a reduction in volume of exams performed, or a recommendation to a lower cost (profit) exam.

Patient Steerage

Last year, I did a blog post on an article on the trend of “patient steerage”. The original article is here. Essentially, patient steerage is when a payer incents a patient to use a provider that offers the imaging service at a lower cost. If a service provider is not price competitive, this will result in a reduction in volume of exams performed.

The Castlight Effect

This company received a lot of attention because of the size of its IPO, but it is also notable for what they actually do. As this article explains, they provide healthcare provider cost information for a range of healthcare services to employee health plans. The intent being that, given the choice, consumers will choose lower cost options. This is very likely to happen when the patient has a significant co-pay (e.g. 20%) and they will personally benefit from lower cost options. If a service provider is not price competitive, this will result in a reduction in volume of exams performed.

Wait, but what about Quality?

With all the talk about the shift of reimbursement from volume of procedures to quality or outcomes, I found this tweet on Castlight interesting… Castlight Tweet If we shift away from volume incentives/payment, reduce the prices paid (through policy or competition), but don’t recognize quality, the service of diagnostic imaging has been commoditized, and I don’t think that this will benefit patients, in the end.

Consolidation

I have heard a couple of opinions that believe that the strong trend of consolidation among healthcare providers will allow the largest of providers to dictate terms and pricing to payers. As it was explained to me, it works like this: The big, well-known healthcare provider, which has bought up many of the facilities in the area, tells the insurance payers, ‘If you don’t give me preferential pricing for my services, I won’t accept your insurance plan at my facilities’. If the healthcare provider is big enough and well respected, the insurance provider will have a tough time selling insurance plans to companies and individuals when the buyer learns that they can’t go to the big provider. This is called leverage. If this is true (and I think that it is), this will result in isolated areas of reimbursement stabilization or even increases. Here is an article talking about what the impact of provider consolidation means to private payers. It cites a steady increase in the number of physicians becoming employees of hospitals (vs. independent private practices)…

“…the number of doctors employed by hospitals increased to over 120,000 from 80,000 between 2003 and 2011. About 13 percent of all doctors are now employed directly by hospitals.”

A Necessary Change in Revenue Cycle Management Systems

Here is an article on the need for an overhaul of Revenue Cycle Management (RCM) systems in the U.S. It includes some stats on administration costs per transaction (compared to financial services transactions) and consolidation trends, as well as the value of analytics. Some excerpts…

“…the number of hospitals per integrated delivery system took a big jump last year from 6.4 to 7.1…”

“…the physicians who go into practice do not want to be entrepreneurs as much as they used to. When 52 or 53 percent of residents today become employees of integrated delivery systems, it tells you that the whole market has changed.”

Using Analytics to Maximize Revenues

Here is an article on using analytics and their reports to optimize financial operations.

So, what do you think?

P.S. Here is an interview that goes into the details of payer vs. provider, along with a case for more bundled payments. And here is a blog post that goes into more detail on bundled payments, including the shift from retrospective to prospective bundles.

P.P.S. Here is an article explaining the difference between charges and costs.

P.P.P.S. Here is a notice of rule changes proposed by CMS on the method by how physicians fees will be determined. “…we are updating our practice expense inputs for x-ray services to reflect that x-rays are currently done digitally rather than with analog film.”

P.P.P.P.S. Here is an article on a study on the disparity of costs for a Mammogram in the L.A. area. $60 to $254 for self-pay, with a bill of $694 to the insurance company for the same procedure elsewhere. 30% of Mammograms in the study were self-pay.

P.P.P.P.P.S Here is an article, with a nice infographic, on 5 common medical practice denials and remedies. Spoiler alert: Radiology made the Top 5 list of unexpected denials.

P.P.P.P.P.P.S Here is an infographic on the declining employment demand and income of Radiologists by a medical recruitment firm.

More Post-SIIM 2013 Annual Meeting Reflections

For years, I have heard providers lament at the slowing (dormant?) pace of innovation in PACS and RIS from established vendors.

Why might this be happening?

It could be that the current architectures have reached their limits. It could be that, with the saturation of PACS in mature markets, vendors are reducing R&D investment in this area. It could be that they can’t sustain the talent needed to innovate, losing creative and skilled people to more interesting/promising areas of IT. It could be innovation-suppressing regulatory burdens. Or the shift of spending to support staff in order to sustain the now sprawling installed base.

Regardless of the root cause(s), I see the emergence of interest in start-ups (such as those in the SIIM Innovator Alley) and open source projects (as seen by the steady traffic at the SIIM Open Source Plug Fest) that attempt to solve problems that the larger vendors appear not to be interested in solving. It seems providers are starting to accept that they are not going to get everything they need from their incumbent PACS vendor in today’s EMR-enabled, Cloud-hosted, analytics-driven, enterprise-accessible market.

Of course, the challenge of the start-up is breaking into the provider’s enterprise where the incumbent vendor may put up some resistance (overtly or passively). And open source is only as good as the staff (or paid service provider) you have installing, integrating and supporting it.

The informatics skills and knowledge provided by SIIM are more important than ever. If SIIM is to continue to lead in providing its members the knowledge and skills they need to survive and succeed, it will likely have to adapt how it organizes the materials to align with new and evolving learning goals. It also needs to adapt the medium by which its members learn, providing focused, on-line options where travel policies and budgets mean attending the annual meeting is not feasible.

I believe in the SIIM strategic plan and am wholly committed to helping the society that has helped me so much over the years thrive.

Post-SIIM 2013 Annual Meeting Reflections

Another great SIIM annual meeting is behind us and it was great, as always. I am going to post some thoughts and reflections this week.

Today, I have been thinking about analytics and, in particular, the use of a workflow engine and a standardized set of terms and definitions (such as what is being defined in SWIM) to ensure analysis of workflow events (type, timing, relationships, patterns, etc.) consistently across systems.

There were several great talks by Dr. Brad Erickson and Chris Meenan and others on the topic and these were followed by a large turnout of engaged attendees for a SWIM demo (see pic below).

...SWIM lessons
…SWIM lessons

My thoughts…

  • The use of a mature, off-the-shelf (open source or commercial) workflow engine has been considered by PACS and RIS vendors, with some attempting to use them in their product. It has not been widely adopted for two main reasons (I believe)…
  1. Most PACS from large vendors were bought, not built by them—the risk of replacing the built in logic with an external engine without introducing functional regression is high (read as: it would be expensive);
  2. Unless the workflow engine spans several systems, it would not have the full benefit (see more on this below).
  • The workflow examples cited often started with the arrival of the image objects from the modality (initial event that starts the workflow channel). Ideally, the workflow engine extends to before the order is placed, managing the order placement, decision support to ensure the right procedure is ordered, scheduling, protocoloing, and acquisition, along with the reading and post-processing steps. It should also span to the results distribution and archiving, managing the timing and destinations of the report and the lifecycle of the historic imaging data.
  • One of the limitations of using a parallel image management pipeline (e.g. sending images through a system before arriving in PACS) in order to detect the event that triggers the workflow can introduce some points of failure. Consider if the system integrated with the workflow engine goes down and images don’t get to the PACS—this outage would limit the value of the integrated image management and workflow engine system. A possible solution is to extend PACS and other systems, such as the RIS, EMR, CDS, VNA, Enterprise Viewer, document management system, etc. to expose the event information. This would allow the workflow engine to apply the desired workflow rules and orchestrate the data flow and work steps without being a potential bottleneck.

More thoughts from SIIM later. Stay tuned.

Article – CHIME seeks Stage 2 delay, defends MU

So, the U.S. government—CMS/ONC and some Senators—and CHIME (College of Healthcare Information Management Executives) are “discussing” the merits and best timing of HITECH and Meaningful Use.

This article provides a good summary of the questions and recommendations posed.

Some key points from the article and my thoughts…

  • The Senators are fairly looking for evidence of results from the significant investment of taxpayer dollars. The reality is that this change is large and multifaceted. It will take time to reap the benefits once operations are normalized and productivity is enhanced.
  • CHIME believe that there are merits to the government’s programs, but wants to slow the pace of change. I know from personal conversations with smart, effective folks working for respected providers that they are reeling from the number of implementation projects driven by ACO, MU and other initiatives that they have going right now. The troops may indeed need a short break and to reflect on lessons learned from the initial change.
  • “CHIME also urged Congress to request an update from ONC regarding what technologies, architectures and strategies exist to mitigate patient matching errors” …it is interesting that CHIME is looking for this, as MPI (Master Patient Index)—also known as PIX (Patient Identifier Cross-Referencing) in the IHE Technical Framework—has been around for years and used in many projects to enable sharing of patient records across patient ID domains