-
BMC Infectious Diseases Mar 2020Congenital Cytomegalovirus (cCMV) is a serious global public health issue that can cause irreversible fetal and neonatal congenital defects in symptomatic or... (Review)
Review
BACKGROUND
Congenital Cytomegalovirus (cCMV) is a serious global public health issue that can cause irreversible fetal and neonatal congenital defects in symptomatic or asymptomatic newborns at birth. In absence of universal cCMV screening, the retrospective diagnosis of cCMV infection in children is only possible by examining Dried Blood Spot (DBS) samples routinely collected at birth and stored for different time spans depending on the newborn screening regulations in force in different countries. In this article, we summarize the arguments in favor of long-term DBS sample storage for detecting cCMV infection.
MAIN TEXT
CMV infection is the most common cause of congenital infection resulting in severe defects and anomalies that can be apparent at birth or develop in early childhood. Sensorineural hearing loss is the most frequent consequence of cCMV infection and may have a late onset and progress in the first years of life. The virological diagnosis of cCMV is essential for clinical research and public health practices. In fact, in order to assess the natural history of CMV infection and distinguish between congenital or acquired infection, children should be diagnosed early by analyzing biological samples collected in the first weeks of life (3 weeks by using viral culture and 2 weeks by molecular assays), which, unfortunately, are not always available for asymptomatic or mildly symptomatic children. It now seems possible to overcome this problem since the CMV-DNA present in the blood of congenitally infected newborns can be easily retrieved from the DBS samples on the Guthrie cards routinely collected and stored within 3 days from birth in the neonatal screening program for genetic and congenital diseases. Early collection and long-term storage are inexpensive methods for long-term bio-banking and are the key points of DBS testing for the detection of cCMV.
CONCLUSION
DBS sampling is a reliable and inexpensive method for long-term bio-banking, which enables to diagnose known infectious diseases - including cCMV - as well as diseases not jet recognized, therefore their storage sites and long-term storage conditions and durations should be the subject of political decision-making.
Topics: Cytomegalovirus Infections; Dried Blood Spot Testing; Hearing Loss, Sensorineural; Humans; Infant, Newborn; Neonatal Screening; Retrospective Studies
PubMed: 32164599
DOI: 10.1186/s12879-020-4941-z -
Beyond the wrist: Using a smartwatch electrocardiogram to detect electrocardiographic abnormalities.Archives of Cardiovascular Diseases Jan 2022When worn on the wrist, smartwatch electrocardiograms may provide important but incomplete information.
BACKGROUND
When worn on the wrist, smartwatch electrocardiograms may provide important but incomplete information.
AIMS
We sought to evaluate the added benefit of placing the smartwatch on the ankle and on the chest to diagnose various electrocardiographic abnormalities compared with 12-lead electrocardiograms.
METHODS
Two hundred and sixty patients with (n=189) or without (n=71) known cardiac disorders underwent 12-lead electrocardiogram and smartwatch electrocardiogram recordings of lead I (AW-I) and of leads I and II and pseudo chest leads V1 and V6 (AW-4). AW-I and AW-4 diagnoses (three-cardiologist consensus) were compared with 12-lead electrocardiogram diagnoses (three-cardiologist consensus) to calculate sensitivity and specificity.
RESULTS
AW-I showed high accuracy for the diagnoses of atrial fibrillation (96% sensitivity, 91% specificity) and complete bundle branch block (85% sensitivity, 98% specificity). Compared with AW-I, AW-4 improved detection of an abnormal 12-lead electrocardiogram (91% vs. 80% sensitivity; P<0.01), atrial flutter/tachycardia (69% vs. 25% sensitivity; P=0.04), T-wave abnormalities (77% vs. 34% sensitivity; P<0.01), pathological Q-waves (41% vs. 7% sensitivity; P<0.01) and left anterior hemiblock (70% vs. 0% sensitivity; P=0.02). AW-4 also enabled better differentiation between atrioventricular block and sinus bradycardia (from 81% to 95% correct; P=0.03) and between atrial fibrillation and atrial flutter/tachycardia (from 71% to 89% correct; P=0.02), but not between bundle branch blocks (from 82% to 87% correct; P=0.57).
CONCLUSIONS
A smartwatch electrocardiogram on the wrist accurately diagnoses atrial fibrillation and bundle branch block. Recording additional leads significantly improves the accuracy of detecting an abnormal electrocardiogram and repolarization changes, and also allows for better differentiation of brady- and tachyarrhythmias.
Topics: Atrial Fibrillation; Bundle-Branch Block; Electrocardiography; Humans; Tachycardia, Supraventricular; Wrist
PubMed: 34953753
DOI: 10.1016/j.acvd.2021.11.003 -
Annals of Medicine Dec 2023The persistent spread of SARS-CoV-2 makes diagnosis challenging because COVID-19 symptoms are hard to differentiate from those of other respiratory illnesses. The...
OBJECTIVE
The persistent spread of SARS-CoV-2 makes diagnosis challenging because COVID-19 symptoms are hard to differentiate from those of other respiratory illnesses. The reverse transcription-polymerase chain reaction test is the current golden standard for diagnosing various respiratory diseases, including COVID-19. However, this standard diagnostic method is prone to erroneous and false negative results (10% -15%). Therefore, finding an alternative technique to validate the RT-PCR test is paramount. Artificial intelligence (AI) and machine learning (ML) applications are extensively used in medical research. Hence, this study focused on developing a decision support system using AI to diagnose mild-moderate COVID-19 from other similar diseases using demographic and clinical markers. Severe COVID-19 cases were not considered in this study since fatality rates have dropped considerably after introducing COVID-19 vaccines.
METHODS
A custom stacked ensemble model consisting of various heterogeneous algorithms has been utilized for prediction. Four deep learning algorithms have also been tested and compared, such as one-dimensional convolutional neural networks, long short-term memory networks, deep neural networks and Residual Multi-Layer Perceptron. Five explainers, namely, Shapley Additive Values, Eli5, QLattice, Anchor and Local Interpretable Model-agnostic Explanations, have been utilized to interpret the predictions made by the classifiers.
RESULTS
After using Pearson's correlation and particle swarm optimization feature selection, the final stack obtained a maximum accuracy of 89%. The most important markers which were useful in COVID-19 diagnosis are Eosinophil, Albumin, T. Bilirubin, ALP, ALT, AST, HbA1c and TWBC.
CONCLUSION
The promising results suggest using this decision support system to diagnose COVID-19 from other similar respiratory illnesses.
Topics: Humans; COVID-19; Artificial Intelligence; SARS-CoV-2; COVID-19 Vaccines; COVID-19 Testing
PubMed: 37436038
DOI: 10.1080/07853890.2023.2233541 -
Medical Science Monitor : International... Jan 2021BACKGROUND It is challenging to entirely show the anterior talofibular ligament (ATFL) and accurately diagnose ATFL injury with traditional 2-dimensional (2D) magnetic...
BACKGROUND It is challenging to entirely show the anterior talofibular ligament (ATFL) and accurately diagnose ATFL injury with traditional 2-dimensional (2D) magnetic resonance imaging (MRI). With the introduction of 3.0T MRI, a 3-dimensional (3D) MRI sequence can achieve images with high spatial resolution. This study aimed to evaluate the accuracy of 3D MRI and compare it with 2D MRI in diagnosing ATFL injury. MATERIAL AND METHODS This was a prospective study in which 45 patients with clinically suspected ATFL injury underwent 2D MRI, 3D MRI, and 3D model reconstruction followed by arthroscopic surgery between February 2018 and April 2019. Two radiologists who had over 11 and 13 years of musculoskeletal experience assessed the injury of ATFL in consensus without any clinical clues. Arthroscopic surgery results were the standard reference of MRI accuracy. RESULTS The 3D MRI results of ATFL injury showed the sensitivity of diagnosis of complete tears of 83% and specificity of 82%. The partial tears diagnosis sensitivity was 78%, and specificity was 100%. The sensitivity of diagnosis of sprains was 100%, and the specificity was 97%. The 3D MRI accuracy of diagnosis was 98% for no injury, 98% for sprain, 91% for partial tear, and 82% for complete tear. The difference in the diagnosis of sprain and partial tears by 3D MRI and 2D MRI was statistically significant (P<0.05). A 3D reconstruction model was successfully created for all patients. CONCLUSIONS 3D MRI may be a reliable and accurate method to detect ATFL injury. The 3D reconstruction model using 3D MRI sequences has excellent prospects in application.
Topics: Adolescent; Adult; Dimensional Measurement Accuracy; Female; Humans; Imaging, Three-Dimensional; Knee Injuries; Lateral Ligament, Ankle; Magnetic Resonance Imaging; Male; Middle Aged
PubMed: 33453097
DOI: 10.12659/MSM.927920 -
Pulmonology 2021Pulmonary vein stenosis (PVS) is a rare condition, often difficult to diagnose and associated with poor prognosis at advanced stages. Lung parenchymal abnormalities are... (Review)
Review
Pulmonary vein stenosis (PVS) is a rare condition, often difficult to diagnose and associated with poor prognosis at advanced stages. Lung parenchymal abnormalities are indirect evidence of PVS and can manifest as multifocal opacities, nodular lesions, unilateral effusions, and interstitial septal thickening. These can lead to erroneous diagnoses of airway disease, pneumonia, malignancies or interstitial lung disease. This review summarizes the current literature about the approach to, evaluation and management of these patients. Our case report demonstrates that PVS is an under-recognized complication of cardiovascular surgery and should be considered in all patients presenting with respiratory symptoms after a cardiac procedure.
Topics: Female; Humans; Lung; Lung Diseases, Interstitial; Magnetic Resonance Imaging; Middle Aged; Phlebography; Pulmonary Veins; Stenosis, Pulmonary Vein
PubMed: 32571674
DOI: 10.1016/j.pulmoe.2020.05.010 -
Annals of Oncology : Official Journal... Sep 2021Clinical management of soft tissue sarcoma (STS) is particularly challenging. Here, we used digital pathology and deep learning (DL) for diagnosis and prognosis...
BACKGROUND
Clinical management of soft tissue sarcoma (STS) is particularly challenging. Here, we used digital pathology and deep learning (DL) for diagnosis and prognosis prediction of STS.
PATIENTS AND METHODS
Our retrospective, multicenter study included a total of 506 histopathological slides from 291 patients with STS. The Cancer Genome Atlas cohort (240 patients) served as training and validation set. A second, multicenter cohort (51 patients) served as an additional test set. The use of the DL model (DLM) as a clinical decision support system was evaluated by nine pathologists with different levels of expertise. For prognosis prediction, 139 slides from 85 patients with leiomyosarcoma (LMS) were used. Area under the receiver operating characteristic (AUROC) and accuracy served as main outcome measures.
RESULTS
The DLM achieved a mean AUROC of 0.97 (±0.01) and an accuracy of 79.9% (±6.1%) in diagnosing the five most common STS subtypes. The DLM significantly improved the accuracy of the pathologists from 46.3% (±15.5%) to 87.1% (±11.1%). Furthermore, they were significantly faster and more certain in their diagnosis. In LMS, the mean AUROC in predicting the disease-specific survival status was 0.91 (±0.1) and the accuracy was 88.9% (±9.9%). Cox regression showed the DLM's prediction to be a significant independent prognostic factor (P = 0.008, hazard ratio 5.5, 95% confidence interval 1.56-19.7) in these patients, outperforming other risk factors.
CONCLUSIONS
DL can be used to accurately diagnose frequent subtypes of STS from conventional histopathological slides. It might be used for prognosis prediction in LMS, the most prevalent STS subtype in our cohort. It can also help pathologists to make faster and more accurate diagnoses. This could substantially improve the clinical management of STS patients.
Topics: Deep Learning; Humans; Prognosis; Retrospective Studies; Sarcoma; Soft Tissue Neoplasms
PubMed: 34139273
DOI: 10.1016/j.annonc.2021.06.007 -
BMC Oral Health Sep 2022Evaluating the diagnostic efficiency of deep learning models to diagnose vertical root fracture in vivo on cone-beam CT (CBCT) images.
OBJECTIVES
Evaluating the diagnostic efficiency of deep learning models to diagnose vertical root fracture in vivo on cone-beam CT (CBCT) images.
MATERIALS AND METHODS
The CBCT images of 276 teeth (138 VRF teeth and 138 non-VRF teeth) were enrolled and analyzed retrospectively. The diagnostic results of these teeth were confirmed by two chief radiologists. There were two experimental groups: auto-selection group and manual selection group. A total of 552 regions of interest of teeth were cropped in manual selection group and 1118 regions of interest of teeth were cropped in auto-selection group. Three deep learning networks (ResNet50, VGG19 and DenseNet169) were used for diagnosis (3:1 for training and testing). The diagnostic efficiencies (accuracy, sensitivity, specificity, and area under the curve (AUC)) of three networks were calculated in two experiment groups. Meanwhile, 552 teeth images in manual selection group were diagnosed by a radiologist. The diagnostic efficiencies of the three deep learning network models in two experiment groups and the radiologist were calculated.
RESULTS
In manual selection group, ResNet50 presented highest accuracy and sensitivity for diagnosing VRF teeth. The accuracy, sensitivity, specificity and AUC was 97.8%, 97.0%, 98.5%, and 0.99, the radiologist presented accuracy, sensitivity, and specificity as 95.3%, 96.4 and 94.2%. In auto-selection group, ResNet50 presented highest accuracy and sensitivity for diagnosing VRF teeth, the accuracy, sensitivity, specificity and AUC was 91.4%, 92.1%, 90.7% and 0.96.
CONCLUSION
In manual selection group, ResNet50 presented higher diagnostic efficiency in diagnosis of in vivo VRF teeth than VGG19, DensenNet169 and radiologist with 2 years of experience. In auto-selection group, Resnet50 also presented higher diagnostic efficiency in diagnosis of in vivo VRF teeth than VGG19 and DensenNet169. This makes it a promising auxiliary diagnostic technique to screen for VRF teeth.
Topics: Cone-Beam Computed Tomography; Deep Learning; Humans; Retrospective Studies; Tooth Fractures; Tooth Root
PubMed: 36064682
DOI: 10.1186/s12903-022-02422-9 -
Journal of Neuroimaging : Official... Jan 2023Alzheimer's disease (AD) is currently diagnosed using a mixture of psychological tests and clinical observations. However, these diagnoses are not perfect, and... (Review)
Review
Alzheimer's disease (AD) is currently diagnosed using a mixture of psychological tests and clinical observations. However, these diagnoses are not perfect, and additional diagnostic tools (e.g., MRI) can help improve our understanding of AD as well as our ability to detect the disease. Accordingly, a large amount of research has been invested into innovative diagnostic methods for AD. Functional MRI (fMRI) is a form of neuroimaging technology that has been used to diagnose AD; however, fMRI is incredibly noisy, complex, and thus lacks clinical use. Nonetheless, recent innovations in deep learning technology could enable the simplified and streamlined analysis of fMRI. Deep learning is a form of artificial intelligence that uses computer algorithms based on human neural networks to solve complex problems. For example, in fMRI research, deep learning models can automatically denoise images and classify AD by detecting patterns in participants' brain scans. In this systematic review, we investigate how fMRI (specifically resting-state fMRI) and deep learning methods are used to diagnose AD. In turn, we outline the common deep neural network, preprocessing, and classification methods used in the literature. We also discuss the accuracy, strengths, limitations, and future direction of fMRI deep learning methods. In turn, we aim to summarize the current field for new researchers, suggest specific areas for future research, and highlight the potential of fMRI to aid AD diagnoses.
Topics: Humans; Alzheimer Disease; Deep Learning; Artificial Intelligence; Magnetic Resonance Imaging; Neuroimaging; Brain
PubMed: 36257926
DOI: 10.1111/jon.13063 -
The Pan African Medical Journal 2019Self-diagnosis and pain management is a worldwide practice. The current study aims to determine the percentage of dental students and interns who self-diagnose and...
INTRODUCTION
Self-diagnosis and pain management is a worldwide practice. The current study aims to determine the percentage of dental students and interns who self-diagnose and manage their dental pain and further establish the proportion of students who depend on various resources for diagnosing and treating their condition.
METHODS
A cross-sectional, self-administered questionnaire-based study was conducted among the dental students in and around Riyadh. The questionnaire consisted of three parts including: part 1-demographic data; part 2-pain and self-diagnosis; part 3-visiting the dentist and managing the pain. The data were analyzed using the Statistical Package for Social Sciences (SPSS version 22.0).
RESULTS
Fifty four percent of the participants were involved in self-diagnosis and managed the pain by themselves. Seventy three percent of the respondents experienced teeth/gum discomfort or any symptoms of an oral health problem, of which 57% searched the symptoms they faced on the internet to arrive at a diagnosis. Besides, 35% of the interns considered internet to be a helpful tool for diagnosing their pain. 16% admitted that they have never visited a dentist.
CONCLUSION
We found that a significant proportion of the participants self-diagnosed by using their background or resorting to the internet, at times consulting a dentist to confirm their diagnosis. The students from the health sciences background should refrain from this practice. Efforts should be made to make the population mindful of the potential risks linked to self-medication and diagnosis. Further research should be done with a larger sample size by including the students and interns from different institutions.
Topics: Cross-Sectional Studies; Diagnostic Self Evaluation; Facial Pain; Female; Humans; Male; Saudi Arabia; Students, Dental; Surveys and Questionnaires; Toothache
PubMed: 32180872
DOI: 10.11604/pamj.2019.34.198.18347 -
Rheumatology (Oxford, England) Nov 2021GCA is the most common large vessel vasculitis in the elderly population. In recent years, advanced imaging has changed the way GCA can be diagnosed in many locations.... (Review)
Review
GCA is the most common large vessel vasculitis in the elderly population. In recent years, advanced imaging has changed the way GCA can be diagnosed in many locations. The GCA fast-track clinic approach combined with US examination allows prompt treatment and diagnosis with high certainty. Fast-track clinics have been shown to improve prognosis while being cost effective. However, all diagnostic modalities are highly operator dependent, and in many locations expertise in advanced imaging may not be available. In this paper, we review the current evidence on GCA diagnostics and propose a simple algorithm for diagnosing GCA for use by rheumatologists not working in specialist centres.
Topics: Aged; Early Detection of Cancer; Early Medical Intervention; Giant Cell Arteritis; Humans; Ultrasonography
PubMed: 34255830
DOI: 10.1093/rheumatology/keab547