-
Neurocritical Care Dec 2021To qualitatively and quantitatively summarize curricula, teaching methods, and effectiveness of educational programs for training bedside care providers (non-experts) in... (Review)
Review
OBJECTIVE
To qualitatively and quantitatively summarize curricula, teaching methods, and effectiveness of educational programs for training bedside care providers (non-experts) in the performance and screening of adult electroencephalography (EEG) for nonconvulsive seizures and other patterns.
METHODS
PRISMA methodological standards were followed. MEDLINE, EMBASE, Cochrane, CINAHL, WOS, Scopus, and MedEdPORTAL databases were searched from inception until February 26, 2020 with no restrictions. Abstract and full-text review was completed in duplicate. Studies were included if they were original research; involved non-experts performing, troubleshooting, or screening adult EEG; and provided qualitative descriptions of curricula and teaching methods and/or quantitative assessment of non-experts (vs gold standard EEG performance by neurodiagnostic technologists or interpretation by neurophysiologists). Data were extracted in duplicate. A content analysis and a meta-narrative review were performed.
RESULTS
Of 2430 abstracts, 35 studies were included. Sensitivity and specificity of seizure identification varied from 38 to 100% and 65 to 100% for raw EEG; 40 to 93% and 38 to 95% for quantitative EEG, and 95 to 100% and 65 to 85% for sonified EEG, respectively. Non-expert performance of EEG resulted in statistically significant reduced delay (86 min, p < 0.0001; 196 min, p < 0.0001; 667 min, p < 0.005) in EEG completion and changes in management in approximately 40% of patients. Non-experts who were trained included physicians, nurses, neurodiagnostic technicians, and medical students. Numerous teaching methods were utilized and often combined, with instructional and hands-on training being most common.
CONCLUSIONS
Several different bedside providers can be educated to perform and screen adult EEG, particularly for the purpose of diagnosing nonconvulsive seizures. While further rigorous research is warranted, this review demonstrates several potential bridges by which EEG may be integrated into the care of critically ill patients.
Topics: Adult; Clinical Competence; Electroencephalography; Humans; Physicians; Seizures; Sensitivity and Specificity
PubMed: 33591537
DOI: 10.1007/s12028-020-01172-2 -
The Tohoku Journal of Experimental... Dec 2022Imaging features of the lung in postmortem computed tomography (CT) scans have been reported in drowning cases. However, it is difficult for forensic pathologists with...
Imaging features of the lung in postmortem computed tomography (CT) scans have been reported in drowning cases. However, it is difficult for forensic pathologists with limited experience to distinguish subtle differences in CT images. In this study, artificial intelligence (AI) with deep learning capability was used to diagnose drowning in postmortem CT images, and its performance was evaluated. The samples consisted of high-resolution CT images of the chest of 153 drowned and 160 non-drowned bodies captured by an 8- or 64-row multislice CT system. The images were captured with an image slice thickness of 1.0 mm and spacing of 30 mm, and 28 images were typically captured. A modified AlexNet was used as the AI architecture. The output result was the drowning probability for each component image. To evaluate the performance of the proposed model, the area under the receiver operating characteristic curve (AUC) was analyzed, and the AUC value of 0.95 was obtained. This indicates that the proposed AI architecture is a useful and powerful complementary testing approach for diagnosing drowning in postmortem CT images. Notably, the accuracy was 81% (62/77) for cases in which resuscitation was performed, and 92% (216/236) for cases in which resuscitation was not attempted. Therefore, the proposed AI method should not be used to diagnose the cause of death when aggressive cardiopulmonary resuscitation was performed. Additionally, because honeycomb lungs are likely to exhibit different morphologies, emphysema cases should also be treated with caution when the proposed AI method is used to diagnose drowning.
Topics: Humans; Drowning; Artificial Intelligence; Tomography, X-Ray Computed; Lung; ROC Curve
PubMed: 36384859
DOI: 10.1620/tjem.2022.J097 -
World Journal of Surgical Oncology Jan 2019In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis...
BACKGROUND
In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis system was established by deep learning using the YOLOv2 neural network. The performance of the system in the diagnosis of thyroid nodules was evaluated, and the application value of artificial intelligence in clinical practice was investigated.
METHODS
The ultrasound images of 276 patients were retrospectively selected. The diagnoses of the radiologists were determined according to the Thyroid Imaging Reporting and Data System; the images were automatically recognized and diagnosed by the established artificial intelligence system. Pathological diagnosis was the gold standard for the final diagnosis. The performances of the established system and the radiologists in diagnosing the benign and malignant thyroid nodules were compared.
RESULTS
The artificial intelligence diagnosis system correctly identified the lesion area, with an area under the receiver operating characteristic (ROC) curve of 0.902, which is higher than that of the radiologists (0.859). This finding indicates a higher diagnostic accuracy (p = 0.0434). The sensitivity, positive predictive value, negative predictive value, and accuracy of the artificial intelligence diagnosis system for the diagnosis of malignant thyroid nodules were 90.5%, 95.22%, 80.99%, and 90.31%, respectively, and the performance did not significantly differ from that of the radiologists (p > 0.05). The artificial intelligence diagnosis system had a higher specificity (89.91% vs 77.98%, p = 0.026).
CONCLUSIONS
Compared with the performance of experienced radiologists, the artificial intelligence system has comparable sensitivity and accuracy for the diagnosis of malignant thyroid nodules and better diagnostic ability for benign thyroid nodules. As an auxiliary tool, this artificial intelligence diagnosis system can provide radiologists with sufficient assistance in the diagnosis of benign and malignant thyroid nodules.
Topics: Adult; Aged; Diagnosis, Differential; Female; Humans; Image Interpretation, Computer-Assisted; Male; Middle Aged; Neural Networks, Computer; Predictive Value of Tests; Prognosis; ROC Curve; Retrospective Studies; Thyroid Gland; Thyroid Nodule; Ultrasonography; Young Adult
PubMed: 30621704
DOI: 10.1186/s12957-019-1558-z -
European Journal of Emergency Medicine... Oct 2021Current guidelines recommend noncontrast computed tomography (NCCT) followed by lumbar puncture for the diagnosis of subarachnoid hemorrhage (SAH). Alternative... (Observational Study)
Observational Study
BACKGROUND AND IMPORTANCE
Current guidelines recommend noncontrast computed tomography (NCCT) followed by lumbar puncture for the diagnosis of subarachnoid hemorrhage (SAH). Alternative strategies, including clinical risk stratification and CT angiography (CTA), are emerging.
OBJECTIVE
To evaluate alternative strategies to current guidelines through clinical risk stratification.
DESIGN, SETTING AND PARTICIPANTS
Single-site, retrospective observational study of patients with SAH suspicion, from 2011 to 2016. We combined results of each investigation (NCCT, CTA and lumbar puncture) with a clinical risk assessment, including Ottawa score.
EXPOSURE
Comparing the current strategy (NCCT ± lumbar puncture if negative CT) to alternative strategies (NCCT + CTA ± lumbar puncture if high clinical risk or negative CT and onset of headache ≥12 h o dds ratio ≥24 h).
OUTCOME MEASURE AND ANALYSIS
Main outcome was diagnosis of SAH at hospital discharge. Secondary outcomes were death from all causes and need for invasive procedures at 28 days. We used sensitivity, specificity, positive predictive value and negative predictive value (NPV) to evaluate the diagnostic performance of three strategies.
MAIN RESULTS
310 patients were included. SAH was diagnosed in 8 cases (2.6%), none died and 7 (2.2%) had a surgical procedure. Performances of different strategies were not statistically different. NPVs were 99.7% [95% Confidence interval (CI), 98.2-100%] for strategy 1 and 100% (95% CI, 98.8-100%) for strategies 2 and 3. More than 4000 lumbar punctures are needed to diagnose one SAH when CTA is performed within 24 h of symptoms' onset and absence of high-risk criteria.
CONCLUSION
Clinical risk stratification and CTA strategy are well-tolerated and effective for diagnosis of SAH, avoiding systematic use of lumbar puncture.
Topics: Emergency Service, Hospital; Humans; Retrospective Studies; Risk Assessment; Spinal Puncture; Subarachnoid Hemorrhage
PubMed: 33709998
DOI: 10.1097/MEJ.0000000000000804 -
The American Journal of Emergency... Apr 2019To assess the sensitivity and specificity of emergency physician-performed point-of-care ultrasonography (EP-POCUS) for diagnosing acute appendicitis (AA). (Meta-Analysis)
Meta-Analysis
OBJECTIVE
To assess the sensitivity and specificity of emergency physician-performed point-of-care ultrasonography (EP-POCUS) for diagnosing acute appendicitis (AA).
MATERIAL AND METHODS
The PubMed and EMBASE databases were searched, and the diagnostic performance of EP-POCUS was evaluated using bivariate modeling and hierarchical summary receiver operating characteristic curves. Subgroup analysis was performed for pediatric patients to compare EP-POCUS and radiologist-performed ultrasonography (RADUS). Meta-regression analyses were performed according to patient and study characteristics.
RESULTS
In 17 studies (2385 patients), EP-POCUS for diagnosing AA exhibited a pooled sensitivity of 84% (95% confidence interval [CI]: 72%-92%) and a pooled specificity of 91% (95% CI: 85%-95%), with even better diagnostic performance for pediatric AA (sensitivity: 95%, 95% CI: 75%-99%; specificity: 95%, 95% CI: 85%-98%). A direct comparison revealed no significant differences (p = 0.18-0.85) between the diagnostic performances of EP-POCUS (sensitivity: 81%, 95% CI: 61%-90%; specificity: 89%, 95% CI: 77%-95%) and RADUS (sensitivity: 74%, 95% CI: 65%-81%; specificity: 97%, 95% CI: 93%-98%). The meta-regression analyses revealed that study location, AA proportion, and mean age were sources of heterogeneity. Higher sensitivity and specificity tended to be associated with an appendix diameter cut-off value of 7 mm and the EP as the initial operator.
CONCLUSION
The diagnostic performances of EP-POCUS and RADUS were excellent for AA, with EP-POCUS having even better performance for pediatric AA. Accurate diagnoses may be achieved when the attending EP is the initial POCUS operator and uses a 7-mm cut-off value.
Topics: Acute Disease; Appendicitis; Appendix; Emergency Service, Hospital; Humans; Point-of-Care Systems; ROC Curve; Sensitivity and Specificity; Ultrasonography
PubMed: 30017693
DOI: 10.1016/j.ajem.2018.07.025 -
European Journal of Pediatrics Mar 2024In the realm of emergency medicine, the swift adoption of lung ultrasound (LU) has extended from the adult population to encompass pediatric and neonatal intensivists.... (Review)
Review
In the realm of emergency medicine, the swift adoption of lung ultrasound (LU) has extended from the adult population to encompass pediatric and neonatal intensivists. LU stands out as a bedside, replicable, and cost-effective modality, distinct in its avoidance of ionizing radiations, a departure from conventional chest radiography. Recent years have witnessed a seamless adaptation of experiences gained in the adult setting to the neonatal and pediatric contexts, underscoring the versatility of bedside Point of care ultrasound (POCUS). This adaptability has proven reliable in diagnosing common pathologies and executing therapeutic interventions, including chest drainage, and central and peripheral vascular cannulation. The surge in POCUS utilization among neonatologists and pediatric intensivists is notable, spanning economically advanced Western nations with sophisticated, high-cost intensive care facilities and extending to low-income countries. Within the neonatal and pediatric population, POCUS has become integral for diagnosing and monitoring respiratory infections and chronic and acute lung pathologies. This, in turn, contributes to a reduction in radiation exposure during critical periods of growth, thereby mitigating oncological risks. Collaboration among various national and international societies has led to the formulation of guidelines addressing both the clinical application and regulatory aspects of operator training. Nevertheless, unified guidelines specific to the pediatric and neonatal population remain lacking, in contrast to the well-established protocols for adults. The initial application of POCUS in neonatal and pediatric settings centered on goal-directed echocardiography. Pivotal developments include expert statements in 2011, the UK consensus statement on echocardiography by neonatologists, and European training recommendations. The Australian Clinician Performed Ultrasound (CPU) program has played a crucial role, providing a robust academic curriculum tailored for training neonatologists in cerebral and cardiac assessment. Notably, the European Society for Paediatric and Neonatal Intensive Care (ESPNIC) recently disseminated evidence-based guidelines through an international panel, delineating the use and applications of POCUS in the pediatric setting. These guidelines are pertinent to any professional tending to critically ill children in routine or emergency scenarios. In light of the burgeoning literature, this paper will succinctly elucidate the methodology of performing an LU scan and underscore its primary indications in the neonatal and pediatric patient cohort. The focal points of this review comprise as follows: (1) methodology for conducting a lung ultrasound scan, (2) key ultrasonographic features characterizing a healthy lung, and (3) the functional approach: Lung Ultrasound Score in the child and the neonate. Conclusion: the aim of this review is to discuss the following key points: 1. How to perform a lung ultrasound scan 2. Main ultrasonographic features of the healthy lung 3. The functional approach: Lung Ultrasound Score in the child and the neonate What is Known: • Lung Ultrasound (LUS) is applied in pediatric and neonatal age for the diagnosis of pneumothorax, consolidation, and pleural effusion. • Recently, LUS has been introduced into clinical practice as a bedside diagnostic method for monitoring surfactant use in NARDS and lung recruitment in PARDS. What is New: • Lung Ultrasound (LUS) has proven to be useful in confirming diagnoses of pneumothorax, consolidation, and pleural effusion. • Furthermore, it has demonstrated effectiveness in monitoring the response to surfactant therapy in neonates, in staging the severity of bronchiolitis, and in PARDS.
Topics: Infant, Newborn; Adult; Child; Humans; Pneumothorax; Australia; Lung; Ultrasonography; Lung Diseases; Pleural Effusion; Radiography; Surface-Active Agents
PubMed: 38127086
DOI: 10.1007/s00431-023-05377-3 -
Sensors (Basel, Switzerland) Nov 2022Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an...
Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the best optimal features while reducing the amount of data. Lastly, diagnosis prediction (classification) is achieved using learnable classifiers. The novel framework for the extraction and selection of features is based on deep learning, auto-encoder, and ACO. The performance of the proposed approach is evaluated using two medical image datasets: chest X-ray (CXR) and magnetic resonance imaging (MRI) for the prediction of the existence of COVID-19 and brain tumors. Accuracy is used as the main measure to compare the performance of the proposed approach with existing state-of-the-art methods. The proposed system achieves an average accuracy of 99.61% and 99.18%, outperforming all other methods in diagnosing the presence of COVID-19 and brain tumors, respectively. Based on the achieved results, it can be claimed that physicians or radiologists can confidently utilize the proposed approach for diagnosing COVID-19 patients and patients with specific brain tumors.
Topics: Humans; COVID-19; Deep Learning; Diagnosis, Computer-Assisted; Brain Neoplasms; Computers
PubMed: 36433595
DOI: 10.3390/s22228999 -
Pediatric Emergency Care Nov 2021This study aimed to investigate the feasibility of point-of-care ultrasound (POCUS) for diagnosing hypertrophic pyloric stenosis (HPS) in the emergency department (ED).
OBJECTIVES
This study aimed to investigate the feasibility of point-of-care ultrasound (POCUS) for diagnosing hypertrophic pyloric stenosis (HPS) in the emergency department (ED).
METHODS
A retrospective study was conducted in infants aged younger than 90 days who were brought to the ED due to vomiting between January 2015 and December 2019. Of these, infants who were clinically suspected of having HPS and underwent ultrasound were included and categorized into 3 groups: POCUS only, POCUS followed by radiologist-performed ultrasound (RADUS), and RADUS only. All confirmative diagnoses of HPS were made by RADUS. The diagnostic performance of POCUS was analyzed, and the ED patient flow was compared between the POCUS-performed (POCUS only or POCUS followed by RADUS) and RADUS-only groups.
RESULTS
Overall, 171 patients with a median age of 34 days were included. Of these, 79 patients (46.2%) underwent POCUS only, and none had HPS; 50 patients (29.2%) underwent POCUS followed by RADUS; and 42 patients (24.5%) underwent RADUS only. Overall, 41 patients (24.0%) were diagnosed with HPS, and POCUS showed a sensitivity of 96.6% and specificity of 94.0%. In the total cohort, length of stay in the ED (EDLOS) was shorter in the POCUS-performed group than in the RADUS-only group (2.6 vs 3.8 hours, P = 0.015). Among non-HPS patients, time to disposition (1.8 vs 2.7 hours, P = 0.005) and EDLOS (2.0 vs 3.0 hours, P = 0.004) were shorter in the POCUS-performed group than in the RADUS-only group. Performing POCUS followed by RADUS did not significantly delay the treatment among HPS patients.
CONCLUSIONS
Point-of-care ultrasound is accurate and useful for diagnosing HPS and improved the ED patient flow by reducing EDLOS and door-to-disposition time in non-HPS patients.
Topics: Emergency Service, Hospital; Feasibility Studies; Humans; Infant; Point-of-Care Systems; Pyloric Stenosis, Hypertrophic; Retrospective Studies; Ultrasonography
PubMed: 34550920
DOI: 10.1097/PEC.0000000000002532 -
Computer Methods and Programs in... Jun 2023Sleep quality is associated with wellness, and its assessment can help diagnose several disorders and diseases. Sleep analysis is commonly performed based on self-rating... (Review)
Review
BACKGROUND AND OBJECTIVES
Sleep quality is associated with wellness, and its assessment can help diagnose several disorders and diseases. Sleep analysis is commonly performed based on self-rating indices, sleep duration, environmental factors, physiologically and polysomnographic-derived parameters, and the occurrence of disorders. However, the correlation that has been observed between the subjective assessment and objective measurements of sleep quality is small. Recently, a few automated systems have been suugested to measure sleep quality to address this challenge. Sleep quality can be assessed by evaluating macrostructure-based sleep analysis via the examination of sleep cycles, namely Rapid Eye Movement (REM) and Non Rapid Eye Movement (NREM) with N1, N2, and N3 stages. However, macrostructure sleep analysis does not consider transitory phenomena like K-complexes and transient fluctuations, which are indispensable in diagnosing various sleep disorders. The CAP, part of the microstructure of sleep, may offer a more precise and relevant examination of sleep and can be considered one of the candidates to measure sleep quality and identify sleep disorders such as insomnia and apnea. CAP is characterized by very subtle changes in the brain's electroencephalogram (EEG) signals that occur during the NREM stage of sleep. The variations among these patterns in healthy subjects and subjects with sleep disorders can be used to identify sleep disorders. Studying CAP is highly arduous for human experts; thus, developing automated systems for assessing CAP is gaining momentum. Developing new techniques for automated CAP detection installed in clinical setups is essential. This paper aims to analyze the algorithms and methods presented in the literature for the automatic assessment of CAP and the development of CAP-based sleep markers that may enhance sleep quality assessment, helping diagnose sleep disorders.
METHODS
This literature survey examined the automated assessment of CAP and related parameters. We have reviewed 34 research articles, including fourteen ML, nine DL, and ten based on some other techniques.
RESULTS
The review includes various algorithms, databases, features, classifiers, and classification performances and their comparisons, advantages, and limitations of automated systems for CAP assessment.
CONCLUSION
A detailed description of state-of-the-art research findings on automated CAP assessment and associated challenges has been presented. Also, the research gaps have been identified based on our review. Further, future research directions are suggested for sleep quality assessment using CAP.
Topics: Humans; Sleep Stages; Polysomnography; Sleep; Sleep, REM; Electroencephalography; Sleep Wake Disorders
PubMed: 37037163
DOI: 10.1016/j.cmpb.2023.107471 -
IEEE Journal of Biomedical and Health... Dec 2022Chest X-ray (CXR) is commonly performed as an initial investigation in COVID-19, whose fast and accurate diagnosis is critical. Recently, deep learning has a great...
Chest X-ray (CXR) is commonly performed as an initial investigation in COVID-19, whose fast and accurate diagnosis is critical. Recently, deep learning has a great potential in detecting people who are suspected to be infected with COVID-19. However, deep learning resulting with black-box models, which often breaks down when forced to make predictions about data for which limited supervised information is available and lack inter-pretability, still is a major barrier for clinical integration. In this work, we hereby propose a semantic-powered explainable model-free few-shot learning scheme to quickly and precisely diagnose COVID-19 with higher reliability and transparency. Specifically, we design a Report Image Explanation Cell (RIEC) to exploit clinically indicators derived from radiology reports as interpretable driver to introduce prior knowledge at training. Meanwhile, multi-task collaborative diagnosis strategy (MCDS) is developed to construct N-way K-shot tasks, which adopts a cyclic and collaborative training approach for producing better generalization performance on new tasks. Extensive experiments demonstrate that the proposed scheme achieves competitive results (accuracy of 98.91%, precision of 98.95%, recall of 97.94% and F1-score of 98.57%) to diagnose COVID-19 and other pneumonia infected categories, even with only 200 paired CXR images and radiology reports for training. Furthermore, statistical results of comparative experiments show that our scheme provides an interpretable window into the COVID-19 diagnosis to improve the performance of the small sample size, the reliability and transparency of black-box deep learning models. Our source codes will be released on https://github.com/AI-medical-diagnosis-team-of-JNU/SPEMFSL-Diagnosis-COVID-19.
Topics: Humans; COVID-19; SARS-CoV-2; Neural Networks, Computer; COVID-19 Testing; Reproducibility of Results; Semantics; X-Rays; Deep Learning; Radiography, Thoracic
PubMed: 36074872
DOI: 10.1109/JBHI.2022.3205167