Validation of a Telemedicine Quality Assurance Method for Point-of-Care Obstetric Ultrasound Used in Low-Resource Settings

The Potential of Tele-Ultrasound, Handheld and Self-Operated Ultrasound in Pregnancy Care: A Systematic Review

OBJECTIVE

To explore the use of tele-ultrasound and handheld or self-operated ultrasound in pregnancy.

METHODS

A systematic search provided 31 studies. The risk of bias for each study was assessed. Results were analyzed and presented in a narrative overview in four domains: tele-ultrasound, patient-operated ultrasound, handheld devices and low- and middle-income countries (LMIC).

RESULTS

The quality of studies was generally low or fair based on the NIH Quality Assessment Tools. Fetal tele-ultrasound services (11 studies) are feasible and especially helpful in rural areas or with increased centralization of specialist care. Three studies with patient-operated ultrasound concluded its feasibility with good-to-high experiences. The use of handheld devices in pregnancy (eight studies) showed similar ultrasound results when compared to standard devices. In LMICs, innovative use of ultrasound (nine studies) can facilitate access to obstetric care performed by trained as well as unskilled caregivers combined with remote evaluation by an expert.

CONCLUSIONS

Innovations in ultrasound in pregnancy care have shown promising results for application. Although most studies demonstrated benefits for pregnant women or care providers, high-level evidence is scarce. High-quality studies on innovations are needed to assess medical outcomes, patient and provider experiences and costs.

Artificial Intelligence (AI) Applications for Point of Care Ultrasound (POCUS) in Low-Resource Settings: A Scoping Review

Advancements in artificial intelligence (AI) for point-of-care ultrasound (POCUS) have ushered in new possibilities for medical diagnostics in low-resource settings. This review explores the current landscape of AI applications in POCUS across these environments, analyzing studies sourced from three databases-SCOPUS, PUBMED, and Google Scholars. Initially, 1196 records were identified, of which 1167 articles were excluded after a two-stage screening, leaving 29 unique studies for review. The majority of studies focused on deep learning algorithms to facilitate POCUS operations and interpretation in resource-constrained settings. Various types of low-resource settings were targeted, with a significant emphasis on low- and middle-income countries (LMICs), rural/remote areas, and emergency contexts. Notable limitations identified include challenges in generalizability, dataset availability, regional disparities in research, patient compliance, and ethical considerations. Additionally, the lack of standardization in POCUS devices, protocols, and algorithms emerged as a significant barrier to AI implementation. The diversity of POCUS AI applications in different domains (e.g., lung, hip, heart, etc.) illustrates the challenges of having to tailor to the specific needs of each application. By separating out the analysis by application area, researchers will better understand the distinct impacts and limitations of AI, aligning research and development efforts with the unique characteristics of each clinical condition. Despite these challenges, POCUS AI systems show promise in bridging gaps in healthcare delivery by aiding clinicians in low-resource settings. Future research endeavors should prioritize addressing the gaps identified in this review to enhance the feasibility and effectiveness of POCUS AI applications to improve healthcare outcomes in resource-constrained environments.

Implementation and evaluation of a pilot antenatal ultrasound imaging programme using tele-ultrasound in Ethiopia

INTRODUCTION

Ultrasound imaging is an important aspect of antenatal care, though access to antenatal ultrasound imaging is limited in many developing countries. The objective of this study was to evaluate a pilot programme which aimed to improve access to antenatal ultrasound for rural Ethiopians through enhanced training of healthcare providers (including midwives, nurses and clinical officers) with support remotely provided by obstetricians using a tele-ultrasound platform.

METHODS

Thirteen healthcare providers in the North Shoa Zone in Ethiopia completed training to enable them to perform antenatal ultrasound with the remote supervision of an obstetrician via a tele-ultrasound platform. Pregnant women attending an antenatal appointment at two facilities were offered an antenatal ultrasound exam performed by one of the healthcare providers. Image interpretations between obstetricians and healthcare providers were compared. Participants and healthcare providers were invited to complete a questionnaire regarding their experience with tele-ultrasound, and participants, healthcare providers and obstetricians were interviewed regarding their experience with the tele-ultrasound pilot programme.

RESULTS

2795 pregnant women had an antenatal ultrasound exam. Of 100 exams randomly selected to assess concordance between healthcare providers' and obstetricians' image interpretations, concordance ranged from 79% to 100% for each parameter assessed. 99.4% of participants surveyed indicated that they would recommend antenatal ultrasound using tele-ultrasound to friends and family. Themes relating to participants' experiences of having a tele-ultrasound exam were reduced travel and cost, equivalence in quality of virtual care to in-person care and empowerment through diagnostic information.

CONCLUSION

Healthcare provider-performed antenatal ultrasound - supported by obstetricians via tele-ultrasound - showed high levels of concordance, was well-received by participants and provided rural Ethiopian women with enhanced access to antenatal imaging.

Society for Maternal-Fetal Medicine Special Statement: Telemedicine in obstetrics-quality and safety considerations

The frequency of telemedicine encounters has increased dramatically in recent years. This review summarizes the literature regarding the safety and quality of telemedicine for pregnancy-related services, including prenatal care, postpartum care, diabetes mellitus management, medication abortion, lactation support, hypertension management, genetic counseling, ultrasound examination, contraception, and mental health services. For many of these, telemedicine has several potential or proven benefits, including expanded patient access, improved patient satisfaction, decreased disparities in care delivery, and health outcomes at least comparable to those of traditional in-person encounters. Considering these benefits, it is suggested that payers should reimburse providers at least as much for telemedicine as for in-person services. Areas for future research are considered.

Automatic Image Guidance for Assessment of Placenta Location in Ultrasound Video Sweeps

Ultrasound-based assistive tools are aimed at reducing the high skill needed to interpret a scan by providing automatic image guidance. This may encourage uptake of ultrasound (US) clinical assessments in rural settings in low- and middle-income countries (LMICs), where well-trained sonographers can be scarce. This paper describes a new method that automatically generates an assistive video overlay to provide image guidance to a user to assess placenta location. The user captures US video by following a sweep protocol that scans a U-shape on the lower maternal abdomen. The sweep trajectory is simple and easy to learn. We initially explore a 2-D embedding of placenta shapes, mapping manually segmented placentas in US video frames to a 2-D space. We map 2013 frames from 11 videos. This provides insight into the spectrum of placenta shapes that appear when using the sweep protocol. We propose classification of the placenta shapes from three observed clusters: complex, tip and rectangular. We use this insight to design an effective automatic segmentation algorithm, combining a U-Net with a CRF-RNN module to enhance segmentation performance with respect to placenta shape. The U-Net + CRF-RNN algorithm automatically segments the placenta and maternal bladder. We assess segmentation performance using both area and shape metrics. We report results comparable to the state-of-the-art for automatic placenta segmentation on the Dice metric, achieving 0.83 ± 0.15 evaluated on 2127 frames from 10 videos. We also qualitatively evaluate 78,308 frames from 135 videos, assessing if the anatomical outline is correctly segmented. We found that addition of the CRF-RNN improves over a baseline U-Net when faced with a complex placenta shape, which we observe in our 2-D embedding, up to 14% with respect to the percentage shape error. From the segmentations, an assistive video overlay is automatically constructed that (i) highlights the placenta and bladder, (ii) determines the lower placenta edge and highlights this location as a point and (iii) labels a 2-cm clearance on the lower placenta edge. The 2-cm clearance is chosen to satisfy current clinical guidelines. We propose to assess the placenta location by comparing the 2-cm region and the bottom of the bladder, which represents a coarse localization of the cervix. Anatomically, the bladder must sit above the cervix region. We present proof-of-concept results for the video overlay.

Portable ultrasound technologies for estimating gestational age in pregnant women: a scoping review and analysis of commercially available models

OBJECTIVES

To identify all available studies assessing the use of portable ultrasound devices for pregnant women, with the specific aim of finding evidence for devices used to determine gestational age and their validity when compared with conventional ultrasound machines. We also wanted to determine what portable ultrasound models are commercially available for obstetric use.

DESIGN

Systematic scoping review.

PRIMARY AND SECONDARY OUTCOME MEASURES

Extracted variables included study design, population, method of ultrasound measurement, devices used and whether studies formally validated accuracy against conventional ultrasound.

RESULTS

We searched four databases-Medline, Embase, CINAHL and Maternal and Infant Care. In total 56 studies from 34 countries were identified; most were observational studies. Across all studies, 27 different portable ultrasound models (from 17 manufacturers) were evaluated. Twenty-one studies assessed use of portable ultrasound for evaluating fetal characteristics or estimating gestational age, and 10 of these were formal validation studies. In total, six portable devices have been validated for gestational age estimation against a conventional ultrasound comparator. The web searches identified 102 portable devices (21 manufacturers). These were a mix of handheld devices that connected to a phone or computer, or laptop-style portable ultrasound devices. Prices ranged from US$1190 to US$30 000 and weight ranged from 0.9 kg to 13.0 kg.

CONCLUSION

While the number of commercially available portable ultrasound devices continues to grow, there remains a lack of peer-reviewed, quality evidence demonstrating their accuracy and validity when compared with conventional ultrasound machines. This review identified some models that may be useful in gestational age estimation in low-resource settings, but more research is required to help implement the technology at scale.

TRIAL REGISTRATION NUMBER

Registered via Open Science Framework (DOI: 10.17605/OSF.IO/U8KXP).

Developing Clinical Artificial Intelligence for Obstetric Ultrasound to Improve Access in Underserved Regions: Protocol for a Computer-Assisted Low-Cost Point-of-Care UltraSound (CALOPUS) Study

BACKGROUND

The World Health Organization recommends a package of pregnancy care that includes obstetric ultrasound scans. There are significant barriers to universal access to antenatal ultrasound, particularly because of the cost and need for maintenance of ultrasound equipment and a lack of trained personnel. As low-cost, handheld ultrasound devices have become widely available, the current roadblock is the global shortage of health care providers trained in obstetric scanning.

OBJECTIVE

The aim of this study is to improve pregnancy and risk assessment for women in underserved regions. Therefore, we are undertaking the Computer-Assisted Low-Cost Point-of-Care UltraSound (CALOPUS) project, bringing together experts in machine learning and clinical obstetric ultrasound.

METHODS

In this prospective study conducted in two clinical centers (United Kingdom and India), participating pregnant women were scanned and full-length ultrasounds were performed. Each woman underwent 2 consecutive ultrasound scans. The first was a series of simple, standardized ultrasound sweeps (the CALOPUS protocol), immediately followed by a routine, full clinical ultrasound examination that served as the comparator. We describe the development of a simple-to-use clinical protocol designed for nonexpert users to assess fetal viability, detect the presence of multiple pregnancies, evaluate placental location, assess amniotic fluid volume, determine fetal presentation, and perform basic fetal biometry. The CALOPUS protocol was designed using the smallest number of steps to minimize redundant information, while maximizing diagnostic information. Here, we describe how ultrasound videos and annotations are captured for machine learning.

RESULTS

Over 5571 scans have been acquired, from which 1,541,751 label annotations have been performed. An adapted protocol, including a low pelvic brim sweep and a well-filled maternal bladder, improved visualization of the cervix from 28% to 91% and classification of placental location from 82% to 94%. Excellent levels of intra- and interannotator agreement are achievable following training and standardization.

CONCLUSIONS

The CALOPUS study is a unique study that uses obstetric ultrasound videos and annotations from pregnancies dated from 11 weeks and followed up until birth using novel ultrasound and annotation protocols. The data from this study are being used to develop and test several different machine learning algorithms to address key clinical diagnostic questions pertaining to obstetric risk management. We also highlight some of the challenges and potential solutions to interdisciplinary multinational imaging collaboration.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR1-10.2196/37374.

Potential for Use of Portable Ultrasound Devices in Rural and Remote Settings in Australia and Other Developed Countries: A Systematic Review

Introduction

Objective

Methods

Results

Conclusion

Testing telediagnostic thyroid ultrasound in Peru: a new horizon in expanding access to imaging in rural and underserved areas

PURPOSE

Thyroid ultrasound is a key tool in the evaluation of the thyroid, but billions of people around the world lack access to ultrasound imaging. In this study, we tested an asynchronous telediagnostic ultrasound system operated by individuals without prior ultrasound training which may be used to effectively evaluate the thyroid and improve access to imaging worldwide.

METHODS

The telediagnostic system in this study utilizes volume sweep imaging (VSI), an imaging technique in which the operator scans the target region with simple sweeps of the ultrasound probe based on external body landmarks. Sweeps are recorded and saved as video clips for later interpretation by an expert. Two operators without prior ultrasound experience underwent 8 h of training on the thyroid VSI protocol and the operation of the telemedicine platform. After training, the operators scanned patients at a health center in Lima. Telediagnostic examinations were sent to the United States for remote interpretation. Standard of care thyroid ultrasound was performed by an experienced radiologist at the time of VSI examination to serve as a reference standard.

RESULTS

Novice operators scanned 121 subjects with the thyroid VSI protocol. Of these exams, 88% were rated of excellent image quality showing complete or near complete thyroid visualization. There was 98.3% agreement on thyroid nodule presence between VSI teleultrasound and standard of care ultrasound (Cohen's kappa 0.91, P < 0.0001). VSI measured the thyroid size, on average, within 5 mm compared to standard of care. Readers of VSI were also able to effectively characterize thyroid nodules, and there was no significant difference in measurement of thyroid nodule size (P = 0.74) between VSI and standard of care.

CONCLUSION

Thyroid VSI telediagnostic ultrasound demonstrated both excellent visualization of the thyroid gland and agreement with standard of care thyroid ultrasound for nodules and thyroid size evaluation. This system could be deployed for evaluation of palpable thyroid abnormalities, nodule follow-up, and epidemiological studies to promote global health and improve the availability of diagnostic imaging in underserved communities.

Association between antenatal ultrasound findings and neonatal outcomes in rural Uganda: a secondary analysis

BACKGROUND

Although the use of prenatal ultrasound services has increased in low- income and lower middle-income countries, there has not been a concurrent improvement in perinatal mortality. It remains unknown whether individual ultrasound findings in this setting are associated with neonatal death or the need for resuscitation at delivery. If associations are identified by ultrasound, they could be used to inform the birth attendant and counsel the family regarding risk, potentially altering delivery preparedness in order to reduce neonatal mortality.

METHODS

This was a secondary analysis of data collected from a prospective cohort. Data was gathered at Nawanyago Health Centre III in Kamuli District, Uganda. Participants included pregnant women who received second and third trimester prenatal ultrasound scans and delivered at that center between July 2010 and August 2018. All ultrasounds were performed at Nawanyago and deliveries were attended solely by midwives or nurses. Predictor variables included the following ultrasound findings: fetal number, fetal presentation, and amniotic fluid volume. The primary outcome was bag-mask ventilation (BMV) of the neonate at delivery. The secondary outcome was stillbirth or neonatal death in the delivery room.

RESULTS

Primary outcome data was available for 1105 infants and secondary outcome data was available for 1098 infants. A total of 33 infants received BMV at delivery. The odds of receiving BMV at delivery was significantly increased if amniotic fluid volume was abnormal (OR 4.2, CI 1.2-14.9) and there were increased odds for multiple gestation (OR 1.9, CI 0.7-5.4) and for non-vertex fetal presentation (OR 1.4, CI 0.6-3.2) that were not statistically significant. Stillbirth or neonatal death in the delivery room was diagnosed for 20 infants. Multiple gestation (OR 4.7, CI 1.6-14.2) and abnormal amniotic fluid volume (OR 4.8, CI 1.0-22.1) increased the odds of stillbirth or neonatal death in the delivery room, though only multiple gestation was statistically significant.

CONCLUSION

Common findings that are easily identifiable on ultrasound in low- and lower middle-income countries are associated with adverse perinatal outcomes. Education could lead to improved delivery preparedness, with the potential to reduce perinatal mortality. This was a preliminary study; larger prospective studies are needed to confirm these findings.

Testing telediagnostic obstetric ultrasound in Peru: a new horizon in expanding access to prenatal ultrasound

Background

Ninety-four percent of all maternal deaths occur in low- and middle-income countries, and the majority are preventable. Access to quality Obstetric ultrasound can identify some complications leading to maternal and neonatal/perinatal mortality or morbidity and may allow timely referral to higher-resource centers. However, there are significant global inequalities in access to imaging and many challenges to deploying ultrasound to rural areas. In this study, we tested a novel, innovative Obstetric telediagnostic ultrasound system in which the imaging acquisitions are obtained by an operator without prior ultrasound experience using simple scan protocols based only on external body landmarks and uploaded using low-bandwidth internet for asynchronous remote interpretation by an off-site specialist.

Methods

This is a single-center pilot study. A nurse and care technician underwent 8 h of training on the telediagnostic system. Subsequently, 126 patients (68 second trimester and 58 third trimester) were recruited at a health center in Lima, Peru and scanned by these ultrasound-naïve operators. The imaging acquisitions were uploaded by the telemedicine platform and interpreted remotely in the United States. Comparison of telediagnostic imaging was made to a concurrently performed standard of care ultrasound obtained and interpreted by an experienced attending radiologist. Cohen’s Kappa was used to test agreement between categorical variables. Intraclass correlation and Bland-Altman plots were used to test agreement between continuous variables.

Results

Obstetric ultrasound telediagnosis showed excellent agreement with standard of care ultrasound allowing the identification of number of fetuses (100% agreement), fetal presentation (95.8% agreement, κ =0.78 (p < 0.0001)), placental location (85.6% agreement, κ =0.74 (p < 0.0001)), and assessment of normal/abnormal amniotic fluid volume (99.2% agreement) with sensitivity and specificity > 95% for all variables. Intraclass correlation was good or excellent for all fetal biometric measurements (0.81–0.95). The majority (88.5%) of second trimester ultrasound exam biometry measurements produced dating within 14 days of standard of care ultrasound.

Conclusion

This Obstetric ultrasound telediagnostic system is a promising means to increase access to diagnostic Obstetric ultrasound in low-resource settings. The telediagnostic system demonstrated excellent agreement with standard of care ultrasound. Fetal biometric measurements were acceptable for use in the detection of gross discrepancies in fetal size requiring further follow up.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12884-021-03720-w.