Healthcare business leader analyzing metrics on a tablet

5 Mistakes Imaging Centers Will Make Post-Pandemic

The COVID-19 pandemic has massively accelerated the adoption and normalization of new technology in healthcare. Here are five mistakes Imaging Centers should look out for -- and what to do now.

1. Messy data

Lacking standardization in your data will directly impact your ability to retrospectively look back on your data and extract insights as digital health solutions evolve.

Having standardized data means you’ll be able to pick an AI solution from the market and efficiently run it on your real-world data and assess results without a long implementation burdon.

The principle of using standard systems and processes exists to help ensure organizations can scale efficiently (with more people). It’s important to now also think about how your data will scale with your organization.

In order to take advantage of new and innovative AI algorithms with short integrations and onboarding, organizations should strategically prioritize standardizing their data. One example is the RadLex radiology lexicon by RSNA. RadLex is a comprehensive set of radiology terms for use in radiology reporting, decision support, data mining, data registries, education, and research – and is licensed freely for commercial and non-commercial users.

Search beyond the trends, too. While a large part of the commercial market is focused on image processing and image interpretation, there is significant untapped potential in other areas such as:

  • Worklist management
  • Automated measurements
  • Operational efficiencies
  • Reporting
  • Standardization

2. Siloed teams and ideas

When teams are disjointed, ideas are formed compartmentally and don’t take into account the wider picture of stakeholders and end-to-end workflows.

Multi-disciplinary teams working together fosters a deep and shared understanding of pain points in existing workflows and underlines the gaps that exist which should be tackled first. 

With the rise of remote work, teams should adopt and operate with a remote-first culture. At the heart of this lies clear and transparent communication – documenting company conversations, research, and decisions, in easy-to-search places. Organizations should spin up multidisciplinary teams consisting of Radiologists, Rad Techs, Clinicians, IT, and more, to identify opportunities for improvement in existing workflows. 

The Data Science Institute by ACR has published DSI USE CASES, which gives guidance on scenarios where AI might improve medical imaging care for both interpretative and non-interpretative use cases. This is a great place for your multi-disciplinary team to start, to help evaluate AI tools and ensure they provide needed information, can be implemented into workflows, and have the potential to improve patient care.

The Data Science Institute has also launched AI-LAB, a data science toolkit designed to help radiologists learn the basics of AI and then use these skills in their practices, and a web-based catalog called AI Central which radiologists can use to learn more about AI algorithms that have clearance from the FDA.

These resources allow teams to first ‘dip their toes’ by exploring the use of basic AI tools applied to a variety of clinical settings. 

Revenue Recapture Calculator

Within our first 30-days of working together, we quantify the care gap at your organization against industry standards and put systems in place to close that gap - streamlining the process to care for more patients and recapture revenue.

3. Widening the Radiologist and Patient gap

With growing trends in teleradiology and distributed practices, there is a widening gap between the Radiologist and the individual patient, increasingly relying on the referring/ordering physician to bridge the communication of findings.

Patient-friendly Radiology reports are a step in the right direction, but it’s often overlooked that Radiologists are physicians that can best help make sense of exams and reports to the patient. 

Here’s a case study on how Radiologists in Colorado are adding their phone numbers to radiology reports, making it easier for referring physicians and patients to reach them for consultation.

Organizations that will take patient experience to the next level will have a program (and technology) to support this 1-1 interaction. Short 10-15min eConsults (electronic consultations) are efficient and can go a long way, and CMS has made eConsults reimbursable in some states, with stipulations.

4. Losing existing patients

Over 60 million imaging exams per year in the US have actionable findings, and of those, up to 70% are missed or not completed. This results in poor patient outcomes, lost revenue, and increased risk (litigation related to communication of findings).

ACR is developing the Closing the Recommendations Follow-Up Loop quality measure set to tackle this challenge. Success here means a greater volume of patients will benefit from the early detection of cancer or other treatable conditions. For organizations, this means increased imaging revenue and reduced medicolegal risk.

Organizations that take this to the next level will identify care gaps that exist in patient populations and proactively reach out to those who are due for screenings or other preventative care opportunities. This can be accomplished by utilizing flags in existing EMR/EHR/scheduling/chart software and conducting inbound and outbound campaigns to set appointments. Check out some of the work on health equity by Dr. Efrén J. Flores at Massachusetts General Hospital Dr. Lucy B. Spalluto at Vanderbilt University Medical Center.

Inflo Health has developed a platform to manage this at scale by using a deep learning NLP engine to identify patients that likely require follow-up care, then automating care navigation workflows including provider and/or patient outreach to ensure these follow-ups are completed. Reach out to us here (link) to learn more.

5. Stalled execution

After all of the work in evaluating and kicking off a new initiative, without a plan for organizing and sharing data with efficiency, projects get stalled in those initial weeks post-kick-off. 

By having systems and processes in place at the onset, projects can kick off with ease and follow a systematic process for executing necessary documents and opening up data sharing and transfer access.

To put into action large-scale ideas on leveraging the world of AI and data science at your organization, consider how you can reduce your time to plan and implement new technology with a big data strategic initiative to pre-plan your approach, while also strengthening cybersecurity and privacy. If you’ll be working in close partnership with another party, consider having a data use agreement (DUA) that you can readily execute. Sharing PHI data creates several challenges for health care providers to navigate:

  • Who will oversee data integrity and stewardship?
  • How will the scope of the project influence the most appropriate data subsets?
  • What kind of data will be shared and how accessible is it?
  • How is the data anonymized?
  • How will data sharing occur?
  • What are the downstream implications of your data's use?

Taking inspiration from API documentation is a great place to start. Here are some excellent examples from Rivet Health and Google Cloud Healthcare.

Having clear documentation or an initial SOP (standard operating procedure) will allow you to audit and refine the process as you go, and make incremental changes over time in a collaborative way with your teams and the vendors you work with.

Want to leverage what we've built?

Inflo Health has developed a platform to prevent revenue leakage and patient out-migration by using a deep learning NLP engine to identify patients that likely require follow-up care. We then automate care navigation workflows including provider and/or patient outreach to ensure these follow-ups are completed. Reach out to us below to learn how our partner sites have improved follow-up adherence at their organizations, resulting in better patient outcomes, new revenue, and reduced risk.

Download our whitepaper on using NLP for workflow automation

Get Free PDF

Enter your email for the full whitepaper titled "Which Study Should I Read Next?"