How AI can increase the effectiveness of point-of-care ultrasound

For patients requiring care in rural areas, obtaining diagnostic tests can be a complicated process. In some cases, individuals may have to travel long distances to larger facilities to access the needed technology.

To address these issues, many developers have focused their innovation efforts on point-of-care ultrasound or POCUS devices.

Like dr. Mark Favot explained: IT news in healthcarecan make such instruments – especially portable – care more widely available and cheaper in remote regions.

Favot, associate professor and director of EM Ultrasound Education at Wayne State University School of Medicine in Detroit, spoke with us about how artificial intelligence could make a difference with POCUS, and shared what makes him excited about the technology in the longer term.

Q. Why does having access to point-of-care ultrasound devices make a difference to patient care, especially in rural areas?

A. Healthcare in rural areas often includes patients seeking medical care in facilities not equipped with the full range of diagnostic testing resources such as large medical centers in urban population centers. Often, the physician caring for the patient must arrange transfers to larger hospitals to give the patient access to things like computed tomography scanning, magnetic resonance imaging, and echocardiography.

Providing quality healthcare in an environment without these resources can be challenging for physicians and frustrating for patients.

Delays in undergoing diagnostic testing (either because the patient is transferred to another facility, or because urgent testing is postponed to a later date in an outpatient setting) not only contribute to the frustrations felt by both physicians and patients, but are often associated with adverse effects on the patient. outcomes related to the disease that caused the patient to primarily seek care in the rural setting.

Traditional ultrasound that takes place in a suite in the radiology department is usually available during the day, but may have limitations as to which parts of the body they can scan.

With the advent of point-of-care ultrasound, or POCUS, the imaging paradigm has shifted from the traditional model of the images obtained by a trained sonographer and then sent to a radiologist for interpretation to a model in which the treating physician’s the patient is being treated. executing and interpreting the POCUS in real time while developing a treatment plan for the patient.

Larger portable POCUS machines with carts have been in the emergency room for the past 20 years, but they’re often quite expensive – and in a low-volume care setting, such as a rural ER, they may not be a financially viable solution if they aren’t used. used often enough.

Handheld POCUS machines have further shifted the imaging paradigm because they are often affordable enough to be owned by physicians (rather than owned by hospitals) and taken to any healthcare setting where that physician works. This development has important implications for patients in rural health care facilities, as the doctors who staff these hospitals often do not live in the community where the hospital is located. If the hospital does not have POCUS equipment with carts, the physician can bring their own portable POCUS machine to the hospital for inpatient emergency services.

Armed with this technology, doctors can now use POCUS to aid in diagnostic testing for patients, which could lead to improvements in the ability to rule out or rule out specific diagnoses for patients, rather than being forced to hand them over to centers where they can end up with completely normal imaging, only to be sent home from a hospital 60 miles from where they live.

Q. How can having artificial intelligence guidance make a difference with these devices?

A. Artificial intelligence has the potential to dramatically increase the effectiveness of POCUS, primarily by reducing the impact of poor image interpretation, which is one of the most common barriers to POCUS implementation.

Many physicians learned POCUS by attending one- or two-day continuing medical education courses taught by a large group of POCUS experts. These courses provide many benefits to participants, including favorable teacher-student relationships, a wide range of high-quality, state-of-the-art POCUS equipment, simulated patient models with excellent ultrasound “windows” and access to lectures covering a wide range of pathologies.

The “problem” for people taking these courses starts when they return to their own facility and now have to scan with their older, often outdated equipment, in patients who may have problems that make ultrasound challenging and without the expert next to them coaching them. on probe movements to enhance the images or aid in interpretation when things don’t look exactly like the textbook or lectures they have recently attended.

Typically, if the physician works in a facility with a robust POCUS program, that ultrasound exam will be reviewed by a POCUS expert one to three days later, and if there were any issues with the exam, that expert can provide them with feedback and suggestions for improvement. . While this feedback may help the clinician the next time they use POCUS, it won’t help the patient they just scanned, and the impact of feedback given backwards and not in real time is limited.

AI can be that important bridge between the expert feedback a few days later and no feedback at all at the time of the exam. Robust AI on POCUS machines can provide the user with immediate actionable feedback to improve the image, such as “Tilt the probe towards the patient’s head to obtain the correct 4-chamber apical view of the heart that includes both atria and both ventricles.” “, instead of the image the user had obtained, which had only the right and left ventricles.

This type of AI feedback has clear immediate benefits for patient care now that a correct diagnosis can be made, as the clinician could obtain a standard, easier-to-interpret POCUS image. However, the long-term impact of direct AI feedback could be even greater.

Often doctors will be excited about using POCUS in their practice right after a training session, but over time, that enthusiasm wanes as their confidence begins to decline as they get further away from the training session. When AI is built into POCUS systems, it can function in a role as the expert bedside POCUS practitioner. However, being a machine and not a human standing next to you, it creates a lower pressure environment that makes it easier for the new POCUS user to use the machine and gradually improve their skills. POCUS is very humble to doctors, and the shame of not being strong in this skill can lead to doctors not using it. AI is one way this can be overcome.

Q. What excites you about the short- and long-term potential for POCUS?

A. I am most excited about what is happening at the medical school level when it comes to the demand for POCUS. Today’s medical students are very technologically savvy, and they will not stand by and accept that more than 200-year-old technology, such as a stethoscope, is the most effective diagnostic tool for their patients. They have and will demand more from their education.

Institutions with strong POCUS curricula for medical students, such as the Medical University of South Carolina, Wayne State University, and University of California-Irvine, have seen an increase in applications as prospective students seek POCUS training. Schools that do not currently have a POCUS curriculum are trying to catch up.

The students drive change from below and force leaders to respond. The earlier in their careers doctors can access POCUS training, the more likely these skills will become sustainable and stay with them for the long haul.

The advent of portable POCUS systems at an affordable price now being marketed to physicians rather than healthcare facilities will help accelerate this shift. As effective as a POCUS curriculum or teacher is, the best learning process often occurs when a curious physician picks up a POCUS system and learns through trial and error. When the machine is hand-held and can be taken home, the doctor, or the doctor’s family, can become the actual ultrasound model. All of us in the field have had this experience ourselves, and while it can be a slower and more difficult way to learn, it is a proven method that is extremely valuable.

While POCUS is a major disruptive technology enabling more accurate and faster physician diagnoses and safer performance of needle-guided procedures, it is important to realize that as the price and availability of portable POCUS equipment continues to improve, it is imperative that doctors receive proper training. Training should ideally start as early as possible in one’s career, be ongoing and target areas with identified deficiencies, and be supported by modern technology such as AI.

The explosion of growth in the affordable handheld POCUS market has put these machines in the hands of a large number of new doctors, not all of whom have received adequate training. This bottom-up move requires an appropriate response from healthcare leaders to ensure adequate funding and resources are devoted to creating and maintaining programs that educate all POCUS users to adequate standards. By doing so, institutions can lead the way in the POCUS wave that has already begun and leverage it to positively impact patients seeking care in a wide variety of destinations.

The ability to provide high-quality imaging to every patient everywhere is the most exciting aspect of the future of POCUS and will be its long-standing legacy.

Kat Jercich is editor-in-chief of Healthcare IT News.
Twitter: @kjercich
Healthcare IT News is a publication of HIMSS Media.

Leave a Comment