-
PloS One 2023Polysomnographic sleep architecture parameters are commonly used to diagnose or evaluate treatment of sleep disorders. Polysomnography (PSG) having practical...
Polysomnographic sleep architecture parameters are commonly used to diagnose or evaluate treatment of sleep disorders. Polysomnography (PSG) having practical constraints, the development of wearable devices and algorithms to monitor and stage sleep is rising. Beside pure validation studies, it is necessary for a clinician to ensure that the conclusions drawn with a new generation wearable sleep scoring device are consistent to the ones of gold standard PSG, leading to similar interpretation and diagnosis. This paper reports on the performance of Somno-Art Software for the detection of differences in sleep parameters between patients suffering from obstructive sleep apnea (OSA), insomniac or major depressive disorder (MDD) compared to healthy subjects. On 244 subjects (n = 26 healthy, n = 28 OSA, n = 66 insomniacs, n = 124 MDD), sleep staging was obtained from PSG and Somno-Art analysis on synchronized electrocardiogram and actimetry signals. Mixed model analysis of variance was performed for each sleep parameter. Possible differences in sleep parameters were further assessed with Mann-Whitney U-test between the healthy subjects and each pathology group. All sleep parameters, except N1+N2, showed significant differences between the healthy and the pathology group. No significant differences were observed between Somno-Art Software and PSG, except a 3.6±2.2 min overestimation of REM sleep. No significant interaction 'group'*'technology' was observed, suggesting that the differences in pathologies are independent of the technology used. Overall, comparable differences between healthy subjects and pathology groups were observed when using Somno-Art Software or polysomnography. Somno-Art proposes an interesting valid tool as an aid for diagnosis and treatment follow-up in ambulatory settings.
Topics: Humans; Polysomnography; Depressive Disorder, Major; Sleep; Sleep Apnea, Obstructive; Software
PubMed: 37862307
DOI: 10.1371/journal.pone.0291593 -
Frontiers in Oncology 2023Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their...
BACKGROUND
Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.
PURPOSE
MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.
METHODS
A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.
RESULTS
The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.
CONCLUSIONS
Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.
PubMed: 37795452
DOI: 10.3389/fonc.2023.1181270 -
Scientific Reports Dec 2023In ophthalmology, the availability of many fundus photographs and optical coherence tomography images has spurred consideration of using artificial intelligence (AI) for...
In ophthalmology, the availability of many fundus photographs and optical coherence tomography images has spurred consideration of using artificial intelligence (AI) for diagnosing retinal and optic nerve disorders. However, AI application for diagnosing anterior segment eye conditions remains unfeasible due to limited standardized images and analysis models. We addressed this limitation by augmenting the quantity of standardized optical images using a video-recordable slit-lamp device. We then investigated whether our proposed machine learning (ML) AI algorithm could accurately diagnose cataracts from videos recorded with this device. We collected 206,574 cataract frames from 1812 cataract eye videos. Ophthalmologists graded the nuclear cataracts (NUCs) using the cataract grading scale of the World Health Organization. These gradings were used to train and validate an ML algorithm. A validation dataset was used to compare the NUC diagnosis and grading of AI and ophthalmologists. The results of individual cataract gradings were: NUC 0: area under the curve (AUC) = 0.967; NUC 1: AUC = 0.928; NUC 2: AUC = 0.923; and NUC 3: AUC = 0.949. Our ML-based cataract diagnostic model achieved performance comparable to a conventional device, presenting a promising and accurate auto diagnostic AI tool.
Topics: Humans; Artificial Intelligence; Cataract; Algorithms; Optic Nerve Diseases
PubMed: 38086904
DOI: 10.1038/s41598-023-49563-7 -
Clinical and Experimental Pediatrics Feb 2024Anorectal manometry is one of the motility tests in children performed by pediatric gastroenterologist. It evaluates the motility function of anorectal tract. It is...
Anorectal manometry is one of the motility tests in children performed by pediatric gastroenterologist. It evaluates the motility function of anorectal tract. It is helpful for diagnosing children with constipation, rectal hypersensitivity, fecal incontinence, Hirschsprung disease, anal achalasia, and anorectal malformations. The most common indication to perform anorectal manometry is to diagnose Hirschsprung disease. It is a safe procedure. This paper discusses recent advances and reviews on anorectal motility disorders in children.
PubMed: 37321574
DOI: 10.3345/cep.2022.01242 -
European Radiology Oct 2023Delayed post-gadolinium magnetic resonance imaging (MRI) detects changes of endolymphatic hydrops (EH) within the inner ear in Meniere's disease (MD). A systematic... (Meta-Analysis)
Meta-Analysis
OBJECTIVES
Delayed post-gadolinium magnetic resonance imaging (MRI) detects changes of endolymphatic hydrops (EH) within the inner ear in Meniere's disease (MD). A systematic review with meta-analysis was conducted to summarise the diagnostic performance of MRI descriptors across the range of MD clinical classifications.
MATERIALS AND METHODS
Case-controlled studies documenting the diagnostic performance of MRI descriptors in distinguishing MD ears from asymptomatic ears or ears with other audio-vestibular conditions were identified (MEDLINE, EMBASE, Web of Science, Scopus databases: updated 17/2/2022). Methodological quality was evaluated with Quality Assessment of Diagnostic Accuracy Studies version 2. Results were pooled using a bivariate random-effects model for evaluation of sensitivity, specificity and diagnostic odds ratio (DOR). Meta-regression evaluated sources of heterogeneity, and subgroup analysis for individual clinical classifications was performed.
RESULTS
The meta-analysis included 66 unique studies and 3073 ears with MD (mean age 40.2-67.2 years), evaluating 11 MRI descriptors. The combination of increased perilymphatic enhancement (PLE) and EH (3 studies, 122 MD ears) achieved the highest sensitivity (87% (95% CI: 79.92%)) whilst maintaining high specificity (91% (95% CI: 85.95%)). The diagnostic performance of "high grade cochlear EH" and "any EH" descriptors did not significantly differ between monosymptomatic cochlear MD and the latest reference standard for definite MD (p = 0.3; p = 0.09). Potential sources of bias were case-controlled design, unblinded observers and variable reference standard, whilst differing MRI techniques introduced heterogeneity.
CONCLUSIONS
The combination of increased PLE and EH optimised sensitivity and specificity for MD, whilst some MRI descriptors also performed well in diagnosing monosymptomatic cochlear MD.
KEY POINTS
• A meta-analysis of delayed post-gadolinium magnetic resonance imaging (MRI) for the diagnosis of Meniere's disease is reported for the first time and comprised 66 studies (3073 ears). • Increased enhancement of the perilymphatic space of the inner ear is shown to be a key MRI feature for the diagnosis of Meniere's disease. • MRI diagnosis of Meniere's disease can be usefully applied across a range of clinical classifications including patients with cochlear symptoms alone.
Topics: Humans; Adult; Middle Aged; Aged; Meniere Disease; Gadolinium; Endolymphatic Hydrops; Ear, Inner; Magnetic Resonance Imaging
PubMed: 37171493
DOI: 10.1007/s00330-023-09651-8 -
Cancer Medicine Aug 2023Endoscopic ultrasonography-guided fine-needle aspiration/biopsy (EUS-FNA/B) is considered to be a first-line procedure for the pathological diagnosis of pancreatic...
BACKGROUND AND AIMS
Endoscopic ultrasonography-guided fine-needle aspiration/biopsy (EUS-FNA/B) is considered to be a first-line procedure for the pathological diagnosis of pancreatic cancer owing to its high accuracy and low complication rate. The number of new cases of pancreatic ductal adenocarcinoma (PDAC) is increasing, and its accurate pathological diagnosis poses a challenge for cytopathologists. Our aim was to develop a hyperspectral imaging (HSI)-based convolution neural network (CNN) algorithm to aid in the diagnosis of pancreatic EUS-FNA cytology specimens.
METHODS
HSI images were captured of pancreatic EUS-FNA cytological specimens from benign pancreatic tissues (n = 33) and PDAC (n = 39) prepared using a liquid-based cytology method. A CNN was established to test the diagnostic performance, and Attribution Guided Factorization Visualization (AGF-Visualization) was used to visualize the regions of important classification features identified by the model.
RESULTS
A total of 1913 HSI images were obtained. Our ResNet18-SimSiam model achieved an accuracy of 0.9204, sensitivity of 0.9310 and specificity of 0.9123 (area under the curve of 0.9625) when trained on HSI images for the differentiation of PDAC cytological specimens from benign pancreatic cells. AGF-Visualization confirmed that the diagnoses were based on the features of tumor cell nuclei.
CONCLUSIONS
An HSI-based model was developed to diagnose cytological PDAC specimens obtained using EUS-guided sampling. Under the supervision of experienced cytopathologists, we performed multi-staged consecutive in-depth learning of the model. Its superior diagnostic performance could be of value for cytologists when diagnosing PDAC.
Topics: Humans; Endoscopic Ultrasound-Guided Fine Needle Aspiration; Cytology; Deep Learning; Pancreatic Neoplasms; Carcinoma, Pancreatic Ductal
PubMed: 37455599
DOI: 10.1002/cam4.6335 -
Current Oncology (Toronto, Ont.) Jan 2024(1) Mucosal melanoma (MM) is a rare tumor, accounting for about 1% of all diagnosed melanomas. The etiology and pathogenesis of this tumor are unknown. It is...
(1) Mucosal melanoma (MM) is a rare tumor, accounting for about 1% of all diagnosed melanomas. The etiology and pathogenesis of this tumor are unknown. It is characterized by an aggressive phenotype with poor prognosis and a low response rate to approved treatments. (2) We retrospectively analyzed the clinical features, treatments and outcomes of patients diagnosed with MM from different sub-sites (head and neck, gynecological and gastro-intestinal region) between 2013 and 2023 at our Institute. Survival times were estimated with the Kaplan-Meier method. Multivariate Cox regression was used to test the independence of significant factors in univariate analysis. (3) Twenty-five patients were included in this study; the disease was equally distributed among females and males. The median age at diagnosis was 74 years old. The majority had MM originating from the head and neck (56%), particularly from the nasal cavity. BRAF V600 mutations were detected in 16% of the study population, limited to gastro-intestinal and gynecological MM. At diagnosis, at least half the patients (52%) had the disease located also at distant sites. The median overall survival (OS) in the whole study population was 22 months, with a longer OS for patients diagnosed at an early stage (38 months, < 0.001). Longer OSs were reported for head and neck MM compared to other anatomic regions (0.06). Surgery of the primary tumor and radiotherapy were performed in 64% and 36% of the study population, respectively. Radiotherapy was performed only in head and neck MM. At multivariate analysis, the single factor that showed a reduced hazard ratio for death was radiotherapy. (4) The overall survival of MM from different sub-sites treated at our Italian Institution was 22 months, with better outcomes for early-stage disease and head and neck MM. Performing radiotherapy may have a protective effect on OS for head and neck MM. New treatment strategies are urgently needed to improve the outcome in this disease.
Topics: Male; Female; Humans; Aged; Melanoma; Prognosis; Retrospective Studies; Head and Neck Neoplasms; Italy
PubMed: 38275835
DOI: 10.3390/curroncol31010042 -
IScience May 2024Swift and accurate diagnosis for earlier-stage monkeypox (mpox) patients is crucial to avoiding its spread. However, the similarities between common skin disorders and...
Swift and accurate diagnosis for earlier-stage monkeypox (mpox) patients is crucial to avoiding its spread. However, the similarities between common skin disorders and mpox and the need for professional diagnosis unavoidably impaired the diagnosis of earlier-stage mpox patients and contributed to mpox outbreak. To address the challenge, we proposed "Super Monitoring", a real-time visualization technique employing artificial intelligence (AI) and Internet technology to diagnose earlier-stage mpox cheaply, conveniently, and quickly. Concretely, AI-mediated "Super Monitoring" (mpox-AISM) integrates deep learning models, data augmentation, self-supervised learning, and cloud services. According to publicly accessible datasets, mpox-AISM's Precision, Recall, Specificity, and F1-score in diagnosing mpox reach 99.3%, 94.1%, 99.9%, and 96.6%, respectively, and it achieves 94.51% accuracy in diagnosing mpox, six like-mpox skin disorders, and normal skin. With the Internet and communication terminal, mpox-AISM has the potential to perform real-time and accurate diagnosis for earlier-stage mpox in real-world scenarios, thereby preventing mpox outbreak.
PubMed: 38711448
DOI: 10.1016/j.isci.2024.109766 -
European Radiology Nov 2023To evaluate the diagnostic performance of attenuation imaging (ATI) with an ultrasound scanner (US) in the detection of paediatric hepatic steatosis.
OBJECTIVES
To evaluate the diagnostic performance of attenuation imaging (ATI) with an ultrasound scanner (US) in the detection of paediatric hepatic steatosis.
METHODS
Ninety-four prospectively enrolled children were classified into normal weight and overweight/obese (OW/OB) groups according to body mass index (BMI). US findings, including hepatic steatosis grade and ATI value, were examined by two radiologists. Anthropometric and biochemical parameters were obtained, and nonalcoholic fatty liver disease (NAFLD) scores, including the Framingham steatosis index (FSI) and hepatic steatosis index (HSI), were calculated.
RESULTS
After screening, 49 OW/OB and 40 normal weight children aged 10-18 years old (55 males and 34 females) participated in this study. The ATI value was significantly higher in the OW/OB group than in the normal weight group and showed a significant positive correlation with BMI, serum alanine transferase (ALT), uric acid, and NAFLD scores (p < 0.05). In the multiple linear regression adjusted for age, sex, BMI, ALT, uric acid, and HSI, ATI showed a significant positive association with BMI and ALT (p < 0.05). The receiver operating characteristic analysis showed a very good ability of ATI to predict hepatic steatosis. The intraclass correlation coefficient (ICC) of interobserver variability was 0.92, and the ICCs of intraobserver variability were 0.96 and 0.93 (p < 0.05). According to the two-level Bayesian latent class model analysis, the diagnostic performance of ATI showed the best performance for predicting hepatic steatosis among other known noninvasive NAFLD predictors.
CONCLUSIONS
This study suggests that ATI is an objective and possible surrogate screening test for detecting hepatic steatosis in paediatric patients with obesity.
CLINICAL RELEVANCE STATEMENT
Using ATI as a quantitative tool in hepatic steatosis allows clinicians to estimate the extent of the condition and track changes over time. This is helpful for monitoring disease progression and guiding treatment decisions, especially in paediatric practice.
KEY POINTS
• Attenuation imaging is a noninvasive US-based method for the quantification of hepatic steatosis. • Attenuation imaging values were significantly higher in the OW/OB and steatosis groups than in the normal weight and no steatosis groups, respectively, with a meaningful correlation with known clinical indicators of nonalcoholic fatty liver disease. • Attenuation imaging performs better than other noninvasive predictive models used to diagnose hepatic steatosis.
Topics: Male; Female; Humans; Child; Adolescent; Non-alcoholic Fatty Liver Disease; Liver; Bayes Theorem; Uric Acid; Ultrasonography; Obesity; Overweight
PubMed: 37195431
DOI: 10.1007/s00330-023-09731-9 -
CoDAS 2023To describe the panorama of children's hearing health in the Unified Health System of the state of Sergipe.
PURPOSE
To describe the panorama of children's hearing health in the Unified Health System of the state of Sergipe.
METHODS
A quantitative and retrospective study consisting of four steps: 1) Search the National Registry of Health Establishments of institutions affiliated to the Health Unic System in the state of Sergipe that perform obstetric services and hearing health services; 2) Collecting Neonatal Hearing Screening (NHS) coverage data through DATASUS (from 2012 to 2020); 3) Data collection from medical records of institutions with obstetrics and that perform NHS; and 4) Interview with the guardians of children undergoing auditory rehabilitation. The results were summarized using descriptive statistics (absolute and relative frequency, measures of central tendency, and dispersion).
RESULTS
Only one out of the 29 establishments with obstetrics performs NHS. Two of the Hearing Health Reference Centers (HHRC) are qualified for cochlear implants and two Specialized Centers are qualified for Rehabilitation. From 2012 to 2020, NHS coverage in the state was less than 40%, and when performed in the maternity ward, there were no referrals for Brainstem Auditory Evoked Response (BERA) and audiological diagnosis. The HHRC showed considerable coverage and a lower evasion rate to perform BERA, with a diagnosis rate of 4.8%. The mean time from the NHS to rehabilitation was longer than recommended.
CONCLUSION
NHS coverage must be increased, adjusting the hearing health network to articulate the different levels of care, and reducing the time for identification, diagnosis, and start of rehabilitation.
Topics: Pregnancy; Infant, Newborn; Child; Humans; Female; Retrospective Studies; Neonatal Screening; Hearing; Hearing Tests; Cochlear Implantation
PubMed: 38126548
DOI: 10.1590/2317-1782/20232021197pt