-
BMJ (Clinical Research Ed.) Jun 2022To evaluate the diagnostic performance of N-terminal pro-B-type natriuretic peptide (NT-proBNP) thresholds for acute heart failure and to develop and validate a decision... (Meta-Analysis)
Meta-Analysis
OBJECTIVES
To evaluate the diagnostic performance of N-terminal pro-B-type natriuretic peptide (NT-proBNP) thresholds for acute heart failure and to develop and validate a decision support tool that combines NT-proBNP concentrations with clinical characteristics.
DESIGN
Individual patient level data meta-analysis and modelling study.
SETTING
Fourteen studies from 13 countries, including randomised controlled trials and prospective observational studies.
PARTICIPANTS
Individual patient level data for 10 369 patients with suspected acute heart failure were pooled for the meta-analysis to evaluate NT-proBNP thresholds. A decision support tool (Collaboration for the Diagnosis and Evaluation of Heart Failure (CoDE-HF)) that combines NT-proBNP with clinical variables to report the probability of acute heart failure for an individual patient was developed and validated.
MAIN OUTCOME MEASURE
Adjudicated diagnosis of acute heart failure.
RESULTS
Overall, 43.9% (4549/10 369) of patients had an adjudicated diagnosis of acute heart failure (73.3% (2286/3119) and 29.0% (1802/6208) in those with and without previous heart failure, respectively). The negative predictive value of the guideline recommended rule-out threshold of 300 pg/mL was 94.6% (95% confidence interval 91.9% to 96.4%); despite use of age specific rule-in thresholds, the positive predictive value varied at 61.0% (55.3% to 66.4%), 73.5% (62.3% to 82.3%), and 80.2% (70.9% to 87.1%), in patients aged <50 years, 50-75 years, and >75 years, respectively. Performance varied in most subgroups, particularly patients with obesity, renal impairment, or previous heart failure. CoDE-HF was well calibrated, with excellent discrimination in patients with and without previous heart failure (area under the receiver operator curve 0.846 (0.830 to 0.862) and 0.925 (0.919 to 0.932) and Brier scores of 0.130 and 0.099, respectively). In patients without previous heart failure, the diagnostic performance was consistent across all subgroups, with 40.3% (2502/6208) identified at low probability (negative predictive value of 98.6%, 97.8% to 99.1%) and 28.0% (1737/6208) at high probability (positive predictive value of 75.0%, 65.7% to 82.5%) of having acute heart failure.
CONCLUSIONS
In an international, collaborative evaluation of the diagnostic performance of NT-proBNP, guideline recommended thresholds to diagnose acute heart failure varied substantially in important patient subgroups. The CoDE-HF decision support tool incorporating NT-proBNP as a continuous measure and other clinical variables provides a more consistent, accurate, and individualised approach.
STUDY REGISTRATION
PROSPERO CRD42019159407.
Topics: Biomarkers; Diagnosis, Differential; Heart Failure; Humans; Natriuretic Peptide, Brain; Observational Studies as Topic; Peptide Fragments; Predictive Value of Tests; Prospective Studies
PubMed: 35697365
DOI: 10.1136/bmj-2021-068424 -
PloS One 2022Artificial intelligence (AI) algorithms have been applied to diagnose temporomandibular disorders (TMDs). However, studies have used different patient selection... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Artificial intelligence (AI) algorithms have been applied to diagnose temporomandibular disorders (TMDs). However, studies have used different patient selection criteria, disease subtypes, input data, and outcome measures. Resultantly, the performance of the AI models varies.
OBJECTIVE
This study aimed to systematically summarize the current literature on the application of AI technologies for diagnosis of different TMD subtypes, evaluate the quality of these studies, and assess the diagnostic accuracy of existing AI models.
MATERIALS AND METHODS
The study protocol was carried out based on the preferred reporting items for systematic review and meta-analysis protocols (PRISMA). The PubMed, Embase, and Web of Science databases were searched to find relevant articles from database inception to June 2022. Studies that used AI algorithms to diagnose at least one subtype of TMD and those that assessed the performance of AI algorithms were included. We excluded studies on orofacial pain that were not directly related to the TMD, such as studies on atypical facial pain and neuropathic pain, editorials, book chapters, and excerpts without detailed empirical data. The risk of bias was assessed using the QUADAS-2 tool. We used Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) to provide certainty of evidence.
RESULTS
A total of 17 articles for automated diagnosis of masticatory muscle disorders, TMJ osteoarthrosis, internal derangement, and disc perforation were included; they were retrospective studies, case-control studies, cohort studies, and a pilot study. Seven studies were subjected to a meta-analysis for diagnostic accuracy. According to the GRADE, the certainty of evidence was very low. The performance of the AI models had accuracy and specificity ranging from 84% to 99.9% and 73% to 100%, respectively. The pooled accuracy was 0.91 (95% CI 0.76-0.99), I2 = 97% (95% CI 0.96-0.98), p < 0.001.
CONCLUSIONS
Various AI algorithms developed for diagnosing TMDs may provide additional clinical expertise to increase diagnostic accuracy. However, it should be noted that a high risk of bias was present in the included studies. Also, certainty of evidence was very low. Future research of higher quality is strongly recommended.
Topics: Artificial Intelligence; Facial Pain; Humans; Pilot Projects; Retrospective Studies; Temporomandibular Joint Disorders
PubMed: 35980894
DOI: 10.1371/journal.pone.0272715 -
Journal of Clinical Pathology Jul 2021Digital pathology (DP) has the potential to fundamentally change the way that histopathology is practised, by streamlining the workflow, increasing efficiency, improving... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Digital pathology (DP) has the potential to fundamentally change the way that histopathology is practised, by streamlining the workflow, increasing efficiency, improving diagnostic accuracy and facilitating the platform for implementation of artificial intelligence-based computer-assisted diagnostics. Although the barriers to wider adoption of DP have been multifactorial, limited evidence of reliability has been a significant contributor. A meta-analysis to demonstrate the combined accuracy and reliability of DP is still lacking in the literature.
OBJECTIVES
We aimed to review the published literature on the diagnostic use of DP and to synthesise a statistically pooled evidence on safety and reliability of DP for routine diagnosis (primary and secondary) in the context of validation process.
METHODS
A comprehensive literature search was conducted through PubMed, Medline, EMBASE, Cochrane Library and Google Scholar for studies published between 2013 and August 2019. The search protocol identified all studies comparing DP with light microscopy (LM) reporting for diagnostic purposes, predominantly including H&E-stained slides. Random-effects meta-analysis was used to pool evidence from the studies.
RESULTS
Twenty-five studies were deemed eligible to be included in the review which examined a total of 10 410 histology samples (average sample size 176). For overall concordance (clinical concordance), the agreement percentage was 98.3% (95% CI 97.4 to 98.9) across 24 studies. A total of 546 major discordances were reported across 25 studies. Over half (57%) of these were related to assessment of nuclear atypia, grading of dysplasia and malignancy. These were followed by challenging diagnoses (26%) and identification of small objects (16%).
CONCLUSION
The results of this meta-analysis indicate equivalent performance of DP in comparison with LM for routine diagnosis. Furthermore, the results provide valuable information concerning the areas of diagnostic discrepancy which may warrant particular attention in the transition to DP.
Topics: Artificial Intelligence; Diagnosis, Computer-Assisted; Humans; Image Interpretation, Computer-Assisted; Microscopy; Pathology, Clinical
PubMed: 32934103
DOI: 10.1136/jclinpath-2020-206764 -
Diseases of the Esophagus : Official... Nov 2023Early detection of esophageal cancer is limited by accurate endoscopic diagnosis of subtle macroscopic lesions. Endoscopic interpretation is subject to expertise,... (Meta-Analysis)
Meta-Analysis
Early detection of esophageal cancer is limited by accurate endoscopic diagnosis of subtle macroscopic lesions. Endoscopic interpretation is subject to expertise, diagnostic skill, and thus human error. Artificial intelligence (AI) in endoscopy is increasingly bridging this gap. This systematic review and meta-analysis consolidate the evidence on the use of AI in the endoscopic diagnosis of esophageal cancer. The systematic review was carried out using Pubmed, MEDLINE and Ovid EMBASE databases and articles on the role of AI in the endoscopic diagnosis of esophageal cancer management were included. A meta-analysis was also performed. Fourteen studies (1590 patients) assessed the use of AI in endoscopic diagnosis of esophageal squamous cell carcinoma-the pooled sensitivity and specificity were 91.2% (84.3-95.2%) and 80% (64.3-89.9%). Nine studies (478 patients) assessed AI capabilities of diagnosing esophageal adenocarcinoma with the pooled sensitivity and specificity of 93.1% (86.8-96.4) and 86.9% (81.7-90.7). The remaining studies formed the qualitative summary. AI technology, as an adjunct to endoscopy, can assist in accurate, early detection of esophageal malignancy. It has shown superior results to endoscopists alone in identifying early cancer and assessing depth of tumor invasion, with the added benefit of not requiring a specialized skill set. Despite promising results, the application in real-time endoscopy is limited, and further multicenter trials are required to accurately assess its use in routine practice.
Topics: Humans; Esophageal Neoplasms; Esophageal Squamous Cell Carcinoma; Artificial Intelligence; Endoscopy; Adenocarcinoma
PubMed: 37480192
DOI: 10.1093/dote/doad048 -
Diagnostic and Interventional Imaging 2020The purpose of this study was to perform a systematic review of current literature describing the efficacy and technical outcomes of transarterial liver therapies using... (Meta-Analysis)
Meta-Analysis Review
PURPOSE
The purpose of this study was to perform a systematic review of current literature describing the efficacy and technical outcomes of transarterial liver therapies using automated feeder detection (AFD) software.
MATERIALS AND METHODS
This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A structured search was performed in the PubMed, SCOPUS, and Embase databases of patients undergoing locoregional therapy of liver tumors utilizing AFD software. Demographic data, procedure data (including radiometrics) and tumor response rate were recorded. Where available, performance of AFD was compared to conventional digital subtraction angiography (DSA) and cone-beam CT (CBCT) without AFD.
RESULTS
A total of 14 full-text manuscripts met inclusion criteria, comprising 1042 tumors in 604 patients (305 men, 156 women; mean age, 68.6±6.0 [SD] years), including 537 patients with hepatocellular carcinoma, 8 with metastases from neuroendocrine tumors, and 59 patients without reported etiology. Reported sensitivity of AFD ranged between 86% and 98.5%, compared to DSA alone (38% - 64%) or DSA in combination with CBCT (69% - 81%). Three studies reported tumor response by modified response evaluation criteria in solid tumors (mRECIST) guidelines, with complete response in the range of 60% - 69%.
CONCLUSION
AFD is a promising new technology for the identification of intrahepatic and extrahepatic tumor-feeding arteries and should be considered a useful adjunct to conventional DSA and CBCT in the treatment of liver tumors.
Topics: Aged; Angiography, Digital Subtraction; Carcinoma, Hepatocellular; Chemoembolization, Therapeutic; Cone-Beam Computed Tomography; Female; Humans; Liver Neoplasms; Male; Middle Aged; Software
PubMed: 32035822
DOI: 10.1016/j.diii.2020.01.011 -
Neuroradiology Aug 2022Endoscopic biopsy is recommended for diagnosis of nasopharyngeal carcinoma (NPC). A proportion of lesions are hidden from endoscopic view but detected with magnetic... (Meta-Analysis)
Meta-Analysis Review
PURPOSE
Endoscopic biopsy is recommended for diagnosis of nasopharyngeal carcinoma (NPC). A proportion of lesions are hidden from endoscopic view but detected with magnetic resonance imaging (MRI). This systematic review and meta-analysis investigated the diagnostic performance of MRI for detection of NPC.
METHODS
An electronic search of twelve databases and registries was performed. Studies were included if they compared the diagnostic accuracy of MRI to a reference standard (histopathology) in patients suspected of having NPC. The primary outcome was accuracy for detection of NPC. Random-effects models were used to pool outcomes for sensitivity, specificity, and positive and negative likelihood ratio (LR). Bias and applicability were assessed using the modified QUADAS-2 tool.
RESULTS
Nine studies were included involving 1736 patients of whom 337 were diagnosed with NPC. MRI demonstrated a pooled sensitivity of 98.1% (95% CI 95.2-99.3%), specificity of 91.7% (95% CI 88.3-94.2%), negative LR of 0.02 (95% CI 0.01-0.05), and positive LR of 11.9 (95% CI 8.35-16.81) for detection of NPC. Most studies were performed in regions where NPC is endemic, and there was a risk of selection bias due to inclusion of retrospective studies and one case-control study. There was limited reporting of study randomization strategy.
CONCLUSION
This study demonstrates that MRI has a high pooled sensitivity, specificity, and negative predictive value for detection of NPC. MRI may be useful for lesion detection prior to endoscopic biopsy and aid the decision to avoid biopsy in patients with a low post-test probability of disease.
Topics: Case-Control Studies; Humans; Magnetic Resonance Imaging; Nasopharyngeal Carcinoma; Nasopharyngeal Neoplasms; Retrospective Studies; Sensitivity and Specificity
PubMed: 35499636
DOI: 10.1007/s00234-022-02941-w -
Alimentary Pharmacology & Therapeutics Mar 2022Artificial intelligence (AI) has recently been applied to endoscopy and questionnaires for the evaluation of oesophageal diseases (ODs). (Meta-Analysis)
Meta-Analysis
BACKGROUND
Artificial intelligence (AI) has recently been applied to endoscopy and questionnaires for the evaluation of oesophageal diseases (ODs).
AIM
We performed a systematic review with meta-analysis to evaluate the performance of AI in the diagnosis of malignant and benign OD.
METHODS
We searched MEDLINE, EMBASE, EMBASE Classic and the Cochrane Library. A bivariate random-effect model was used to calculate pooled diagnostic efficacy of AI models and endoscopists. The reference tests were histology for neoplasms and the clinical and instrumental diagnosis for gastro-oesophageal reflux disease (GERD). The pooled area under the summary receiver operating characteristic (AUROC), sensitivity, specificity, positive and negative likelihood ratio (PLR and NLR) and diagnostic odds ratio (DOR) were estimated.
RESULTS
For the diagnosis of Barrett's neoplasia, AI had AUROC of 0.90, sensitivity 0.89, specificity 0.86, PLR 6.50, NLR 0.13 and DOR 50.53. AI models' performance was comparable with that of endoscopists (P = 0.35). For the diagnosis of oesophageal squamous cell carcinoma, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.97, 0.95, 0.92, 12.65, 0.05 and DOR 258.36, respectively. In this task, AI performed better than endoscopists although without statistically significant differences. In the detection of abnormal intrapapillary capillary loops, the performance of AI was: AUROC 0.98, sensitivity 0.94, specificity 0.94, PLR 14.75, NLR 0.07 and DOR 225.83. For the diagnosis of GERD based on questionnaires, the AUROC, sensitivity, specificity, PLR, NLR and DOR were 0.99, 0.97, 0.97, 38.26, 0.03 and 1159.6, respectively.
CONCLUSIONS
AI demonstrated high performance in the clinical and endoscopic diagnosis of OD.
Topics: Artificial Intelligence; Endoscopy; Gastroesophageal Reflux; Humans; Odds Ratio; ROC Curve
PubMed: 35098562
DOI: 10.1111/apt.16778 -
The Lancet. Digital Health Dec 2023Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease... (Meta-Analysis)
Meta-Analysis
Machine learning and deep learning predictive models for long-term prognosis in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis.
BACKGROUND
Machine learning and deep learning models have been increasingly used to predict long-term disease progression in patients with chronic obstructive pulmonary disease (COPD). We aimed to summarise the performance of such prognostic models for COPD, compare their relative performances, and identify key research gaps.
METHODS
We conducted a systematic review and meta-analysis to compare the performance of machine learning and deep learning prognostic models and identify pathways for future research. We searched PubMed, Embase, the Cochrane Library, ProQuest, Scopus, and Web of Science from database inception to April 6, 2023, for studies in English using machine learning or deep learning to predict patient outcomes at least 6 months after initial clinical presentation in those with COPD. We included studies comprising human adults aged 18-90 years and allowed for any input modalities. We reported area under the receiver operator characteristic curve (AUC) with 95% CI for predictions of mortality, exacerbation, and decline in forced expiratory volume in 1 s (FEV). We reported the degree of interstudy heterogeneity using Cochran's Q test (significant heterogeneity was defined as p≤0·10 or I>50%). Reporting quality was assessed using the TRIPOD checklist and a risk-of-bias assessment was done using the PROBAST checklist. This study was registered with PROSPERO (CRD42022323052).
FINDINGS
We identified 3620 studies in the initial search. 18 studies were eligible, and, of these, 12 used conventional machine learning and six used deep learning models. Seven models analysed exacerbation risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·69-0·85]) and there was significant heterogeneity (I 97%, p<0·0001). 11 models analysed mortality risk, with only six reporting AUC and 95% CI on internal validation datasets (pooled AUC 0·77 [95% CI 0·74-0·80]) with significant degrees of heterogeneity (I 60%, p=0·027). Two studies assessed decline in lung function and were unable to be pooled. Machine learning and deep learning models did not show significant improvement over pre-existing disease severity scores in predicting exacerbations (p=0·24). Three studies directly compared machine learning models against pre-existing severity scores for predicting mortality and pooled performance did not differ (p=0·57). Of the five studies that performed external validation, performance was worse than or equal to regression models. Incorrect handling of missing data, not reporting model uncertainty, and use of datasets that were too small relative to the number of predictive features included provided the largest risks of bias.
INTERPRETATION
There is limited evidence that conventional machine learning and deep learning prognostic models demonstrate superior performance to pre-existing disease severity scores. More rigorous adherence to reporting guidelines would reduce the risk of bias in future studies and aid study reproducibility.
FUNDING
None.
Topics: Adult; Humans; Reproducibility of Results; Deep Learning; Quality of Life; Pulmonary Disease, Chronic Obstructive; Prognosis
PubMed: 38000872
DOI: 10.1016/S2589-7500(23)00177-2 -
Journal of Investigative Medicine High... 2021Jejunal Dieulafoy's lesion is an exceedingly rare but important cause of gastrointestinal bleeding. It frequently presents as a diagnostic and therapeutic conundrum due...
Jejunal Dieulafoy's lesion is an exceedingly rare but important cause of gastrointestinal bleeding. It frequently presents as a diagnostic and therapeutic conundrum due to the rare occurrence, intermittent bleeding symptoms often requiring prompt clinical action, variability in the detection and treatment methods, and the risk of rebleeding. We performed a systematic literature search of MEDLINE, Cochrane, Embase, and Scopus databases regarding jejunal Dieulafoy's lesio from inception till June 2020. A total of 136 cases were retrieved from 76 articles. The mean age was 55 ± 24 years, with 55% of cases reported in males. Patients commonly presented with melena (33%), obscure-overt gastrointestinal bleeding (29%), and hemodynamic compromise (20%). Hypertension (26%), prior gastrointestinal surgery (14%), and valvular heart disease (13%) were the major underlying disorders. Conventional endoscopy often failed but single- and double-balloon enteroscopy identified the lesion in 96% and 98% of patients, respectively. There was no consensus on the treatment. Endoscopic therapy was instituted in 64% of patients. Combination therapy (34%) with two or more endoscopic modalities, was the preferred approach. With regard to endoscopic monotherapy, hemoclipping (19%) and argon plasma coagulation (4%) were frequently employed procedures. Furthermore, direct surgical intervention in 32% and angiographic embolization was performed in 4% of patients. The rebleeding rate was 13.4%, with a mean follow-up duration of 17.6 ± 21.98 months. The overall mortality rate was 4.4%. Jejunal Dieulafoy's lesion is still difficult to diagnose and manage. Although the standard diagnostic and therapeutic modalities remain to be determined, device-assisted enteroscopy might yield promising outcomes.
Topics: Endoscopy, Gastrointestinal; Gastrointestinal Hemorrhage; Humans; Male; Middle Aged
PubMed: 33472441
DOI: 10.1177/2324709620987703 -
Clinical Journal of Gastroenterology Apr 2022In 2019, the American Society for Gastrointestinal Endoscopy (ASGE) guideline on the endoscopic management of choledocholithiasis modified the individual predictors of... (Meta-Analysis)
Meta-Analysis Review
In 2019, the American Society for Gastrointestinal Endoscopy (ASGE) guideline on the endoscopic management of choledocholithiasis modified the individual predictors of choledocholithiasis proposed in the widely referenced 2010 guideline to improve predictive performance. Nevertheless, the primary literature, especially for the 2019 iteration, is limited. We performed a systematic review with meta-analysis to examine the diagnostic performance of the 2010, and where possible the 2019, predictors. PROSPERO protocol CRD42020194226. A comprehensive literature search from 2001 to 2020 was performed to identify studies on the diagnostic performance of any of the 2010 and 2019 ASGE choledocholithiasis predictors. Identified studies underwent keyword screening, abstract review, and full-text review. The primary outcomes included multivariate odds ratios (ORs) and 95% confidence intervals for each criterion. Secondary outcomes were reported sensitivities, specificities, and positive and negative predictive value. A total of 20 studies met inclusion criteria. Based on reported ORs, of the 2010 guideline "very strong" predictors, ultrasound with stone had the strongest performance. Of the "strong" predictors, CBD > 6 mm demonstrated the strongest performance. "Moderate" predictors had inconsistent and/or weak performance; moreover, all studies reported gallstone pancreatitis as non-predictive of choledocholithiasis. Only one study examined the new predictor (bilirubin > 4 mg/dL and CBD > 6 mm) proposed in the 2019 guideline. Based on this review, aside from CBD stone on ultrasound, there is discordance between the proposed strength of 2010 choledocholithiasis predictors and their published diagnostic performance. The 2019 guideline appears to do away with the weakest 2010 predictors.
Topics: Cholangiopancreatography, Endoscopic Retrograde; Choledocholithiasis; Endoscopy, Gastrointestinal; Humans; Predictive Value of Tests; Retrospective Studies; Ultrasonography; United States
PubMed: 35072902
DOI: 10.1007/s12328-021-01575-4