Excellent Diagnostic Performance Research Articles

Diagnostic performance of simultaneous PET-MR versus PET-CT in oncology with an overview on clinical utility and referral pattern of PET-MR: a single institutional study.

PET-Magnetic Resonance (PET-MR) imaging is an upcoming investigative modality with a few installations in Asia and only three in India. PET-Computed Tomography (PET-CT) is an established diagnostic cornerstone for oncological indications but with limited resolution for small lesions due to low soft-tissue contrast and additional radiation exposure. Our primary objective was to evaluate the diagnostic performance of simultaneous PET-MR and PET-CT in lesion detection in oncological practice. Secondly to assess the referral pattern and study the clinical utility of PET-MR in a university hospital practice. A total of 100 consecutive biopsy-proven cancer patients (breast or lung malignancy with suspected metastases) underwent 18 F Fluorodeoxyglucose (FDG) PET-MR and PET-CT for staging as a single injection, double examination protocol. Morphological lesion detection on correlative imaging/histopathology was used as the gold standard. Analysing the referral pattern, a total of 9366 patients underwent simultaneous PET-MR imaging for various indications in the past 5 years since installation. 18 F FDG PET-MR detected 100% of primary tumours in breast/lung carcinoma patients while PET-CT was positive in 96%. Overall accuracy of nodal metastases detection for PET-MR and PET-CT was 96 and 88%, while for distant metastases the accuracy was 100 and 93%, respectively. FDG PET-MR proved more sensitive and specific than PET-CT for regional nodal ( P = 0.011 and P < 0.001) and distant metastases detection ( P = 0.017 and P < 0.001, respectively). Analysing the general referral pattern for PET-MR, the majority were oncology referrals when compared to nononcological indications (66.5, 33.5%). About 66.24% were FDG based, followed by 68 Ga Prostate-Specific Membrane Antigen (PSMA) and dodecane tetraacetic acid (DOTA). The general utility of PET-MR was found incremental in better delineation of small lesions especially in head, neck, liver, brain and gynaecological malignancies. In our past 5 years of PET-MR practice, we found that simultaneous PET-MR is a highly recommended ideal imaging technique for oncological and nononcological indications. It has excellent diagnostic performance with high sensitivity, specificity and accuracy when compared to PET-CT in primary tumour, nodal and distant metastases (TNM) staging in specific subgroup of breast and lung malignancy patients.

Identifying Hub Genes for Glaucoma based on Bulk RNA Sequencing Data and Multi-machine Learning Models.

The aims of this study were to determine hub genes in glaucoma through multiple machine learning algorithms. Glaucoma has afflicted many patients for many years, with excessive pressure in the eye continuously damaging the nervous system and leading to severe blindness. An effective molecular diagnostic method is currently lacking. The present study attempted to reveal the molecular mechanism and gene regulatory network of hub genes in glaucoma, followed by an attempt to reveal the drug-gene-disease network regulated by hub genes. A microarray sequencing dataset (GSE9944) was obtained through the Gene Expression Omnibus database. The differentially expressed genes in Glaucoma were identified. Based on these genes, we constructed three machine learning models for feature training, Random Forest model (RF), Least absolute shrinkage and selection operator regression model (LASSO), and Support Vector Machines model (SVM). Meanwhile, Weighted Gene Co-Expression Network Analysis (WGCNA) was performed for GSE9944 expression profiles to identify Glaucoma-related genes. The overlapping genes in the four groups were considered as hub genes of Glaucoma. Based on these genes, we also constructed a molecular diagnostic model of Glaucoma. In this study, we also performed molecular docking analysis to explore the gene-drug network targeting hub genes. In addition, we evaluated the immune cell infiltration landscape in Glaucoma samples and normal samples by applying CIBERSORT method. 8 hub genes were determined: ATP6V0D1, PLEC, SLC25A1, HRSP12, PKN1, RHOD, TMEM158 and GSN. The diagnostic model showed excellent diagnostic performance (area under the curve=1). GSN might positively regulate T cell CD4 naïve as well as negatively regulate T cell regulation (Tregs). In addition, we constructed gene-drug networks in an attempt to explore novel therapeutic agents for Glaucoma. Our results systematically determined 8 hub genes and established a molecular diagnostic model that allowed the diagnosis of Glaucoma. Our study provided a basis for future systematic studies of Glaucoma pathogenesis.

Predicting radiation pneumonitis in lung cancer using machine learning and multimodal features: a systematic review and meta-analysis of diagnostic accuracy.

To evaluate the diagnostic accuracy of machine learning models incorporating multimodal features for predicting radiation pneumonitis in lung cancer through a systematic review and meta-analysis. Relevant studies were identified through a systematic search of PubMed, Web of Science, Embase, and the Cochrane Library from October 2003 to December 2023. Additional studies were located by reviewing bibliographies and relevant websites. Two independent researchers screened titles, abstracts, and full-text articles according to predefined inclusion and exclusion criteria. Data extraction was performed using standardized forms, and study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The primary outcomes, including combined sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC), were calculated using STATA MP-64 software(Stata Corporation LLC, College Station, USA) with a random-effects model. Meta-analysis was conducted to synthesize diagnostic accuracy measures, and analyses of heterogeneity and publication bias were performed. A total of 1,406 patients with primary lung cancer were included in this systematic review, drawing data from 9 studies. The pooled analysis revealed a sensitivity of 0.74 [0.58-0.85] and a specificity of 0.91 [0.87-0.95] for machine learning models in diagnosing radiation pneumonitis. The positive likelihood ratio (PLR) was 8.69 [5.21-14.50], the negative likelihood ratio (NLR) was 0.28 [0.16-0.49], and the diagnostic odds ratio (DOR) was 30.73 [11.96-78.97]. The area under the curve (AUC) was 0.93 [0.90-0.95], indicating excellent diagnostic performance. Meta-regression analysis identified that the number of machine learning models, year of publication, and study design contributed to heterogeneity among studies. No evidence of publication bias was found. Overall, machine learning models incorporating multimodal characteristics demonstrated 75% accuracy in predicting moderate to severe radiation pneumonitis. In conclusion, by integrating the current machine learning (ML) algorithm's ability in big data mining, a predictive model can be constructed by combining multi-modal features such as genetics, imaging, and cell factors. By selecting multiple machine learning algorithm frameworks and competing for the best combination model based on research goals, the reliability and accuracy of the radiation pneumonitis prediction model can be greatly improved. PROSPERO (CRD42024497599).

Diagnostic and prognostic value of plasma lipocalin-2 levels in patients with metabolic dysfunction–associated steatotic liver disease

Abstract Background Non-Alcoholic Fatty Liver Disease, recently better recognised as Metabolic Dysfunction–Associated Steatotic Liver Disease, is the most prevalent form of chronic liver disease at present time. It is estimated to impact 32% of the world's population, hence representing a significant health burden. Aim of the work To assess the significance of plasma Lipocalin-2 (LCN2) levels in the diagnosis and prognosis of NAFLD patients. Patients and methods In this retrospective case–control study we recruited 102 subjects aged between 18 and 70 years. The included participants were split into two study groups. Group I: 51 NAFLD patients (61% men, 39% females) and Group II: 51 healthy controls (51% men and 49% females), for whom plasma LCN2 levels were assessed and correlated with NAFLD fibrosis score, FIB4 and fatty liver index. Results In this study, LCN2 levels in NAFLD patients were significantly greater compared to individuals in the control group (p &lt; 0.001), with a mean of 1893.214 ± 1002.852 ng/dL in the cases and a mean of 466.020 ± 397.699 ng/dL in the controls. This suggests the use of LCN2 as a possible diagnostic marker of NAFLD. The mean LCN2 levels in this study also significantly increased as the grade of fatty liver increased from I to III (p &lt; 0.001). This in turn proposes the use of LCN2 as a prognostic marker for NAFLD progression. LCN2 also significantly correlated with the fatty liver index and NAFLD Fibrosis scoring systems, but not with Fib-4. With an area under the ROC of 0.906, it demonstrated excellent diagnostic performance with 84% sensitivity, 90% specificity, 89.6% PPV and 85.2% NPV for the prediction of NAFLD patients. Conclusion Lipocalin-2 performs as a diagnostic and a possible prognostic marker for metabolic dysfunction-associated steatotic liver disease.

GUCA2A dysregulation as a promising biomarker for accurate diagnosis and prognosis of colorectal cancer

Colorectal cancer is a leading cause of global mortality and presents a significant barrier to improving life expectancy. The primary objective of this study was to discern a unique differentially expressed gene (DEG) that exhibits a strong association with colorectal cancer. By achieving this goal, the research aims to contribute valuable insights to the field of translational medicine. We performed analysis of colorectal cancer microarray and the TCGA colon adenoma carcinoma (COAD) datasets to identify DEGs associated with COAD and common DEGs were selected. Furthermore, a pan-cancer analysis encompassing 33 different cancer types was performed to identify differential genes significantly expressed only in COAD. Then, comprehensively in-silico analysis including gene set enrichment analysis, constructing Protein–Protein interaction, co-expression, and competing endogenous RNA (ceRNA) networks, investigating the correlation between tumor-immune signatures in distinct tumor microenvironment and also the potential interactions between the identified gene and various drugs was executed. Further, the candidate gene was experimentally validated in tumoral colorectal tissues and colorectal adenomatous polyps by qRael-Time PCR. GUCA2A emerged as a significant DEG specific to colorectal cancer (|log2FC|> 1 and adjusted q-value < 0.05). Importantly, GUCA2A exhibited excellent diagnostic performance for COAD, with a 99.6% and 78% area under the curve (AUC) based on TCGA-COAD and colon cancer patients. In addition, GUCA2A expression in adenomatous polyps equal to or larger than 5 mm was significantly lower compared to smaller than 5 mm. Moreover, low expression of GUCA2A significantly impacted overall patient survival. Significant correlations were observed between tumor-immune signatures and GUCA2A expression. The ceRNA constructed included GUCA2A, 8 shared miRNAs, and 61 circRNAs. This study identifies GUCA2A as a promising prognostic and diagnostic biomarker for colorectal cancer. Further investigations are warranted to explore the potential of GUCA2A as a therapeutic biomarker.

Identification of Chronic Pancreatitis Associated microRNAs and Genes for the Diagnosis of Pancreatic Cancer.

The timely identification of both malignant and nonmalignant pancreatic lesions has the potential to significantly enhance prognosis and implement risk management strategies across various levels. microRNAs (miRs) and their corresponding targets play a crucial role in the development of pancreatic lesions and can serve as valuable diagnostic and therapeutic targets. The objective of our study was to investigate potential diagnostic markers that can effectively differentiate between malignant and nonmalignant pancreatic lesions. Gene Expression Omnibus (GEO) database with GSE24279 dataset was utilized to screen differentially expressed miRNAs (DEMs). We utilized the TargetScanHuman database to predict the target genes associated with hsa-miR-150-3p, hsa-miR-150-5p, and hsa-miR-214-3p. Furthermore, a cohort comprising healthy individuals (n = 52), chronic pancreatitis (CP; n = 34), and pancreatic adenocarcinoma (PAAD; n = 53) patients was recruited to ascertain the levels of plasma markers. We identified 3 miRNAs (hsa-miR-150-3p, hsa-miR-150-5p, and hsa-miR-214-3p) and 2 proteins (PCDH1 and AMN) as potential diagnostic markers for distinguishing between CP and PAAD. The area under the curve (AUC) values for all markers exceeded .800. Notably, a combination of plasma PCDH1 and AMN demonstrated excellent diagnostic performance (AUC = .921; 95% CI: .866-.977; sensitivity = .792; specificity = .941) in discriminating between CP and PAAD. In addition, the model of hsa-miR-150-3p, hsa-miR-150-5p, and hsa-miR-214-3p yielded an AUC of .928, sensitivity of .830, and specificity of .912, respectively. Plasma levels of miRNAs (hsa-miR-150-3p, hsa-miR-150-5p, and hsa-miR-214-3p) and their corresponding targets (PCDH1 and AMN) hold promise as potential biomarkers for predicting PAAD in patients with CP.

Discovery of a blood-based miRNA signature that can predict onset of active tuberculosis among household contacts of TB patients

BackgroundNon-sputum based predictive biomarkers capable of identifying individuals with high risk of progression to active tuberculosis (TB) are critical for global TB control. MicroRNAs (miRNAs) are significant regulators involved in TB pathogenesis and hence we aimed to identify a miRNA signature capable of predicting progression to TB disease.MethodsWe compared the differential miRNA expression profile of QuantiFERON supernatants of TB Progressors, defined as healthy household contacts (HHCs) of TB patients, who developed active TB disease during a 2-year follow-up period, and Non-progressors defined as HHCs from the same longitudinal cohort who did not develop TB disease during the entire follow-up period, using the nanostring nCounter platform. Receiver Operator Characteristic (ROC) analysis was performed to evaluate the diagnostic accuracy of the identified miRNA biomarkers, followed by random forest analysis to determine the best predictive model.ResultsWe identified 30 differentially regulated miRNAs between the two groups. Of these, hsa-miR-585-3p and hsa-miR-92a-3p were up-regulated with a maximum fold change of 1.74 and 1.71 respectively, while hsa-miR-223-3p and hsa-miR-451a were down-regulated by −2.05 and −2.04 fold respectively. Random forest analysis revealed that hsa-miR-181a-5p, hsa-miR-204-5p, hsa-miR-197-3p, hsa-miR-92a-3p, hsa-miR-451a, hsa-miR-24-3p, and hsa-miR-487a-3p exhibited 100% accuracy in identifying Progressors. This panel of 7 miRNAs demonstrated excellent diagnostic performance characteristics with 100% sensitivity and specificity.ConclusionWe propose that the identified miRNA signature has the potential to serve as a very useful tool for early identification of individuals who bear the highest risk of progression to TB, so that they can be targeted for timely intervention.

Interethnic validation of an artificial intelligence algorithm for prediction of atrial fibrillation using sinus rhythm electrocardiogram

Abstract Background Previous research has demonstrated acceptable diagnostic accuracy of artificial intelligence (AI)-enabled sinus rhythm (SR) electrocardiogram (ECG) interpretation for identifying paroxysmal atrial fibrillation (AF). However, interethnic validations of the AI algorithms have not been widely conducted. Purpose We aimed to develop our own AI model for the identification of paroxysmal AF based on SR ECGs in the Korean population and to validate its diagnostic performance in Brazilian citizens. Methods We trained a Transformer-based vision network on 90% of a dataset comprising 808,194 ECGs from 121,282 patients at Seoul National University Bundang Hospital (2003-2020). The remaining 10% of the dataset was used for internal validation. The model was trained to compute a risk score for paroxysmal AF or new-onset AF within 2 years. External validation was conducted using non-AF ECGs from the CODE 15% dataset provided by the Telehealth Network of Minas Gerais, Brazil. Results In internal validation, our AI model achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.911 (95% CI: 0.902 - 0.921), with a sensitivity of 78.1% and a specificity of 89.0%. Subgroup analyses showed an AUROC of 0.893 (95% CI: 0.876 - 0.909) for patients in routine health checkups or outpatient settings, and 0.854 for patients with "Normal ECG" interpretations. In external validation with the CODE 15% dataset, the AI model exhibited an AUROC of 0.884 (95% CI: 0.869-0.900), which increased to 0.906 (95% CI: 0.893-0.919) when adjusted for age and sex (Figure 1). In the subset of patients with "Normal ECG" interpretations, the AUROC was 0.826 (95% CI: 0.769-0.883), increasing to 0.861 (95% CI: 0.814-0.908) after applying the same adjustments. Conclusions Our AI-powered SR ECG interpretation model demonstrated excellent diagnostic performance in predicting paroxysmal AF, with valid performance in the Brazilian population as well. This suggests that the model has potential for broad application across different ethnic groups.Figure 1

Exploring IRGs as a Biomarker of Pulmonary Hypertension Using Multiple Machine Learning Algorithms.

Pulmonary arterial hypertension (PAH) is a severe disease with poor prognosis and high mortality, lacking simple and sensitive diagnostic biomarkers in clinical practice. This study aims to identify novel diagnostic biomarkers for PAH using genomics research. We conducted a comprehensive analysis of a large transcriptome dataset, including PAH and inflammatory response genes (IRGs), integrated with 113 machine learning models to assess diagnostic potential. We developed a clinical diagnostic model based on hub genes, evaluating their effectiveness through calibration curves, clinical decision curves, and ROC curves. An animal model of PAH was also established to validate hub gene expression patterns. Among the 113 machine learning algorithms, the Lasso + LDA model achieved the highest AUC of 0.741. Differential expression profiles of hub genes CTGF, DDR2, FGFR2, MYH10, and YAP1 were observed between the PAH and normal control groups. A diagnostic model utilizing these hub genes was developed, showing high accuracy with an AUC of 0.87. MYH10 demonstrated the most favorable diagnostic performance with an AUC of 0.8. Animal experiments confirmed the differential expression of CTGF, DDR2, FGFR2, MYH10, and YAP1 between the PAH and control groups (p < 0.05); Conclusions: We successfully established a diagnostic model for PAH using IRGs, demonstrating excellent diagnostic performance. CTGF, DDR2, FGFR2, MYH10, and YAP1 may serve as novel molecular diagnostic markers for PAH.

External validation of a machine learning based classification algorithm for ambulatory heart rhythm diagnostics using smartphone-photoplethysmography - the SMARTBEATS algorithm study

Abstract Introduction Smartphone-photoplethysmography (PPG) can be used for heart rhythm monitoring. According to current guidelines, ECG verification is required for a new diagnosis of atrial fibrillation (AF). Accurate machine learning (ML) based automatic algorithms have the potential to facilitate clinical applications generating large numbers of PPG recordings, by offloading the need for manual over-read. Purpose The aim of this study was to evaluate the diagnostic performance of an automatic ML-based algorithm for heart rhythm diagnostics using smartphone-PPG recorded by patients with AF in an unsupervised ambulatory setting. Methods Patients undergoing direct current cardioversion (DCCV) at a university hospital for treatment of AF or atrial flutter (AFL) were asked to perform one-minute heart rhythm recordings post-cardioversion at least twice daily for 30 days. All participants were provided with an iPhone 7 smartphone running the CORAI Heart Monitor PPG application simultaneously with a single-lead ECG recording (KardiaMobile). The automatic algorithm uses support vector machines (SVM) to classify heart rhythm from smartphone-PPG recordings. The SVM classifier evaluated here was trained on ambulatory PPG recordings made by patients in a separate cardioversion cohort, ensuring complete independence between training and validation sets. PPG recordings in the validation cohort were analyzed by the automatic algorithm and diagnostic performance was calculated by comparing heart rhythm classification output from the SVM classifier to the heart rhythm diagnosis from the simultaneous ECG recordings. ECG recordings were interpreted independently by two cardiologists and were set as gold standard. Results The SVM classifier was trained on data from 153 patients with 11,749 PPG recordings, of which 5,873 (50.0%) were labelled as AF and 5,876 (50.0%) as sinus rhythm (SR), as assessed by manual reading. In the validation cohort, 280 patients, with a median age of 69.0 years (31% women), registered 18,005 simultaneous PPG and ECG recordings. Recordings interpreted as AFL on ECG (2.0%), as having insufficient quality on ECG (4.9%) or PPG (2.8%), and low certainty algorithmic classifications (1.2%) were excluded, leaving 16,057 PPG recordings. Included ECG recordings consisted of 71.2% interpreted as (SR) and 28.8% as AF. Algorithm classification of the PPG recordings in the validation cohort diagnosed AF (sensitivity) in 99.7% and SR (specificity) in 99.7% of the recordings, with an overall accuracy of 99.7%. F1-score was 99.4% and area under the ROC curve (AUC) was 0.999. Conclusion A machine learning based algorithm for automatic heart rhythm diagnostics showed excellent diagnostic performance for smartphone-PPG recordings in an unsupervised ambulatory setting, minimizing the need for ECG verification in cardioversion populations.

Same-Day Positron Emission Tomography/Computed Tomography with 68Ga-Radiolabeled Fibroblast Activation Protein Inhibitors and 18F-Fluorodeoxyglucose Imaging for Gastrointestinal Cancers.

Objective: We investigated the clinical practicability of same-day 68Ga-radiolabeled fibroblast activation protein inhibitors (68Ga-FAPI)-first and 18F-fluorodeoxyglucose (18F-FDG) imaging and compared it with same-day 18F-FDG-first or 2-day procedures in diagnosing gastrointestinal cancers. Materials and Methods: Sixty-five patients with confirmed gastrointestinal cancers were divided into same-day 68Ga-FAPI-first group (Group A), same-day 18F-FDG-first group (Group B), and 2-day group (Group C). Low-dose CT and low injection activity were performed on 68Ga-FAPI positron emission tomography/computed tomography (PET/CT). Interval times, radiation dose, diagnostic performance, and detectability were assessed among groups. Additionally, the uptake, tumor-to-liver ratio (TLR), diagnostic efficacy, and TNM stage were compared between the two modalities. Results: The total waiting time for Group C was significantly longer than that for Group A or B (both p < 0.001). The total dose-length product and effective dose decreased in all groups. There were comparable detectability and diagnostic performance among groups (all p > 0.05). The within-group analysis in Group B indicated that 68Ga-FAPI PET/CT had higher uptake in the primary and recurrent lesions than 18F-FDG without differences in TLR, due to higher liver background on 68Ga-FAPI PET than Group A or C (both p < 0.001).68Ga-FAPI PET/CT possessed higher accuracy than 18F-FDG and changed staging in 14 patients (14/65, 21.54%). Conclusions: The same-day 68Ga-FAPI-first and 18F-FDG imaging reduced examination waiting time without increased radiation dose, simultaneously achieving excellent diagnostic performance and improving clinical staging in diagnosing gastrointestinal cancers.

Diagnostic Performance and Clinical Impact of Photon-Counting Detector Computed Tomography in Coronary Artery Disease.

Photon-counting detector-computed tomography (PCD-CT) has emerged as a promising technology, offering improved spatial resolution. This study aimed to evaluate the clinical impact and diagnostic performance of PCD-CT vs conventional energy-integrating detector computed tomography (EID-CT) for obstructive coronary artery disease (CAD). From 2022 to 2023, we retrospectively identified 7,833 consecutive patients who underwent clinically indicated coronary computed tomography angiography (CCTA) at a single center, with either PCD-CT (n=3,876; NAEOTOM Alpha [Siemens Healthineers]) or EID-CT (n=3,957; Revolution Apex 256 [GE HealthCare] or Aquilion ONE ViSION 320 [Canon Medical Systems]) scanners. Subsequent invasive coronary angiography (ICA) and percutaneous or surgical revascularization were performed as part of routine clinical care. Among those referred for ICA after coronary CTA, the presence of obstructive CAD in each vessel was determined by coronary CTA (severe stenosis on visual assessment per the Coronary Artery Disease Reporting and Data System) and ICA (≥50% diameter stenosis on quantitative coronary angiography) in a blinded fashion. The diagnostic performance of EID-CT and PCD-CT was compared by using quantitative coronary angiography as the reference standard. Patients who underwent PCD-CT were less frequently referred to subsequent ICA than those undergoing EID-CT (9.9% vs 13.1%; P< 0.001). Among those who underwent ICA, revascularization was more frequently performed in the PCD-CT group than in the EID-CT group (43.4% vs 35.5%; P=0.02). In the vessel-level analysis (n=1,686), specificity (98.0% vs 93.0%; P< 0.001), positive predictive value (83.3% vs 63.0%; P=0.002), and diagnostic accuracy (97.2% vs 92.8%; P< 0.001) were improved by PCD-CT. Sensitivity (90.9% vs 90.7%; P=0.95) and negative predictive value (98.9% vs 98.7%; P=0.83) for obstructive CAD were similar between the PCD-CT and EID-CT groups, respectively. PCD-CT exhibited excellent diagnostic performance for detecting obstructive CAD. Compared with patients undergoing conventional EID-CT, fewer patients were referred to ICA after PCD-CT, but those referred were more likely to undergo revascularization.

Diagnostic Value of Magnetocardiography to Detect Abnormal Myocardial Perfusion: A Pilot Study.

Magnetocardiography (MCG) is a novel non-invasive technique that detects subtle magnetic fields generated by cardiomyocyte electrical activity, offering sensitive detection of myocardial ischemia. This study aimed to assess the ability of MCG to predict impaired myocardial perfusion using single-photon emission computed tomography (SPECT). A total of 112 patients with chest pain underwent SPECT and MCG scans, from which 65 MCG output parameters were analyzed. Using least absolute shrinkage and selection operator (LASSO) regression to screen for significant MCG variables, three machine learning models were established to detect impaired myocardial perfusion: random forest (RF), decision tree (DT), and support vector machine (SVM). The diagnostic performance was evaluated based on the sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUC). Five variables, the ratio of magnetic field amplitude at R-peak and positive T-peak (RoART+), R and T-peak magnetic field angle (RTA), maximum magnetic field angle (MAmax), maximum change in current angle (CCAmax), and change positive pole point area between the T-wave beginning and peak (CPPPATbp), were selected from 65 automatic output parameters. RTA emerged as the most critical variable in the RF, DT, and SVM models. All three models exhibited excellent diagnostic performance, with AUCs of 0.796, 0.780, and 0.804, respectively. While all models showed high sensitivity (RF = 0.870, DT = 0.826, SVM = 0.913), their specificity was comparatively lower (RF = 0.500, DT = 0.300, SVM = 0.100). Machine learning models utilizing five key MCG variables successfully predicted impaired myocardial perfusion, as confirmed by SPECT. These findings underscore the potential of MCG as a promising future screening tool for detecting impaired myocardial perfusion. ChiCTR2200066942, https://www.chictr.org.cn/showproj.html?proj=187904.

Using a sum of the cross diameters of the appendix measured on ultrasonographyas a criterion can more effectively predict acute appendicitis.

To investigate whether usingasum of the cross diameters on the transverse section of the appendix as a criterioncan improve the diagnosis of acute appendicitis (AA). In this retrospective study, 433 patients with AA and 207 patients with a normal appendix were assigned to the training and validation groups in a proportion of 7:3. Each group was divided into subgroups consisting of patients with AA and a normal appendix. The training group included 144 patients with a normal appendix and 302 patients with AA, while the validation group comprised 63 patients with a normal appendix and 131 patients with AA. Graded compression ultrasound was performed to evaluate the appendix, and the cross diameters on the transverse section were measured, with one of them used as the maximum outer diameter (MOD). The cut-off value of the sum of cross diameters for predicting AA was 13.5 mm or more. When it was applied to evaluate the appendix in the training group, a sensitivity of 98.7%, specificity of 99.3%, positive predictive value of 99.7%, negative predictive value of 97.3%, and an area under the receiver operating characteristic curve of 0.990 were achieved. Which were significantly higher than those (except for a sensitivity of 99.3%) obtained using the criteria of MOD ≥ 6 mm. Similar results were obtained in the validation group. Using a sum of cross diameters of the appendix of 13.5 mm or more as a criterionto diagnose AA can yield excellent diagnostic performance, and can replace the current criteria of MOD of 6 mm or more. Question A MOD of the appendix ≥ 6 mm is a recommended criterion for diagnosing AA, but often results in a false-positive diagnosis. Findings Using the sum of the cross diameters of the appendix ≥ 13.5 mm as acriterionyielded significantly higher diagnostic performance than the recommended criteria. Clinical relevance The sum of the cross diameters of the appendix is a better criterion for the evaluation of patients with suspected AA, exhibiting significantly higher diagnostic performance than the MOD of the appendix.

Radiomics based on MRI in predicting lymphovascular space invasion of cervical cancer: a meta-analysis.

The objective of this meta-analysis is to assess the efficacy of radiomics techniques utilizing magnetic resonance imaging (MRI) for predicting lymphovascular space invasion (LVSI) in patients with cervical cancer (CC). A comprehensive literature search was conducted in databases including PubMed, Embase, Cochrane Library, Medline, Scopus, CNKI, and Wanfang, with studies published up to 08/04/2024, being considered for inclusion. The meta-analysis was performed using Stata 15 and Review Manager 5.4. The quality of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies 2 and Radiomics Quality Score tools. The analysis encompassed the pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR). Summary ROC curves were constructed, and the AUC was calculated. Heterogeneity was investigated using meta-regression. Statistical significance was set at p ≤ 0.05. There were 13 studies involving a total of 2,245 patients that were included in the meta-analysis. The overall sensitivity and specificity of the MRI-based model in the Training set were 83% (95% CI: 77%-87%) and 72% (95% CI: 74%-88%), respectively. The AUC, DOR, PLR, and NLR of the MRI-based model in the Training set were 0.89 (95% CI: 0.86-0.91), 22 (95% CI: 12-40), 4.6 (95% CI: 3.1-7.0), and 0.21 (95% CI: 0.16-0.29), respectively. Subgroup analysis revealed that the AUC of the model combining radiomics with clinical factors [0.90 (95% CI: 0.87-0.93)] was superior to models based on T2-weighted imaging (T2WI) sequence [0.78 (95% CI: 0.74-0.81)], contrast-enhanced T1-weighted imaging (T1WI-CE) sequence [0.85 (95% CI: 0.82-0.88)], and multiple sequences [0.86 (95% CI: 0.82-0.89)] in the Training set. The pooled sensitivity and specificity of the model integrating radiomics with clinical factors [83% (95% CI: 73%-89%) and 86% (95% CI: 73%-93%)] surpassed those of models based on the T2WI sequence [79% (95% CI: 71%-85%) and 72% (95% CI: 67%-76%)], T1WI-CE sequence [78% (95% CI: 67%-86%) and 78% (95% CI: 68%-86%)], and multiple sequences [78% (95% CI: 67%-87%) and 79% (95% CI: 70%-87%)], respectively. Funnel plot analysis indicated an absence of publication bias (p > 0.05). MRI-based radiomics demonstrates excellent diagnostic performance in predicting LVSI in CC patients. The diagnostic performance of models combing radiomics and clinical factors is superior to that of models utilizing radiomics alone. https://www.crd.york.ac.uk/PROSPERO/#myprospero, identifier CRD42024538007.

Identification of neutrophil extracellular traps genes as potential biomarkers in psoriasis based on bioinformatics analysis

The epidermal infiltration of neutrophils is a hallmark of psoriasis (PSO) and its activation leads to the release of neutrophil extracellular traps (NETs). However, the molecular mechanism of NETs-related genes (NETRGs) has not been extensively studied in PSO. To define NETs-related-biomarkers for PSO. The GSE13355 and GSE78097 datasets, and NETRGs gene set were included in this study. The datasets used in this study were all microarray data. The weighted gene co-expression network analysis (WGCNA) and machine learning algorithms were used to mine key genes. Later on, single-gene gene set enrichment analysis (GSEA) and immune infiltration analysis were implemented. Finally, the expression of key genes was verified using quantitative real-time fluorescence PCR (qRT-PCR). A total of 3 key genes (S100A9, CLEC7A, and CXCR4) were derived, and they all had excellent diagnostic performance. The single-gene GSEA enrichment results indicated that the key genes were mainly enriched in the chemokine signaling pathway and humoral immune response in the high-expression group, while focal adhesion was enriched in the low-expression group. The correlation analysis indicated that all key genes were strongly negatively correlated with resting mast cells and TGF-β family member receptor, while they were strongly positively correlated with activated CD4 memory T cells and antigen processing and presentation. Lastly, the experimental results showed that the expression trends of key genes were consistent with public database. In this study, we successfully screened three potential PSO diagnostic genes (S100A9, CLEC7A and CXCR4) that were closely related to NETs, and these findings not only provided new molecular marker candidates for the precise diagnosis of PSO patients, but also revealed possible future therapeutic targets. However, further in-depth research and validation were necessary.

Diagnostic Accuracy of 18 F-FES PET/CT for the Detection of Recurrent and Metastatic Breast Cancer.

To evaluate the diagnostic value of 16α- 18 F-fluoro-17β-fluoroestradiol ( 18 F-FES) PET/CT for distant metastasis or recurrence in patients with estrogen receptor (ER)-positive breast cancer. Patients with ER-positive breast cancer and suspected of de novo metastasis or recurrence were retrospectively identified from a prospective cohort enrolled for a postmarketing surveillance study of 18 F-FES at our institution. Per-patient diagnostic accuracy was assessed using pathology or 2 or more standard-of-care imaging procedures with a minimum of 6 months of follow-up as the reference standard. The per-region detection rate of 18 F-FES PET/CT was evaluated and compared with that of standard-of-care imaging. Of the 162 included patients, 104 and 58 were suspected to have recurrence or de novo metastasis, respectively. The overall sensitivity and specificity of 18 F-FES PET/CT were 95% (95% confidence interval [CI], 89%-98%) and 89% (95% CI, 76%-96%), respectively. When stratified according to clinical settings, the sensitivity and specificity were 95% (95% CI, 88%-99%) and 96% (95% CI, 78%-100%), respectively, for detecting recurrence, and 94% (95% CI, 81%-99%) and 82% (95% CI, 60%-95%) for detecting distant metastasis. In region-based analysis, the overall detection rate of 18 F-FES PET/CT was significantly higher than that of standard-of-care imaging (92% [95% CI, 89%-94%] vs 83% [95% CI, 79%-87%], P < 0.001). 18 F-FES PET/CT showed excellent diagnostic performance in patients with ER-positive breast cancer suspected of de novo metastasis or recurrence.

Extracellular Vesicle Characteristics in Local Fluid and Plasma Measured by Nanoparticle Tracking Analysis Can Help Differentiate High-Grade Serous Carcinoma from Benign Ovarian Pathology

Background: High-grade serous carcinoma (HGSC) is the most lethal of gynecological cancers in developed countries. It usually presents late with non-specific symptoms and most cases are diagnosed at an advanced stage, with 5-year overall survival being around 40%. Biomarkers for screening and early diagnosis of this aggressive disease are, thus, a research priority. Extracellular vesicles (EVs) that reflect the cell of origin and that can be isolated from local fluid and plasma by minimally invasive liquid biopsy are such promising biomarkers. Besides EV concentration and molecular profile, which have been the main focus of research for many years, recent studies have also called attention to EV size distribution. The aim of our study was to evaluate the potential of EV concentration and size distribution in local fluid and plasma as diagnostic biomarkers for HGSC. Methods: Paired pretreatment ascites and plasma samples from 37 patients with advanced HGSC and paired pretreatment free peritoneal fluid (FPF) and plasma samples from 40 controls with benign ovarian pathology (BOP) were analyzed using nanoparticle tracking analysis (NTA). Results: We observed a significant difference in EV concentration in local fluid, but not in plasma, between HGSC patients and the control group. We also found a significant difference in EV size distribution in both local fluid and plasma between HGSC patients and the control group. The receiver operating characteristics (ROC) curve analysis of EV characteristics showed excellent diagnostic performance for the mode, D10, and D50 in local fluid and acceptable diagnostic performance for EV concentration and mean EV size in local fluid, as well as for the mode and D10 value in plasma. Conclusions: The results of our study show that EV concentration in local fluid and more importantly EV size distribution in both local fluid and plasma are significantly changed in the presence of HGSC. Future research of size-dependent molecular profiling of EVs could help identify novel diagnostic biomarkers for HGSC.

B-212 Laboratory Performance in Molecular Detection of Mycobacterium tuberculosis Through Analysis of External Quality Assessment Program Results: WHO-Recommended Tests Outperform Others

Abstract Background In 2022, tuberculosis caused 11,200 deaths in Brazil and 1,300,000 globally. With 87,344 new cases, it remains a leading infectious cause of death, second only to COVID-19. Prompt detection is critical, particularly with the growing resistance to rifampicin and isoniazid, highlighting the need for molecular testing. External Quality Assessment Programs (EQAP) are essential to ensure the accuracy, reliability, and harmonization of laboratory results amid the complexities of M. tuberculosis infection. Here, we evaluate the overall performance of participating laboratories (labs) in three EQAP related to tuberculosis: M. tuberculosis molecular detection (MTB), Rifampicin resistance detection (RIF), and Isoniazid resistance detection (INH). All are organized by a Brazilian provider accredited according to the ABNT NBR ISO/IEC 17043:2011 standard. Methods The EQAP samples were suspensions containing human cells, with or without the addition of cultured, inactivated, and lyophilized M. tuberculosis. Labs received two samples quarterly for testing accuracy, sensitivity, and specificity. We computed these metrics along with participant and round numbers. The Mann-Kendall test assessed accuracy trends over time. Furthermore, kit type accuracies for in-vitro diagnostic (IVD) vs. laboratory-developed tests (LDT), World Health Organization recommended (WHO-recommended) vs. other kits (non-WHO), and methods (qPCR vs. PCR) were compared using chi-square tests and odds-ratio calculations. Results In the MTB EQAP (2018-2022), 63 labs participated over 20 rounds, with 22 (range: 6-48) labs per round on median, achieving 96.6% accuracy (853/883), 97.5% sensitivity (556/570), and 94.9% specificity (297/313). The Mann-Kendall test found no significant accuracy trends over time (τ = -0.91, p = 0.36). IVDs outperformed LDTs with 97.8% (751/768) vs. 87.9% (102/116) accuracy (OR=6.0, 95%CI 3.42-20.9, p&amp;lt;0.0001). WHO-recommended kits were more accurate than non-WHO kits, 98.2% (674/686) vs. 90.4% (179/198) (OR=5.96, 95%CI 1.05-12.7, p&amp;lt;0.0001). qPCR exceeded the accuracy of PCR, 97.2% (833/857) versus 74% (20/27) (OR=12.1, 95%CI 4.8-32.9, p&amp;lt;0.0001). For RIF EQAP (2020-2022), 49 laboratories in 9 rounds, with 25 (range: 18-42) laboratories per round on median, showed 97.4% accuracy (297/305), 97.2% sensitivity (176/181), and 97.6% specificity (121/124). In the INH EQAP (2021-2022), 7 laboratories over 7 rounds, with 4 (range: 2-5) laboratories per round on median, reached 95.2% accuracy (20/21), 100% sensitivity (4/4), and 94.1% specificity (16/17). Differences between types of kits and methods for RIF and INH, as well as trends over time, were not significant or could not be calculated due to the limited number of samples. Conclusions The MTB EQAP underscored the high participation and suitability of labs, along with excellent diagnostic performance; IVD kits were 6 times more likely to yield adequate results than LDTs. WHO-recommended kits were 5.9 times more likely to produce adequate results than non-WHO kits. qPCR was 12.6 times more likely to achieve adequate results than PCR. Despite fewer participants in RIF and INH, their performance rates were high; more data are needed for conclusive results on kit and method types. This study affirms the quality of molecular diagnostics for tuberculosis in Brazil, informs on kit and method selection, and underscores the critical role of EQAPs in combating a significant global health issue.

Accuracy of the model derived from red blood cell indices in predicting α0-thalassemia trait among non-anemic pregnant women

BackgroundThe study aims to establish prediction model derived from red blood cell indices to improve the accuracy of α0-thalassemia trait screening in non-anemic pregnant women. MethodA diagnostic study as secondary analysis on the prospective database was conducted. The participants were pregnant women, undergoing α0-thalassemia screening at first visit antenatal care using red blood cell indices with confirmation by PCR method. Diagnostic performance of each of red blood cell parameter and their combination derived from logistic regression analysis in predicting α0-thalassemia trait were determined. FindingsThe total 587 Thai pregnant women were included in the analysis, consisting of 136 cases of α0-thalassemia trait and 451 normal controls. Diagnostic performance analysis revealed that, the mean corpuscular volume (MCV) provided a sensitivity of 98.5 % and a false positive rate of 20.2 %. While The mean corpuscular hemoglobin (MCH) provided a sensitivity of 99.3 % and a false positive rate of 15.7 %. The combined-parameters prediction model including hemoglobin (Hb), MCV, MCH, mean corpuscular hemoglobin concentration (MCHC), red cell distribution width (RDW), and red blood cell (RBC) count, demonstrated excellent diagnostic performance with an area under the curve (AUC) of 0.992, sensitivity of 99.3 %, and much lower false positive rate of 4 %. InterpretationThe combined-parameter prediction model provided excellent diagnostic performance with low false positive rate. The application of the prediction model could decrease unnecessary PCR method for α0-thalassemia testing, thereby decreasing the cost of investigation. Our proposed model can possibly have a great impact or significant change in clinical practice, especially in Southeast Asia.