-
World Journal of Emergency Surgery :... Dec 2023To assess the efficacy of artificial intelligence (AI) models in diagnosing and prognosticating acute appendicitis (AA) in adult patients compared to traditional... (Review)
Review
BACKGROUND
To assess the efficacy of artificial intelligence (AI) models in diagnosing and prognosticating acute appendicitis (AA) in adult patients compared to traditional methods. AA is a common cause of emergency department visits and abdominal surgeries. It is typically diagnosed through clinical assessments, laboratory tests, and imaging studies. However, traditional diagnostic methods can be time-consuming and inaccurate. Machine learning models have shown promise in improving diagnostic accuracy and predicting outcomes.
MAIN BODY
A systematic review following the PRISMA guidelines was conducted, searching PubMed, Embase, Scopus, and Web of Science databases. Studies were evaluated for risk of bias using the Prediction Model Risk of Bias Assessment Tool. Data points extracted included model type, input features, validation strategies, and key performance metrics.
RESULTS
In total, 29 studies were analyzed, out of which 21 focused on diagnosis, seven on prognosis, and one on both. Artificial neural networks (ANNs) were the most commonly employed algorithm for diagnosis. Both ANN and logistic regression were also widely used for categorizing types of AA. ANNs showed high performance in most cases, with accuracy rates often exceeding 80% and AUC values peaking at 0.985. The models also demonstrated promising results in predicting postoperative outcomes such as sepsis risk and ICU admission. Risk of bias was identified in a majority of studies, with selection bias and lack of internal validation being the most common issues.
CONCLUSION
AI algorithms demonstrate significant promise in diagnosing and prognosticating AA, often surpassing traditional methods and clinical scores such as the Alvarado scoring system in terms of speed and accuracy.
Topics: Adult; Humans; Artificial Intelligence; Appendicitis; Prognosis; Algorithms; Machine Learning; Acute Disease
PubMed: 38114983
DOI: 10.1186/s13017-023-00527-2 -
Journal of Tropical Medicine 2024To understand how congenital toxoplasmosis (CT) diagnosis has evolved over the years, we performed a systematic review and meta-analysis to summarize the kind of... (Review)
Review
OBJECTIVE
To understand how congenital toxoplasmosis (CT) diagnosis has evolved over the years, we performed a systematic review and meta-analysis to summarize the kind of analysis that has been employed for CT diagnosis.
METHODS
PubMed and Lilacs databases were used in order to access the kind of analysis that has been employed for CT diagnosis in several samples. Our search combined the following combining terms: "congenital toxoplasmosis" or "gestational toxoplasmosis" and "diagnosis" and "blood," "serum," "amniotic fluid," "placenta," or "colostrum." We extracted data on true positive, true negative, false positive, and false negative to generate pooled sensitivity, specificity, and diagnostic odds ratio (DOR). Random-effects models using MetaDTA were used for analysis.
RESULTS
Sixty-five articles were included in the study aiming for comparisons (75.4%), diagnosis performance (52.3%), diagnosis improvement (32.3%), or to distinguish acute/chronic infection phases (36.9%). Amniotic fluid (AF) and placenta were used in 36.9% and 10.8% of articles, respectively, targeting parasites and/or DNA. Blood was used in 86% of articles for enzymatic assays. Colostrum was used in one article to search for antibodies. In meta-analysis, PCR in AF showed the best performance for CT diagnosis based on the highest summary sensitivity (85.1%) and specificity (99.7%) added to lower magnitude heterogeneity.
CONCLUSION
Most of the assays being researched to diagnose CT are basically the same traditional approaches available for clinical purposes. The range in diagnostic performance and the challenges imposed by CT diagnosis indicate the need to better explore pregnancy samples in search of new possibilities for diagnostic tools. Exploring immunological markers and using bioinformatics tools and recombinant antigens should address the research needed for a new generation of diagnostic tools to face these challenges.
PubMed: 38419946
DOI: 10.1155/2024/1514178 -
Diagnosis and prevalence of sarcopenic obesity in patients with colorectal cancer: A scoping review.Clinical Nutrition (Edinburgh, Scotland) Sep 2023Sarcopenic obesity (SO) is associated with worse outcomes in patients with colorectal cancer (CRC); however, the diagnostic methods and prevalence of SO vary among... (Review)
Review
BACKGROUND & AIMS
Sarcopenic obesity (SO) is associated with worse outcomes in patients with colorectal cancer (CRC); however, the diagnostic methods and prevalence of SO vary among studies. Therefore, we conducted this scoping review to investigate the diagnosis of SO in CRC, identify the associated problems, and determine its prevalence.
METHODS
A systematic review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews reporting guidelines. A literature search was performed by two independent reviewers on studies that diagnosed SO in CRC using the MEDLINE, EMBASE, CINAHL, CENTRAL, Web of Science, and Ichushi-Web (in Japanese) databases. Observational, longitudinal, cross-sectional, and clinical trials written in English or Japanese as of July 2022 were included. Studies that did not define SO were excluded from the analysis. The study protocol was pre-registered in Figshare.
RESULTS
In total, 670 studies were identified, 22 of which were included. Eighteen studies used sarcopenia in combination with obesity to diagnose SO. Sarcopenia was mainly diagnosed using skeletal muscle mass index (SMI), and only one combined with grip strength or gait speed. Obesity was diagnosed based on the body mass index (BMI; n = 11), followed by visceral fat area (VFA; n = 5). The overall prevalence of SO in patients with CRC was 15% (95%CI, 11-21%). The prevalence of SO in surgical resection and colorectal cancer liver metastases was 18% (95%CI, 12-25%) and 11% (95%CI, 3-36%), respectively.
CONCLUSIONS
SO in patients with CRC was mainly diagnosed based on a combination of SMI and BMI, and muscle strength and body composition were rarely evaluated. The prevalence of SO was approximately 15%, depending on the diagnostic methods used. Since SO in patients with CRC is associated with poor prognosis, further research on diagnostic methods for the early detection of SO and its clinical outcomes is needed.
Topics: Humans; Sarcopenia; Cross-Sectional Studies; Prevalence; Obesity; Colorectal Neoplasms
PubMed: 37480796
DOI: 10.1016/j.clnu.2023.06.025 -
Therapeutic Advances in Gastroenterology 2023Magnetically controlled capsule endoscopy (MCCE) is a non-invasive, painless, comfortable, and safe equipment to diagnose gastrointestinal diseases (GID), partially... (Review)
Review
BACKGROUND
Magnetically controlled capsule endoscopy (MCCE) is a non-invasive, painless, comfortable, and safe equipment to diagnose gastrointestinal diseases (GID), partially overcoming the shortcomings of conventional endoscopy and wireless capsule endoscopy (WCE). With advancements in technology, the main technical parameters of MCCE have continuously been improved, and MCCE has become more intelligent.
OBJECTIVES
The aim of this systematic review was to summarize the research progress of MCCE and artificial intelligence (AI) in the diagnosis and treatment of GID.
DATA SOURCES AND METHODS
We conducted a systematic search of PubMed and EMBASE for published studies on GID detection of MCCE, physical factors related to MCCE imaging quality, the application of AI in aiding MCCE, and its additional functions. We synergistically reviewed the included studies, extracted relevant data, and made comparisons.
RESULTS
MCCE was confirmed to have the same performance as conventional gastroscopy and WCE in detecting common GID, while it lacks research in detecting early gastric cancer (EGC). The body position and cleanliness of the gastrointestinal tract are the main factors affecting imaging quality. The applications of AI in screening intestinal diseases have been comprehensive, while in the detection of common gastric diseases such as ulcers, it has been developed. MCCE can perform some additional functions, such as observations of drug behavior in the stomach and drug damage to the gastric mucosa. Furthermore, it can be improved to perform a biopsy.
CONCLUSION
This comprehensive review showed that the MCCE technology has made great progress, but studies on GID detection and treatment by MCCE are in the primary stage. Further studies are required to confirm the performance of MCCE.
PubMed: 37900007
DOI: 10.1177/17562848231206991 -
The Cochrane Database of Systematic... Nov 2023Keratoconus remains difficult to diagnose, especially in the early stages. It is a progressive disorder of the cornea that starts at a young age. Diagnosis is based on... (Review)
Review
BACKGROUND
Keratoconus remains difficult to diagnose, especially in the early stages. It is a progressive disorder of the cornea that starts at a young age. Diagnosis is based on clinical examination and corneal imaging; though in the early stages, when there are no clinical signs, diagnosis depends on the interpretation of corneal imaging (e.g. topography and tomography) by trained cornea specialists. Using artificial intelligence (AI) to analyse the corneal images and detect cases of keratoconus could help prevent visual acuity loss and even corneal transplantation. However, a missed diagnosis in people seeking refractive surgery could lead to weakening of the cornea and keratoconus-like ectasia. There is a need for a reliable overview of the accuracy of AI for detecting keratoconus and the applicability of this automated method to the clinical setting.
OBJECTIVES
To assess the diagnostic accuracy of artificial intelligence (AI) algorithms for detecting keratoconus in people presenting with refractive errors, especially those whose vision can no longer be fully corrected with glasses, those seeking corneal refractive surgery, and those suspected of having keratoconus. AI could help ophthalmologists, optometrists, and other eye care professionals to make decisions on referral to cornea specialists. Secondary objectives To assess the following potential causes of heterogeneity in diagnostic performance across studies. • Different AI algorithms (e.g. neural networks, decision trees, support vector machines) • Index test methodology (preprocessing techniques, core AI method, and postprocessing techniques) • Sources of input to train algorithms (topography and tomography images from Placido disc system, Scheimpflug system, slit-scanning system, or optical coherence tomography (OCT); number of training and testing cases/images; label/endpoint variable used for training) • Study setting • Study design • Ethnicity, or geographic area as its proxy • Different index test positivity criteria provided by the topography or tomography device • Reference standard, topography or tomography, one or two cornea specialists • Definition of keratoconus • Mean age of participants • Recruitment of participants • Severity of keratoconus (clinically manifest or subclinical) SEARCH METHODS: We searched CENTRAL (which contains the Cochrane Eyes and Vision Trials Register), Ovid MEDLINE, Ovid Embase, OpenGrey, the ISRCTN registry, ClinicalTrials.gov, and the World Health Organization International Clinical Trials Registry Platform (WHO ICTRP). There were no date or language restrictions in the electronic searches for trials. We last searched the electronic databases on 29 November 2022.
SELECTION CRITERIA
We included cross-sectional and diagnostic case-control studies that investigated AI for the diagnosis of keratoconus using topography, tomography, or both. We included studies that diagnosed manifest keratoconus, subclinical keratoconus, or both. The reference standard was the interpretation of topography or tomography images by at least two cornea specialists.
DATA COLLECTION AND ANALYSIS
Two review authors independently extracted the study data and assessed the quality of studies using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. When an article contained multiple AI algorithms, we selected the algorithm with the highest Youden's index. We assessed the certainty of evidence using the GRADE approach.
MAIN RESULTS
We included 63 studies, published between 1994 and 2022, that developed and investigated the accuracy of AI for the diagnosis of keratoconus. There were three different units of analysis in the studies: eyes, participants, and images. Forty-four studies analysed 23,771 eyes, four studies analysed 3843 participants, and 15 studies analysed 38,832 images. Fifty-four articles evaluated the detection of manifest keratoconus, defined as a cornea that showed any clinical sign of keratoconus. The accuracy of AI seems almost perfect, with a summary sensitivity of 98.6% (95% confidence interval (CI) 97.6% to 99.1%) and a summary specificity of 98.3% (95% CI 97.4% to 98.9%). However, accuracy varied across studies and the certainty of the evidence was low. Twenty-eight articles evaluated the detection of subclinical keratoconus, although the definition of subclinical varied. We grouped subclinical keratoconus, forme fruste, and very asymmetrical eyes together. The tests showed good accuracy, with a summary sensitivity of 90.0% (95% CI 84.5% to 93.8%) and a summary specificity of 95.5% (95% CI 91.9% to 97.5%). However, the certainty of the evidence was very low for sensitivity and low for specificity. In both groups, we graded most studies at high risk of bias, with high applicability concerns, in the domain of patient selection, since most were case-control studies. Moreover, we graded the certainty of evidence as low to very low due to selection bias, inconsistency, and imprecision. We could not explain the heterogeneity between the studies. The sensitivity analyses based on study design, AI algorithm, imaging technique (topography versus tomography), and data source (parameters versus images) showed no differences in the results.
AUTHORS' CONCLUSIONS
AI appears to be a promising triage tool in ophthalmologic practice for diagnosing keratoconus. Test accuracy was very high for manifest keratoconus and slightly lower for subclinical keratoconus, indicating a higher chance of missing a diagnosis in people without clinical signs. This could lead to progression of keratoconus or an erroneous indication for refractive surgery, which would worsen the disease. We are unable to draw clear and reliable conclusions due to the high risk of bias, the unexplained heterogeneity of the results, and high applicability concerns, all of which reduced our confidence in the evidence. Greater standardization in future research would increase the quality of studies and improve comparability between studies.
Topics: Humans; Artificial Intelligence; Keratoconus; Cross-Sectional Studies; Physical Examination; Case-Control Studies
PubMed: 37965960
DOI: 10.1002/14651858.CD014911.pub2 -
Journal of Gastroenterology and... Aug 2023We aim to conduct a systematic review and determine the association between obstructive sleep apnea (OSA) and gastroesophageal reflux disease (GERD). (Meta-Analysis)
Meta-Analysis Review
BACKGROUND AND AIM
We aim to conduct a systematic review and determine the association between obstructive sleep apnea (OSA) and gastroesophageal reflux disease (GERD).
METHODS
Literature search for eligible studies was performed across major databases. The main endpoint was to assess the association between GERD and OSA. Subgroup analyses were performed to determine this strength of the association stratified by the diagnostic tools used for OSA (nocturnal polysomnogram or Berlin questionnaire) and GERD (validated reflux questionnaire or esophagogastroduodenoscopy). We also compared sleep efficiency, apnea hypopnea index, oxygen desaturation index, and Epworth Sleepiness Scale in OSA patients with or without GERD. Results were pooled together using Reviewer Manager 5.4.
RESULTS
Six studies involving 2950 patients with either GERD or OSA were included in the pooled analysis. Our findings suggest that there was a statistically significant unidirectional association between GERD and OSA (odds ratio [OR] = 1.53, P = 0.0001). Subgroup analyses redemonstrated an OSA-GERD association irrespective of the tools used for diagnosing either GERD or OSA (P = 0.24 and P = 0.82, respectively). Sensitivity analyses demonstrated the same association after controlling for gender (OR = 1.63), BMI (OR = 1.81), smoking (OR = 1.45), and alcohol consumption (OR = 1.79). In patients with OSA, there were no statistically significant differences between patients with or without GERD in terms of apnea hypopnea index (P = 0.30), sleep efficiency (P = 0.67), oxygen desaturation index (P = 0.39), and Epworth Sleepiness Scale (P = 0.07).
CONCLUSION
There exists an association between OSA and GERD that is independent of the modalities used for screening or diagnosing both disorders. However, the presence of GERD did not affect the severity of OSA.
Topics: Humans; Sleepiness; Sleep Apnea, Obstructive; Gastroesophageal Reflux; Polysomnography; Alcohol Drinking
PubMed: 37300443
DOI: 10.1111/jgh.16245 -
Journal of Clinical Medicine Aug 2023The use of radiomics and artificial intelligence applied for the diagnosis and monitoring of Alzheimer's disease has developed in recent years. However, this approach is... (Review)
Review
The use of radiomics and artificial intelligence applied for the diagnosis and monitoring of Alzheimer's disease has developed in recent years. However, this approach is not yet completely applicable in clinical practice. The aim of this paper is to provide a systematic analysis of the studies that have included the use of radiomics from different imaging techniques and artificial intelligence for the diagnosis and monitoring of Alzheimer's disease in order to improve the clinical outcomes and quality of life of older patients. A systematic review of the literature was conducted in February 2023, analyzing manuscripts and articles of the last 5 years from the PubMed, Scopus and Embase databases. All studies concerning discrimination among Alzheimer's disease, Mild Cognitive Impairment and healthy older people performing radiomics analysis through machine and deep learning were included. A total of 15 papers were included. The results showed a very good performance of this approach in the differentiating Alzheimer's disease patients-both at the dementia and pre-dementia phases of the disease-from healthy older people. In summary, radiomics and AI can be valuable tools for diagnosing and monitoring the progression of Alzheimer's disease, potentially leading to earlier and more accurate diagnosis and treatment. However, the results reported by this review should be read with great caution, keeping in mind that imaging alone is not enough to identify dementia due to Alzheimer's.
PubMed: 37629474
DOI: 10.3390/jcm12165432 -
Frontiers in Immunology 2023The utility of metagenomic next-generation sequencing (mNGS) in the diagnosis of tuberculous meningitis (TBM) remains uncertain. We performed a meta-analysis to... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
The utility of metagenomic next-generation sequencing (mNGS) in the diagnosis of tuberculous meningitis (TBM) remains uncertain. We performed a meta-analysis to comprehensively evaluate its diagnostic accuracy for the early diagnosis of TBM.
METHODS
English (PubMed, Medline, Web of Science, Cochrane Library, and Embase) and Chinese (CNKI, Wanfang, and CBM) databases were searched for relevant studies assessing the diagnostic accuracy of mNGS for TBM. Review Manager was used to evaluate the quality of the included studies, and Stata was used to perform the statistical analysis.
RESULTS
Of 495 relevant articles retrieved, eight studies involving 693 participants (348 with and 345 without TBM) met the inclusion criteria and were included in the meta-analysis. The pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and area under the summary receiver-operating characteristic curve of mNGS for diagnosing TBM were 62% (95% confidence interval [CI]: 0.46-0.76), 99% (95% CI: 0.94-1.00), 139.08 (95% CI: 8.54-2266), 0.38 (95% CI: 0.25-0.58), 364.89 (95% CI: 18.39-7239), and 0.97 (95% CI: 0.95-0.98), respectively.
CONCLUSIONS
mNGS showed good specificity but moderate sensitivity; therefore, a more sensitive test should be developed to assist in the diagnosis of TBM.
Topics: Humans; Tuberculosis, Meningeal; Sensitivity and Specificity; ROC Curve; High-Throughput Nucleotide Sequencing; Databases, Factual
PubMed: 37822937
DOI: 10.3389/fimmu.2023.1223675 -
Best Practice & Research. Clinical... Aug 2023Of all neonates, 21% are delivered by cesarean section (CS). A long-term maternal complication of an SC is a uterine niche. The aim of this review is to provide an... (Review)
Review
Of all neonates, 21% are delivered by cesarean section (CS). A long-term maternal complication of an SC is a uterine niche. The aim of this review is to provide an overview of the current literature on imaging techniques and niche-related symptomatology. We performed systematic searches on imaging and niche symptoms. For both searches, 87 new studies were included. Niche evaluation by transvaginal sonography (TVS) or contrast sonohysterography (SHG) proved superior over hysteroscopy or magnetic resonance imaging. Studies that used SHG in a random population identified a niche prevalence of 42%-84%. Niche prevalence differed based on niche definition, symptomatology, and imaging technique. Most studies reported an association with gynecological symptoms, poor reproductive outcomes, obstetrical complications, and reduced quality of life. In conclusion, non-invasive TVS and SHG are the superior imaging modalities to diagnose a niche. Niches are prevalent and strongly associated with gynecological symptoms and poor reproductive outcomes.
Topics: Infant, Newborn; Pregnancy; Female; Humans; Cesarean Section; Quality of Life; Uterus; Hysteroscopy; Ultrasonography; Cicatrix
PubMed: 37506497
DOI: 10.1016/j.bpobgyn.2023.102390 -
Psychiatry Research Aug 2023We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome.
INTRODUCTION
We developed and tested a Bayesian network(BN) model to predict ECT remission for depression, with non-response as a secondary outcome.
METHODS
We performed a systematic literature search on clinically available predictors. We combined these predictors with variables from a dataset of clinical ECT trajectories (performed in the University Medical Center Utrecht) to create priors and train the BN. Temporal validation was performed in an independent sample.
RESULTS
The systematic literature search yielded three meta-analyses, which provided prior knowledge on outcome predictors. The clinical dataset consisted of 248 treatment trajectories in the training set and 44 trajectories in the test set at the same medical center. The AUC for the primary outcome remission estimated on an independent validation set was 0.686 (95%CI 0.513-0.859) (AUC values of 0.505 - 0.763 observed in 5-fold cross validation of the model within the train set). Accuracy 0.73 (balanced accuracy 0.67), sensitivity 0.55, specificity 0.79, after temporal validation in the independent sample. Prior literature information marginally reduced CI width.
DISCUSSION
A BN model comprised of prior knowledge and clinical data can predict remission of depression after ECT with reasonable performance. This approach can be used to make outcome predictions in psychiatry, and offers a methodological framework to weigh additional information, such as patient characteristics, symptoms and biomarkers. In time, it may be used to improve shared decision-making in clinical practice.
Topics: Humans; Electroconvulsive Therapy; Depression; Bayes Theorem; Prognosis; Biomarkers; Treatment Outcome
PubMed: 37429173
DOI: 10.1016/j.psychres.2023.115328