Prospective Comparison of Diagnostic Accuracy Between Point-of-Care and Conventional Ultrasound in a General Diagnostic Department: Implications for Resource-Limited Settings

Haider, Steffen J.; diFlorio-Alexander, Roberta; Lam, David Chuen Chun; Cho, Joo Y; Sohn, Jae Ho; Harris, Robert D.

doi:10.7863/ultra.16.06084

Cited by 4 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…EfficientNet proposed a new scaling method for depth/width/resolution whilst being 7.6´ smaller and 5.7´ faster than ResNet-152 [111]. [87] These…”

Section: Transfer Learningmentioning

confidence: 99%

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Ibrahim,

Blázquez-García,

Lightstone

et al. 2023

J. Med. Imag.

View full text Add to dashboard Cite

.PurposeNon-alcoholic fatty liver disease (NAFLD) is an increasing global health concern, with a prevalence of 25% worldwide. The rising incidence of NAFLD, an asymptomatic condition, reinforces the need for systematic screening strategies in primary care. We present the use of non-expert acquired point-of-care ultrasound (POCUS) B-mode images for the development of an automated steatosis classification algorithm.ApproachWe obtained a Health Insurance Portability and Accountability Act compliant dataset consisting of 478 patients [body mass index 23.60 ± 3.55, age 40.97 ± 10.61], imaged with POCUS by non-expert health care personnel. A U-Net deep learning (DL) model was used for liver segmentation in the POCUS B-mode images, followed by 224 × 224 patch extraction of liver parenchyma. Several DL models including VGG-16, ResNet-50, Inception V3, and DenseNet-121 were trained for binary classification of steatosis. All layers of each tested model were unfrozen, and the final layer was replaced with a custom classifier. Majority voting was applied for patient-level results.ResultsOn a hold-out test set of 81 patients, the final DenseNet-121 model yielded an area under the receiver operator characteristic curve of 90.1%, sensitivity of 95.0%, and specificity of 85.2% for the detection of liver steatosis. Average cross-validation performance in models using patches of liver parenchyma as input outperformed methods using complete B-mode frames.ConclusionsDespite minimal POCUS acquisition training, and low-quality B-mode images, it is possible to detect steatosis using DL algorithms. Implementation of this algorithm in POCUS software may offer an accessible, low-cost steatosis screening technology, for use by non-expert health care personnel.

show abstract

“…EfficientNet proposed a new scaling method for depth/width/resolution whilst being 7.6´ smaller and 5.7´ faster than ResNet-152 [111]. [87] These…”

Section: Transfer Learningmentioning

confidence: 99%

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Ibrahim,

Blázquez-García,

Lightstone

et al. 2023

J. Med. Imag.

View full text Add to dashboard Cite

show abstract

“…[6][7][8][9][10] Standard USG or echocardiography requires the treating physician in the ED to rely on the radiologist or cardiologist to perform it in a timely and clinically relevant manner. 11 Provided the physicians in the ED have skill at image acquisition, image interpretation, and the cognitive elements required for using POCUS, they are able to rapidly incorporate the results of the POCUS examination into the management plan without delay. In addition to this, the radiology or cardiology consultant may not be fully aware of the clinical facts of the case.…”

Section: Introductionmentioning

confidence: 99%

<p>Evaluation of Interdisciplinary Emergency Ultrasound Workshop for Primary Care Physicians in Nepal</p>

Shrestha¹,

Blank²,

Shrestha³

et al. 2020

OAEM

View full text Add to dashboard Cite

Point-of-care ultrasound (POCUS) is a quick bedside tool that has the potential to improve emergency care in resource-limited settings due to its relatively low cost and accessibility. Effort to disseminate the knowledge and skills about POCUS is inadequate in low and middle income countries like Nepal. We conducted a two-day interdisciplinary advanced emergency ultrasound workshop that targeted physicians working in emergency department and primary care, especially in rural Nepal. We explored the effectiveness of this training based on validated Kirkpatrick's 4 steps of evaluating training outcomes. Materials and Methods: We conducted a prospective quasi-experimental study with mixed research design. Multidisciplinary physicians working in emergency departments participated in the two-day workshop. We assessed and compared the pre-and post-workshop knowledge. We collected on-site and a follow-up feedback to explore pre-and post-workshop confidence level, perceived usefulness and clinical use of ultrasound using a 5-point Likert scale. The barriers to use POCUS were explored. Results: A total of 50 physicians from different parts of Nepal participated in the workshop. The academic level of the participants, duration of their clinical experience and the previous use of POCUS did not have a significant difference in their pre-and posttest knowledge scores. The difference between the median (IQR) pre-and posttest scores [14 (12.75-17.75) and 24.5 (22.25-25.5), respectively] was statistically significant (p<0.001). Perceived confidence level and usefulness of the POCUS increased significantly in all of its domains (p<0.001). Self-reported increase in its clinical use was significant (p<0.001) for all fields. Conclusion: The participation in this emergency ultrasound workshop increased the knowledge of participants in POCUS. Their confidence, perceived usefulness and clinical use of POCUS improved significantly. Objective longitudinal follow-up of participants' skill and demonstration of increased clinical use of POCUS in emergency department influencing the clinical outcome would be the focus of future research.

show abstract

Recommendations for Cardiac Point-of-Care Ultrasound in Children: A Report from the American Society of Echocardiography

Lu¹,

Riley²,

Conlon³

et al. 2023

Journal of the American Society of Echocardiography

View full text Add to dashboard Cite

Prospective Comparison of Diagnostic Accuracy Between Point-of-Care and Conventional Ultrasound in a General Diagnostic Department: Implications for Resource-Limited Settings

Abstract: Point-of-care was nearly as accurate as conventional sonography for basic, focused examinations. Observed differences in accuracy were attributed to greater variation in POC image quality.

Cited by 4 publications

References 30 publications

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

Automated fatty liver disease detection in point-of-care ultrasound B-mode images

<p>Evaluation of Interdisciplinary Emergency Ultrasound Workshop for Primary Care Physicians in Nepal</p>

Recommendations for Cardiac Point-of-Care Ultrasound in Children: A Report from the American Society of Echocardiography

Contact Info

Product

Resources

About