I have heard frustration from oncologic practices regarding radiology reports. Here are a few ways we can help improve radiologic-oncology care.
Oncologic imaging has exploded in many groups over recent years. Many protocols require repeated, frequent imaging and therefore management depends importantly on radiologic reporting.
On the oncologic side, a tremendous amount of information is provided to care co-coordinators and oncologists for management. This includes not only radiology information, but increased lab data and ever-more specific pathology data. Care also increasingly depends on integration of this information with radiological findings, accurate sub-typing of cancer and concordance between radiology lab values and radiology pathology results.
In some cases I have heard frustration from oncologic practices regarding radiology reports. Sometimes this is justified, sometimes not. But it points out a few things to us as we improve radiologic-oncology care:
1. Oncologists need consistency of reporting for individual patients. Some radiologists resist having uniform reporting, as it may not fit their style. Where possible, the practice would serve its referring physicians and patients well to look for a consensus on reporting. This can be developed in discussion with the leadership of referring oncologic providers. At a minimum, it is a good idea to open a dialogue with the oncologists as to what information should be targeted in oncologic reports for them. The structure of the report may need to be different than a classical model, perhaps with summary relevant oncologic information separately identified.
2. The most specific diagnosis yields the best treatment, and relies on consistency or concordance of radiologic and pathologic data. We’ve all been at conferences where the pathologic diagnosis suggests something that is not likely by imaging.
Today, there is no excuse for either radiologists or pathologists to work in the dark, and independent of one another. The low tech solution is multi-disciplinary conferences, and your practice should actively participate in those. You may want to identify a handful of oncologic radiologists to offer consistency for those. The phone is a low tech tool too. Don’t resist picking it up and consulting with your pathology colleagues. That process should be formalized and mandated, and occur as real-time as possible.
The high-tech methods are novel IT systems that allow for summary display of radiology and pathology information. Ask your IT system administrator if that is available to you. If so, it is a powerful tool. Merging data and unstructured text into a summary simplifies its interpretation greatly.
3. The processes of radiologic, laboratory and pathologic diagnosis need to be uniform too. In fact, this process should be formalized so that there is always communication between these disciplines, there is standard method used and work flow is coordinated. Sit down with the lab and pathologist and make sure that there is a consistent method for acquiring pathologic material and processing. Talk with your group and seek to have uniformity of methods. Wherever the process can be coordinated and made more uniform, you should seek to do so.
4. When there are problems and delays, patients can’t be managed. Have a QA process to analyze all turn-around-time delays. This means that instead of looking only at your report TAT, you should look at the system TAT for things that are multi-disciplinary (biopsies), including all modalities if appropriate.
Ultimately, good oncologic radiology care will rely on consistency, real-time collaboration across disciplines and rigor of process
New Study Examines Short-Term Consistency of Large Language Models in Radiology
November 22nd 2024While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
FDA Grants Expanded 510(k) Clearance for Xenoview 3T MRI Chest Coil in GE HealthCare MRI Platforms
November 21st 2024Utilized in conjunction with hyperpolarized Xenon-129 for the assessment of lung ventilation, the chest coil can now be employed in the Signa Premier and Discovery MR750 3T MRI systems.
FDA Clears AI-Powered Ultrasound Software for Cardiac Amyloidosis Detection
November 20th 2024The AI-enabled EchoGo® Amyloidosis software for echocardiography has reportedly demonstrated an 84.5 percent sensitivity rate for diagnosing cardiac amyloidosis in heart failure patients 65 years of age and older.