Diagnostic Metrics Research Articles

Sex differences in recovery from postoperative sarcopenia during adjuvant CAPOX therapy for colorectal cancer

BackgroundWomen are predisposed to develop intolerance to cancer chemotherapy. Sarcopenia and chemotherapy are mutually related. Women are generally intolerable to chemotherapeutics such as 5-fluorouracil. Although adjuvant oxaliplatin-based chemotherapy, e.g. CAPOX is commonly used to treat colorectal cancer, its effects on patients in terms of sarcopenia and sex remain unknown. We investigated sex disparities in the impacts of CAPOX on body composition in this study.MethodsWe conducted a prospective study on diagnostic metrics used for sarcopenia in colorectal cancer patients receiving adjuvant CAPOX. Evaluations of the nutritional status by the Mini-Nutritional Assessment (MNA), gait speed, grip strength, skeletal muscle mass, fat mass, and bone mineral content using a body composition analyzer were performed in the first, fourth, and eighth cycles of CAPOX (first, second, and third measurements, respectively).ResultsAmong 80 eligible patients, 61 completed four CAPOX cycles. The median differences in MNA, gait, grip strength, muscle mass, fat mass, and bone mineral content between the first and second measurements for men (n = 35) and women (n = 26) were + 10.5% and + 2.9% (p = 0.067), + 4.5% and − 2.6% (p = 0.16), + 1.8% and + 2.8% (p = 0.66), + 2.7% and + 1.3% (p = 0.021), + 4.5% and + 3.5% (p = 0.59), and + 3.3% and + 0.0% (p = 0.006), There were no sex differences in comparisons of the above metrics between the first and third measurements in 34 patients who completed eight CAPOX cycles (19 wen and 15 women).ConclusionsEarly cycles of adjuvant CAPOX may have a negative impact on the postoperative recovery of several metrics for diagnosing sarcopenia in women.

Envelope Protein in Differential Serodiagnosis of Dengue, Zika, and Chikungunya Viruses: A Systematic Review.

This systematic review was conducted to evaluate the applicability of the envelope (E) protein in the diagnosis of arboviruses. This review was performed in accordance with the PRISMA statement. Five databases were explored (PubMed, Web of Science, Scopus, EMBASE, and IEDB). The inclusion and exclusion criteria were applied to study eligibility. After data extraction, the risk of bias and evidence certainty were evaluated according to QUADAS and GRADE assessments, respectively. Eleven studies were included. A total of 11 studies were included in the review. ELISA was the most frequently utilized technique, with two studies employing it for antigen detection and nine for antibodies. The E protein was used as a whole protein, heterologous protein, and peptides. The diagnostic metrics were enhanced by optimizations on techniques, such as antibody capture, competitors, and nanosensors. Monoclonal antibodies showed improved specificity, including in coinfected samples. Seven studies demonstrated a minimal risk of bias, and the evidence certainty was considered moderate for dengue diagnosis. The E protein was successfully employed in different immunological assays with large-scale strategies, enhancing the applicability potential for differential arboviruses' diagnosis. Furthermore, both the antigen design and the implementation of innovative methodologies will have a substantial impact on the quality of the new tests. The PROSPERO protocol related to this work: CRD42021265243.

Cardiac CT vs Echocardiography for Intracardiac Thrombus Detection in Ischemic Stroke: A Systematic Review and Meta-Analysis of 43 Studies.

Ischemic stroke, a leading cause of mortality, necessitates understanding its mechanism for effective prevention. Echocardiography, especially transesophageal echocardiography (TEE), is the gold standard for detection of cardiac sources of stroke including left atrial thrombus, although its invasiveness, operator skill dependence, and limited availability in some centers prompt exploration of alternatives, such as cardiac CT (CCT). We conducted a systematic review and meta-analysis assessing the ability of CCT in the detection of intracardiac thrombus compared with echocardiography. We searched 4 databases up through September 8, 2023. Major search terms included a combination of the terms "echocardiograph," "CT," "TEE," "imaging," "stroke," "undetermined," and "cryptogenic." The current systematic literature review of the English language literature was reported in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses reporting guidelines. We assessed risk of bias using the QUADAS-2 tool and used random-effects meta-analysis to calculate different diagnostic metrics. The meta-analysis investigating CCT vs echocardiography for intracardiac thrombus detection yielded a total of 43 studies of 9,552 patients. Risk-of-bias assessment revealed a predominantly low risk of bias in the flow and timing, index test, and patient selection domains and a predominantly unclear risk of bias in the reference standard domain. The analysis revealed an overall sensitivity of 98.38% (95% CI 89.2-99.78) and specificity of 96.0% (95% CI 92.55-97.88). Subgroup analyses demonstrated that delayed-phase, electrocardiogram-gated CCT had the highest sensitivity (100%; 95% CI 0-100) while early-phase, nongated CCT exhibited a sensitivity of 94.31% (95% CI 28.58-99.85). The diagnostic odds ratio was 98.59 (95% CI 44.05-220.69). Heterogeneity was observed, particularly in specificity and diagnostic odds ratio estimates. CCT demonstrates high sensitivity, specificity, and diagnostic odds ratios in detecting intracardiac thrombus compared with traditional echocardiography. Limitations include the lack of randomized controlled studies, and other cardioembolic sources of stroke such as valvular disease, cardiac function, and aortic arch disease were not examined in our analysis. Large-scale studies are warranted to further evaluate CCT as a promising alternative for identifying intracardiac thrombus and other sources of cardioembolic stroke.

TCT-662 Influence of Comorbidities and Lesion Characteristics on the Diagnostic Performance of Non-Hyperemic Diagnostic Metrics in Coronary Artery Disease

TCT-662 Influence of Comorbidities and Lesion Characteristics on the Diagnostic Performance of Non-Hyperemic Diagnostic Metrics in Coronary Artery Disease

Multicentre external validation of the Neonatal Healthcare-associated infectiOn Prediction (NeoHoP) score: a retrospective case–control study

Background and objectivesNeonatal mortality due to severe bacterial infections is a pressing global issue, especially in low-middle-income countries (LMICs) with constrained healthcare resources. This study aims to validate the Neonatal...

An interpretable tinnitus prediction framework using gap-prepulse inhibition in auditory late response and electroencephalogram.

Tinnitus is a neuropathological condition that results in mild buzzing or ringing of the ears without an external sound source. Current tinnitus diagnostic methods often rely on subjective assessment and require intricate medical examinations. This study aimed to propose an interpretable tinnitus diagnostic framework using auditory late response (ALR) and electroencephalogram (EEG), inspired by the gap-prepulse inhibition (GPI) paradigm. We collected spontaneous EEG and ALR data from 44 patients with tinnitus and 47 hearing loss-matched controls using specialized hardware to capture responses to sound stimuli with embedded gaps. In this cohort study of tinnitus and control groups, we examined EEG spectral and ALR features of N-P complexes, comparing the responses to gap durations of 50 and 20 ms alongside no-gap conditions. To this end, we developed an interpretable tinnitus diagnostic model using ALR and EEG metrics, boosting machine learning architecture, and explainable feature attribution approaches. Our proposed model achieved 90 % accuracy in identifying tinnitus, with an area under the performance curve of 0.89. The explainable artificial intelligence approaches have revealed gap-embedded ALR features such as the GPI ratio of N1-P2 and EEG spectral ratio, which can serve as diagnostic metrics for tinnitus. Our method successfully provides personalized prediction explanations for tinnitus diagnosis using gap-embedded auditory and neurological features. Deficits in GPI alongside activity in the EEG alpha-beta ratio offer a promising screening tool for assessing tinnitus risk, aligning with current clinical insights from hearing research.

Towards Interpretable Physical‐Conceptual Catchment‐Scale Hydrological Modeling Using the Mass‐Conserving‐Perceptron

AbstractWe investigate the applicability of machine learning technologies to the development of parsimonious, interpretable, catchment‐scale hydrologic models using directed‐graph architectures based on the mass‐conserving perceptron (MCP) as the fundamental computational unit. Here, we focus on architectural complexity (depth) at a single location, rather than universal applicability (breadth) across large samples of catchments. The goal is to discover a minimal representation (numbers of cell‐states and flow paths) that represents the dominant processes that can explain the input‐state‐output behaviors of a given catchment, with particular emphasis given to simulating the full range (high, medium, and low) of flow dynamics. We find that a “HyMod Like” architecture with three cell‐states and two major flow pathways achieves such a representation at our study location, but that the additional incorporation of an input‐bypass mechanism significantly improves the timing and shape of the hydrograph, while the inclusion of bi‐directional groundwater mass exchanges significantly enhances the simulation of baseflow. Overall, our results demonstrate the importance of using multiple diagnostic metrics for model evaluation, while highlighting the need for properly selecting and designing the training metrics based on information‐theoretic foundations that are better suited to extracting information across the full range of flow dynamics. This study sets the stage for interpretable regional‐scale MCP‐based hydrological modeling (using large sample data) by using neural architecture search to determine appropriate minimal representations for catchments in different hydroclimatic regimes.

Use of NIR in COVID-19 Screening: Proof of Principles for Future Application.

The COVID-19 pandemic that affected the world between 2019 and 2022 showed the need for new tools to be tested and developed to be applied in global emergencies. Although standard diagnostic tools exist, such as the reverse-transcription polymerase chain reaction (RT-PCR), these tools have shown severe limitations when mass application is required. Consequently, a pressing need remains to develop a rapid and efficient screening test to deliver reliable results. In this context, near-infrared spectroscopy (NIRS) is a fast and noninvasive vibrational technique capable of identifying the chemical composition of biofluids. This study aimed to develop a rapid NIRS testing methodology to identify individuals with COVID-19 through the spectral analysis of swabs collected from the oral cavity. Swab samples from 67 hospitalized individuals were analyzed using NIR equipment. The spectra were preprocessed, outliers were removed, and classification models were constructed using partial least-squares for discriminant analysis (PLS-DA). Two models were developed: one with all the original variables and another with a limited number of variables selected using ordered predictors selection (OPS-DA). The OPS-DA model effectively reduced the number of redundant variables, thereby improving the diagnostic metrics. The model achieved a sensitivity of 92%, a specificity of 100%, an accuracy of 95%, and an AUROC of 94% for positive samples. These preliminary results suggest that NIRS could be a potential tool for future clinical application. A fast methodology for COVID-19 detection would facilitate medical diagnoses and laboratory routines, helping to ensure appropriate treatment.

Histopathological correlations of CT-based radiomics imaging biomarkers in native kidney biopsy

BackgroundKidney biopsy is the standard of care for the diagnosis of various kidney diseases. In particular, chronic histopathologic lesions, such as interstitial fibrosis and tubular atrophy, can provide prognostic information regarding chronic kidney disease progression. In this study, we aimed to evaluate historadiological correlations between CT-based radiomic features and chronic histologic changes in native kidney biopsies and to construct and validate a radiomics-based prediction model for chronicity grade.MethodsWe included patients aged ≥ 18 years who underwent kidney biopsy and abdominal CT scan within a week before kidney biopsy. Left kidneys were three-dimensionally segmented using a deep learning model based on the 3D Swin UNEt Transformers architecture. We additionally defined isovolumic cortical regions of interest near the lower pole of the left kidneys. Shape, first-order, and high-order texture features were extracted after resampling and kernel normalization. Correlations and diagnostic metrics between extracted features and chronic histologic lesions were examined. A machine learning-based radiomic prediction model for moderate chronicity was developed and compared according to the segmented regions of interest (ROI).ResultsOverall, moderate correlations with statistical significance (P < 0.05) were found between chronic histopathologic grade and top-ranked radiomic features. Total parenchymal features were more strongly correlated than cortical ROI features, and texture features were more highly ranked. However, conventional imaging markers, including kidney length, were poorly correlated. Top-ranked individual radiomic features had areas under receiver operating characteristic curves (AUCs) of 0.65 to 0.74. Developed radiomics models for moderate-to-severe chronicity achieved AUCs of 0.89 (95% confidence interval [CI] 0.75–0.99) and 0.74 (95% CI 0.52–0.93) for total parenchymal and cortical ROI features, respectively.ConclusionSignificant historadiological correlations were identified between CT-based radiomic features and chronic histologic changes in native kidney biopsies. Our findings underscore the potential of CT-based radiomic features and their prediction model for the non-invasive assessment of kidney fibrosis.

Dysfunctional HDL Diagnostic Metrics for Cardiovascular Disease Risk Stratification: Are we Ready to Implement in Clinics?

Dysfunctional HDL Diagnostic Metrics for Cardiovascular Disease Risk Stratification: Are we Ready to Implement in Clinics?

Validation of the eye screening tool GoCheck Kids for the detection of amblyopia risk factors in toddlers in Flanders

PurposeTo assess the validity of the GoCheck Kids photoscreening application (Gobiquity Mobile Health, Scottdale, AZ) on iPhone, which was used (2018-2022) as standard of care by Child and Family (Kind en Gezin) to detect amblyopia risk factors in children 12-30 months of age. MethodsBetween August 2021 and May 2022, 453 children 11-16 months of age underwent a confirmatory ophthalmic examination within 2 months of GoCheck Kids photoscreening at Child and Family, Flanders, Belgium. Additionally, manual review was performed by specialists of GoCheck Kids. Diagnostic metrics were assessed using the 2013 criteria of the American Association for Pediatric Ophthalmology and Strabismus as reference. ResultsSpecificity was similar for automatic screening with or without manual review: 90.0% (95% CI, 87.6%-92.3%) and 90.3% (95% CI, 88.0%-92.7%), respectively. Sensitivity was estimated at 52.0% (95% CI, 35.6%-68.4%) for automatic grading and 56.0% (95% CI, 39.7%-72.3%) after manual review. Positive predictive values for automatic screening and manual review were, respectively, 23.2% (95% CI, 13.9-32.5) and 25.5% (95% CI, 15.8-35.1). Negative predictive values for automatic screening and manual review were, respectively, 97.0% (95% CI, 95.6-98.4) and 97.2 (95% CI, 95.8-98.6). ConclusionsIn our study cohort of children around 12 months of age, the GoCheck Kids application had a specificity of 90% for the targeted amblyopia risk factors, with sensitivity just over 50%.

Diagnostic Transitions of Cystic Fibrosis and CRMS Compared After 12 Years of Newborn Screening in California

To compare the long-term diagnostic transitions for cystic fibrosis (CF) and CF-Related Metabolic Syndrome (CRMS) side-by-side during follow-up since the onset of newborn screening in California. Using real-world data, we conducted a retrospective cohort study to compare long-term observations of CRMS and CF in California and the diagnostic transitions from one to the other using clinical and diagnostic metrics. The California Genetic Disease Screening Program (GDSP) newborn screening for CF employs an immunoreactive trypsinogen tier-1 laboratory test, followed by molecular testing. This approach captures CF and CRMS, a diagnosis of "watchful waiting" among infants at risk for CF but with signs and symptoms that may emerge outside the screening window. Waiting entails periodic diagnostic reviews that can continue for many years; GDSP routinely conducts five years of follow-up for each child identified with a disorder. We utilized categorial logistic regression to compare the transitions with CRMS. After screening 5,944,700 newborns between July 2007 and July 2019, 694 CF cases and 1,258 CRMS cases were identified. Of the 1,258 CRMS cases, 66 (5.2%, 95% CI=3.9%,6.4%) transitioned from CRMS to CF (CRMS2CF) at a mean age of 3.3 years (median=2.9 years). CRMS2CF cases had longer follow-up periods and were more likely later to develop positive sweat chloride and fecal elastase test results after 6 months of life than other CRMS cases. These results suggest that children who have a CRMS2CF transition are more likely to develop positive biochemical markers than other CRMS patients and have few clinical indications during the first five years of follow-up.

Mycobacterium tuberculosis Detection Using CRISPR Technology: An Updated Systematic Review and Meta-analysis.

Rapid and precise detection of Mycobacterium tuberculosis (MTB) is paramount for effective management and control of tuberculosis. Clustered regularly interspaced short palindromic repeats (CRISPR) technology has emerged as a promising tool for pathogenic diagnosis owing to its specificity and adaptability. This systematic review and meta-analysis aimed to appraise the diagnostic accuracy of CRISPR-based techniques in identifying MTB. A meticulous search was conducted in Medline, Scopus, Embase, and ISI Web of Science to retrieve relevant studies, adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Quality was assessed using the Joanna Briggs Institute checklist. Data synthesis and analyses, including subgroup analyses, were performed with R v 4.3.1, examining variables like CRISPR variants, gene targets, pre-amplification techniques, and signal readout methods. From 389 identified studies, 14 met the inclusion criteria, encompassing 2175 MTB strains. The pooled sensitivity and specificity of CRISPR-based techniques were 0.93 (95% CI 0.85-0.99) and 0.97 (95% CI 0.94-0.99), respectively. The pooled diagnostic odds ratio was 273.4379 (95% CI 103.3311-723.5794), with an area under the curve of 0.97 for the summary receiver operating characteristic (SROC) curve, denoting excellent diagnostic accuracy. Subgroup analyses illustrated variations in diagnostic metrics based on factors like CRISPR variant utilized, target gene, and pre-amplification methods. For instance, CRISPR-Cas12 exhibited a sensitivity and specificity of 0.93 (95% CI 0.78-0.98) and 0.98 (95% CI 0.93-1), respectively. Moreover, this technology showed a sensitivity of 96% and specificity of 100% in detecting resistant MTB. CRISPR-based methods exhibit substantial diagnostic sensitivity and specificity for detecting MTB, with notable variances across different CRISPR variants and methodological approaches. Further studies must be conducted to optimize CRISPR's potential as a diagnostic tool for MTB in a variety of clinical and research settings.

RT-qPCR Testing and Performance Metrics in the COVID-19 Era.

The COVID-19 pandemic highlighted the crucial role of diagnostic testing in managing infectious diseases, particularly through the use of reverse transcription-quantitative polymerase chain reaction (RT-qPCR) tests. RT-qPCR has been pivotal in detecting and quantifying viral RNA, enabling the identification and management of SARS-CoV-2 infections. However, despite its widespread use, there remains a notable gap in understanding fundamental diagnostic metrics such as sensitivity and specificity among many scientists and healthcare practitioners. This gap is not merely academic; it has profound implications for interpreting test results, making public health decisions, and affecting patient outcomes. This review aims to clarify the distinctions between laboratory- and field-based metrics in the context of RT-qPCR testing for SARS-CoV-2 and summarise the global efforts that led to the development and optimisation of these tests during the pandemic. It is intended to enhance the understanding of these fundamental concepts among scientists and healthcare professionals who may not be familiar with the nuances of diagnostic test evaluation. Such knowledge is crucial for accurately interpreting test results, making informed public health decisions, and ultimately managing infectious disease outbreaks more effectively.

The Legacy of Hermann Rorschach and His Inkblots: Portrait of a Man or Mental Disease?

Hermann Rorschach was a Swiss psychiatrist and psychoanalyst who experimented with inkblots for the purpose of diagnosing mental illness and personality temperaments. This paper highlights the legacy of Rorschach through discussion of the events that led to the inkblots' creation during Rorschach's life and after his death. The foundational elements of the inkblots were conceived in Rorschach's 1911 dissertation regarding reflex hallucinations, a form of synesthesia, that ultimately served as Rorschach's experimental focus and development of his iconic inkblots. After Rorschach's death in 1922, the inkblots were disseminated in America by Samuel Beck and Bruno Klopfer during the 1930s and 1940s while expanding on intelligence and personality metrics. Further research regarding the concept of a "group Rorschach'' was expanded by Molly Harrower and ultimately applied by Douglas Kelly and Gustav Gilbert to the Nazi Defendants at Nuremberg with the aim of conceptualizing the "Nazi personality." However, due to interpreter bias and conflicting interpretation, the results surrounding the Nazi Rorschachs remain controversial. Further controversy ensued after John Exner's attemptto standardize the Rorschach methodology while introducing new diagnostic metrics. Today, the Rorschach inkblots are criticized for their lack of validity and clinical relevance.

The Cobra sign: A marker for overestimation of tendon retraction in proximal semimembranosus tendon avulsion.

To introduce a new magnetic resonance imaging (MRI) sign, termed the Cobra sign, and identify its diagnostic metrics. The secondary aim was to demonstrate that this sign can be a source of false evaluation of tendon retraction in patients with proximal hamstring avulsion injury. This retrospective cohort study targeted patients surgically treated for proximal hamstring avulsion injury from January 2019 to June 2023. The MRI Cobra sign was defined as a wavy curved T2-hypointense band with the free end folding distally over itself, resembling a cobra head. The primary outcome measure was the characterization of the Cobra sign in patients with proximal hamstring avulsion injury. The secondary outcome was the association of this sign with tendon retraction. The study included 81 proximal hamstring avulsion injury patients (mean age of 45.7, SD = 13.9), with 41 (50.6%) complete avulsions, 33 semimembranosus, and 7 conjoint tendons. The MRI Cobra sign was found in 25 patients (17 semimembranosus and 8 complete). It was confirmed surgically only in semimembranosus cases. It demonstrated 51.5% sensitivity and 83.3% specificity for isolated semimembranosus avulsions, with a significant positive likelihood ratio of 3.0. MRI retraction was 10.05 cm (±3.0), reducing to 7.9 cm (±2.5) on surgical measurement (mean difference = 2.0 cm, p < 0.001). The regression analysis confirmed MRI retraction's influence on the Cobra sign, with a 1.4 odds increase per unit (p < 0.001). In linear regression analysis, each unit increase in MRI retraction corresponded to a 79% increase in surgical retraction (coefficient 0.7, t = 11.1, p < 0.001). The Cobra sign demonstrated acceptable diagnostic accuracy for isolated semimembranosus avulsion, with a high specificity of 83.3%, a low sensitivity of 51.5%, and a positive likelihood ratio of 3.0. The presence of the Cobra sign indicates an overestimated MRI retraction by approximately 21%. Level III.

Diagnostic Performance of ASL-MRI and FDG-PET in Frontotemporal Dementia: A Systematic Review and Meta-Analysis.

While the diagnosis of frontotemporal dementia (FTD) is based mostly on clinical features, [18F]-FDG PET has been investigated as a potential imaging golden standard in ambiguous cases, with arterial spin labeling (ASL) MRI gaining recent interest. The purpose of this study is to conduct a systematic review and meta-analysis on the diagnostic performance of ASL MRI in FTD patients and compare it to that of [18F]-FDG PET. A systematic search of PubMed, Scopus and EMBASE was conducted until March 13, 2024. Inclusion criteria were: original articles, patients with FTD and/or its variants, use of ASL MR perfusion imaging with or without [18F]-FDG PET, presence of sufficient diagnostic performance data. Exclusion criteria were: meeting abstracts, comments, summaries, protocols, letters and guidelines, longitudinal studies, overlapping cohorts. The quality of eligible studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2. Pooled sensitivity, specificity, and diagnostic odds ratio (DOR) for [18F]-FDG PET and ASL MRI were calculated, and a summary receiver operating characteristic curve was plotted. Seven eligible studies were identified, which included a total of 102 FTD patients. Aside from some of the studies showing at worst an unclear risk of bias in patient selection, index test, flow and timing, all studies showed low risk of bias and applicability concerns in all categories. Data from 4 studies was included in our meta-analysis for ASL MRI and 3 studies for [18F]-FDG PET. Pooled sensitivity, specificity and DOR were 0.70 (95% CI: 0.59-0.79), 0.81 (95% CI: 0.71-0.88) and 8.00 (95% CI: 3.74-17.13) for ASL MRI, and 0.88 (95% CI: 0.71-0.96), 0.89 (95% CI: 0.43-0.99) and 47.18 (95% CI: 10.77-206.75) for [18F]-FDG PET. The number of studies was relatively small, with a small sample size. The studies used different scanning protocols as well as a mix of diagnostic metrics, all of which might have introduced heterogeneity in the data. While ASL MRI performed worse than [18F]-FDG PET in the diagnosis of FTD, it exhibited a decent diagnostic performance to justify its further investigation as a quicker and more convenient alternative. 3DPCASL, 3D pseudocontinuous ASL; AD, Alzheimer's disease; ASL, arterial spin labeling; AUC, area under the curve; CI, confidence interval; DOR, diagnostic odds ratio; FN, false negative; FP, false positive; FTD, frontotemporal dementia; LE, limbic encephalitis; NLR, negative likelihood ratio; PASL, pulsed ASL; PLD, post-label delay; PLR, positive likelihood ratio; PRISMA, PSP, progressive supranuclear palsy; Preferred Reporting Items for Systematic Reviews and Meta-Analysis; SROC, summary receiver operative characteristic; TN, true negative; TP, true positive; QUADAS-2, Quality Assessment of Diagnostic Accuracy Studies-2.

Diagnostic Accuracy of Cone-Beam CT for Acute Intracranial Hemorrhage: A Systematic Review and Meta-Analysis

ObjectiveOur purpose was to synthesize evidence in the literature to determine the diagnostic accuracy of cone-beam CT (CBCT) for the detection of intracranial hemorrhage (ICH) and hemorrhage types, including intraparenchymal hemorrhage (IPH), subarachnoid hemorrhage (SAH), and intraventricular hemorrhage (IVH). MethodsWe performed a meta-analysis following the Preferred Reporting Items for Systematic Review and Meta-Analyses guidelines. Our protocol was registered with International Prospective Register of Systematic Reviews (PROSPERO-CRD42021261915). Systematic searches were last performed on April 30, 2024, in EMBASE, PubMed, Web-of-Science, Scopus, and Cumulative Index to Nursing and Allied Health Literature databases. Inclusion criteria were (1) studies reporting diagnostic metrics of CBCT for ICH and (2) studies using a reference standard to determine ICH. Exclusion criteria were (1) case reports, abstracts, reviews and (2) studies without patient-level data. Pooled estimates and 95% confidence intervals (CIs) were calculated for diagnostic odds ratios (DORs), sensitivity, and specificity using random-effects and common-effects models. Mixed methods appraisal tool was used to evaluate risk of bias. ResultsSeven studies were included in the meta-analysis yielding 466 patients. Mean or median age ranged from 54 to 75 years. Female patients represented 51.4% (222 of 432) in reported studies. Multidetector CT was the reference standard in all studies. DOR, pooled sensitivity, and pooled specificity for ICH were 5.28 (95% CI: 4.11-6.46), 0.88 (95% CI: 0.79-0.97), and 0.99 (95% CI: 0.98-1.0). Pooled sensitivity for IPH, SAH, and IVH was 0.98 (95% CI: 0.95-1.0), 0.82 (95% CI: 0.57-1.0), and 0.78 (95% CI: 0.55-1.0). Pooled specificity for IPH, SAH, and IVH was 0.99 (95% CI: 0.98-1.0), 0.99 (95% CI: 0.97-1.0), and 1.0 (95% CI: 0.98-1.0). DiscussionCBCT had moderate DOR and high pooled specificity for ICH and hemorrhage types. However, pooled sensitivity varied by hemorrhage type, with the highest sensitivity for IPH, followed by SAH and IVH.

High-resolution oblique coronal MRI at optimal flexed-knee angle: a novel imaging method for enhanced anterior cruciate ligament tear diagnosis

BackgroundThe accuracy of traditional knee MR imaging in diagnosing anterior cruciate ligament tears, especially partial tears, is relatively low, which may lead to misdiagnosis and missed diagnosis. This study aimed to assess the diagnostic performance of a novel imaging method, high-resolution oblique coronal MRI at an optimal flexed-knee Angle, for ACL tears.Methods50 healthy volunteers were scanned with a scan-assisted device for the optimal flexion angle of ACL. For 92 knee trauma patients selected strictly according to inclusion and exclusion criteria, conventional extended-knee scans (control group) and high-resolution oblique coronal scans based on the optimal flexed-knee angle (experimental group) were conducted. Two observers rated ACL visibility blindly on a 5-point scale. Arthroscopy-defined outcomes determined diagnostic metrics for each method and sensitivity, specificity, positive predictive value, negative predictive value and accuracy were calculated.ResultsThe average optimal flexion angle for healthy volunteers was approximately 30° (30.3° ± 5.0°). Imaging demonstrated complete visualization of the ACL in 96.7% of images in the experimental group versus 12.0% in the control group. The diagnostic indicators of the experimental group surpassed those of the control group: sensitivity (94.9% vs. 76.3%), specificity (97.0% vs. 81.8%), positive predictive value (98.2% vs. 88.2%), negative predictive value(91.4% vs. 65.9%), and accuracy (95.7% vs. 78.3%). ROC analysis indicated superior diagnostic performance in the experimental group, with an AUC of 0.945 compared with 0.776 for the control group (p < 0.0001).ConclusionsHigh-resolution oblique coronal imaging at the optimal 30° flexed-knee angle improved ACL visualization and diagnostic performance compared with conventional techniques.

Independent evaluation of the accuracy of 5 artificial intelligence software for detecting lung nodules on chest X-rays.

The integration of artificial intelligence (AI) into medicine is growing, with some experts predicting its standalone use soon. However, skepticism remains due to limited positive outcomes from independent validations. This research evaluates AI software's effectiveness in analyzing chest X-rays (CXR) to identify lung nodules, a possible lung cancer indicator. This retrospective study analyzed 7,670,212 record pairs from radiological exams conducted between 2020 and 2022 during the Moscow Computer Vision Experiment, focusing on CXR and computed tomography (CT) scans. All images were acquired during clinical routine. The final dataset comprised 100 CXR images (50 with lung nodules, 50 without), selected consecutively and based on inclusion and exclusion criteria, to evaluate the performance of all five AI-based solutions, participating in the Moscow Computer Vision Experiment and analyzing CXR. The evaluation was performed in 3 stages. In the first stage, the probability of a nodule in the lung obtained from AI services was compared with the Ground Truth (1-there is a nodule, 0-there is no nodule). In the second stage, 3 radiologists evaluated the segmentation of nodules performed by the AI services (1-nodule correctly segmented, 0-nodule incorrectly segmented or not segmented at all). In the third stage, the same radiologists additionally evaluated the classification of the nodules (1-nodule correctly segmented and classified, 0-all other cases). The results obtained in stages 2 and 3 were compared with Ground Truth, which was common to all three stages. For each stage, diagnostic accuracy metrics were calculated for each AI service. Three software solutions (Celsus, Lunit INSIGHT CXR, and qXR) demonstrated diagnostic metrics that matched or surpassed the vendor specifications, and achieved the highest area under the receiver operating characteristic curve (AUC) of 0.956 [95% confidence interval (CI): 0.918 to 0.994]. However, when evaluated by three radiologists for accurate nodule segmentation and classification, all solutions performed below the vendor-declared metrics, with the highest AUC reaching 0.812 (95% CI: 0.744 to 0.879). Meanwhile, all AI services demonstrated 100% specificity at stages 2 and 3 of the study. To ensure the reliability and applicability of AI-based software, it is crucial to validate performance metrics using high-quality datasets and engage radiologists in the evaluation process. Developers are recommended to improve the accuracy of the underlying models before allowing the standalone use of the software for lung nodule detection. The dataset created during the study may be accessed at https://mosmed.ai/datasets/mosmeddatargogksnalichiemiotsutstviemlegochnihuzlovtipvii/.