By Inga Shugalo
Driven by technology advances, significant increases in medical imaging data have created an overload of information for radiologists to deal with—but technology can also resolve the issue.
Artificial-intelligence solutions exist, which can help humans to scan and analyze images more quickly, and even take some of the work off their hands. Meanwhile, smarter communication strategies that leverage mobile capabilities can bring about more effective patient-scheduling and help reduce time wasted by appointment cancellations and no-shows.
Here are a few ideas and examples to consider if you’d like to assist your radiology team in gaining efficiencies and cutting wait times for patients.
Train A-Eyes on The Prize
As Dr. Richard Wiggins, University of Utah Health, explained in a Healthcare IT News article about imaging turnaround times (TAT), the number of medical images viewed daily has increased a hundredfold over the last 25 years.
At the same time, as human evolution moves at a snail’s pace, radiologists’ capabilities for completing studies have not grown to any measurable degree. Therefore, if you want to speed up the evaluation of medical images meaningfully, it’s worth looking to machine learning and computer vision to give your radiologists a lift.
One crucial advantage of increased volumes of visual data is the possibility to train artificial intelligence software to generate diagnoses from medical images. AI can even learn to spot abnormalities that the human eye can easily miss.
By leveraging these powerful AI capabilities in your radiology department, you can shorten the time required to view and evaluate X-rays, MRI, CAT, and ultrasound scans. Consequently, your team can complete more studies every day and reduce TAT, perhaps by a substantial degree, through a combination of digital and human effort.
Apply AI to the No-Show Nuisance
Every time a patient fails to keep an imaging appointment, it contributes to a range of issues. Some of them affect the patient herself, and others the efficiency and performance of the radiology department. Specifically, problems arising from no-shows include:
- The risk that the patient’s health deteriorates from a potentially severe undiagnosed condition
- The loss of an imaging time-slot that could have been used for another patient
- Extended waiting lists as a result, which increases the lead times for appointments
Each of the above issues makes it harder for radiology departments to reduce turnaround times.
When the patient’s condition increases in severity, more imaging sessions are likely to be required, and of course, the patient loses the opportunity for early diagnosis and treatment. Lost time-slots reduce productivity, and longer lead times mean longer turnaround times.
How AI and Predictive Analytics Can Help
By integrating AI and predictive analytics into your healthcare solutions, your organization can move beyond mere tracking of no-show metrics to deciphering subtle patterns in associated variables.
Armed with the knowledge of trends in no-shows among various age, gender and demographic groups, you can apply analytics to predict the likelihood of a patient making it to a screening.
After achieving this enhanced level of granularity, it should be possible to take a more personalized approach to appointment management. You might want to think about the following solutions:
- Amending scheduling structures, so patients at risk of no-showing could be scheduled later in the day to reduce the impact on daily workflow.
- Introducing technology such as mobile apps and chatbots to improve methods and processes for sending appointment reminders.
- Developing advanced communication strategies targeting individuals based on applicable no-show risk factors.
Add Digital Intelligence to Radiology Workflows
Radiology turnaround times, in general, are ripe for improvement. When it comes to imaging requests from emergency departments (EDs) and intensive care units (ICUs), though, timely results are not just a matter of patient satisfaction. They are of immediate importance to patients’ treatment and recovery.
However, as revealed in a 2017 study by researchers from Atlanta’s Emory University, typical manual prioritization methodologies don’t make it easy for radiologists to identify genuinely urgent cases.
As a result, requests from EDs and ICUs commonly receive the same level of attention within the same timescales as those from other departments in a healthcare environment. In short, clinicians are in the habit of categorizing requests as urgent whenever they feel that a fast turnaround time is necessary, which can be for many different reasons.
Automation for Objective Prioritization
Some hospitals are overcoming this problem by deploying workflows with automated prioritization, eliminating the confusion caused by the overuse of subjective STAT designation, which indicates the requirement for urgency.
If your radiologists are finding it challenging to pick out the studies that should be prioritized among those which are less urgent, such a solution could make a telling difference. Automated, intelligent prioritization can enable faster turnaround times for the most critical cases and contribute more meaningfully to successful emergency and intensive care outcomes.
Look Beyond Imaging to Boost Radiology Turnaround Times
The challenges of improving radiology turnaround times come in many forms. They might relate to the need to shorten the imaging process and improve the speed of data analysis and results delivery. The technology is available to tackle issues in each of these areas.
There is a clear evidence of the need for faster radiology results. Patients in the United States expect imaging results to be available within three days of attending their screening appointments, on average. The expected TAT is as little as 24 hours for patients screened for potentially serious conditions such as cancer or heart diseases.
Longer waiting times mean more anxiety for patients, and in some cases this might affect the ability of clinicians to commence effective treatment.
Given these emotional and medical implications, how might your radiology department apply new technologies to meet and exceed TAT expectations? Remember to think not only about imaging but also communication with patients and doctors, image data analysis, and accurate prioritization of screenings.
Inga Shugalo is a Healthcare Industry Analyst at Itransition, a custom software development company headquartered in Denver, Colorado. She focuses on Healthcare IT, highlighting the industry challenges and technology solutions that tackle them. Inga’s articles explore diagnostic potential of healthcare IoT, opportunities of precision medicine, robotics and VR in healthcare and more.