March 23, 2020

COVID-19: Is AI-enabled bedside ultrasound the stethoscope of the new millennium?

New millennium, new tools?


March 23, 2020 – The role of radiology, mobile imaging, realtime collaboration, and its significance in screening, detection and ongoing management of COVD-19 patients is gaining prominence. While the appropriateness of Chest X-rays or CT scans to pinpoint COVID-19 pneumonia is being evaluated (discussed here), a group of Italian experts has been exploring the benefits of bedside ultrasound as one possible alternative for detection of COVID-19 pneumonia.

While the data from Italy is preliminary and further studies are needed to confirm the role of lung ultrasound in the diagnosis and management of COVID-19, the authors are strongly recommending the use of bedside ultrasound for early diagnosis of COVID-19 pneumonia in all patients presenting to the emergency department with flu-like symptoms. The publication is available here.

An intensivist from Seattle has created a one page summary of what he has read and seen caring for people with COVID-19. This is a distillation of data and guidelines available elsewhere complete with references posted here.

Another study funded by National Natural Science Foundation of China and National Natural Science Foundation of China was published recently. According to this publication, as lung abnormalities may develop before clinical manifestations and nucleic acid detection, experts have recommended early chest computerized tomography (CT) for screening suspected patients. The high contagiousness of SARS-CoV-2 and the risk of transporting unstable patients with hypoxemia and hemodynamic failure make chest CT a limited option for the patient with suspected or established COVID-19. Lung ultrasonography gives the results that are similar to chest CT and superior to standard chest radiography for evaluation of pneumonia and/or adult respiratory distress syndrome (ARDS) with the added advantage of ease of use at point of care, repeatability, absence of radiation exposure, and low cost [References]

These two recent publications (Peng et al and Huang et al) have characterized important lung ultrasound findings in patients with COVID-19. A review of these two publications is highly recommended if you plan on incorporating bedside ultrasound into your clinical management of suspected COVID-19 patients. Characteristic ultrasound findings compared to CT are described in the provided below (Table1 Peng et al 2020):

Table 1 CT and ultrasonographic features of COVID-19 pneumonia

Based on their experience, the authors consider that lung ultrasonography has major utility for the management of COVID-19 with respiratory involvement due to its safety, repeatability, absence of radiation, low cost and point of care use; chest CT may be reserved for cases where lung ultrasonography is not sufficient to answer the clinical question.

Another publication, A Preliminary Study on the Ultrasonic Manifestations of Peripulmonary Lesions of Non-Critical Novel Coronavirus Pneumonia (COVID-19), discusses how ultrasound was used to observe the imaging manifestations of COVID-19 in order to provide a reference for real-time bedside evaluation. The purpose of this study was to explore the ultrasonic manifestations of peripulmonary lesions of non-critical COVID-19, so as to provide a reference for clinical diagnosis and efficacy evaluation. This study was approved by the ethics committee of Xi’an Chest Hospital, and conducted with the consent of recruited patients.

This study concluded:

The non-critical COVID-19 has characteristic ultrasonic manifestations, which are visible in the posterior and inferior areas of the lung. The lesions are mainly characterized by a large number of B lines, subpleural pulmonary consolidation and poor blood flow. Lung ultrasound can provide reference for the clinical diagnosis and efficacy evaluation.

Reference: link

The Opportunity: The use of tools such as a stethoscope and radiology devices, with the possibility of contamination of the medical devices and nosocomial (infections caught in the hospital) spreading of the virus; eventually, can cause the contagion of health-care workers (from doctor to nurse to radiology technicians) and hospitalized patients who have a higher risk of developing severe COVID-19. Hence, the COVID-19 outbreak, it is important to minimize the health care–patient interactions to only the necessary procedures. The studies quoted above and others in progress seem to indicate an accuracy of lung ultrasound in detecting lung pathologies, from bacterial and viral pneumonia to acute respiratory distress syndrome and its non-inferiority to chest x-ray and clinical examination.

In another detailed publication titled Portable bedside ultrasound: the visual stethoscope of the 21st century, the authors concluded that as technological advances make ultrasound less and less prohibitive in terms of cost and size, its time to augment the archaic tools of past centuries and embrace ultrasound as the visual stethoscope of the 21st century.

Augmented Intelligence – AI-enabled POCUS (point of care ultrasound): By enabling fast correlation of medical knowledge, clinical data and advanced image analysis, there’s an opportunity to go beyond Artificial Intelligence to more meaningful Augmented Intelligence.

Augmented Intelligence is the intersection of machine learning and advanced applications, where clinical knowledge and medical data converge on a single platform. The potential benefits of Augmented Intelligence are realized when it is used in the context of workflows and systems that healthcare practitioners operate and interact with. Unlike Artificial Intelligence, which tries to replicate human intelligence, Augmented Intelligence works with and amplifies human intelligence, writes Dr. Anjum Ahmed (Global Chief Medical Officer – AGFA HealthCare), in this white paper on Augmented Intelligence, published by HIMSS

When it comes to POCUS, AI may help with:

  1. Image Acquisition
  2. Real-time analysis and comparison with similar image datasets
  3. Quality control
  4. Identification of life-threatening findings
  5. Virtual assistant, as a second reader

Bringing it all together – The Enterprise Imaging Strategy: Whether it is Chest X-ray, CT Scan or Point of Care Ultrasound, or AI, the creation of longitudinal patient imaging and the clinical record will play a significant role in helping physicians and radiologists collaborate meaningfully to make informed clinical decisions. If bed-side patient images acquired by portable ultrasound devices are not part of the patient’s overall imaging health record, this may not provide a complete case-centred view of patients’ care pathway. Hence, it is recommended that diagnostic and point of care imaging should not reside in its own silo, it should become part of the patient’s health data so that ongoing care management is well-documented. The images should be intelligently indexed within their clinical context, and these images should be readily accessible to minimize audit or legal risk, should the need arise. – Stay tuned for latest on health, technology, advanced applications, Artificial Intelligence and Data Analytics.