Patients now see their radiology results as soon as they’re finalized, often before their provider does. With 90% of portal users viewing test results online and nearly 60% reading them before hearing from a clinician, health systems face a new reality: patients are engaged, but the experience of receiving complex imaging findings through a portal was never designed for them. The result is confusion, anxiety, delayed follow-up, and a growing gap between information access and genuine understanding. Closing that gap requires rethinking how imaging results are communicated, how patients are guided to next steps, and how the system supports both sides of the care relationship.
The Problem: Access Without Context
The 21st Century Cures Act eliminated the information embargo. Since its implementation, health systems are required to release test results — including radiology reports — to patients immediately upon finalization, with limited exceptions (Office of the National Coordinator for Health Information Technology [ONC], 2020). The intent was patient empowerment. The unintended consequence has been a flood of clinical language landing in the hands of people who were never trained to read it.
The scale of the issue is hard to overstate. According to the National Cancer Institute’s Health Information National Trends Survey (HINTS), 90.1% of portal users now view test results online, and 78.8% view clinical notes (NCI, 2024). A 2026 JAMA Network Open study found that 27% of patients learned of a cancer diagnosis through their patient portal — not from a conversation with their care team (Katz et al., 2026). Meanwhile, patient-initiated messaging to providers has roughly doubled since the onset of COVID-19, from approximately 10 messages per week in early 2019 to over 20 per week, and has remained elevated (Holmgren et al., 2025). Providers already spend 11 times more time responding to patient messages than to system-generated alerts (Rotenstein et al., 2019; Akbar et al., 2021; Sinsky et al., 2022). The system is creating demand it cannot absorb.
And the clinical stakes are real. Incidental findings on cross-sectional imaging now appear in more than 31% of CT scans performed in the ER, a rate that continues to climb as detection technology improves and imaging volume grows (Evans et al. 2022). Yet adherence to radiologist follow-up recommendations sits at just 39.1% for incidental findings (Hansra et al., 2021). When a radiology recommendation uses hedging language, lacks specificity, or buries the action item in clinical jargon, the ordering provider is left guessing and the patient is left in the dark. The American Medical Group Association (AMGA) recently urged HHS to broaden the federal definition of patient harm to include the mental and emotional distress caused by receiving complex, decontextualized results without clinical support — citing member reports of patients learning of cancer diagnoses, miscarriages, and infectious diseases through automated portal notifications (AMGA, 2026).
The Solution: Intelligent Patient Engagement at the Point of Results
The answer isn’t to pull back on transparency. Patients want access — 96% prefer receiving immediately released results even before their provider has reviewed them (Steitz et al., 2023). The answer is to build an intelligent layer between the result and the patient that translates clinical language, triages urgency, and guides the next step.
What this looks like in practice:
Plain-language translation of imaging results. Patients will receive the raw radiology report — that stays, and it should. But alongside it, the system delivers a translation layer written at a 6th-grade reading level. A normal chest X-ray shouldn’t leave a patient staring at “No acute cardiopulmonary abnormality.” It should also tell them: “Your lungs are clear and fully expanded. Your heart and chest look normal. Nothing concerning was found.” For abnormal findings, the translation names the finding in plain language, provides reassurance where appropriate, and makes the next step explicit — not buried in a footnote. The report says what was seen. The translation says what it means and what happens now.
Triaged urgency and guided action. Not all results require the same response. A system that can differentiate between a normal result, an incidental finding requiring surveillance, and an urgent follow-up recommendation — and present each with appropriate framing and next steps — reduces confusion and prevents a scenario where a patient reads a vague recommendation and panics.
Proactive follow-up coordination. Identifying that a patient needs follow-up imaging is only half the problem. The other half is making sure the appointment actually gets scheduled. That means alerting the ordering provider, engaging the patient directly, and tracking whether the loop gets closed — not hoping it happens on its own.
How to Activate This in the Patient Journey
Deploying patient-facing intelligence around imaging results isn’t a standalone initiative — it sits at a specific point in the care pathway where multiple handoffs converge and often fail.
The activation sequence follows the natural flow of a diagnostic result: the radiology report is finalized, the AI/NLP layer classifies the finding and recommendation, the ordering provider is notified, and the patient receives a translated, contextualized version of their result. From there, the system should be doing the work that currently falls to overburdened clinical staff — sending reminders, scheduling nudges, and escalating unresolved cases before they become lost-to-follow-up statistics.
The key design principle is reducing the cognitive burden on both sides. Providers shouldn’t need to manually interpret and relay every imaging result. Patients shouldn’t need a medical degree to understand what happens next. And no one should be relying on a single fax or a single inbox message to close a loop that could affect whether a cancer gets caught at stage I or stage III.
The Impact: What Research Tells Us About Meeting Patients Where They Are
The evidence base for this approach is strong and growing. A recent systematic review in the Journal of Medical Internet Research found that visual, patient‑friendly laboratory result displays (for example, horizontal line bars with color blocks and interpretive labels) were associated with significantly higher patient satisfaction, perceived usability, and understanding than raw numerical formats, and reduced patients’ tendency to seek additional clarification from clinicians (van der Mee et al., 2024). In a Vanderbilt‑led quality‑improvement study covering more than 800,000 test results, introducing patient‑friendly educational formatting for lab results was associated with a reduction of approximately 15 patient‑initiated messages per week (Steitz et al., 2025). On the follow‑up side, the Radiology FIND Program demonstrated that implementing a structured incidental‑findings tracking system increased completion of recommended imaging from 30.8% to 50.7% overall, and among emergency department patients, adherence rose from 19.2% to 55.0% (Zaki‑Metias et al., 2023). Complementary work in the Journal of the American College of Radiology has shown that clearer, more explicit follow‑up recommendations and direct communication with ordering providers are associated with higher follow‑up completion rates and shorter time to follow‑up, underscoring the importance of both message design and communication pathways in closing the loop (Mattay et al., 2024; Makeeva, 2025).
The through-line across all of this research is the same: patients are engaged. They are reading their results. They want to understand. What they need is a layer of intelligence that meets them at the moment of highest anxiety and lowest comprehension, and turns raw clinical output into a clear path forward.
References
Akbar, S., et al. (2021). Physician inbox burden. Journal of the American Medical Informatics Association, 28(11), 2401–2408.
American Medical Group Association. (2026, March 9). AMGA regulatory priorities letter to the U.S. Department of Health and Human Services [Letter to the Honorable Robert F. Kennedy, Jr.]. https://www.amga.org/getmedia/8c4c9e97-66f4-45ab-a7b7-9f32d49ac539/amga-priorities-letter-to-hhs-final.pdf
Evans, C. S., Arthur, R., Kane, M., Omofoye, F., Chung, A. E., Moreton, E., & Moore, C. (2022). Incidental Radiology Findings on Computed Tomography Studies in Emergency Department Patients: A Systematic Review and Meta-Analysis. Annals of Emergency Medicine, 80(3), 243–256. https://doi.org/10.1016/j.annemergmed.2022.03.027
Hansra, S. S., Loehfelm, T. W., Wilson, M., & Corwin, M. T. (2021). Factors Affecting Adherence to Recommendations for Additional Imaging of Incidental Findings in Radiology Reports. Journal of the American College of Radiology, 18(2), 233–239. https://doi.org/10.1016/j.jacr.2020.02.021
Holmgren, A. J., Apathy, N. C., Sinsky, C. A., Adler-Milstein, J., Bates, D. W., & Rotenstein, L. (2025). Trends in physician electronic health record time and message volume. JAMA Internal Medicine, 185(4), 461–463. https://doi.org/10.1001/jamainternmed.2024.8138
Katz, M. S., et al. (2026). Patient perspectives on electronic communication of cancer diagnoses. JAMA Network Open, 9(6), e2619977. https://doi.org/10.1001/jamanetworkopen.2026.19977
Makeeva, V. (2025). Managing incidental findings. Applied Radiology.
Mattay, G., et al. (2024). Communication and follow-up of noncritical actionable imaging findings. Journal of the American College of Radiology.
National Cancer Institute. (2024). Health Information National Trends Survey (HINTS 7). https://hints.cancer.gov
Office of the National Coordinator for Health Information Technology. (2020, May 1). 21st Century Cures Act: Interoperability, information blocking, and the ONC Health IT Certification Program. Federal Register. https://www.federalregister.gov/documents/2020/05/01/2020-07419/21st-century-cures-act-interoperability-information-blocking-and-the-onc-health-it-certification
Rotenstein, L. S., et al. (2019). The volume and nature of physician inbox messages. Health Affairs, 38(12), 2045–2052.
Sinsky, C. A., et al. (2022). Allocation of physician time in ambulatory practice. Journal of General Internal Medicine, 37(12), 3111–3116.
Steitz, B. D., Turer, R. W., Lin, C. T., MacDonald, S., Salmi, L., Wright, A., Lehmann, C. U., Langford, K., McDonald, S. A., Reese, T. J., Sternberg, P., Chen, Q., Rosenbloom, S. T., & DesRoches, C. M. (2023). Perspectives of Patients About Immediate Access to Test Results Through an Online Patient Portal. JAMA Network Open, 6(3), e233572. https://doi.org/10.1001/jamanetworkopen.2023.3572
Steitz, B. D., et al. (2025). Patient-friendly test results and patient-initiated messaging in a large health system. JAMA Network Open.
van der Mee, F. A. M., et al. (2024). Enhancing patient understanding of laboratory test results: A systematic review. Journal of Medical Internet Research. Zaki-Metias, K. M., et al. (2023). The FIND Program: Improving follow-up of incidental imaging findings. Journal of the American College of Radiology.
