In combination with cloud-based data infrastructure and artificial intelligence (AI) applications, handheld ultrasound devices may have the potential to significantly enhance efficiency for providers and contribute to improved patient outcomes.
Just about every new technological device we interact with has one thing in common: they all get smaller, nimbler, and more efficient over time. Just look at personal computers and how they have become smaller and more powerful over the years. Imaging equipment is no different, although the evolutionary timeline has arguably been much slower than that of personal computers.
The shift toward imaging devices with a smaller footprint accelerated during the pandemic when mobile care units and efficient triage were necessary. Today, handheld ultrasound devices are growing in use as a clinical asset and have the potential to revolutionize care.
These pocket-sized, portable devices are being likened by many as the “new stethoscope” for their impactful and swift diagnostic capabilities. Already a key feature of emergency departments and triage situations that require rapid insight, handheld ultrasound modalities are seeing a widespread adoption that will go hand in hand with hospitals, health systems, and private practices using cloud infrastructure to manage imaging data. For example, my company, Ambra Health by Intelerad recently partnered with Butterfly Network, one of the pioneering companies in the handheld ultrasound space, in order to enable providers to view and securely share encounter-based ultrasound information through seamless online data integration.
Here is what providers need to know about the importance of online data management and point-of-care imaging.
Assessing the Benefits of Cloud Infrastructure
When leveraging point-of-care imaging, it is important to consider how its rich data asset will be incorporated into your overall imaging process and workflow. A cloud image exchange network enables providers of all sizes to break down silos between care environments and securely aggregate data across their network.
Having the ability to easily connect a big "fleet" of hundreds or thousands of point-of-care devices to an online image exchange network allows providers to more easily incorporate their mobile data into their existing imaging workflows and processes. The aggregation of this data produces a rich data asset that can improve productivity by eliminating imaging redundancies and seamlessly integrating data across various care environments.
Cloud infrastructure even allows imaging data, both reports and the images themselves, to be included directly with the patient record. Enhancing the single-sign-on experience for a physician can reduce administrative burden, speed up time to care delivery, and develop more productive patient appointments. Facilities can take integrated data a step further by allowing patients access within a patient portal, offering them the ability to become the leaders in their own health-care journeys.
What About Data Storage Implications?
When archiving and storing imaging data from point-of-care devices, providers will need to follow the same guidelines that surround imaging from other stationary equipment. In many countries, it is required that medical imaging data be stored locally within that country to meet local data privacy regulations.
Therefore, when deciding on a cloud imaging provider, it is critical for this imaging provider to meet these requirements to serve as the backend archive and hosting environment to bring mobile ultrasound technology to new areas in a compliant manner.
While simply “plugging” the mobile devices into legacy on-site PACS systems is a possibility, it keeps the imaging stored in silos, eliminating real-time image exchange, and preventing providers from unlocking the rich insights from various points of care or layering on additional artificial intelligence (AI) applications for greater efficiency.
Recognizing the Potential of Combining Handheld Ultrasound with AI Applications
Along with the proliferation of handheld devices, there has been rapid advancement of supporting AI tools that have the potential to improve care efficiency and outcomes. Many devices now also have AI applications built directly into the device to help facilitate more rapid insights.
For example, studies have shown a significant reduction in diagnostic time for cardiopulmonary manifestations when using a handheld ultrasound device equipped with an AI application to detect ejection fraction (nine minutes compared to 20 minutes with the conventional method). In certain emergency care situations, 11 minutes can make a huge difference in health outcomes.
Handheld ultrasound paired with AI has the potential to dramatically improve the efficiency of health care, leading to better outcomes. The lower cost of these devices enables more care environments to have this important diagnostic tool at their disposal.
In Conclusion
We are going to continue to see handheld ultrasound play a more visible role in a patient's care. When handheld ultrasound is paired with a cloud imaging strategy, patients will have greater access to their imaging in real time. For example, workflows can be designed that make it easy for obstetricians to ensure ultrasound images are quickly emailed or texted to pregnant women following their appointment with a link to where the image is securely stored in the cloud.
Point-of-care ultrasound devices are already optimizing patient care in many health-care systems. As the quality of imaging improves, so will the ubiquity of these devices in a variety of on-site and mobile care environments. When incorporating bedside imaging into routine care, studies show that these devices are leading to earlier and more accurate diagnoses, improvements in patient treatment and better allocation of care resources.
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.
The Reading Room: Artificial Intelligence: What RSNA 2020 Offered, and What 2021 Could Bring
December 5th 2020Nina Kottler, M.D., chief medical officer of AI at Radiology Partners, discusses, during RSNA 2020, what new developments the annual meeting provided about these technologies, sessions to access, and what to expect in the coming year.
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.
New Study Examines Agreement Between Radiologists and Referring Clinicians on Follow-Up Imaging
November 18th 2024Agreement on follow-up imaging was 41 percent more likely with recommendations by thoracic radiologists and 36 percent less likely on recommendations for follow-up nuclear imaging, according to new research.