-
Pain Research & Management 2021The study explored the clinical influence, effectiveness, limitations, and human comparison outcomes of machine learning in diagnosing (1) dental diseases, (2)...
PURPOSE
The study explored the clinical influence, effectiveness, limitations, and human comparison outcomes of machine learning in diagnosing (1) dental diseases, (2) periodontal diseases, (3) trauma and neuralgias, (4) cysts and tumors, (5) glandular disorders, and (6) bone and temporomandibular joint as possible causes of dental and orofacial pain.
METHOD
Scopus, PubMed, and Web of Science (all databases) were searched by 2 reviewers until 29 October 2020. Articles were screened and narratively synthesized according to PRISMA-DTA guidelines based on predefined eligibility criteria. Articles that made direct reference test comparisons to human clinicians were evaluated using the MI-CLAIM checklist. The risk of bias was assessed by JBI-DTA critical appraisal, and certainty of the evidence was evaluated using the GRADE approach. Information regarding the quantification method of dental pain and disease, the conditional characteristics of both training and test data cohort in the machine learning, diagnostic outcomes, and diagnostic test comparisons with clinicians, where applicable, were extracted.
RESULTS
34 eligible articles were found for data synthesis, of which 8 articles made direct reference comparisons to human clinicians. 7 papers scored over 13 (out of the evaluated 15 points) in the MI-CLAIM approach with all papers scoring 5+ (out of 7) in JBI-DTA appraisals. GRADE approach revealed serious risks of bias and inconsistencies with most studies containing more positive cases than their true prevalence in order to facilitate machine learning. Patient-perceived symptoms and clinical history were generally found to be less reliable than radiographs or histology for training accurate machine learning models. A low agreement level between clinicians training the models was suggested to have a negative impact on the prediction accuracy. Reference comparisons found nonspecialized clinicians with less than 3 years of experience to be disadvantaged against trained models.
CONCLUSION
Machine learning in dental and orofacial healthcare has shown respectable results in diagnosing diseases with symptomatic pain and with improved future iterations and can be used as a diagnostic aid in the clinics. The current review did not internally analyze the machine learning models and their respective algorithms, nor consider the confounding variables and factors responsible for shaping the orofacial disorders responsible for eliciting pain.
Topics: Algorithms; Artificial Intelligence; Diagnostic Tests, Routine; Facial Pain; Humans; Machine Learning; Pain Management
PubMed: 33986900
DOI: 10.1155/2021/6659133 -
Journal of Obstetrics and Gynaecology :... Dec 2024The diagnosis of endometriomas in patients with endometriosis is of primary importance because it influences the management and prognosis of infertility and pain.... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION
The diagnosis of endometriomas in patients with endometriosis is of primary importance because it influences the management and prognosis of infertility and pain. Imaging techniques are evolving constantly. This study aimed to systematically assess the diagnostic accuracy of transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) in detecting endometrioma using the surgical visualisation of lesions with or without histopathological confirmation as reference standards in patients of reproductive age with suspected endometriosis.
METHODS
PubMed, Embase, Web of Science, Cumulative Index to Nursing and Allied Health Literature and ClinicalTrials.gov databases were searched from their inception to 12 October 2022, using a manual search for additional articles. Two authors independently performed title, abstract and full-text screening of the identified records, extracted study details and quantitative data and assessed the quality of the studies using the 'Quality Assessment of Diagnostic Accuracy Study 2' tool. Bivariate random-effects models were used to determine the pooled sensitivity and specificity, compare the two imaging modalities and evaluate the sources of heterogeneity.
RESULTS
Sixteen prospective studies (10 assessing TVUS, 4 assessing MRI and 2 assessing both TVUS and MRI) were included, representing 1976 participants. Pooled TVUS and MRI sensitivities for endometrioma were 0.89 (95% confidence interval 'CI', 0.86-0.92) and 0.94 (95% CI, 0.74-0.99), respectively (indirect comparison -value of 0.47). Pooled TVUS and MRI specificities for endometrioma were 0.95 (95% CI, 0.92-0.97) and 0.94 (95% CI, 0.89-0.97), respectively (indirect comparison p-value of 0.51). These studies had a high or unclear risk of bias. A direct comparison (all participants undergoing TVUS and MRI) of the modalities was available in only two studies.
CONCLUSION
TVUS and MRI have high accuracy for diagnosing endometriomas; however, high-quality studies comparing the two modalities are lacking.
Topics: Female; Humans; Endometriosis; Prospective Studies; Ultrasonography; Magnetic Resonance Imaging; Sensitivity and Specificity; Diagnostic Tests, Routine
PubMed: 38348799
DOI: 10.1080/01443615.2024.2311664 -
Journal of Magnetic Resonance Imaging :... May 2023Accurate diagnosis of axillary lymph node metastasis (ALNM) of breast cancer patients is important to guide local and systemic treatment. (Meta-Analysis)
Meta-Analysis
Different Imaging Modalities for the Diagnosis of Axillary Lymph Node Metastases in Breast Cancer: A Systematic Review and Network Meta-Analysis of Diagnostic Test Accuracy.
BACKGROUND
Accurate diagnosis of axillary lymph node metastasis (ALNM) of breast cancer patients is important to guide local and systemic treatment.
PURPOSE
To evaluate the diagnostic performance of different imaging modalities for ALNM in patients with breast cancer.
STUDY TYPE
Systematic review and network meta-analysis (NMA).
SUBJECTS
Sixty-one original articles with 8011 participants.
FIELD STRENGTH
1.5 T and 3.0 T.
ASSESSMENT
We used the QUADAS-2 and QUADAS-C tools to assess the risk of bias in eligible studies. The identified articles assessed ultrasonography (US), MRI, mammography, ultrasound elastography (UE), PET, CT, PET/CT, scintimammography, and PET/MRI.
STATISTICAL ANALYSIS
We used random-effects conventional meta-analyses and Bayesian network meta-analyses for data analyses. We used sensitivity and specificity, relative sensitivity and specificity, superiority index, and summary receiver operating characteristic curve (SROC) analysis to compare the diagnostic value of different imaging modalities.
RESULTS
Sixty-one studies evaluated nine imaging modalities. At patient level, sensitivities of the nine imaging modalities ranged from 0.27 to 0.84 and specificities ranged from 0.84 to 0.95. Patient-based NMA showed that UE had the highest superiority index (5.95) with the highest relative sensitivity of 1.13 (95% confidence interval [CI]: 0.93-1.29) among all imaging methods when compared to US. At lymph node level, MRI had the highest superiority index (6.91) with highest relative sensitivity of 1.13 (95% CI: 1.01-1.23) and highest relative specificity of 1.11 (95% CI: 0.95-1.23) among all imaging methods when compared to US. SROCs also showed that UE and MRI had the largest area under the curve (AUC) at patient level and lymph node level of 0.92 and 0.94, respectively.
DATA CONCLUSION
UE and MRI may be superior to other imaging modalities in the diagnosis of ALNM in breast cancer patients at the patient level and the lymph node level, respectively. Further studies are needed to provide high-quality evidence to validate our findings.
EVIDENCE LEVEL
3 TECHNICAL EFFICACY: Stage 2.
Topics: Humans; Female; Positron Emission Tomography Computed Tomography; Lymphatic Metastasis; Breast Neoplasms; Network Meta-Analysis; Bayes Theorem; Positron-Emission Tomography; Sensitivity and Specificity; Magnetic Resonance Imaging; Lymph Nodes; Diagnostic Tests, Routine
PubMed: 36054564
DOI: 10.1002/jmri.28399 -
Preventive Veterinary Medicine May 2018A systematic review was conducted to identify studies with data for statistical meta-analyses of sensitivity (Se) and specificity (Sp) of ante-mortem and post-mortem... (Review)
Review
A systematic review was conducted to identify studies with data for statistical meta-analyses of sensitivity (Se) and specificity (Sp) of ante-mortem and post-mortem diagnostic tests for bovine tuberculosis (bTB) in cattle. Members of a working group (WG) developed and tested search criteria and developed a standardised two-stage review process, to identify primary studies with numerator and denominator data for test performance and an agreed range of covariate data. No limits were applied to year, language, region or type of test in initial searches of electronic databases. In stage 1, titles and available abstracts were reviewed. References that complied with stage 1 selection criteria were reviewed in entirety and agreed data were extracted from references that complied with stage 2 selection criteria. At stage 1, 9782 references were reviewed and 261 (2.6%) passed through to stage 2 where 215 English language references were each randomly allocated to two of 18 WG reviewers and 46 references in other languages were allocated to native speakers. Agreement regarding eligibility between reviewers of the same reference at stage 2 was moderate (Kappa statistic = 0.51) and a resolution procedure was conducted. Only 119 references (published 1934-2009) were identified with eligible performance estimates for one or more of 14 different diagnostic test types; despite a comprehensive search strategy and the global impact of bTB. Searches of electronic databases for diagnostic test performance data were found to be nonspecific with regard to identifying references with diagnostic test Se or Sp data. Guidelines for the content of abstracts to research papers reporting diagnostic test performance are presented. The results of meta-analyses of the sensitivity and specificity of the tests, and of an evaluation of the methodological quality of the source references, are presented in accompanying papers (Nuñez-Garcia et al., 2017; Downs et al., 2017).
Topics: Animals; Autopsy; Cattle; Diagnostic Tests, Routine; Sensitivity and Specificity; Tuberculosis, Bovine
PubMed: 29395122
DOI: 10.1016/j.prevetmed.2017.11.004 -
Malaria Journal Apr 2023Health facilities' availability of malaria diagnostic tests and anti-malarial drugs (AMDs), and the correctness of treatment are critical for the appropriate case... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Health facilities' availability of malaria diagnostic tests and anti-malarial drugs (AMDs), and the correctness of treatment are critical for the appropriate case management, and malaria surveillance programs. It is also reliable evidence for malaria elimination certification in low-transmission settings. This meta-analysis aimed to estimate summary proportions for the availability of malaria diagnostic tests, AMDs, and the correctness of treatment.
METHODS
The Web of Science, Scopus, Medline, Embase, and Malaria Journal were systematically searched up to 30th January 2023. The study searched any records reporting the availability of diagnostic tests and AMDs and the correctness of malaria treatment. Eligibility and risk of bias assessment of studies were conducted independently in a blinded way by two reviewers. For the pooling of studies, meta-analysis using random effects model were carried out to estimate summary proportions of the availability of diagnostic tests, AMDs, and correctness of malaria treatment.
RESULTS
A total of 18 studies, incorporating 7,429 health facilities, 9,745 health workers, 41,856 febrile patients, and 15,398 malaria patients, and no study in low malaria transmission areas, were identified. The pooled proportion of the availability of malaria diagnostic tests, and the first-line AMDs in health facilities was 76% (95% CI 67-84); and 83% (95% CI 79-87), respectively. A pooled meta-analysis using random effects indicates the overall proportion of the correctness of malaria treatment 62% (95% CI 54-69). The appropriate malaria treatment was improved over time from 2009 to 2023. In the sub-group analysis, the correctness of treatment proportion was 53% (95% CI 50-63) for non-physicians health workers and 69% (95% CI 55-84) for physicians.
CONCLUSION
Findings of this review indicated that the correctness of malaria treatment and the availability of AMDs and diagnostic tests need improving to progress the malaria elimination stage.
Topics: Humans; Antimalarials; Diagnostic Tests, Routine; Malaria; Case Management; Health Personnel
PubMed: 37072759
DOI: 10.1186/s12936-023-04555-w -
Bulletin of the World Health... Jul 2022To evaluate the clinical accuracy of rapid diagnostic tests for the detection of Ebola virus. (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
To evaluate the clinical accuracy of rapid diagnostic tests for the detection of Ebola virus.
METHODS
We searched MEDLINE®, Embase® and Web of Science for articles published between 1976 and October 2021 reporting on clinical studies assessing the performance of Ebola virus rapid diagnostic tests compared with reverse transcription polymerase chain reaction (RT-PCR). We assessed study quality using the QUADAS-2 criteria. To estimate the pooled sensitivity and specificity of these rapid diagnostic tests, we used a bivariate random-effects meta-analysis.
FINDINGS
Our search identified 113 unique studies, of which nine met the inclusion criteria. The studies were conducted in the Democratic Republic of the Congo, Guinea, Liberia and Sierra Leone and they evaluated 12 rapid diagnostic tests. We included eight studies in the meta-analysis. The pooled sensitivity and specificity of the rapid tests were 86% (95% confidence interval, CI: 80-91) and 95% (95% CI: 91-97), respectively. However, pooled sensitivity decreased to 83% (95% CI: 77-88) after removing outliers. Pooled sensitivity increased to 90% (95% CI: 82-94) when analysis was restricted to studies using the RT-PCR from altona Diagnostics as gold standard. Pooled sensitivity increased to 99% (95% CI: 67-100) when the analysis was restricted to studies using whole or capillary blood specimens.
CONCLUSION
The included rapid diagnostic tests did not detect all the Ebola virus disease cases. While the sensitivity and specificity of these tests are moderate, they are still valuable tools, especially useful for triage and detecting Ebola virus in remote areas.
Topics: Diagnostic Tests, Routine; Ebolavirus; Hemorrhagic Fever, Ebola; Humans; Reverse Transcriptase Polymerase Chain Reaction; Sensitivity and Specificity
PubMed: 35813519
DOI: 10.2471/BLT.21.287496 -
Journal of Magnetic Resonance Imaging :... Jan 2021
Meta-Analysis
Editorial for "MRI vs. CT for the Detection of Liver Metastases in Patients With Pancreatic Carcinoma: A Comparative Diagnostic Test Accuracy Systematic Review and Meta-Analysis".
Topics: Diagnostic Tests, Routine; Humans; Liver Neoplasms; Magnetic Resonance Imaging; Pancreatic Neoplasms; Sensitivity and Specificity; Tomography, X-Ray Computed
PubMed: 32034836
DOI: 10.1002/jmri.27072 -
Journal of Medical Internet Research Dec 2021Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models.
OBJECTIVE
To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images.
METHODS
We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed.
RESULTS
Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected.
CONCLUSIONS
CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.
Topics: Capsule Endoscopy; Computers; Diagnostic Tests, Routine; Hemorrhage; Humans; Ulcer
PubMed: 34904949
DOI: 10.2196/33267 -
Transfusion Medicine Reviews Jan 2021Treatment guidelines recommend the routine use of point-of-care diagnostic tests for coagulopathy in the management of cardiac surgery patients at risk of severe... (Meta-Analysis)
Meta-Analysis Review
Treatment guidelines recommend the routine use of point-of-care diagnostic tests for coagulopathy in the management of cardiac surgery patients at risk of severe bleeding despite uncertainty as to their diagnostic accuracy. We performed a systematic review and meta-analysis of studies that evaluated the diagnostic accuracy of viscoelastometry, platelet function tests, and modified thromboelastography (TEG) tests, for coagulopathy in cardiac surgery patients. The reference standard included resternotomy for bleeding, transfusion of non-red cell components, or massive transfusion. We searched MEDLINE, EMBASE, CINAHL, and Clinical Trials.gov, from inception to June 2019. Study quality was assessed using QUADAS-2. Bivariate models were used to estimate summary sensitivity and specificity with (95% confidence intervals). All 29 studies (7440 participants) included in the data synthesis evaluated the tests as predictors of bleeding. No study evaluated their role in the management of bleeding. None was at low risk of bias. Four were judged as low concern regarding applicability. Pooled estimates of diagnostic accuracy were; Viscoelastic tests, 12 studies, sensitivity 0.61 (0.44, 0.76), specificity 0.83 (0.70, 0.91) with significant heterogeneity. Platelet function tests, 12 studies, sensitivity 0.63 (0.53, 0.72), specificity 0.75 (0.64, 0.84) with significant heterogeneity. TEG modification tests, 3 studies, sensitivity 0.80 (0.67, 0.89), specificity 0.76 (0.69, 0.82) with no evidence of heterogeneity. Studies reporting the highest values for sensitivity and specificity had important methodological limitations. In conclusion, we did not demonstrate predictive accuracy for commonly used point-of-care devices for coagulopathic bleeding in cardiac surgery. However, the certainty of the evidence was low.
Topics: Blood Coagulation Disorders; Cardiac Surgical Procedures; Diagnostic Tests, Routine; Humans; Point-of-Care Testing; Thrombelastography
PubMed: 33187808
DOI: 10.1016/j.tmrv.2020.09.012 -
Academic Radiology Nov 2021To perform a meta-analysis to compare the diagnostic test accuracy (DTA) of deep learning (DL) in detecting coronavirus disease 2019 (COVID-19), and to investigate how... (Meta-Analysis)
Meta-Analysis
RATIONALE AND OBJECTIVE
To perform a meta-analysis to compare the diagnostic test accuracy (DTA) of deep learning (DL) in detecting coronavirus disease 2019 (COVID-19), and to investigate how network architecture and type of datasets affect DL performance.
MATERIALS AND METHODS
We searched PubMed, Web of Science and Inspec from January 1, 2020, to December 3, 2020, for retrospective and prospective studies on deep learning detection with at least reported sensitivity and specificity. Pooled DTA was obtained using random-effect models. Sub-group analysis between studies was also carried out for data source and network architectures.
RESULTS
The pooled sensitivity and specificity were 91% (95% confidence interval [CI]: 88%, 93%; I = 69%) and 92% (95% CI: 88%, 94%; I = 88%), respectively for 19 studies. The pooled AUC and diagnostic odds ratio (DOR) were 0.95 (95% CI: 0.88, 0.92) and 112.5 (95% CI: 57.7, 219.3; I = 90%) respectively. The overall accuracy, recall, F1-score, LR and LR are 89.5%, 89.5%, 89.7%, 23.13 and 0.13. Sub-group analysis shows that the sensitivity and DOR significantly vary with the type of network architectures and sources of data with low heterogeneity are (I = 0%) and (I = 18%) for ResNet architecture and single-source datasets, respectively.
CONCLUSION
The diagnosis of COVID-19 via deep learning has achieved incredible performance, and the source of datasets, as well as network architectures, strongly affect DL performance.
Topics: COVID-19; Deep Learning; Diagnostic Tests, Routine; Humans; Prospective Studies; Retrospective Studies; SARS-CoV-2
PubMed: 34649779
DOI: 10.1016/j.acra.2021.08.008