-
European Geriatric Medicine Oct 2022Community-acquired pneumonia (CAP) is highly common across the world. It is reported that over 90% of CAP in older adults may be due to aspiration. However, the... (Review)
Review
PURPOSE
Community-acquired pneumonia (CAP) is highly common across the world. It is reported that over 90% of CAP in older adults may be due to aspiration. However, the diagnostic criteria for aspiration pneumonia (AP) have not been widely agreed. Is there a consensus on how to diagnose AP? What are the clinical features of patients being diagnosed with AP? We conducted a systematic review to answer these questions.
METHODS
We performed a literature search in MEDLINE, EMBASE, CINHAL, and Cochrane to review the steps taken toward diagnosing AP. Search terms for "aspiration pneumonia" and "aged" were used. Inclusion criteria were: original research, community-acquired AP, age ≥ 75 years old, acute hospital admission.
RESULTS
A total of 10,716 reports were found. Following the removal of duplicates, 7601 were screened, 95 underwent full-text review, and 9 reports were included in the final analysis. Pneumonia was diagnosed using a combination of symptoms, inflammatory markers, and chest imaging findings in most studies. AP was defined as pneumonia with some relation to aspiration or dysphagia. Aspiration was inferred if there was witnessed or prior presumed aspiration, episodes of coughing on food or liquids, relevant underlying conditions, abnormalities on videofluoroscopy or water swallow test, and gravity-dependent distribution of shadows on chest imaging. Patients with AP were older, more frailer, and had more comorbidities than in non-AP.
CONCLUSION
There is a broad consensus on the clinical criteria to diagnose AP. It is a presumptive diagnosis with regards to patients' general frailty rather than in relation to swallowing function itself.
Topics: Aged; Community-Acquired Infections; Deglutition; Humans; Pneumonia; Pneumonia, Aspiration; Water
PubMed: 36008745
DOI: 10.1007/s41999-022-00689-3 -
Alimentary Pharmacology & Therapeutics Oct 2021Advances in imaging technology have the potential to transform the early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis.... (Review)
Review
BACKGROUND
Advances in imaging technology have the potential to transform the early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis. Computational "radiomic" techniques extract biomarker information from images which can be used to improve diagnosis and predict tumour biology.
AIMS
To perform a systematic review on radiomic features in HCC diagnosis and prognosis, with a focus on reporting metrics and methodologic standardisation.
METHODS
We performed a systematic review of all full-text articles published from inception through December 1, 2019. Standardised data extraction and quality assessment metrics were applied to all studies.
RESULTS
A total of 54 studies were included for analysis. Radiomic features demonstrated good discriminatory performance to differentiate HCC from other solid lesions (c-statistics 0.66-0.95), and to predict microvascular invasion (c-statistic 0.76-0.92), early recurrence after hepatectomy (c-statistics 0.71-0.86), and prognosis after locoregional or systemic therapies (c-statistics 0.74-0.81). Common stratifying features for diagnostic and prognostic radiomic tools included analyses of imaging skewness, analysis of the peritumoural region, and feature extraction from the arterial imaging phase. The overall quality of the included studies was low, with common deficiencies in both internal and external validation, standardised imaging segmentation, and lack of comparison to a gold standard.
CONCLUSIONS
Quantitative image analysis demonstrates promise as a non-invasive biomarker to improve HCC diagnosis and management. However, standardisation of protocols and outcome measurement, sharing of algorithms and analytic methods, and external validation are necessary prior to widespread application of radiomics to HCC diagnosis and prognosis in clinical practice.
Topics: Carcinoma, Hepatocellular; Hepatectomy; Humans; Liver Neoplasms; Prognosis; Retrospective Studies
PubMed: 34390014
DOI: 10.1111/apt.16563 -
International Journal of Environmental... May 2021Due to drawbacks of the percentage-based approach, velocity-based training was proposed as a method to better and more accurately prescribe training loads to increase... (Review)
Review
Due to drawbacks of the percentage-based approach, velocity-based training was proposed as a method to better and more accurately prescribe training loads to increase general and specific performance. The purpose of this study was to perform a systematic review of the studies that show effects of velocity-based resistance training on strength and power performance in elite athletes. Electronic searches of computerized databases were performed according to a protocol that was agreed by all co-authors. Four databases-SportDiscus with Full Text and MEDLINE via EBSCO, SCOPUS, and Web of Science-were searched. Seven studies were found which researched the effects of velocity-based resistance training on athletes after a given training period. The analyzed studies suggest that applying velocity losses of 10-20% can help induce neuromuscular adaptations and reduce neuromuscular fatigue. Using velocity zones as part of a separate or combined (e.g., plyometric) training program can elicit adaptations in body composition and performance parameters. Moreover, velocity zones can be programmed using a periodized or non-periodized fixed velocity zones protocol. Lastly, obtaining instantaneous feedback during training is a more effective tool for increasing performance in sport-specific parameters, and should be used by sport practitioners to help keep athletes accountable for their performance.
Topics: Adaptation, Physiological; Athletes; Humans; Muscle Strength; Resistance Training
PubMed: 34069249
DOI: 10.3390/ijerph18105257 -
Endocrine Aug 2023To summarize the more robust evidence about the performance of tools useful for diagnosis of medullary thyroid carcinoma (MTC) such as calcitonin (Ctn) and other... (Review)
Review
PURPOSE
To summarize the more robust evidence about the performance of tools useful for diagnosis of medullary thyroid carcinoma (MTC) such as calcitonin (Ctn) and other circulating markers, ultrasound (US), fine-needle aspiration (FNA), and other imaging procedures.
METHODS
This systematic review of systematic reviews was carried out according to a predefined protocol. A search string was created. An electronical comprehensive search of literature was performed on December 2022. Quality assessment of eligible systematic reviews was performed and main findings were described.
RESULTS
Twenty-three systematic reviews were included and several findings were achieved. Ctn is the most reliable diagnostic marker of MTC with no evidence of improvement with stimulation test. CEA doubling time is more reliable than Ctn in identifying MTC with poorer prognosis. US sensitivity is suboptimal in MTC and only just over half of cases are at high risk according to Thyroid Imaging And Reporting Data Systems. Cytology can correctly detect MTC in just over half of cases and measuring Ctn in washout fluid from FNA is necessary. PET/CT is useful for detecting recurrent MTC.
CONCLUSIONS
Future guidelines of both thyroid nodule management and MTC diagnosis should consider these evidence-based data.
Topics: Thyroid Neoplasms; Thyroid Nodule; Positron Emission Tomography Computed Tomography; Diagnostic Tests, Routine; Calcitonin; Systematic Reviews as Topic; Biopsy, Fine-Needle
PubMed: 36877452
DOI: 10.1007/s12020-023-03326-6 -
Journal of Hepatology Oct 2021Vibration-controlled transient elastography (VCTE), point shear wave elastography (pSWE), 2-dimensional shear wave elastography (2DSWE), magnetic resonance elastography... (Meta-Analysis)
Meta-Analysis
BACKGROUND AND AIMS
Vibration-controlled transient elastography (VCTE), point shear wave elastography (pSWE), 2-dimensional shear wave elastography (2DSWE), magnetic resonance elastography (MRE), and magnetic resonance imaging (MRI) have been proposed as non-invasive tests for patients with non-alcoholic fatty liver disease (NAFLD). This study evaluated their diagnostic accuracy for liver fibrosis and non-alcoholic steatohepatitis (NASH).
METHODS
PubMED/MEDLINE, EMBASE and the Cochrane Library were searched for studies examining the diagnostic accuracy of these index tests, against histology as the reference standard, in adult patients with NAFLD. Two authors independently screened and assessed methodological quality of studies and extracted data. Summary estimates of sensitivity, specificity and area under the curve (sAUC) were calculated for fibrosis stages and NASH, using a random effects bivariate logit-normal model.
RESULTS
We included 82 studies (14,609 patients). Meta-analysis for diagnosing fibrosis stages was possible in 53 VCTE, 11 MRE, 12 pSWE and 4 2DSWE studies, and for diagnosing NASH in 4 MRE studies. sAUC for diagnosis of significant fibrosis were: 0.83 for VCTE, 0.91 for MRE, 0.86 for pSWE and 0.75 for 2DSWE. sAUC for diagnosis of advanced fibrosis were: 0.85 for VCTE, 0.92 for MRE, 0.89 for pSWE and 0.72 for 2DSWE. sAUC for diagnosis of cirrhosis were: 0.89 for VCTE, 0.90 for MRE, 0.90 for pSWE and 0.88 for 2DSWE. MRE had sAUC of 0.83 for diagnosis of NASH. Three (4%) studies reported intention-to-diagnose analyses and 15 (18%) studies reported diagnostic accuracy against pre-specified cut-offs.
CONCLUSIONS
When elastography index tests are acquired successfully, they have acceptable diagnostic accuracy for advanced fibrosis and cirrhosis. The potential clinical impact of these index tests cannot be assessed fully as intention-to-diagnose analyses and validation of pre-specified thresholds are lacking.
LAY SUMMARY
Non-invasive tests that measure liver stiffness or use magnetic resonance imaging (MRI) have been suggested as alternatives to liver biopsy for assessing the severity of liver scarring (fibrosis) and fatty inflammation (steatohepatitis) in patients with non-alcoholic fatty liver disease (NAFLD). In this study, we summarise the results of previously published studies on how accurately these non-invasive tests can diagnose liver fibrosis and inflammation, using liver biopsy as the reference. We found that some techniques that measure liver stiffness had a good performance for the diagnosis of severe liver scarring.
Topics: Adult; Area Under Curve; Elasticity Imaging Techniques; Humans; Magnetic Resonance Imaging; Non-alcoholic Fatty Liver Disease; ROC Curve
PubMed: 33991635
DOI: 10.1016/j.jhep.2021.04.044 -
The Journal of Clinical Endocrinology... Mar 2020Signs and symptoms of Cushing's syndrome (CS) overlap with common diseases, such as the metabolic syndrome, obesity, osteoporosis, and depression. Therefore, it can take... (Meta-Analysis)
Meta-Analysis
CONTEXT
Signs and symptoms of Cushing's syndrome (CS) overlap with common diseases, such as the metabolic syndrome, obesity, osteoporosis, and depression. Therefore, it can take years to finally diagnose CS, although early diagnosis is important for prevention of complications.
OBJECTIVE
The aim of this study was to assess the time span between first symptoms and diagnosis of CS in different populations to identify factors associated with an early diagnosis.
DATA SOURCES
A systematic literature search via PubMed was performed to identify studies reporting on time to diagnosis in CS. In addition, unpublished data from patients of our tertiary care center and 4 other centers were included.
STUDY SELECTION
Clinical studies reporting on the time to diagnosis of CS were eligible. Corresponding authors were contacted to obtain additional information relevant to the research question.
DATA EXTRACTION
Data were extracted from the text of the retrieved articles and from additional information provided by authors contacted successfully. From initially 3326 screened studies 44 were included.
DATA SYNTHESIS
Mean time to diagnosis for patients with CS was 34 months (ectopic CS: 14 months; adrenal CS: 30 months; and pituitary CS: 38 months; P < .001). No difference was found for gender, age (<18 and ≥18 years), and year of diagnosis (before and after 2000). Patients with pituitary CS had a longer time to diagnosis in Germany than elsewhere.
CONCLUSIONS
Time to diagnosis differs for subtypes of CS but not for gender and age. Time to diagnosis remains to be long and requires to be improved.
Topics: Age Factors; Cushing Syndrome; Delayed Diagnosis; Early Diagnosis; Humans; Sex Factors; Time Factors
PubMed: 31665382
DOI: 10.1210/clinem/dgz136 -
Journal of Dental Sciences Jan 2021In the recent years artificial intelligence (AI) has revolutionized in the field of dentistry. The aim of this systematic review was to document the scope and... (Review)
Review
BACKGROUND/PURPOSE
In the recent years artificial intelligence (AI) has revolutionized in the field of dentistry. The aim of this systematic review was to document the scope and performance of the artificial intelligence based models that have been widely used in orthodontic diagnosis, treatment planning, and predicting the prognosis.
MATERIALS AND METHODS
The literature for this paper was identified and selected by performing a thorough search for articles in the electronic data bases like Pubmed, Medline, Embase, Cochrane, and Google scholar, Scopus and Web of science, Saudi digital library published over the past two decades (January 2000-February 2020). After applying the inclusion and exclusion criteria, 16 articles were read in full and critically analyzed. QUADAS-2 were adapted for quality analysis of the studies included.
RESULTS
AI technology has been widely applied for identifying cephalometric landmarks, determining need for orthodontic extractions, determining the degree of maturation of the cervical vertebra, predicting the facial attractiveness after orthognathic surgery, predicting the need for orthodontic treatment, and orthodontic treatment planning. Most of these artificial intelligence models are based on either artificial neural networks (ANNs) or convolutional neural networks (CNNs).
CONCLUSION
The results from these reported studies are suggesting that these automated systems have performed exceptionally well, with an accuracy and precision similar to the trained examiners. These systems can simplify the tasks and provide results in quick time which can save the dentist time and help the dentist to perform his duties more efficiently. These systems can be of great value in orthodontics.
PubMed: 33384838
DOI: 10.1016/j.jds.2020.05.022 -
Pediatric Emergency Care Sep 2020The aims of the study were to perform the first systematic review of pediatric syncope etiologies and to determine the most common diagnoses with credible intervals...
OBJECTIVES
The aims of the study were to perform the first systematic review of pediatric syncope etiologies and to determine the most common diagnoses with credible intervals (CredIs).
METHODS
Review was performed within Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines and used Embase, Scopus, PubMed, and the Cochrane Controlled Trial databases. The following inclusion criteria for the articles were used: minimum of 10 patients, standard definition of syncope used, subjects who were 21 years or younger, and subjects who were either a consecutive retrospective group or a prospective group. No restrictions were made regarding language of the studies, but an English abstract was required. The following information was collected: purpose of the study, definition of syncope, number of patients, patient age range, inclusion/exclusion criteria, and etiologies of syncope.
RESULTS
Of the 500 articles initially identified, 11 studies met the inclusion criteria and were the basis for this review. Three thousand seven hundred patients were included, ranging in age from 3 months to 21 years. The most common etiologies identified were vasovagal (52.2%; 95% CredI, 50.6-53.9), postural orthostatic tachycardia syndrome (13.1%; 95% CredI, 12.1-14.2), and cardiac causes (4.0%; 95% CredI, 3.39-4.65). A total of 18.3% (95% CredI, 17.0-19.5) of patients were found to have syncope of unknown cause.
CONCLUSIONS
Syncope is a common pediatric complaint. Most cases seen are a result of benign causes, with only a small percentage because of serious medical conditions. In addition, most syncopal episodes in the pediatric population are diagnosed clinically or with minimally invasive testing, emphasizing the importance of a detailed history and physical examination.
Topics: Child; Diagnosis, Differential; Humans; Medical History Taking; Physical Examination; Syncope
PubMed: 32530839
DOI: 10.1097/PEC.0000000000002149 -
Journal of the American Medical... Jan 2022To determine the effects of using unstructured clinical text in machine learning (ML) for prediction, early detection, and identification of sepsis.
OBJECTIVE
To determine the effects of using unstructured clinical text in machine learning (ML) for prediction, early detection, and identification of sepsis.
MATERIALS AND METHODS
PubMed, Scopus, ACM DL, dblp, and IEEE Xplore databases were searched. Articles utilizing clinical text for ML or natural language processing (NLP) to detect, identify, recognize, diagnose, or predict the onset, development, progress, or prognosis of systemic inflammatory response syndrome, sepsis, severe sepsis, or septic shock were included. Sepsis definition, dataset, types of data, ML models, NLP techniques, and evaluation metrics were extracted.
RESULTS
The clinical text used in models include narrative notes written by nurses, physicians, and specialists in varying situations. This is often combined with common structured data such as demographics, vital signs, laboratory data, and medications. Area under the receiver operating characteristic curve (AUC) comparison of ML methods showed that utilizing both text and structured data predicts sepsis earlier and more accurately than structured data alone. No meta-analysis was performed because of incomparable measurements among the 9 included studies.
DISCUSSION
Studies focused on sepsis identification or early detection before onset; no studies used patient histories beyond the current episode of care to predict sepsis. Sepsis definition affects reporting methods, outcomes, and results. Many methods rely on continuous vital sign measurements in intensive care, making them not easily transferable to general ward units.
CONCLUSIONS
Approaches were heterogeneous, but studies showed that utilizing both unstructured text and structured data in ML can improve identification and early detection of sepsis.
Topics: Humans; Machine Learning; Natural Language Processing; Sepsis; Shock, Septic; Vital Signs
PubMed: 34897469
DOI: 10.1093/jamia/ocab236 -
JAMA Network Open Mar 2023Artificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and... (Meta-Analysis)
Meta-Analysis
IMPORTANCE
Artificial intelligence (AI) enables powerful models for establishment of clinical diagnostic and prognostic tools for hip fractures; however the performance and potential impact of these newly developed algorithms are currently unknown.
OBJECTIVE
To evaluate the performance of AI algorithms designed to diagnose hip fractures on radiographs and predict postoperative clinical outcomes following hip fracture surgery relative to current practices.
DATA SOURCES
A systematic review of the literature was performed using the MEDLINE, Embase, and Cochrane Library databases for all articles published from database inception to January 23, 2023. A manual reference search of included articles was also undertaken to identify any additional relevant articles.
STUDY SELECTION
Studies developing machine learning (ML) models for the diagnosis of hip fractures from hip or pelvic radiographs or to predict any postoperative patient outcome following hip fracture surgery were included.
DATA EXTRACTION AND SYNTHESIS
This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses and was registered with PROSPERO. Eligible full-text articles were evaluated and relevant data extracted independently using a template data extraction form. For studies that predicted postoperative outcomes, the performance of traditional predictive statistical models, either multivariable logistic or linear regression, was recorded and compared with the performance of the best ML model on the same out-of-sample data set.
MAIN OUTCOMES AND MEASURES
Diagnostic accuracy of AI models was compared with the diagnostic accuracy of expert clinicians using odds ratios (ORs) with 95% CIs. Areas under the curve for postoperative outcome prediction between traditional statistical models (multivariable linear or logistic regression) and ML models were compared.
RESULTS
Of 39 studies that met all criteria and were included in this analysis, 18 (46.2%) used AI models to diagnose hip fractures on plain radiographs and 21 (53.8%) used AI models to predict patient outcomes following hip fracture surgery. A total of 39 598 plain radiographs and 714 939 hip fractures were used for training, validating, and testing ML models specific to diagnosis and postoperative outcome prediction, respectively. Mortality and length of hospital stay were the most predicted outcomes. On pooled data analysis, compared with clinicians, the OR for diagnostic error of ML models was 0.79 (95% CI, 0.48-1.31; P = .36; I2 = 60%) for hip fracture radiographs. For the ML models, the mean (SD) sensitivity was 89.3% (8.5%), specificity was 87.5% (9.9%), and F1 score was 0.90 (0.06). The mean area under the curve for mortality prediction was 0.84 with ML models compared with 0.79 for alternative controls (P = .09).
CONCLUSIONS AND RELEVANCE
The findings of this systematic review and meta-analysis suggest that the potential applications of AI to aid with diagnosis from hip radiographs are promising. The performance of AI in diagnosing hip fractures was comparable with that of expert radiologists and surgeons. However, current implementations of AI for outcome prediction do not seem to provide substantial benefit over traditional multivariable predictive statistics.
Topics: Humans; Artificial Intelligence; Hip Fractures; Prognosis; Algorithms; Length of Stay
PubMed: 36930153
DOI: 10.1001/jamanetworkopen.2023.3391