Does Size Matter? A Prospective Study on the Feasibility of Using a Handheld Ultrasound Device in Place of a Cart-Based System in the Evaluation of Trauma Patients.

BACKGROUND: As emergency physicians are looking at handheld devices as alternatives to the traditional, cart-based systems, concerns center around whether they are forsaking image quality for a lower price point and whether the handheld can be trusted for medical decision making. OBJECTIVE: We aimed to determine the feasibility of using a handheld ultrasound device in place of a cart-based system during the evaluation of trauma patients using the Focused Assessment with Sonography for Trauma (FAST) examination. METHODS: This was a prospective study of adult trauma patients who received a FAST examination as part of their evaluation. A FAST examination was performed using a cart-based machine and a handheld device. The results of the examinations were compared with computed tomography imaging. Images obtained from both ultrasound devices were reviewed by an expert for image quality. RESULTS: A total of 62 patients were enrolled in the study. The mean (SD) time to perform a FAST examination using the handheld device was 307.3 (65.3) s, which was significantly less (p = 0.002) than the 336.1 (86.8) s with the cart-based machine. There was strong agreement between the examination results of the handheld and cart-based devices and between the handheld and computed tomography. Image quality scores obtained with the handheld device were lower than those from the cart-based system. Most operators and reviewers agreed that the images obtained from the handheld were adequate for medical decision making. CONCLUSIONS: Data support that it is feasible to use the handheld ultrasound device for evaluation of the trauma patient in place of the cart-based system.

Surgical Resident Education and Performance in Extended Focused Abdominal Sonography for Trauma.

Extended focused assessment with sonography for trauma (eFAST) is a rapid triage tool aiding the detection of life-threatening injuries. In academic settings, residents perform most eFAST; however, the ACGME has no recommendations for eFAST training standards. We surveyed general surgery programs (GSPs) regarding eFAST training and established a baseline for sensitivity, specificity, and positive and negative predictive values for resident-performed eFAST. US GSP eFAST surveys were conducted by email and phone. We prospectively collected patient variables and evaluated resident performance from May to September 2022 and 2023 at an academic level I trauma center. A total of 60/339 general surgery residency programs (GSRPs) responded: Ten use Advanced Trauma Life Support (ATLS) only, n = 7 group training, n = 8 on-the-job only, and n = 33 several methods. Resident-performed eFAST had accuracy = 85.6%, sensitivity = 35.6%, specificity = 97.2%, PPV = 75%, and NPV = 87%. General surgery residency program training in eFAST is non-standardized. Sensitivity was considerably lower than the literature suggests. Positive resident-performed eFAST is generally accurate. We recommend a standardized approach to resident training in eFAST.

Assessing the efficacy of simulation-based education for paramedics in extended focused assessment with sonography for trauma under physician guidance.

We investigated the effectiveness of simulation-based education in Focused Assessment with Sonography for Trauma (FAST) to increase the number of Emergency Medical Technicians (EMTs) capable of performing ultrasound examinations in vehicles under the guidance of a physician. Twenty-eight paramedics watched a 14-min video on the features of the ultrasound system, its use, and the scanning method for each part of the body. Each participant performed four FAST examinations using a portable ultrasound device, and the task performance was rated using the Task Specific Checklist (TSC) and Global Rating Scale (GRS). The time required for visualizing each examination site and each FAST was assessed. The mean time required for the first and fourth FAST was 144.6 ± 52.4 s and 90.5 ± 31.0 s, respectively. The time required for each test significantly decreased with repeated testing (p < 0.001). The time to complete FAST was significantly shortened for the pericardial cavity (33.4 ± 23.1/15.3 ± 10.6 s, p < 0.01), right thoracic cavity (25.2 ± 11.8/12.1 ± 8.3 s, p < 0.01), Morrison fossa (19.1 ± 10.8/10.8 ± 6.3 s, p < 0.05), and left thoracic cavity (19.0 ± 8.3/15.6 ± 8.3 s, p < 0.05). TSC and GRS scores were elevated, and all EMTs could obtain valid images. The combination of a brief video lecture and hands-on training significantly reduced the time required for FAST performance. Moreover, repeated practice enabled the EMTs to efficiently obtain accurate and clinically useful images.

Updates on the clinical integration of point-of-care ultrasound in pediatric emergency medicine.

PURPOSE OF REVIEW: There is expanding evidence for point-of-care ultrasound (POCUS) use in pediatric emergency medicine - this review highlights the benefits and challenges in the clinical integration of high-yield POCUS applications. Specifically, it will delve into POCUS applications during resuscitations, controversies of Focused Assessment with Sonography for Trauma (FAST) in pediatric trauma, POCUS-guided procedures, and examples of clinical pathways where POCUS can expedite definitive care. RECENT FINDINGS: POCUS can enhance diagnostic accuracy and aid in management of pediatric patients in shock and help identify reversible causes during cardiac arrest. The use of the FAST in pediatric blunt abdominal trauma remains nuanced - its proper use requires an integration with clinical findings and an appreciation of its limitations. POCUS has been shown to enhance safety and efficacy of procedures such as nerve blocks, incision & drainage, and intravenous access. Integrating POCUS into pathways for conditions such as intussusception and testicular torsion expedites downstream care. SUMMARY: POCUS enhances diagnostic efficiency and management in pediatric patients arriving at the ED with undifferentiated shock, cardiac arrest, or trauma. Additionally, POCUS improves procedural success and safety, and is integral to clinical pathways for expediting definitive care for various pediatric emergencies. Future research should continue to focus on the impact of POCUS on patient outcomes, ensuring user competency, and the expansion of POCUS into diverse settings.

Bioanalytical evaluation of wound depth and musculoskeletal injuries: Synergizing focused assessment with sonography for trauma with computed tomography/magnetic resonance imaging in orthopaedic trauma care.

Orthopaedic trauma care frequently necessitates prompt and precise assessment of musculoskeletal injuries and wound depth. The potential for improved diagnostic accuracy and patient outcomes exists with the integration of sophisticated imaging modalities such as computed tomography (CT) and magnetic resonance imaging (MRI) with focused assessment with sonography for trauma (FAST). The purpose of this research was to examine the benefits and drawbacks of this integrative method in the clinical environment. From June 2022 to September 2023, 250 patients who were admitted to Ningbo University Affiliated People's Hospital, participated in this cross-sectional observational study. Following the administration of FAST, CT and MRI were utilized to evaluate orthopaedic injuries and skin wounds in patients. Analyses of data centred on the precision of diagnoses, the influence of treatment decisions and patient outcomes. Aged and gendered differently, the study participants sustained the variety of injuries and superficial wounds that were predominantly the result of traffic accidents. The FAST assay exhibited sensitivity of 65%, specificity of 80% and 72% overall accuracy. MRI demonstrated the finest diagnostic performance (85% sensitivity, 95% specificity and 89% accuracy), whereas CT scans offered improved diagnostic efficacy (80% sensitivity, 90% specificity and 84% accuracy). Treatment decisions were substantially impacted by integration of these imaging modalities, resulting in modifications in 20%-35% of cases, depending on the specific modality employed. Specifically, MRI played a pivotal role in informing treatment approaches, influencing non-surgical as well as surgical procedures. This study substantiates the significant advantages of integrating FAST with CT and MRI in orthopaedic trauma care, particularly in the accurate assessment of wound depth. The synergistic use of these imaging techniques not only enhances diagnostic precision but also positively impacts treatment strategies and patient outcomes, emphasizing the need for a comprehensive diagnostic approach in trauma care settings.

Evaluation of Focused Assessment With Sonography for Trauma Completeness of Children in the Clinical Setting.

OBJECTIVES: We evaluated the completeness of real-world Focused Assessment with Sonography for Trauma (FAST) in children after blunt abdominal trauma by benchmarking against established expert guidelines. METHODS: We conducted a retrospective cohort study, analyzing a random sample of FASTs from two urban pediatric emergency departments. Two experts reviewed and labeled all FASTs for completeness using a predefined guideline of 5 anatomic views and 30 landmarks. We compared frequencies of views and landmarks as medians with interquartile ranges. RESULTS: We analyzed 200 FASTs, consisting of 1636 video clips, performed by 31 clinicians representing 198 children with a median age of 10 years (IQR 5,14). Over half of FASTs (52%) had all 5 views. The right upper quadrant view was most commonly visualized (96.5%), and suprapubic sagittal was least (65%). None of the FASTs included all 30 landmarks, ranging from 0 to 28 and median of 19 (IQR 15,23). The least visualized landmark of the right and left upper quadrants was caudal liver edge (60%) and splenic tip (64%), respectively. In the pericardial view, it was left atrium (45%). In both transverse and sagittal pelvic views, retro-uterine space was least visualized in girls, 21 and 29% respectively. CONCLUSIONS: In our study, most FAST views and landmarks were visualized. However, the pelvic sagittal view was the least frequently visualized view, and caudal liver edge was the least visualized landmark. Future research should evaluate if variability in visualizing FAST views and landmarks correlates with inconsistencies in diagnostic test performance.

Ascending with ultrasound: telementored eFAST in flight-a feasibility study.

PURPOSE: Teleultrasound uses telecommunication technologies to transmit ultrasound images from a remote location to an expert who guides the acquisition of images and interprets them in real time. Multiple studies have demonstrated the feasibility of teleultrasound. However, its application during helicopter flight using long-term evolution (LTE) for streaming has not been studied. Therefore, we conducted a study to examine the feasibility of teleultrasound in an Airbus H145 helicopter. METHODS: Four anesthesiologists and one military physician were recruited to perform telementored extended Focused Assessment with Sonography in Trauma (eFAST) during nine helicopter flights, each with a unique healthy volunteer. A radiologist was recruited as a remote expert, guiding the physicians in their examinations. The examining physicians reported the user experience of telementored eFAST on a questionnaire, while the remote expert rated the diagnostic quality of the images on a 1-5 Likert scale. In addition, we measured the duration of the examinations and key LTE network parameters including signal strength, quality, and continuity. RESULTS: The images were rated to an average of 4.9 by the remote expert, corresponding to good diagnostic quality. The average duration of telementored eFAST was 05:54 min. LTE coverage was negatively affected by proximity to urban areas and ceased above 2000 ft altitude. Occasional audio problems were addressed by using the Voice over LTE network for communication. The examining physicians unanimously reported on the questionnaire that they would use telementored eFAST on patients. CONCLUSION: Telementored eFAST is feasible in ambulance helicopters and can produce images of good diagnostic quality. However, it relies on stable LTE coverage, which is influenced by many factors, including the helicopter's altitude and flight path. Furthermore, its benefit on patient outcomes remains to be proven.

Education in Focused Assessment With Sonography for Trauma Using Immersive Virtual Reality: A Prospective, Interventional Cohort Study and Non-inferiority Analysis With a Historical Control.

OBJECTIVE: Focused assessment with sonography for trauma (FAST) is a valuable ultrasound procedure in emergency settings, and there is a need for evidence-based education in FAST to ensure competencies. Immersive virtual reality (IVR) is a progressive training modality gaining traction in the field of ultrasound training. IVR holds several economic and practical advantages to the common instructor-led FAST courses using screen-based simulation (SBS). METHODS: This prospective, interventional cohort study investigated whether training FAST using IVR unsupervised and out-of-hospital was non-inferior to a historical control group training at a 90 min SBS course in terms of developing FAST competencies in novices. Competencies were assessed in both groups using the same post-training simulation-based FAST test with validity evidence, and a non-inferiority margin of 2 points was chosen. RESULTS: A total of 27 medical students attended the IVR course, and 27 junior doctors attended the SBS course. The IVR group trained for a median time of 117 min and scored a mean 14.2 ± 2.0 points, compared with a mean 13.7 ± 2.5 points in the SBS group. As the lower bound of the 95% confidence interval at 13.6 was within the range of the non-inferiority margin (11.7-13.7 points), training FAST in IVR for a median of 117 min was found non-inferior to training at a 90 min SBS course. No significant correlation was found between time spent in IVR and test scores. CONCLUSION: Within the limitations of the use of a historical control group, the results suggest that IVR could be an alternative to SBS FAST training and suitable for unsupervised, out-of-hospital courses in basic FAST competencies.

Focused Assessment with Sonography for Trauma (FAST) Exam: Image Acquisition.

Over the past twenty years, the Focused Assessment with Sonography for Trauma (FAST) exam has transformed the care of patients presenting with a combination of trauma (blunt or penetrating) and hypotension. In these hemodynamically unstable trauma patients, the FAST exam permits rapid and noninvasive screening for free pericardial or peritoneal fluid, the latter of which implicates intra-abdominal injury as a likely contributor to the hypotension and justifies emergent abdominal surgical exploration. Further, the abdominal portion of the FAST exam can also be used outside of the trauma setting to screen for free peritoneal fluid in patients who become hemodynamically unstable in any context, including after procedures that may inadvertently injure abdominal organs. These "non-trauma" situations of hemodynamic instability are often triaged by providers from specialties other than emergency medicine or trauma surgery who are not familiar with the FAST exam. Therefore, there is a need to promulgate knowledge about the FAST exam to all clinicians caring for critically ill patients. Toward this end, this article describes FAST exam image acquisition: patient positioning, transducer selection, image optimization, and exam limitations. Since the free fluid is likely to be found in specific anatomic locations that are unique for each canonical FAST exam view, this work centers on the unique image acquisition considerations for each window: subcostal, right upper quadrant, left upper quadrant, and pelvis.

Ultrasound Rounds: Anesthesiologist-Performed Intraoperative Point-of-Care Focused Assessment With Sonography in Trauma Examination Changes Surgical Management.

Focused Assessment with Sonography in Trauma (FAST) examinations have been performed for decades by surgeons during initial patient presentation for emergency care and surgical planning, as well as for guiding resuscitation. This case highlights how use of intraoperative FAST examinations performed by anesthesiologists can dramatically change patient management. Use by anesthesiologists perioperatively is an important skill, although it is not widely practiced.

[Intra-abdominal vascular injuries after blunt abdominal trauma]. / Intraabdominelle Gefäßverletzungen nach stumpfem Bauchtrauma.

Vascular injuries and hemorrhaging are serious potential complications in the management of patients with blunt abdominal trauma. The treatment depends on the extent and localization and can range from surveillance to endovascular treatment up to open surgery. The keys to success include the focused assessment with sonography for trauma (FAST) management and timely decision making. Abdominal vascular trauma continues to be a difficult problem and open and endovascular techniques continue to evolve in order to address this complex disease process.

Using Deep Learning to Detect the Presence and Location of Hemoperitoneum on the Focused Assessment with Sonography in Trauma (FAST) Examination in Adults.

Abdominal ultrasonography has become an integral component of the evaluation of trauma patients. Internal hemorrhage can be rapidly diagnosed by finding free fluid with point-of-care ultrasound (POCUS) and expedite decisions to perform lifesaving interventions. However, the widespread clinical application of ultrasound is limited by the expertise required for image interpretation. This study aimed to develop a deep learning algorithm to identify the presence and location of hemoperitoneum on POCUS to assist novice clinicians in accurate interpretation of the Focused Assessment with Sonography in Trauma (FAST) exam. We analyzed right upper quadrant (RUQ) FAST exams obtained from 94 adult patients (44 confirmed hemoperitoneum) using the YoloV3 object detection algorithm. Exams were partitioned via fivefold stratified sampling for training, validation, and hold-out testing. We assessed each exam image-by-image using YoloV3 and determined hemoperitoneum presence for the exam using the detection with highest confidence score. We determined the detection threshold as the score that maximizes the geometric mean of sensitivity and specificity over the validation set. The algorithm had 95% sensitivity, 94% specificity, 95% accuracy, and 97% AUC over the test set, significantly outperforming three recent methods. The algorithm also exhibited strength in localization, while the detected box sizes varied with a 56% IOU averaged over positive cases. Image processing demonstrated only 57-ms latency, which is adequate for real-time use at the bedside. These results suggest that a deep learning algorithm can rapidly and accurately identify the presence and location of free fluid in the RUQ of the FAST exam in adult patients with hemoperitoneum.

Focused and Extended Focused Assessment With Sonography for Trauma.

Timing is crucial when caring for an injured patient, and the evaluation requires a systematic, rapid, and thorough assessment to identify and treat immediate life-threatening injuries. An integral component of this assessment is the Focused Assessment with Sonography for Trauma (FAST) and the extended FAST (eFAST). These assessments allow for a rapid, noninvasive, portable, accurate, repeatable, and inexpensive means of diagnosing internal injury to the abdomen, chest, and pelvis. Understanding the basic principles of ultrasonography, having a thorough familiarity with the equipment, and being knowledgeable in anatomy allow the bedside practitioner to use this tool to rapidly assess injured patients. This article reviews the basic tenets that underpin the FAST and eFAST evaluations. Practical interventions and tips are provided to assist novice operators-all with the goal of decreasing the learning curve.

Artificial intelligence evaluation of focused assessment with sonography in trauma.

BACKGROUND: The focused assessment with sonography in trauma (FAST) is a widely used imaging modality to identify the location of life-threatening hemorrhage in a hemodynamically unstable trauma patient. This study evaluates the role of artificial intelligence in interpretation of the FAST examination abdominal views, as it pertains to adequacy of the view and accuracy of fluid survey positivity. METHODS: Focused assessment with sonography for trauma examination images from 2015 to 2022, from trauma activations, were acquired from a quaternary care level 1 trauma center with more than 3,500 adult trauma evaluations, annually. Images pertaining to the right upper quadrant and left upper quadrant views were obtained and read by a surgeon or radiologist. Positivity was defined as fluid present in the hepatorenal or splenorenal fossa, while adequacy was defined by the presence of both the liver and kidney or the spleen and kidney for the right upper quadrant or left upper quadrant views, respectively. Four convolutional neural network architecture models (DenseNet121, InceptionV3, ResNet50, Vgg11bn) were evaluated. RESULTS: A total of 6,608 images, representing 109 cases were included for analysis within the "adequate" and "positive" data sets. The models relayed 88.7% accuracy, 83.3% sensitivity, and 93.6% specificity for the adequate test cohort, while the positive cohort conferred 98.0% accuracy, 89.6% sensitivity, and 100.0% specificity against similar models. Augmentation improved the accuracy and sensitivity of the positive models to 95.1% accurate and 94.0% sensitive. DenseNet121 demonstrated the best accuracy across tasks. CONCLUSION: Artificial intelligence can detect positivity and adequacy of FAST examinations with 94% and 97% accuracy, aiding in the standardization of care delivery with minimal expert clinician input. Artificial intelligence is a feasible modality to improve patient care imaging interpretation accuracy and should be pursued as a point-of-care clinical decision-making tool. LEVEL OF EVIDENCE: Diagnostic Test/Criteria; Level III.

Impact of Telemedicine on Extended Focused Assessment With Sonography for Trauma Performance and Workload by Critical Care Transport Personnel.

INTRODUCTION: There are currently no reports on whether telementoring for extended focused assessment with sonography for trauma (eFAST) improves critical care transport providers' performance in prehospital settings. Our objective was to determine the impact of teleguidance on eFAST performance and quantify workload experience. METHODS: Eight trauma injury modules were selected on simulated patients. Critical care transport (CCT) providers were tasked to complete one independent and one emergency physician-telementored eFAST. The time to completion and the percent of correct findings were obtained. Participants completed the NASA Task Load Index after each iteration to assess workload. RESULTS: Eight independent and 8 telementored eFASTs were completed. The mean times to complete the independent and telementored eFAST were 5 minutes 16 seconds (95% confidence interval [CI], 3 minutes 32 seconds, 6 minutes 59 seconds) and 8 minutes 27 seconds (95% CI, 5 minutes 14 seconds, 11 minutes 39 seconds), respectively (P = .06). The percentage of correctly identified injuries for the independent versus the teleguided eFAST was 65% versus 92.5% (P = .01). The CCT providers experienced higher mental (P = .004), temporal (P = .01), and effort (P = .004) demands; greater frustration (P = .001); and subjective lower performance (P = .003) during independent trials. The emergency physician experienced higher mental (P = .001), temporal (P = .02), effort (P = .005), and frustration (P = .001) demands than the CCT members. CONCLUSION: The teleguided eFAST yielded higher accuracy than the independent eFAST. The CCT providers relied on teleguidance of the remote physician when performing the eFAST. Teleguidance may improve the accuracy of ultrasounds performed by prehospital personnel in real-life scenarios.

The Effect of BMI on eFAST Accuracy in Trauma by Residents in the Emergency Room.

Blunt trauma patients are often evaluated with extended focused assessment with sonography for trauma (eFAST). eFAST is a noninvasive, rapid, ultrasound-guided assessment for hemoperitoneum, pericardial effusion, and hemopneumothorax. Specificity and sensitivity are as high as 95% and 74%, respectively. Research suggests obesity confers increased morbidity and mortality and is an independent risk factor for trauma death. A previous study demonstrated that a BMI change from 36 to 40 changed the odds ratio for inaccurate eFAST from 1.85 to 3.12. Our current prospective data collection is 202 consecutive blunt trauma patients from 5/13/22 to 8/18/22 receiving an eFAST and a CT/OR for comparison. Odds ratio of inaccurate eFAST increased by 5.65% for each increase of 1 kg/m3 of BMI (95% Cl 0.1%-10.8%). This research also investigated surgical resident eFAST accuracy to improve patient outcomes through the implementation of individualized training in normal and obese models.

Effect of the Extended Focused Assessment With Sonography for Trauma on the Screening Performance of the National Emergency X-Radiography Utilization Study Chest Decision Instrument.

STUDY OBJECTIVE: Developed to decrease unnecessary thoracic computed tomography use in adult blunt trauma patients, the National Emergency X-Radiography Utilization Study (NEXUS) Chest clinical decision instrument does not include the extended Focused Assessment with Sonography in Trauma (eFAST). We assessed whether eFAST improves the NEXUS Chest clinical decision instrument's diagnostic performance and may replace the chest radiograph (CXR) as a predictor variable. METHODS: We performed a secondary analysis of prospective data from 8 Level I trauma centers from 2011-2014. We compared performance of modified clinical decision instruments that (1) added eFAST as a predictor (eFAST-added clinical decision instrument), and (2) replaced CXR with eFAST (eFAST-replaced clinical decision instrument), in screening for blunt thoracic injuries. RESULTS: One thousand nine hundred fifty-seven patients had documented computed tomography, CXR, clinical NEXUS criteria, and adequate eFAST; 624 (31.9%) patients had blunt thoracic injuries, and 126 (6.4%) had major injuries. Compared to the NEXUS Chest clinical decision instrument, the eFAST-added clinical decision instrument demonstrated unchanged screening performance for major injury (sensitivity 0.98 [0.94 to 1.00], specificity 0.28 [0.26 to 0.30]) or any injury (sensitivity 0.97 [0.95 to 0.98], specificity 0.21 [0.19 to 0.23]). The eFAST-replaced clinical decision instrument demonstrated unchanged sensitivity for major injury (sensitivity 0.93 [0.87 to 0.97], specificity 0.31 [0.29 to 0.34]) and decreased sensitivity for any injury (0.93 [0.91 to 0.951] versus 0.97 [0.953 to 0.98]). CONCLUSION: In our secondary analysis, adding eFAST as a predictor variable did not improve the diagnostic screening performance of the original NEXUS Chest clinical decision instrument; eFAST cannot replace the CXR criterion of the NEXUS Chest clinical decision instrument.

Remote Instruction in Focused Assessment With Sonography in Trauma (FAST) Exams for Surgery Residents: A Pilot Study.

BACKGROUND: The Focused Assessment with Sonography in Trauma (FAST) exam is an important component to the evaluation of trauma patients. With advances in technology and meeting limitations due to COVID-19, remote instruction and learning have gained popularity. We sought to determine whether remote instruction of FAST exams was feasible as sustainable surgical education and a possible alternative to traditional in-person teaching. METHODS: General surgery residents completed a baseline survey and skills assessment on FAST exams and were then randomized to remote or in-person instruction. The remote group participated in an instructional session with a content expert through video conference and then practiced on a simulated mannequin while the expert remotely provided feedback. The in-person group received the experience with the content expert in the room. Both groups completed a post-course survey immediately after the session and a follow-up survey and objective assessment at six-months. Results were compared with two-way analysis of variance (ANOVA). RESULTS: 14 residents underwent the curriculum, seven in each group. There was a significant increase in self-reported confidence when comparing pre- and immediate post-course results for both the remote and in-person groups. At six months, confidence scores remained elevated and skill assessment scores improved, although the latter did not reach significance. There was no significant difference in post-course results between the groups. CONCLUSIONS: Remote instruction of FAST exams was feasible. Pilot data demonstrated an increase in confidence and suggest outcomes that are similar to in-person instruction, which has positive implications for future remote educational and potentially clinical initiatives.

Deep Learning for FAST Quality Assessment.

OBJECTIVES: To determine the feasibility of using a deep learning (DL) algorithm to assess the quality of focused assessment with sonography in trauma (FAST) exams. METHODS: Our dataset consists of 441 FAST exams, classified as good-quality or poor-quality, with 3161 videos. We first used convolutional neural networks (CNNs), pretrained on the Imagenet dataset and fine-tuned on the FAST dataset. Second, we trained a CNN autoencoder to compress FAST images, with a 20-1 compression ratio. The compressed codes were input to a two-layer classifier network. To train the networks, each video was labeled with the quality of the exam, and the frames were labeled with the quality of the video. For inference, a video was classified as poor-quality if half the frames were classified as poor-quality by the network, and an exam was classified as poor-quality if half the videos were classified as poor-quality. RESULTS: The results with the encoder-classifier networks were much better than the transfer learning results with CNNs. This was primarily because the Imagenet dataset is not a good match for the ultrasound quality assessment problem. The DL models produced video sensitivities and specificities of 99% and 98% on held-out test sets. CONCLUSIONS: Using an autoencoder to compress FAST images is a very effective way to obtain features that can be used to predict exam quality. These features are more suitable than those obtained from CNNs pretrained on Imagenet.