-
International Journal of Surgery... Dec 2023Diagnosing pancreatic lesions, including chronic pancreatitis, autoimmune pancreatitis, and pancreatic cancer, poses a challenge and, as a result, is time-consuming. To... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Diagnosing pancreatic lesions, including chronic pancreatitis, autoimmune pancreatitis, and pancreatic cancer, poses a challenge and, as a result, is time-consuming. To tackle this issue, artificial intelligence (AI) has been increasingly utilized over the years. AI can analyze large data sets with heightened accuracy, reduce interobserver variability, and can standardize the interpretation of radiologic and histopathologic lesions. Therefore, this study aims to review the use of AI in the detection and differentiation of pancreatic space-occupying lesions and to compare AI-assisted endoscopic ultrasound (EUS) with conventional EUS in terms of their detection capabilities.
METHODS
Literature searches were conducted through PubMed/Medline, SCOPUS, and Embase to identify studies eligible for inclusion. Original articles, including observational studies, randomized control trials, systematic reviews, meta-analyses, and case series specifically focused on AI-assisted EUS in adults, were included. Data were extracted and pooled, and a meta-analysis was conducted using Meta-xl. For results exhibiting significant heterogeneity, a random-effects model was employed; otherwise, a fixed-effects model was utilized.
RESULTS
A total of 21 studies were included in the review with four studies pooled for a meta-analysis. A pooled accuracy of 93.6% (CI 90.4-96.8%) was found using the random-effects model on four studies that showed significant heterogeneity ( P <0.05) in the Cochrane's Q test. Further, a pooled sensitivity of 93.9% (CI 92.4-95.3%) was found using a fixed-effects model on seven studies that showed no significant heterogeneity in the Cochrane's Q test. When it came to pooled specificity, a fixed-effects model was utilized in six studies that showed no significant heterogeneity in the Cochrane's Q test and determined as 93.1% (CI 90.7-95.4%). The pooled positive predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 91.6% (CI 87.3-95.8%). The pooled negative predictive value which was done using the random-effects model on six studies that showed significant heterogeneity was 93.6% (CI 90.4-96.8%).
CONCLUSION
AI-assisted EUS shows a high degree of accuracy in the detection and differentiation of pancreatic space-occupying lesions over conventional EUS. Its application may promote prompt and accurate diagnosis of pancreatic pathologies.
Topics: Adult; Humans; Artificial Intelligence; Sensitivity and Specificity; Pancreas; Endosonography; Pancreatic Neoplasms
PubMed: 37800594
DOI: 10.1097/JS9.0000000000000717 -
Nutrition, Metabolism, and... Aug 2023The Controlling Nutritional Status (CONUT) score is a tool for assessing the risk of malnutrition (undernutrition) that can be calculated from albumin concentration,... (Meta-Analysis)
Meta-Analysis
AIMS
The Controlling Nutritional Status (CONUT) score is a tool for assessing the risk of malnutrition (undernutrition) that can be calculated from albumin concentration, total peripheral lymphocyte count, and total cholesterol concentration. CONUT score has been proposed as a promising prognostic marker in several clinical settings; however, a consensus on its prognostic value in patients with stroke is lacking. The aim of this systematic review and meta-analysis was to evaluate the relationship between CONUT score and clinical outcomes in patients with stroke based on all current available studies.
DATA SYNTHESIS
Systematic research on PubMed, Scopus and Web of Science from inception to February 2023 was performed on the association between CONUT score and clinical outcomes in patients with stroke. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses were followed. Methodological quality was evaluated using the Newcastle-Ottawa Scale quality assessment tool. Pooled effect estimation was calculated by a random-effect model. Through the initial literature search, 15 studies (all high-quality) including 16 929 patients were found to be eligible and analysed in the meta-analysis. A significant risk of malnutrition (in most studies defined by a CONUT score ≥5) was directly associated with mortality, higher risk of poor functional outcome according to the modified Rankin Scale and total infection development. Evidence was consistent for acute ischaemic stroke and preliminary for acute haemorrhagic stroke.
CONCLUSION
CONUT score is an independent prognostic indicator, and it is associated with major disability and infection development during hospitalisation.
PROSPERO ID
CRD42022306560.
Topics: Humans; Nutritional Status; Brain Ischemia; Stroke; Malnutrition; Prognosis; Retrospective Studies; Nutrition Assessment
PubMed: 37336716
DOI: 10.1016/j.numecd.2023.05.012 -
BMC Medical Informatics and Decision... Jul 2023Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are...
INTRODUCTION
Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients' outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC.
METHODS
We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as "ML", "Deep Learning (DL (", "Neural Networks (NN)", "Esophagus", "EC" and "Early Detection". After applying inclusion and exclusion criteria, 31 articles were retained for full review.
RESULTS
The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods.
CONCLUSION
Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.
Topics: Humans; Deep Learning; Early Detection of Cancer; Machine Learning; Neural Networks, Computer; Esophageal Neoplasms
PubMed: 37460991
DOI: 10.1186/s12911-023-02235-y -
European Journal of Physical and... Dec 2023Adhesive capsulitis, a condition marked by pain and stiffness of the shoulder, can have a frustrating clinical course for patients and health care professionals. Despite...
INTRODUCTION
Adhesive capsulitis, a condition marked by pain and stiffness of the shoulder, can have a frustrating clinical course for patients and health care professionals. Despite huge research interest, a universally accepted and used definition of clinical criteria for the diagnosis of adhesive capsulitis is currently still lacking. This systematic review aimed to identify diagnostic values for clinical examinations tests used in the diagnosis of adhesive capsulitis.
EVIDENCE ACQUISITION
A total of 5 electronic databases (PubMed, Web of Science, Embase, Cochrane Central Register of Controlled Trials [CENTRAL] and PEDro) were searched for relevant studies from 2002 until October 2022 using the terms: "adhesive capsulitis AND diagnosis" and "frozen shoulder AND diagnosis." The Downs and Black Checklist (modified) was used to assess the risk of bias. The study protocol was prospectively registered at the International prospective register of systematic reviews (PROSPERO, CRD42022365993).
EVIDENCE SYNTHESIS
The initial database search identified 1799 studies, of which 9 (0.50%) were eventually included in the systematic review. Non-intrusive shoulder range of motion measurements in patients with adhesive capsulitis using the Kinect for Windows (Microsoft, Redmond, WA, USA) showed high correlation with clinical range of motion measurement. Two specific clinical tests, the affected-unaffected shoulder approach of the Coracoid Pain Test and the Distension Test in Passive External Rotation, were identified and presented excellent sensibility and specificity in the diagnosis of adhesive capsulitis, in their original study. Comparison between clinical tests was not possible due to the heterogeneity in clinical tools.
CONCLUSIONS
This systematic review identified several physical examination tests developed for the diagnosis of adhesive capsulitis but could not compare them nor advance a set of clinical diagnostic tests that are scientifically validated. Further research is warranted to obtain validation of clinical diagnosis tools for adhesive capsulitis.
Topics: Humans; Bursitis; Pain; Range of Motion, Articular; Shoulder Joint
PubMed: 37737049
DOI: 10.23736/S1973-9087.23.07940-6 -
British Journal of Cancer Oct 2023Detecting cancer early is essential to improving cancer outcomes. Minoritized groups remain underrepresented in early detection cancer research, which means that... (Review)
Review
Detecting cancer early is essential to improving cancer outcomes. Minoritized groups remain underrepresented in early detection cancer research, which means that findings and interventions are not generalisable across the population, thus exacerbating disparities in cancer outcomes. In light of these challenges, this paper sets out twelve recommendations to build relations of trust and include minoritized groups in ED cancer research. The Recommendations were formulated by a range of stakeholders at the 2022 REPRESENT consensus-building workshop and are based on empirical data, including a systematic literature review and two ethnographic case studies in the US and the UK. The recommendations focus on: Long-term relationships that build trust; Sharing available resources; Inclusive and accessible communication; Harnessing community expertise; Unique risks and benefits; Compensation and support; Representative samples; Demographic data; Post-research support; Sharing results; Research training; Diversifying research teams. For each recommendation, the paper outlines the rationale, specifications for how different stakeholders may implement it, and advice for best practices. Instead of isolated recruitment, public involvement and engagement activities, the recommendations here aim to advance mutually beneficial and trusting relationships between researchers and research participants embedded in ED cancer research institutions.
Topics: Humans; Trust; Early Detection of Cancer; Neoplasms
PubMed: 37689805
DOI: 10.1038/s41416-023-02414-8 -
Clinical Microbiology and Infection :... Apr 2024Centor and McIsaac scores are clinical prediction rules for diagnosing group A streptococcus (GAS) infection in patients with pharyngitis. Their recommended thresholds... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Centor and McIsaac scores are clinical prediction rules for diagnosing group A streptococcus (GAS) infection in patients with pharyngitis. Their recommended thresholds vary between guidelines.
OBJECTIVES
To estimate the sensitivity and specificity of the McIsaac and Centor scores to diagnose GAS pharyngitis and evaluate their impact on antibiotic prescribing at each threshold in patients presenting to secondary care.
DATA SOURCES
MEDLINE, Embase, and Web of Science were searched from inception to September 2022.
STUDY ELIGIBILITY CRITERIA
Studies of patients presenting with acute pharyngitis to emergency or outpatient clinics that estimated the accuracy of McIsaac or Centor scores against throat cultures and/or rapid antigen detection tests (RADT) as reference standards.
TESTS
Centor or McIsaac score.
REFERENCE STANDARD
Throat cultures and/or RADT.
ASSESSMENT OF RISK OF BIAS
Quality Assessment of Diagnostic Accuracy Studies.
METHODS OF DATA SYNTHESIS
The sensitivities and specificities of the McIsaac and Centor scores were pooled at each threshold using bivariate random effects meta-analysis.
RESULTS
Fourteen studies were included (eight McIsaac and six Centor scores). Eight studies had unclear and six had a high risk of bias. The McIsaac score had higher estimated sensitivity and lower specificity relative to Centor scores at equivalent thresholds but with wide and overlapping confidence regions. Using either score as a triage to RADT to decide antibiotic treatment would reduce antibiotic prescription to patients with non-GAS pharyngitis relative to RADT test for everyone, but also reduce antibiotic prescription to patients with GAS.
DISCUSSION
Centor and McIsaac scores are equally ineffective at triaging patients who need antibiotics presenting with pharyngitis at hospitals. At high thresholds, too many true positive cases are missed, whereas at low thresholds, too many false positives are treated, leading to the over prescription of antibiotics. The former may be compensated by adequate safety netting by clinicians, ensuring that patients can seek help if symptoms worsen.
Topics: Humans; Secondary Care; Streptococcal Infections; Pharyngitis; Streptococcus pyogenes; Anti-Bacterial Agents; Sensitivity and Specificity
PubMed: 38182052
DOI: 10.1016/j.cmi.2023.12.025 -
Frontiers in Artificial Intelligence 2023Hepatocellular carcinoma is a malignant neoplasm of the liver and a leading cause of cancer-related deaths worldwide. The multimodal data combines several modalities,...
BACKGROUND
Hepatocellular carcinoma is a malignant neoplasm of the liver and a leading cause of cancer-related deaths worldwide. The multimodal data combines several modalities, such as medical images, clinical parameters, and electronic health record (EHR) reports, from diverse sources to accomplish the diagnosis of liver cancer. The introduction of deep learning models with multimodal data can enhance the diagnosis and improve physicians' decision-making for cancer patients.
OBJECTIVE
This scoping review explores the use of multimodal deep learning techniques (i.e., combining medical images and EHR data) in diagnosing and prognosis of hepatocellular carcinoma (HCC) and cholangiocarcinoma (CCA).
METHODOLOGY
A comprehensive literature search was conducted in six databases along with forward and backward references list checking of the included studies. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping review guidelines were followed for the study selection process. The data was extracted and synthesized from the included studies through thematic analysis.
RESULTS
Ten studies were included in this review. These studies utilized multimodal deep learning to predict and diagnose hepatocellular carcinoma (HCC), but no studies examined cholangiocarcinoma (CCA). Four imaging modalities (CT, MRI, WSI, and DSA) and 51 unique EHR records (clinical parameters and biomarkers) were used in these studies. The most frequently used medical imaging modalities were CT scans followed by MRI, whereas the most common EHR parameters used were age, gender, alpha-fetoprotein AFP, albumin, coagulation factors, and bilirubin. Ten unique deep-learning techniques were applied to both EHR modalities and imaging modalities for two main purposes, prediction and diagnosis.
CONCLUSION
The use of multimodal data and deep learning techniques can help in the diagnosis and prediction of HCC. However, there is a limited number of works and available datasets for liver cancer, thus limiting the overall advancements of AI for liver cancer applications. Hence, more research should be undertaken to explore further the potential of multimodal deep learning in liver cancer applications.
PubMed: 37965284
DOI: 10.3389/frai.2023.1247195 -
Pediatric Radiology Sep 2023The role of postnatal Doppler measurements of the superior mesenteric artery (SMA) in detecting neonates at risk of necrotizing enterocolitis (NEC) remains uncertain;... (Meta-Analysis)
Meta-Analysis Review
The role of postnatal Doppler measurements of the superior mesenteric artery (SMA) in detecting neonates at risk of necrotizing enterocolitis (NEC) remains uncertain; therefore, we systematically reviewed and meta-analyzed the existing evidence regarding the usefulness of SMA Doppler measurements in detecting neonates at risk for NEC. We used the Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines, and we included studies which reported the following Doppler ultrasonography indices: peak systolic velocity, end-diastolic velocity, time average mean velocity, differential velocity, pulsatility index (PI) and resistive index. Eight studies were eligible for inclusion in the meta-analysis. Evidence suggested that, during the first postnatal day, neonates who developed NEC had a significantly higher peak systolic velocity (mean difference of 2.65 cm/s (95% confidence interval [CI] 1.23, 4.06, overall effect Z=3.66, P<0.001)), higher PI (mean difference of 1.52 (95% CI 0.00, 3.04, Z=1.96, P=0.05)) and higher resistive index (mean difference of 1.09 (95% CI 0.59, 1.60, Z=4.24, P<0.001)), compared to neonates who did not develop NEC. However, our findings do not support a strong association between the Doppler ultrasound indices and development of NEC at the time of disease onset. This meta-analysis suggests that first postnatal day SMA Doppler parameters, namely peak systolic velocity, PI and resistive index, are higher in neonates who develop NEC. On the other hand, the aforementioned indices are of uncertain significance once the diagnosis of NEC has been established.
Topics: Female; Infant, Newborn; Humans; Enterocolitis, Necrotizing; Mesenteric Artery, Superior; Ultrasonography; Ultrasonography, Doppler; Infant, Newborn, Diseases; Fetal Diseases; Blood Flow Velocity
PubMed: 37310444
DOI: 10.1007/s00247-023-05695-6 -
The Spine Journal : Official Journal of... Aug 2023Spinal cord injury (SCI) is a serious health problem which carries a heavy economic burden. Imaging technologies play an important role in the diagnosis of SCI. Although...
BACKGROUND CONTEXT
Spinal cord injury (SCI) is a serious health problem which carries a heavy economic burden. Imaging technologies play an important role in the diagnosis of SCI. Although several organizations have developed guidelines for diagnostic imaging of SCI, their quality has not yet been systematically assessed.
PURPOSE
We aim to conduct a systematic review to appraise SCI guidelines and summarize their recommendations for diagnostic imaging of SCI.
STUDY DESIGN
Systematic review.
METHODS
We searched Embase, Medline, Web of Science, Cochrane, some guideline-specific databases (eg, Scottish Intercollegiate Guidelines Network) and Google Scholar from January 2000 to January 2022. We included guidelines developed by nationally recognized organizations. If multiple versions could be obtained, we included the latest one. We appraised included guidelines using the Appraisal of Guidelines for Research and Evaluation, 2nd edition instrument which contains six domains (eg, scope and purpose). We also extracted recommendations and assessed their supporting evidence using levels of evidence (LOE). The evidence was categorized as A (the best quality), B, C, and D (the worst quality).
RESULTS
Seven guidelines (2008-2020) were included. They all received the lowest scores in the domain of applicability. All guidelines (7/7, 100%) recommended magnetic resonance imaging (MRI) in patients with SCI or SCI without radiographic abnormality (SCIWORA). A total of 12 recommendations involving patient age (eg, adult and child patients), timing of MRI (eg, as soon as possible and in the acute period), symptoms indicated for MRI (eg, a stiff spine and midline tenderness, suspected disc and posterior ligamentous complex injury, and neurological deficit), and types of MRI (eg, T2-weighted imaging and diffusion tensor imaging) were extracted. Among them, the LOE was C in nine (75%) recommendations and D in three (25%) recommendations.
CONCLUSIONS
Seven guidelines were included in the present systematic review, and all of them showed the worst applicability scores in the Appraisal of Guidelines for Research and Evaluation, 2nd edition instrument. They all weakly recommended MRI for patients with suspected SCI or SCIWORA based on a low LOE.
Topics: Adult; Child; Humans; Diffusion Tensor Imaging; Magnetic Resonance Imaging; Spinal Cord Injuries
PubMed: 36934792
DOI: 10.1016/j.spinee.2023.03.003 -
Asian Pacific Journal of Cancer... Nov 2023Colonoscopy may detect colorectal polyp and facilitate its removal in order to prevent colorectal cancer. However, substantial miss rate for colorectal adenomas... (Meta-Analysis)
Meta-Analysis
INTRODUCTION
Colonoscopy may detect colorectal polyp and facilitate its removal in order to prevent colorectal cancer. However, substantial miss rate for colorectal adenomas detection still occurred during screening colonoscopy procedure. Nowadays, artificial intelligence (AI) have been employed in trials to improve polyp detection rate (PDR) and adenoma detection rate (ADR). Therefore, we would like to determine the impact of AI in increasing PDR and ADR.
METHODS
The present study adhered to the guidelines outlined in the Preferred Reporting Items for Systematic Reviews and Meta-analyses 2020 (PRISMA 2020) statement. To identify relevant literature, comprehensive searches were conducted on major scientific databases, including Pubmed, EBSCO-host, and Proquest. The search was limited to articles published up to November 30, 2022. Inclusion criteria for the study encompassed full-text accessibility, articles written in the English language, and randomized controlled trials (RCTs) that reported both ADR and PDR values, comparing conventional diagnostic methods with AI-aided approaches. To synthesize the data, we computed the combined pooled odds ratio (OR) using a random-effects model. This model was chosen due to the expectation of considerable heterogeneity among the selected studies. To evaluate potential publication bias, the Begg's funnel diagram was employed.
RESULTS
A total of 13 studies were included in this study. Colonoscopy with AI had significantly higher PDR compared to without AI (pooled OR 1.46, 95% CI 1.13-1.89, p = 0.003) and higher ADR (pooled OR 1.58, 95% CI 1.37-1.82, p < 0.00001). PDR analysis showed moderate heterogeneity between included studies (p = 0.004; I2=63%). Furthermore, ADR analysis showed moderate heterogeneity (p < 0.007; I2 = 57%). Additionally, the funnels plot of ADR and PDR analysis showed an asymmetry plot and low publication bias.
CONCLUSION
AI may improve colonoscopy result quality through improving PDR and ADR.
Topics: Humans; Adenoma; Artificial Intelligence; Colonoscopy; Colorectal Neoplasms; Databases, Factual
PubMed: 38019222
DOI: 10.31557/APJCP.2023.24.11.3655