-
World Journal of Surgical Oncology Feb 2024The application of machine learning (ML) for identifying early gastric cancer (EGC) has drawn increasing attention. However, there lacks evidence-based support for its... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
The application of machine learning (ML) for identifying early gastric cancer (EGC) has drawn increasing attention. However, there lacks evidence-based support for its specific diagnostic performance. Hence, this systematic review and meta-analysis was implemented to assess the performance of image-based ML in EGC diagnosis.
METHODS
We performed a comprehensive electronic search in PubMed, Embase, Cochrane Library, and Web of Science up to September 25, 2022. QUADAS-2 was selected to judge the risk of bias of included articles. We did the meta-analysis using a bivariant mixed-effect model. Sensitivity analysis and heterogeneity test were performed.
RESULTS
Twenty-one articles were enrolled. The sensitivity (SEN), specificity (SPE), and SROC of ML-based models were 0.91 (95% CI: 0.87-0.94), 0.85 (95% CI: 0.81-0.89), and 0.94 (95% CI: 0.39-1.00) in the training set and 0.90 (95% CI: 0.86-0.93), 0.90 (95% CI: 0.86-0.92), and 0.96 (95% CI: 0.19-1.00) in the validation set. The SEN, SPE, and SROC of EGC diagnosis by non-specialist clinicians were 0.64 (95% CI: 0.56-0.71), 0.84 (95% CI: 0.77-0.89), and 0.80 (95% CI: 0.29-0.97), and those by specialist clinicians were 0.80 (95% CI: 0.74-0.85), 0.88 (95% CI: 0.85-0.91), and 0.91 (95% CI: 0.37-0.99). With the assistance of ML models, the SEN of non-specialist physicians in the diagnosis of EGC was significantly improved (0.76 vs 0.64).
CONCLUSION
ML-based diagnostic models have greater performance in the identification of EGC. The diagnostic accuracy of non-specialist clinicians can be improved to the level of the specialists with the assistance of ML models. The results suggest that ML models can better assist less experienced clinicians in diagnosing EGC under endoscopy and have broad clinical application value.
Topics: Humans; Stomach Neoplasms; Endoscopy; Machine Learning
PubMed: 38297303
DOI: 10.1186/s12957-024-03321-9 -
Journal of Neurological Surgery. Part... Dec 2021Ipsilateral cochlear implantation (CI) in vestibular schwannoma (VS) has been an emerging trend over the last two decades. We conducted the first systematic review...
Ipsilateral cochlear implantation (CI) in vestibular schwannoma (VS) has been an emerging trend over the last two decades. We conducted the first systematic review of hearing outcomes comparing neurofibromatosis 2 (NF2) and sporadic VS undergoing CI. A comparison of the two populations and predictor of outcome was assessed. This is an update to a previously presented study. Systemic data searches were performed in PubMed NCBI and Scopus by an academic librarian. No restrictions based on the year of publication were used. Studies were selected if patients had a diagnosis of NF2 and a CI placed in the affected side with reports of hearing outcome. Two independent reviewers screened each abstract and full-text article. Studies were extracted at the patient level, and the assessment of quality and bias was evaluated according to the National Institutes of Health Quality Assessment Tool. Outcome predictors were determined by using the chi-square test and Student's -test. Overall, most CI recipients functioned in the high-to-intermediate performer category for both sporadic and NF2-related VS. Median AzBio (Arizona Biomedical Institute Sentence Test) was 72% (interquartile range [IQR]: 50) in NF2 patients and 70% (IQR: 7.25) in sporadic patients. Larger tumor size predicted a poorer final audiometric outcome. Categorization of hearing outcome into superior performance and inferior performance based on sentence recognition revealed a generally good hearing outcome regardless of treatment or patient population. Select patients with sporadic and NF2 VS may benefit from CI.
PubMed: 34745832
DOI: 10.1055/s-0040-1715606 -
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 -
European Journal of Internal Medicine Dec 2022Point-of-care ultrasound (POCUS) has been adopted as a powerful tool in acute medicine. This systematic review aims to critically appraise the existing literature on... (Review)
Review
BACKGROUND
Point-of-care ultrasound (POCUS) has been adopted as a powerful tool in acute medicine. This systematic review aims to critically appraise the existing literature on point-of-care ultrasound in respiratory or circulatory deterioration.
METHODS
Original studies on POCUS and dyspnea, nontraumatic hypotension, and shock from March 2002 until March 2022 were assessed in the PubMed and Embase Databases. Two reviewers independently screened articles for inclusion, extracted data, and assessed the quality of included studies using an established checklist.
RESULTS
We included 89 articles in this review. Point-of-care ultrasound in the initial workup increases the diagnostic accuracy in patients with dyspnea, nontraumatic hypotension and shock in the ED, ICU and medical ward setting. No improvement is found in patients with severe sepsis in the ICU setting. POCUS is capable of narrowing the differential diagnoses and is faster, and more feasible in the acute setting than other diagnostics available. Results on outcome measures are heterogenous. The quality of the included studies is considered low most of the times, mainly because of performance and selection bias and absence of a gold standard as the reference test.
CONCLUSION
We conclude that POCUS contributes to a higher diagnostic accuracy in dyspnea, nontraumatic hypotension, and shock. It aides in narrowing the differential diagnoses and shortening the time to correct diagnosis and effective treatment.
TRIAL REGISTRY
INPLASY; Registration number: INPLASY202220020; URL: https://inplasy.com/.
Topics: Humans; Point-of-Care Systems; Emergency Service, Hospital; Ultrasonography; Dyspnea; Shock; Hypotension
PubMed: 35927185
DOI: 10.1016/j.ejim.2022.07.017 -
Frontiers in Artificial Intelligence 2023Detecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used...
INTRODUCTION
Detecting and accurately diagnosing early melanocytic lesions is challenging due to extensive intra- and inter-observer variabilities. Dermoscopy images are widely used to identify and study skin cancer, but the blurred boundaries between lesions and besieging tissues can lead to incorrect identification. Artificial Intelligence (AI) models, including vision transformers, have been proposed as a solution, but variations in symptoms and underlying effects hinder their performance.
OBJECTIVE
This scoping review synthesizes and analyzes the literature that uses vision transformers for skin lesion detection.
METHODS
The review follows the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Revise) guidelines. The review searched online repositories such as IEEE Xplore, Scopus, Google Scholar, and PubMed to retrieve relevant articles. After screening and pre-processing, 28 studies that fulfilled the inclusion criteria were included.
RESULTS AND DISCUSSIONS
The review found that the use of vision transformers for skin cancer detection has rapidly increased from 2020 to 2022 and has shown outstanding performance for skin cancer detection using dermoscopy images. Along with highlighting intrinsic visual ambiguities, irregular skin lesion shapes, and many other unwanted challenges, the review also discusses the key problems that obfuscate the trustworthiness of vision transformers in skin cancer diagnosis. This review provides new insights for practitioners and researchers to understand the current state of knowledge in this specialized research domain and outlines the best segmentation techniques to identify accurate lesion boundaries and perform melanoma diagnosis. These findings will ultimately assist practitioners and researchers in making more authentic decisions promptly.
PubMed: 37529760
DOI: 10.3389/frai.2023.1202990 -
Medicina (Kaunas, Lithuania) Apr 2023: prosthetic loosening after hip and knee arthroplasty is one of the most common causes of joint arthroplasty failure and revision surgery. Diagnosis of prosthetic... (Meta-Analysis)
Meta-Analysis Review
: prosthetic loosening after hip and knee arthroplasty is one of the most common causes of joint arthroplasty failure and revision surgery. Diagnosis of prosthetic loosening is a difficult problem and, in many cases, loosening is not clearly diagnosed until accurately confirmed during surgery. The purpose of this study is to conduct a systematic review and meta-analysis to demonstrate the analysis and performance of machine learning in diagnosing prosthetic loosening after total hip arthroplasty (THA) and total knee arthroplasty (TKA). : three comprehensive databases, including MEDLINE, EMBASE, and the Cochrane Library, were searched for studies that evaluated the detection accuracy of loosening around arthroplasty implants using machine learning. Data extraction, risk of bias assessment, and meta-analysis were performed. : five studies were included in the meta-analysis. All studies were retrospective studies. In total, data from 2013 patients with 3236 images were assessed; these data involved 2442 cases (75.5%) with THAs and 794 cases (24.5%) with TKAs. The most common and best-performing machine learning algorithm was DenseNet. In one study, a novel stacking approach using a random forest showed similar performance to DenseNet. The pooled sensitivity across studies was 0.92 (95% CI 0.84-0.97), the pooled specificity was 0.95 (95% CI 0.93-0.96), and the pooled diagnostic odds ratio was 194.09 (95% CI 61.60-611.57). The I2 statistics for sensitivity and specificity were 96% and 62%, respectively, showing that there was significant heterogeneity. The summary receiver operating characteristics curve indicated the sensitivity and specificity, as did the prediction regions, with an AUC of 0.9853. : the performance of machine learning using plain radiography showed promising results with good accuracy, sensitivity, and specificity in the detection of loosening around THAs and TKAs. Machine learning can be incorporated into prosthetic loosening screening programs.
Topics: Humans; Arthroplasty, Replacement, Knee; Retrospective Studies; Prosthesis Failure; Arthroplasty, Replacement, Hip; Machine Learning; Reoperation
PubMed: 37109740
DOI: 10.3390/medicina59040782 -
Frontiers in Endocrinology 2022To evaluate the diagnostic value of conventional ultrasound and elastosonography in malignant thyroid nodules by meta-analysis. (Meta-Analysis)
Meta-Analysis
PURPOSE
To evaluate the diagnostic value of conventional ultrasound and elastosonography in malignant thyroid nodules by meta-analysis.
METHODS
The literature included in the Cochrane Library, PubMed, and Embase were searched by using "elastosonography, ultrasonography, thyroid nodules" as the keywords. The clinical studies using elastosonography and conventional ultrasound to diagnose thyroid nodules were selected, and histopathology of thyroid nodules was used as reference standards. The quality evaluation and heterogeneity test were performed on the literature that met the requirements, the combined specificity and sensitivity were pooled, and a comprehensive ROC curve analysis was performed. The Quality Assessment of Diagnostic Accuracy Studies (QUADAS) tool was utilized to evaluate the quality of each included study. Meta-DiSc version 1.4, StataSE 12 and Review Manager 5.4 were used.
RESULTS
A total of nine studies assessed 3066 thyroid nodules (2043 benign and 1023 malignant). The pooled sensitivity, specificity, PLR, NLR, and DOR of conventional ultrasound for the diagnose of malignant thyroid nodules were 0.833 (95% CI 0.809-0.855), 0.818 (95% CI 0.801-0.835), 4.85 (95% CI 4.36-5.39), 0.20 (95% CI 0.17-0.23), and 29.38 (95% CI 23.28-37.08), respectively, with an AUC of 0.9068. Also, the pooled sensitivity, specificity, PLR, NLR, and DOR of elastosonography were 0.774 (95% CI 0.741-0.804), 0.737 (95% CI 0.715-0.758), 3.14(95% CI 2.85-3.47), 0.29 (95% CI 0.25-0.34), and 9.35 (95% CI 7.63-11.46), respectively, with an AUC of 0.8801. Three studies provided data regarding the conventional ultrasound and elastosonography. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC were 0.902 (95% CI 0.870-0.928), 0.649 (95% CI 0.616-0.681), 2.72 (95% CI 2.46-3.00), 0.14 (95% CI 0.11-0.19), 25.51 (95%CI 17.11-38.03), and 0.9294.
CONCLUSION
The existing evidence shows that elastosonography cannot completely replace conventional ultrasound in the diagnosis of malignant thyroid nodules, and the combination of elastosonography and conventional ultrasound gives a better diagnostic precision.
SYSTEMATIC REVIEW REGISTRATION
www.crd.york.ac.uk, identifier PROSPERO CRD42022375808.
Topics: Humans; Thyroid Nodule; Sensitivity and Specificity; Diagnosis, Differential; Ultrasonography; ROC Curve
PubMed: 36686488
DOI: 10.3389/fendo.2022.1082881 -
Ultrasound in Obstetrics & Gynecology :... Apr 2022To perform a systematic review and meta-analysis of the diagnostic test accuracy of ultrasound and magnetic resonance imaging (MRI) and compare the performance of the... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVES
To perform a systematic review and meta-analysis of the diagnostic test accuracy of ultrasound and magnetic resonance imaging (MRI) and compare the performance of the two modalities in the diagnosis of placenta accreta spectrum (PAS).
METHODS
This was a systematic review conducted following the Cochrane Diagnostic Test Accuracy Reviews guideline. A literature search was performed in five databases: PubMed, EMBASE, PMC, The Cochrane Library and BVS-Bireme between 27 July and 4 August 2020. The search was updated on 18 August 2021. We included observational studies evaluating diagnostic accuracy in women with risk factors for PAS who had undergone both ultrasound and MRI examinations, published in English between 2011 and 2021. Quality Assessment of Diagnostic Accuracy Studies-2 was used to evaluate the quality of the studies. Forest plots for sensitivity and specificity with 95% CIs and receiver-operating-characteristics curves for ultrasound and MRI were constructed.
RESULTS
The literature search identified 266 studies. After reviewing the titles and abstracts of the articles, 51 were selected for full-text review and 17 studies including 1301 women with MRI and ultrasound data available were selected for the meta-analysis. The study population included 457 cases with PAS diagnosed using the gold standard method (intraoperative or histopathological analysis). The overall quality of the evaluated studies was considered satisfactory according to QUADAS-2. The meta-analysis revealed a sensitivity of 0.833 (95% CI, 0.776-0.878) and specificity of 0.834 (95% CI, 0.746-0.897) for ultrasound. For MRI, sensitivity was 0.838 (95% CI, 0.786-0.879) and specificity was 0.831 (95% CI, 0.770-0.878). There was no statistically significant difference between the two modalities. The Cochran's Q values indicated a high level of heterogeneity of sensitivity and specificity of ultrasound and MRI across studies.
CONCLUSIONS
Ultrasound and MRI have similar accuracy in the diagnosis of PAS. These results suggest that, in a setting with a high prevalence of risk factors, the choice of imaging modality for initial screening for PAS should depend on the availability of equipment and the examiner's expertise. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.
Topics: Female; Humans; Magnetic Resonance Imaging; Magnetic Resonance Spectroscopy; Placenta Accreta; Pregnancy; Sensitivity and Specificity; Ultrasonography
PubMed: 35041250
DOI: 10.1002/uog.24861 -
International Journal of Environmental... May 2021Arterial hypertension (HT) is a chronic condition of elevated blood pressure (BP), which may cause increased incidence of cardiovascular disease, stroke, kidney failure... (Review)
Review
Arterial hypertension (HT) is a chronic condition of elevated blood pressure (BP), which may cause increased incidence of cardiovascular disease, stroke, kidney failure and mortality. If the HT is diagnosed early, effective treatment can control the BP and avert adverse outcomes. Physiological signals like electrocardiography (ECG), photoplethysmography (PPG), heart rate variability (HRV), and ballistocardiography (BCG) can be used to monitor health status but are not directly correlated with BP measurements. The manual detection of HT using these physiological signals is time consuming and prone to human errors. Hence, many computer-aided diagnosis systems have been developed. This paper is a systematic review of studies conducted on the automated detection of HT using ECG, HRV, PPG and BCG signals. In this review, we have identified 23 studies out of 250 screened papers, which fulfilled our eligibility criteria. Details of the study methods, physiological signal studied, database used, various nonlinear techniques employed, feature extraction, and diagnostic performance parameters are discussed. The machine learning and deep learning based methods based on ECG and HRV signals have yielded the best performance and can be used for the development of computer-aided diagnosis of HT. This work provides insights that may be useful for the development of wearable for continuous cuffless remote monitoring of BP based on ECG and HRV signals.
Topics: Electrocardiography; Heart Rate; Humans; Hypertension; Monitoring, Physiologic; Photoplethysmography
PubMed: 34072304
DOI: 10.3390/ijerph18115838 -
European Journal of Nuclear Medicine... Jun 2021Polymyalgia rheumatica (PMR) can be difficult to diagnose. Whole-body [18F]FDG-PET/CT allows for a comprehensive evaluation of all relevant articular and extra-articular... (Meta-Analysis)
Meta-Analysis Review
PURPOSE
Polymyalgia rheumatica (PMR) can be difficult to diagnose. Whole-body [18F]FDG-PET/CT allows for a comprehensive evaluation of all relevant articular and extra-articular structures affected by PMR. We aimed to summarize current evidence on the diagnostic value of [18F]FDG-PET/CT for a diagnosis of PMR.
METHODS
PubMed/MEDLINE and the Cochrane Library database were searched from inception through May 31, 2020. Studies containing patients with PMR who underwent [18F]FDG-PET/CT were included. Screening and full-text review were performed by 3 investigators and data extraction by 2 investigators. Risk of bias was examined with the QUADAS-2 tool. Diagnostic test meta-analysis was performed with a bivariate model.
RESULTS
Twenty studies were included in the systematic review, of which 9 studies (n = 636 patients) were eligible for meta-analysis. [18F]FDG positivity at the following sites was associated with a diagnosis of PMR: interspinous bursae (positive likelihood ratio (LR+) 4.00; 95% CI 1.84-8.71), hips (LR+ 2.91; 95% CI 2.09-4.05), ischial tuberosities (LR+ 2.86; 95% CI 1.91-4.28), shoulders (LR+ 2.57; 95% CI 1.24-5.32) and sternoclavicular joints (LR+ 2.31; 95% CI 1.33-4.02). Negative likelihood ratios (LR-) for these sites, as well as the greater trochanters, were all less than 0.50. Composite [18F]FDG-PET/CT scores, as reported in 3 studies, provided a pooled LR+ of 3.91 (95% CI 2.42-6.32) and LR- of 0.19 (95% CI 0.10-0.36). Moderate to high heterogeneity was observed across the studies, mainly due to differences in patient selection, scanning procedures and/or interpretation criteria.
CONCLUSION
Significant [18F]FDG uptake at a combination of anatomic sites is informative for a diagnosis of PMR. [18F]FDG-PET/CT might be an important diagnostic tool in patients with suspected PMR. This study also highlights the need for adherence to published procedural recommendations and standardized interpretation criteria for the use of [18F]FDG-PET/CT in PMR.
Topics: Fluorodeoxyglucose F18; Giant Cell Arteritis; Humans; Polymyalgia Rheumatica; Positron Emission Tomography Computed Tomography; Positron-Emission Tomography; Radiopharmaceuticals
PubMed: 33372248
DOI: 10.1007/s00259-020-05162-6