Artificial intelligence versus expert: a comparison of rapid visual inferior vena cava collapsibility assessment between POCUS experts and a deep learning algorithm

AI for the hemodynamic assessment of critically ill and surgical patients: focus on clinical applications

Several artificial intelligence (AI)-driven tools have emerged for the hemodynamic evaluation of critically ill and surgical patients. This article provides an overview of current developments and potential clinical applications of machine learning (ML) for blood pressure measurements, hypotension prediction, hemodynamic profiling, and echocardiography. ML algorithms have shown promise in enabling continuous, non-invasive blood pressure monitoring by analyzing pulse oximetry waveforms, though these methods require periodic calibration with traditional oscillometric brachial cuffs. Additionally, a variety of ML models have been trained to forecast impending hypotension. However, clinical research indicates that these algorithms often primarily rely on mean arterial pressure, leading to questions about their added predictive value. The issue of false-positive alerts is also significant and can result in unwarranted clinical interventions. In terms of hemodynamic profiling, ML algorithms have been proposed to automatically classify patients into specific hemodynamic endotypes. However, current evidence suggests these models tend to replicate conventional hemodynamic profiles found in medical textbooks or depicted on advanced hemodynamic monitors. This raises questions about their practical clinical utility, especially given occasional discrepancies that could impact treatment decisions. Point-of-care ultrasound (POCUS) has gained traction for evaluating cardiac function in patients experiencing circulatory shock. ML algorithms now embedded in some POCUS systems can assist by recognizing ultrasound images, guiding users for optimal imaging, automating and reducing the variability of key echocardiographic measurements. These capabilities are especially beneficial for novice operators, potentially enhancing accuracy and confidence in clinical decision-making. In conclusion, while several AI-based technologies show promise for refining hemodynamic assessment in both critically ill and surgical patients, their clinical value varies. Comprehensive validation studies and real-world testing are essential to identify which innovations will genuinely contribute to improving the quality of care.

Visualizing hemodynamics: innovative graphical displays and imaging techniques in anesthesia and critical care

The advancements in cardiovascular imaging over the past two decades have been significant. The miniaturization of ultrasound devices has greatly contributed to their widespread adoption in operating rooms and intensive care units. The integration of AI-enabled tools has further transformed the field by simplifying echocardiographic evaluations and enhancing the reproducibility of hemodynamic measurements, even for less experienced operators. Speckle tracking echocardiography offers a direct, visual, and quantitative assessment of myocardial shortening, serving as a compelling alternative to traditional methods for evaluating right and left ventricular systolic function. In critically ill patients, sublingual microcirculation imaging has revealed a high prevalence of microvascular alterations, which are markers of disease severity. The use of handheld vital microscopes enables the quantification of several key parameters, including vessel density, perfusion, red blood cell velocity, and the perfused vascular density. Such metrics are useful for evaluating microcirculatory health. The development of automated software marks a significant advance toward real-time bedside microvascular assessment. These advancements could eventually allow shock resuscitation to be tailored based on microvascular responses. In parallel with imaging advances, cardiac output monitors have evolved significantly. Once cumbersome devices displaying basic numerical data in tabular form, they now feature sleek, touch-screen interfaces integrated with visual decision-support tools. These tools synthesize hemodynamic data into intuitive graphical formats, allowing clinicians to quickly grasp the determinants of circulatory shock. This visual clarity supports more efficient and accurate decision-making, which may ultimately lead to improved patient care and outcomes.

The premise, promise, and perils of artificial intelligence in critical care cardiology

Artificial intelligence (AI) is an emerging technology with numerous healthcare applications. AI could prove particularly useful in the cardiac intensive care unit (CICU) where its capacity to analyze large datasets in real-time would assist clinicians in making more informed decisions. This systematic review aimed to explore current research on AI as it pertains to the CICU. A PRISMA search strategy was carried out to identify the pertinent literature on topics including vascular access, heart failure care, circulatory support, cardiogenic shock, ultrasound, and mechanical ventilation. Thirty-eight studies were included. Although AI is still in its early stages of development, this review illustrates its potential to yield numerous benefits in the CICU.

Overview of artificial intelligence in point-of-care ultrasound. New horizons for respiratory system diagnoses

Throughout the past decades ultrasonography did not prove to be a procedure of choice if regarded as part of the routine bedside examination. The reason was the assumption defining the lungs and the bone structures as impenetrable by ultrasound. Only during the recent several years has the approach to the use of such tool in clinical daily routines changed dramatically to offer so-called point-of-care ultrasonography (POCUS). Both vertical and horizontal artefacts became valuable sources of information about the patient's clinical condition, assisting therefore the medical practitioner in differential diagnosis and monitoring of the patient. What is important is that the information is delivered in real time, and the procedure itself is non-invasive. The next stage marking the progress made in this area of diagnostic imaging is the development of arti-ficial intelligence (AI) based on machine learning algorithms. This article is intended to present the available, innovative solutions of the ultrasound systems, including Smart B-line technology, to ensure automatic identification process, as well as interpretation of B-lines in the given lung area of the examined patient. The article sums up the state of the art in ultrasound artefacts and AI applied in POCUS.

Evaluation of an artificial intelligence-based system for echocardiographic estimation of right atrial pressure

Current noninvasive estimation of right atrial pressure (RAP) by inferior vena cava (IVC) measurement during echocardiography may have significant inter-rater variability due to different levels of observers' experience. Therefore, there is a need to develop new approaches to decrease the variability of IVC analysis and RAP estimation. This study aims to develop a fully automated artificial intelligence (AI)-based system for automated IVC analysis and RAP estimation. We presented a multi-stage AI system to identify the IVC view, select good quality images, delineate the IVC region and quantify its thickness, enabling temporal tracking of its diameter and collapsibility changes. The automated system was trained and tested on expert manual IVC and RAP reference measurements obtained from 255 patients during routine clinical workflow. The performance was evaluated using Pearson correlation and Bland-Altman analysis for IVC values, as well as macro accuracy and chi-square test for RAP values. Our results show an excellent agreement (r=0.96) between automatically computed versus manually measured IVC values, and Bland-Altman analysis showed a small bias of [Formula: see text]0.33 mm. Further, there is an excellent agreement ([Formula: see text]) between automatically estimated versus manually derived RAP values with a macro accuracy of 0.85. The proposed AI-based system accurately quantified IVC diameter, collapsibility index, both are used for RAP estimation. This automated system could serve as a paradigm to perform IVC analysis in routine echocardiography and support various cardiac diagnostic applications.

Artificial Intelligence (AI) versus POCUS Expert: A Validation Study of Three Automatic AI-Based, Real-Time, Hemodynamic Echocardiographic Assessment Tools

BACKGROUND

Point Of Care Ultra-Sound (POCUS) is an operator dependent modality. POCUS examinations usually include 'Eyeballing' the inspected anatomical structure without conducting accurate measurements due to complexity and insufficient time. Automatic real time measuring tools can make accurate measurements fast and simple and dramatically increase examination reliability while saving the operator much time and effort. In this study we aim to assess three automatic tools which are integrated into the Venue™ device by GE: the automatic ejection fraction, velocity time integral, and inferior vena cava tools in comparison to the gold standard-an examination by a POCUS expert.

METHODS

A separate study was conducted for each of the three automatic tools. In each study, cardiac views were acquired by a POCUS expert. Relevant measurements were taken by both an auto tool and a POCUS expert who was blinded to the auto tool's measurement. The agreement between the POCUS expert and the auto tool was measured for both the measurements and the image quality using a Cohen's Kappa test.

RESULTS

All three tools have shown good agreement with the POCUS expert for high quality views: auto LVEF (0.498; p < 0.001), auto IVC (0.536; p = 0.009), and the auto VTI (0.655; p = 0.024). Auto VTI has also shown a good agreement for medium quality clips (0.914; p < 0.001). Image quality agreement was significant for the auto EF and auto IVC tools.

CONCLUSIONS

The Venue™ show a high agreement with a POCUS expert for high quality views. This shows that auto tools can provide reliable real time assistance in performing accurate measurements, but do not reduce the need of a good image acquisition technique.

Artificial Intelligence-Augmented Pediatric Lung POCUS: A Pilot Study of Novice Learners

OBJECTIVE

Respiratory symptoms are among the most common chief complaints of pediatric patients in the emergency department (ED). Point-of-care ultrasound (POCUS) outperforms conventional chest X-ray and is user-dependent, which can be challenging to novice ultrasound (US) users. We introduce a novel concept using artificial intelligence (AI)-enhanced pleural sweep to generate complete panoramic views of the lungs, and then assess its accuracy among novice learners (NLs) to identify pneumonia.

METHODS

Previously healthy 0- to 17-year-old patients presenting to a pediatric ED with cardiopulmonary chief complaint were recruited. NLs received a 1-hour training on traditional lung POCUS and the AI-assisted software. Two POCUS-trained experts interpreted the images, which served as the criterion standard. Both expert and learner groups were blinded to each other's interpretation, patient data, and outcomes. Kappa was used to determine agreement between POCUS expert interpretations.

RESULTS

Seven NLs, with limited to no prior POCUS experience, completed examinations on 32 patients. The average patient age was 5.53 years (±1.07). The median scan time of 7 minutes (minimum-maximum 3-43; interquartile 8). Three (8.8%) patients were diagnosed with pneumonia by criterion standard. Sensitivity, specificity, and accuracy for NLs AI-augmented interpretation were 66.7% (confidence interval [CI] 9.4-99.1%), 96.5% (CI 82.2-99.9%), and 93.7% (CI 79.1-99.2%). The average image quality rating was 2.94 (±0.16) out of 5 across all lung fields. Interrater reliability between expert sonographers was high with a kappa coefficient of 0.8.

CONCLUSION

This study shows that AI-augmented lung US for diagnosing pneumonia has the potential to increase accuracy and efficiency.

Making Artificial Intelligence Lemonade Out of Data Lemons: Adaptation of a Public Apical Echo Database for Creation of a Subxiphoid Visual Estimation Automatic Ejection Fraction Machine Learning Algorithm

OBJECTIVES

A paucity of point-of-care ultrasound (POCUS) databases limits machine learning (ML). Assess feasibility of training ML algorithms to visually estimate left ventricular ejection fraction (EF) from a subxiphoid (SX) window using only apical 4-chamber (A4C) images.

METHODS

Researchers used a long-short-term-memory algorithm for image analysis. Using the Stanford EchoNet-Dynamic database of 10,036 A4C videos with calculated exact EF, researchers tested 3 ML training permeations. First, training on unaltered Stanford A4C videos, then unaltered and 90° clockwise (CW) rotated videos and finally unaltered, 90° rotated and horizontally flipped videos. As a real-world test, we obtained 615 SX videos from Harbor-UCLA (HUCLA) with EF calculations in 5% ranges. Researchers performed 1000 randomizations of EF point estimation within HUCLA EF ranges to compensate for ML and HUCLA EF mismatch, obtaining a mean value for absolute error (MAE) comparison and performed Bland-Altman analyses.

RESULTS

The ML algorithm EF mean MAE was estimated at 23.0, with a range of 22.8-23.3 using unaltered A4C video, mean MAE was 16.7, with a range of 16.5-16.9 using unaltered and 90° CW rotated video, mean MAE was 16.6, with a range of 16.3-16.8 using unaltered, 90° CW rotated and horizontally flipped video training. Bland-Altman showed weakest agreement at 40-45% EF.

CONCLUSIONS

Researchers successfully adapted unrelated ultrasound window data to train a POCUS ML algorithm with fair MAE using data manipulation to simulate a different ultrasound examination. This may be important for future POCUS algorithm design to help overcome a paucity of POCUS databases.

Deep Learning in Kidney Ultrasound: Overview, Frontiers, and Challenges

Ultrasonography is a practical imaging technique used in numerous health care settings. It is relatively inexpensive, portable, and safe, and it has dynamic capabilities that make it an invaluable tool for a wide variety of diagnostic and interventional studies. Recently, there has been a revolution in medical imaging using artificial intelligence (AI). A particularly potent form of AI is deep learning, in which the computer learns to recognize pixel or written data on its own without the selection of predetermined features, usually through a specific neural network architecture. Neural networks vary in architecture depending on their task, and key design considerations include the number of layers and complexity, data available, technical requirements, and domain knowledge. Deep learning models offer the potential for promising innovations to workflow, image quality, and vision tasks in sonography. However, there are key limitations and challenges in creating reliable and safe AI models for patients and clinicians.