Area Under The ROC Curve Research Articles

Developing a Reproducible Radiomics Model for Diagnosis of Active Crohn's Disease on CT Enterography Across Annotation Variations and Acquisition Differences.

To systematically identify radiomics features on CT enterography (CTE) scans which can accurately diagnose active Crohn's disease across multiple sources of variation. Retrospective study of CTE scans curated between 2013 and 2015, comprising 164 subjects (65 male, 99 female; all patients were over the age of 18) with endoscopic confirmation for the presence or absence of active Crohn's disease. All patients had three distinct sets of scans available (full and reduced dose, where the latter had been reconstructed via two different methods), acquired on a single scanner at a single institution. Radiomics descriptors from annotated terminal ileum regions were individually and systematically evaluated for resilience to different imaging variations (changes in dose/reconstruction, batch effects, and simulated annotation differences) via multiple reproducibility measures. Multiple radiomics models (by accounting for each source of variation) were evaluated in terms of classifier area under the ROC curve (AUC) for identifying patients with active Crohn's disease, across separate discovery and hold-out validation cohorts. Radiomics descriptors selected based on resiliency to multiple sources of imaging variation yielded the highest overall classification performance in the discovery cohort (AUC = 0.79 ± 0.04) which also best generalized in hold-out validation (AUC = 0.81). Performance was maintained across multiple doses and reconstructions while also being significantly better (p < 0.001) than non-resilient descriptors or descriptors only resilient to a single source of variation. Radiomics features can accurately diagnose active Crohn's disease on CTE scans across multiple sources of imaging variation via systematic analysis of reproducibility measures. Clinical utility and translatability of radiomics features for diagnosis and characterization of Crohn's disease on CTE scans will be contingent on their reproducibility across multiple types and sources of imaging variation.

Waiting for hip fracture surgery: Analysis of individual heterogeneity and discriminatory accuracy

Abstract Background Evaluation of healthcare inequality could be improved by considering (i) the intersection of socioeconomic axes of inequality, (ii) the existence of individual heterogeneity and (iii) criteria to quantify group differences and how those differences translate into recommendations for universal or targeted interventions. In this study we illustrate how to achieve these improvements. Methods We applied analysis of individual heterogeneity and discriminatory accuracy (AIHDA) to analyze data from the Swedish patient registry for the quality indicator hip fracture (HF) surgery within the same day. We analyzed 57,340 patients residing in Sweden during 2011-2014 and belonging to 36 socioeconomic strata defined by age, sex, income, and country of birth and the 21 Swedish regions. We calculated prevalences and 95% confidence intervals as well as the absolute number of cases. The benchmark was set to 80%. To quantify group differences, we evaluated the discriminatory accuracy (DA) using the area under the ROC curve (AUC). Results 68% (39,073/57,340) of the patients were operated in time. The prevalence across the 36 sociodemographic strata ranged from 51% (43-58%) to 81% (67-91%). However, the DA was low (AUC= 0.562) indicating very small group differences. About half of the operated HP (n = 20,287) occurs in 18/36 strata with the lowest prevalences of operations in time. The regions’ prevalences ranged from 37% (36-38%) to 88% (88-89%) with a rather high DA (AUC= 0.736) indicating larger differences. About half of the operated HP (n = 19,677) occurs in 12/21 regions with the lowest prevalence of operations in time. Conclusions The 80% benchmark was only achieved in one socioeconomic stratum and the group differences were very small. 6/21 regions achieved the benchmark and the group differences were large. Interventions aiming to reach the benchmark in the entire population should proportionately target regions and be universal and tailored to sociodemographic strata. Key messages • The AIHDA-framework improves evaluations of healthcare inequalities. • Both differences between group averages and the groups’ DA need be considered when planning healthcare interventions.

Clinical validated risk prediction model for development of heart failure after contemporary breast cancer treatment

Abstract Background Patients receiving breast cancer (BC) treatment are at risk for heart failure and cardiomyopathy (HF/CM). European Society of Cardiology (ESC) cardio-oncology guidelines recommend baseline cardiovascular (CV) assessment, however, there is limited data about cardiotoxicity risk specific to patients with BC. Our aim was to develop and validate model for prediction of HF/CM in women receiving contemporary treatment for invasive early-stage BC. Methods We assembled a cohort women diagnosed with Stage I-III BC from 2008-2020 and followed through 2021 in a large health care plan. Women age &amp;gt;80, with history of HF/CM, and women who received both anthracyclines and trastuzumab were excluded, leaving N=26,044 for analysis. Study cohort was randomly split into derivation (60%) and validation (40%) datasets. Elastic-net penalized Cox proportional hazard model was created using the derivation dataset to select risk factors and to calculate the panelized coefficient which defined the HF/CM risk score. Risk score system was assessed by Hosmer-Lemeshow goodness-of-fit test and area under the ROC curve (AUC). Event rates of &amp;lt;5% constituted low risk; 5-14% moderate; and &amp;gt;15% high risk category. Incident HF/CM events were examined using Kaplan-Meier approach in derivation and validation datasets. Results HF/CM risk score had high discrimination ability and sufficiently good model of fit regarding HF/CM events (P value=0.163 and 0.667 from Hosmer–Lemeshow test;AUC 0.751 and 0.764, in derivation and validation sets, respectively). There were 10% of women in the high risk; 30% in moderate; and 60% in low-risk group. Variables associated with the higher HF/CM risk score included age, receipt of anthracycline-based chemotherapy or anti-HER2 therapy, presence of hypertension, diabetes, or history of other CV conditions at baseline. The score pattern showed major effect of age, with anthracycline and anti-HER2 therapy increasing the risk across all age groups (Figure 1). Kaplan-Meier analysis of incident HF/CM over 14 years after BC diagnosis showed significantly lower number of HF/CM events in low risk compared to moderate and high-risk score groups (p&amp;lt;0.0001, Figure 2). Conclusion Our robust risk prediction model for HF/CM among women with early-stage BC provides a new tool to identify women at higher CV risk and inform cardiac function monitoring during and after BC treatment. Our findings may guide further validation studies and build evidence for the cardiotoxicity risk stratification in patients with BC.Risk Score for HF/CM by Age/ChemoTxK-M curves of freedom from HF/CM

Triglyceride-glucose index predicts the prognosis of patients with ischemic cardiomyopathy

Abstract Objective A large number of studies have provided strong statistical evidence that the Triglyceride-glucose (TYG) index is associated with the development and prognosis of cardiovascular disease. However, little is known about the predictive value of TYG index for ischemic cardiomyopathy (ICM). This study aimed to investigate the predictive value of TYG index in patients with ICM. Methods Hospitalized patients ICM in our Hospital from April 2014 to December 2017 were included in this study. Inclusion criteria: previous definite diagnosis of coronary atherosclerotic heart disease (coronary angiography found one or more vessels stenosis &amp;gt; 50%) and echocardiography showed LVEF &amp;lt; 45 percent. In addition, the TYG index was calculated as follows :LN[fasting triglycerides (mg /dl)× fasting blood glucose (mg /dl)x1/2]. The endpoint of the study was MACE events, including all-cause death, myocardial infarction, ischemia-induced revascularization and heart failure (HF) rehospitalization. Results A total of 688 patients were included in this study and followed up for 1 year. In the multivariate Cox proportional hazards model, TYG index (adjusted HR 2.33 [95% CI: 1.30-4.20], P&amp;lt;0.01) were associated with an increased risk of MACE events, and the area under the ROC curve (AUC) was 0.604 (95%CI: 0.528-0.680, p &amp;lt;0.05). A total of 197 ICM patients with previously diagnosed diabetes were screened for analysis. We found that TYG index (adjusted HR 6.63 [95% CI: 2.15-20.47], P&amp;lt;0.01), and the AUC was 0.691 (95%CI: 0.562-0.820, p&amp;lt;0.05). Conclusion TYG index can predict the poor prognosis of ICM patients, and the predictive value of TyG index for ICM patients with diabetes is more significant.

Prediction, prognosis and monitoring of neurodegeneration at biobank-scale via machine learning and imaging.

Alzheimer's disease and related dementias (ADRD) and Parkinson's disease (PD) are the most common neurodegenerative conditions. These central nervous system disorders impact both the structure and function of the brain and may lead to imaging changes that precede symptoms. Patients with ADRD or PD have long asymptomatic phases that exhibit significant heterogeneity. Hence, quantitative measures that can provide early disease indicators are necessary to improve patient stratification, clinical care, and clinical trial design. This work uses machine learning techniques to derive such a quantitative marker from T1-weighted (T1w) brain Magnetic resonance imaging (MRI). In this retrospective study, we developed machine learning (ML) based disease-specific scores based on T1w brain MRI utilizing Parkinson's Disease Progression Marker Initiative (PPMI) and Alzheimer's Disease Neuroimaging Initiative (ADNI) cohorts. We evaluated the potential of ML-based scores for early diagnosis, prognosis, and monitoring of ADRD and PD in an independent large-scale population-based longitudinal cohort, UK Biobank. 1,826 dementia images from 731 participants, 3,161 healthy control images from 925 participants from the ADNI cohort, 684 PD images from 319 participants, and 232 healthy control images from 145 participants from the PPMI cohort were used to train machine learning models. The classification performance is 0.94 [95% CI: 0.93-0.96] area under the ROC Curve (AUC) for ADRD detection and 0.63 [95% CI: 0.57-0.71] for PD detection using 790 extracted structural brain features. The most predictive regions include the hippocampus and temporal brain regions in ADRD and the substantia nigra in PD. The normalized ML model's probabilistic output (ADRD and PD imaging scores) was evaluated on 42,835 participants with imaging data from the UK Biobank. There are 66 cases for ADRD and 40 PD cases whose T1 brain MRI is available during pre-diagnostic phases. For diagnosis occurrence events within 5 years, the integrated survival model achieves a time-dependent AUC of 0.86 [95% CI: 0.80-0.92] for dementia and 0.89 [95% CI: 0.85-0.94] for PD. ADRD imaging score is strongly associated with dementia-free survival (hazard ratio (HR) 1.76 [95% CI: 1.50-2.05] per S.D. of imaging score), and PD imaging score shows association with PD-free survival (hazard ratio 2.33 [95% CI: 1.55-3.50]) in our integrated model. HR and prevalence increased stepwise over imaging score quartiles for PD, demonstrating heterogeneity. As a proxy for diagnosis, we validated AD/PD polygenic risk scores of 42,835 subjects against the imaging scores, showing a highly significant association after adjusting for covariates. In both the PPMI and ADNI cohorts, the scores are associated with clinical assessments, including the Mini-Mental State Examination (MMSE), Alzheimer's Disease Assessment Scale-cognitive subscale (ADAS-Cog), and pathological markers, which include amyloid and tau. Finally, imaging scores are associated with polygenic risk scores for multiple diseases. Our results suggest that we can use imaging scores to assess the genetic architecture of such disorders in the future. Our study demonstrates the use of quantitative markers generated using machine learning techniques for ADRD and PD. We show that disease probability scores obtained from brain structural features are useful for early detection, prognosis prediction, and monitoring disease progression. To facilitate community engagement and external tests of model utility, an interactive app to explore summary level data from this study and dive into external data can be found here https://ndds-brainimaging-ml.streamlit.app. As far as we know, this is the first publicly available cloud-based MRI prediction application. US National Institute on Aging, and US National Institutes of Health.

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.

Cardio-pulmonary exercise testing in adult congenital heart patients: a new data-focused approach to predict mortality

Abstract Background/Introduction The cardio-pulmonary exercise test (CPET) has been a pivotal tool for functional and prognostic evaluation in adults with congenital heart disease (ACHD). During a routine CPET test, a myriad of variables are collected reflecting the cardiovascular, pulmonary, and skeletal muscle systems. However, clinicians typically use only a few easily and accessible variables to establish prognosis, which can come at an accuracy cost. Machine learning algorithms have undergone significant development in recent years and have found applications in the medical field. One of their main advantages is the ability to handle a large number of variables and extract information from their various combinations, while excluding redundant data, thus offering a higher level of prediction accuracy. Purpose Our objective was to develop a machine learning model to predict death during follow-up in a large population of ACHD patients who have undergone routine CPET in a large-volume single specialist centre. Methods All available CPET studies for adult ACHD patients (age &amp;gt; 15 years) performed from December 1999 to December 2021 at our centre were included, and all standard available variables were extracted. The primary outcome was all-cause mortality since the CPET, collected up to November 2023. Data exploration, data cleaning, and feature engineering steps were conducted using Python (v3.8). Continuous variables were standardised. The supervised machine learning algorithm XGBoost was used for classification (all-cause mortality), with the best hyperparameters selected through cross-validation. For the final model, a feature importance analysis based on permutation techniques was used to explore the variables with more impact on model accuracy. Results A total of 6361 studies were included, with median age of 31 years (IQR 23-43), 56% male. During follow-up, a total of 491 deaths were recorded. Of available demographic, clinical and exercise parameters (n=129 variables), 21 were deemed sufficient in terms of completeness, absence of significant correlation and clinically relevant for the subsequent analysis. These included demographic variables (age and sex) and CPET variables (peak VO2, FEV1, peak heart rate, exercise time, etc.) and were used to train the model. The accuracy of the model in predicting death after CPET in the test set had an accuracy of 93.5% and an area under the ROC curve (AUC) of 85.0% (Figure1). The parameters with the highest relative feature importance were FEV1, body mass index and percent predicted peak VO2 (Figure 2). Conclusions Machine learning models can be effectively employed in specialised cardiac populations, such as ACHD, potentially providing a high level of prediction accuracy by efficiently harnessing the potential of available data. However, its applicability to mortality prediction for ACHD patients requires further external validation.ROC curve AUC for the model predictionsFeature importance using permutation

Understanding Ultrasound Power Doppler Synovitis at Clinically Quiescent Joints and Thermographic Joint Inflammation Assessment in Patients with Rheumatoid Arthritis.

Background/Objectives: Rheumatoid arthritis (RA) is a chronic autoimmune inflammatory arthritis. We aim to study subclinical PD synovitis and thermographic joint inflammation assessment in patients with RA. Methods: We compared (1) PD synovitis at clinically quiescent (non-swollen; non-tender) joints based on patients' disease activity and (2) thermography (hands/wrists) outcomes based on PD joint inflammation findings and patient's disease activity. Results: Among eighty RA patients (mean (SD) age 57.0 (12.6) years; 61 of whom (76.3%) were female), the wrists (62.7%), second metacarpophalangeal joints (MCPJs) (37.0%), third MCPJs (33.8%), fourth MCPJs (24.8%), and fifth MCPJs (20.9%) were the five joint sites most frequently displaying subclinical PD synovitis; with no statistically significance differences (p > 0.05) between patients with 28-joint disease activity score (DAS28) < 3.2 versus those with DAS28 ≥ 3.2. At these five joint sites bilaterally, (1) the total maximum (Total Tmax), total average (Total Tavg), and total minimum (Total Tmin) temperatures were significantly greater (p < 0.05) for Total PD (TPD) score >1 versus TPD score ≤ 1, while their area under the ROC curve (AUC) values in identifying TPD score >1 ranged from 0.789 to 0.810, and (2) Total Tmax, Total Tavg, Total Tmin, and TPD score were significantly greater (p < 0.05) for patients with DAS28 ≥ 3.2 versus those with DAS28 < 3.2. Conclusions: Our results would serve as useful background data in studies on RA monitoring strategies detecting subclinical PD synovitis. Thermographic temperatures were greater in patients with greater disease activity and can help discriminate ultrasound PD joint inflammation severity.

Utilizing Pseudo Color Image to Improve the Performance of Deep Transfer Learning-Based Computer-Aided Diagnosis Schemes in Breast Mass Classification.

The purpose of this study is to investigate the impact of using morphological information in classifying suspicious breast lesions. The widespread use of deep transfer learning can significantly improve the performance of themammogram based CADx schemes.However, digital mammograms are grayscale images, while deep learning models are typically optimized using the natural images containing three channels. Thus, it is needed to convert the grayscale mammograms into three channel images for the input of deep transfer models. This study aims to developa novel pseudo color image generation methodwhich utilizesthe mass contour information to enhance the classification performance.Accordingly, a total of 830 breast cancer cases were retrospectively collected, which contains 310 benign and 520 malignant cases, respectively. For each case, a total of four regions of interest (ROI) are collected from the grayscale images captured for both the CC and MLO views of the two breasts. Meanwhile, a total of seven pseudo color image sets are generated as the input of the deep learning models, which arecreated through a combination of the original grayscale image, a histogram equalized image, a bilaterally filtered image, and a segmented mass. Accordingly, the output features from four identical pre-trained deep learning models are concatenated and then processed by a support vector machine-based classifier to generate the final benign/malignant labels. The performance of each image set was evaluated and compared. The results demonstrate that the pseudo color sets containing the manually segmented mass performed significantly better than all other pseudo color sets, which achieved an AUC (area under the ROC curve) up to 0.889 ± 0.012 and an overall accuracy up to 0.816 ± 0.020, respectively. At the same time, the performance improvement is also dependent on the accuracy of the mass segmentation. The results of this study support our hypothesis that adding accurately segmented mass contours can provide complementary information, thereby enhancing the performance of the deep transfer model in classifying suspicious breast lesions.

Deep learning techniques for quality of transmission estimation in optical networks

A large body of research has recently examined the estimation of the quality of transmission (QoT) in optical networks with deep learning. This paper discusses a lightpath’s quality of transmission to design fiber-optic communication and networks using deep learning algorithms. We need different major estimation parameters for advanced optical fiber communication and networks, i.e., modulation formats, baud rate, and code rate. Currently, the quality of transmission for unspecified optical paths depends on different estimation techniques i.e., (1) analytical models estimating physical layer impairments (PLIs) and (2) margined formulas. This paper focuses on deep-learning techniques that can be applied to optimization and complex systems. The deep learning algorithms contain different classifiers that can simulate results and estimate the bit-error rate, and signal-to-noise ratio of unspecified optical paths with threshold values, traffic volume, and modulation format. We must train and test the datasets for various classifiers, and classification features using Korean network topology. The classifier accuracy and Area Under the ROC Curve (AUC) simulation results are carried out using MATLAB.

Development of a Lateral Flow Strip-Based Recombinase-Aided Amplification for Active Streptococcus dysgalactiae emerging in channel catfish (Ictalurus punctatus)

Streptococcus dysgalactiae has become an important pathogen affecting mammals and fish (especially farmed fish). The development of a rapid, accurate, and sensitive diagnostic method will aid in the prevention of S. dysgalactiae infection. In this study, a method combining recombinase-aided amplification and a lateral flow dipstick (RAA-LFD) was developed to detect active S. dysgalactiae infection. The RAA-LFD detection was based on the ISP gene of S. dysgalactiae as the target, which could be accomplished with the lowest detection limit of 1.002×102 pg/μL reaction under optimal reaction conditions of 39 °C for 15 min. RAA-LFD and conventional PCR were used to detect 50 experimental samples invaded by S. dysgalactiae disease materials. The results showed that the positive concordance rate of the two methods was 97.6%, the negative concordance rate was 90.0%, and the total concordance rate was 98.0%. Compared with conventional PCR, the Area Under the ROC Curve (AUC) of RAA-LFD was 0.950, and the sensitivity and specificity were 100% and 90%, respectively. The RAA-LFD of S. dysgalactiae infection is convenient for rapid clinical detection.

The potential for species distribution models to distinguish source populations from sinks.

While species distribution models (SDM) are frequently used to predict species occurrences to help inform conservation management, there is limited evidence evaluating whether habitat suitability can reliably predict intrinsic growth rates or distinguish source populations from sinks. Filling this knowledge gap is critical for conservation science, as applications of SDMs for management purposes ultimately depend on these typically unobserved population or metapopulation dynamics. Using linear regression, we associated previously published population level estimates of intrinsic growth and abundance derived from a Bayesian analysis of mark-recapture data for 17 bird species found in the contiguous United States with SDM habitat suitability estimates fitted here to opportunistic data for these same species. We then used the area under the ROC curve (AUC) to measure how well SDMs can distinguish populations categorized as sources and sinks. We built SDMs using two different approaches, boosted regression trees (BRT) and generalized linear models (GLM), and compared their source/sink predictive performance. Each SDM was built with presence points obtained from eBird (a web-available database) and 10 environmental variables previously selected to model intrinsic growth rates and abundance for these species. We show that SDMs built with opportunistic data are poor predictors of species demography in general; both BRT and GLM explained very little spatial variation of intrinsic growth rate and population abundance (median R2 across 17 species was close to 0.1 for both SDM methods). SDMs, however, estimated higher suitability for source populations as compared to sinks. Out of 13 species which had both source and sink populations, both BRT and GLM had AUC values greater than 0.7 for 7 species when discriminating between sources and sinks. Habitat suitability have the potential to be a useful measure to indicate a population's ability to sustain itself as a source population; however more research on a diverse set of taxa is essential to fully explore this potential. This interpretation of habitat suitability can be particularly useful for conservation practice, and identification of explicit cases of when and how SDMs fail to match population demography can be informative for advancing ecological theory.

Plasma acellular transcriptome contains Parkinson's disease signatures that can inform clinical diagnosis.

We aimed to identify plasma cell-free transcripts (cfRNA) associated with Parkinson's disease (PD) that also have a high predictive value to differentiate PD from healthy controls. Leveraging two independent populations from two different movement disorder centers we identified 2,188 differentially expressed cfRNAs after meta-analysis. The identified transcripts were enriched in PD relevant pathways, such as PD (p=9.26×10 -4 ), ubiquitin-mediated proteolysis (p=7.41×10 -5 ) and endocytosis (p=4.21×10 -6 ). Utilizing in-house and publicly available brain, whole blood, and acellular plasma transcriptomic and proteomic PD datasets, we found significant overlap across dysregulated biological species in the different tissues and the different biological layers. We developed three predictive models containing increasing number of transcripts that can distinguish PD from healthy control with an area under the ROC Curve (AUC) ≥0.85. Finally, we showed that several of the predictive transcripts significantly correlate with symptom severity measured by UPDRS-III. Overall, we have demonstrated that cfRNA contains pathological signatures and has the potential to be utilized as biomarker to aid in PD diagnostics and monitoring.

Bioinformatics investigation of the prognostic value and mechanistic role of CD9 in glioma

In recent years, CD9 has been extensively studied as a potential biomarker for cancer. However, the biological role of CD9 in gliomas remains unclear. This study investigates the function of CD9 in gliomas and its molecular mechanisms. Utilizing pan-cancer analysis with TCGA, CGGA, and GEO databases, differential expression of CD9 was observed in 11 tumor types within the TCGA cohort, and it was associated with patient survival rates. Analysis of the CGGA glioma database revealed that patients with high CD9 expression had lower survival rates. The area under the ROC curve (AUC) for GSE16011 was greater than 0.7, indicating a high discriminative ability. Through gene set enrichment analysis (GSEA), immune-related analysis, and CD9 mutation detection, CD9 was found to have the strongest correlation with neutrophil involvement (cor = 0.30, P < 0.05), and the high CD9 expression group exhibited higher rejection responses and TIDE scores, suggesting a lower likelihood of successful immunotherapy. The high CD9 expression group was more sensitive to 81 drugs, indicating potential therapeutic effects for gliomas. Furthermore, overexpression of CD9 in gliomas may be associated with gene mutations. Down-regulation or up-regulation of CD9 expression in the glioblastoma cell line LN229 showed that CD9 could positively regulate the migratory ability of LN229 cells. Further, several marker genes, such as VEGFR-2, TGF-β1, CASP1 and PI3K, were down regulated in CD9 knockdown cell lines and up regulated in CD9 overexpression cell lines, compared with control cell line. This study preliminarily explores the role of CD9 in gliomas and its prognostic value, providing new insights for personalized treatment strategies in glioma therapy.

P10.09.A BLOOD-BASED CLASSIFICATION OF IDH-STATUS OF NON-ENHANCING GLIOMAS: A MACHINE LEARNING APPROACH

Abstract BACKGROUND Non-invasive determination of IDH mutational status in patients with glioma could offer significant therapeutic opportunities. While IDH wildtype tumors (e.g., GBM) typically show enhancement on MRI, IDH mutant tumors often lack this enhancement. However, relying solely on anatomic radiology may lead to misclassification, and currently, tissue acquisition is the primary method for assessing IDH status in gliomas. This limitation hampers the development of neoadjuvant or intraoperative therapeutic strategies based on IDH status; thus, more minimally invasive methods to determine IDH status are needed. In this study, we assessed immune cell proportions, which vary by glioma subtype, from pre-surgery peripheral blood samples as an alternative method of classifying the IDH status in gliomas without enhancement. MATERIAL AND METHODS First, we employed a highly accurate large language model (GPT-4-Turbo-128k) with over 99% accuracy to read radiology notes and exclude patients with enhancing gliomas. Then, we identified twelve immune cell subtypes from whole blood using deconvolution algorithms based on DNA methylation data. These immune cell subtypes, along with patient age, were integrated into a machine learning model (random forest) to predict IDH status (wildtype vs. mutant), leveraging conditional Generative Adversarial Networks to generate synthetic data and mitigate bias in the datasets. Two independent datasets were included for training and validating the model. RESULTS The random forest model had an area under the ROC curve (AUC) of 0.90 and accurately identified IDH status in 81% of a training set of 287 gliomas (65 wildtype and 222 mutant tumors at varied time points after diagnosis). In an independent validation data set of 99 gliomas (6 wildtype and 93 mutant) from pre-surgery blood samples, the AUC was 0.93, and accuracy predicted IDH status in 92% of cases with a sensitivity of 93% and specificity of 83%. CONCLUSION We could accurately predict IDH status in pre-surgical peripheral blood samples from patients with non-enhancing gliomas. This minimally invasive approach is a promising step toward reducing risk and exploring opportunities for earlier therapies based on IDH status.

The value of nomogram based on MRI functional imaging in differentiating cerebral alveolar echinococcosis from brain metastases

ObjectiveThis study aims to evaluate the effectiveness of a nomogram model constructed using Diffusion Kurtosis Imaging (DKI) and 3D Arterial Spin Labeling (3D-ASL) functional imaging techniques in distinguishing between cerebral alveolar echinococcosis (CAE) and brain metastases (BM).MethodsProspectively collected were 24 cases (86 lesions) of patients diagnosed with CAE and 16 cases (69 lesions) of patients diagnosed with BM at the affiliated hospital of Qinghai University from 2018 to 2023, confirmed either pathologically or through comprehensive diagnosis. Both patient groups underwent DKI and 3D-ASL scanning. DKI parameters (Kmean, Dmean, FA, ADC) and cerebral blood flow (CBF) were analyzed for the parenchymal area, edema area, and symmetrical normal brain tissue area in both groups. There were 155 lesions in total in the two groups of patients. We used SPSS to randomly select 70% as the training set (108 lesions) and the remaining 30% as the test set (47 lesions) and performed a difference analysis between the two groups. The independent factors distinguishing CAE from BM were identified using univariate and multivariate logistic regression analyses. Based on these factors, a diagnostic model was constructed and expressed as a nomogram.ResultUnivariate and multivariate logistic regression analyses identified nDmean1 and nCBF1 in the lesion parenchyma area, as well as nKmean2 and nDmean2 in the edema area, as independent factors for distinguishing CAE from BM. The model's performance, measured by the area under the ROC curve (AUC), had values of 0.942 and 0.989 for the training and test sets, respectively. Calibration curves demonstrated that the predicted probabilities were highly consistent with the actual values, and DCA confirmed the model's high clinical utility.ConclusionThe nomogram model, which incorporates DKI and 3D-ASL functional imaging, effectively distinguishes CAE from BM. It offers an intuitive, accurate, and non-invasive method for differentiation, thus providing valuable guidance for subsequent clinical decisions.

The Utility of Micro-R/Hypo-He Ratio Cut-off for Distinguishing Iron Deficiency Anemia and Minor Thalassemia

Thalassemia is a genetic disease with impaired synthesis of the globin chain that causes anemia. Thalassemia and Iron Deficiency Anemia (IDA) are both microcytic hypochromic anemia but have different proportions of hypochromic and microcytic erythrocytes due to differences in disease mechanisms. Research parameters of the hematology analyzer: %Micro-R, %Hypo-He, and MH ratio can be used as early screening for thalassemia and IDA. This study aimed to evaluate the cut-off of %Micro-R, %Hypo-He, and MH ratio to differentiate thalassemia from IDA. A cross-sectional study was carried out on 217 subjects. Subjects were divided into two groups, thalassemia and IDA based on hemoglobin electrophoresis, hematology examination, and Mentzer index. Differences and cut-off values of %Micro-R, %Hypo-He, and MH ratio between the two groups were analyzed. The number of collected data was 134, consisting of 89 thalassemia patients and 45 IDA patients. Thalassemia patients had a median %Micro-R value of 51.2 (4.3-79.0), %Hypo-He value of 7.2 (0.2-50.2), and MH ratio of 7.17 (1.10-64.50), higher than IDA patients (p=0.000; p=0.176; p=0.000). The optimal cut-off value for %Micro-R in discriminating thalassemia trait from IDA was &gt;12.7, with the area under the ROC curve (AUC) of 0.945, sensitivity of 92.1%, and specificity of 82.2%. The cut-off value for MH ratio &gt; 3.27 with AUC 0.833, sensitivity of 85.4%, and specificity 77.8% showed lower performance of cut-off value compared to %Micro-R. The algorithm using %Micro-R and MH ratio was proposed for thalassemia trait screening. High %Micro-R and MH are suggestive of thalassemia trait than of IDA.

Circulating Endocannabinoids in Canine Cutaneous Mast Cell Tumor.

A cutaneous mast cell tumor (cMCT) is among the most common tumors in dogs. Endocannabinoids (eCBs) belong to the endocannabinoid system (ECS), which involves also cannabinoid receptors and an enzymatic system of biosynthesis and degradation. In this study, plasma levels of N-arachidonoylethanolamine (AEA), 2-arachidonoylglycerol (2-AG), N-palmitoylethanolamine (PEA), and N-oleoylethanolamine (OEA) were evaluated in 17 dogs with MCTs of varying histological grades and clinical stages, as well as in a control group of 11 dogs. Dogs affected by cMCT had higher plasma levels of 2-AG (p = 0.0001) and lower levels of AEA (p = 0.0012) and PEA (p = 0.0075) compared to the control group, while no differences were observed at the OEA level between healthy and cMCT dogs (p = 0.9264). The ability of eCBs to help discriminate between healthy and cMCT dogs was interrogated through the area under the ROC curve (AUC). An accuracy of 0.98 (95% confidence interval [CI], 0.94-1.02) was found for 2-AG, of 0.85 (95% CI, 0.71-0.99) for AEA, and of 0.81% for PEA (95% CI, 0.64-0.69). Values > 52.75 pmol/mL for 2-AG showed 94% sensitivity and 90% specificity in distinguishing cMCT. This is the first study to demonstrate alterations in plasmatic levels of eCBs in dogs affected by MCTs, suggesting the significance of these biomarkers in the tumorigenic process and their potential use as biomarkers in the future.

Assessment of a fully-automated diagnostic AI software in prostate MRI: Clinical evaluation and histopathological correlation

ObjectiveThis study aims to evaluate the diagnostic performance of a commercial, fully-automated, artificial intelligence (AI) driven software tool in identifying and grading prostate lesions in prostate MRI, using histopathological findings as the reference standard, while contextualizing its performance within the framework of PI-RADS v2.1 criteria. Material and methodsThis retrospective study analyzed 123 patients who underwent multiparametric prostate MRI followed by systematic and targeted biopsies. MRI protocols adhered to international guidelines and included T2-weighted, diffusion-weighted, T1-weighted, and dynamic contrast-enhanced imaging. The AI software tool mdprostate was integrated into the Picture Archiving and Communication System to automatically segment the prostate, calculate prostate volume, and classify lesions according to PI-RADS scores using biparametric T2-weighted and diffusion-weighted imaging. Histopathological analysis of biopsy cores served as the reference standard. Diagnostic performance metrics including sensitivity, specificity, positive and negative predictive value (PPV, NPV), and area under the ROC curve (AUC) were calculated. Resultsmdprostate demonstrated 100 % sensitivity at a PI-RADS ≥ 2 cutoff, effectively ruling out both clinically significant and non-significant prostate cancers for lesions remaining below this threshold. For detecting clinically significant prostate cancer (csPCa) using a PI-RADS ≥ 4 cutoff, mdprostate achieved a sensitivity of 85.5 % and a specificity of 63.2 %. The AUC for detecting cancers of any grade was 0.803. The performance metrics of mdprostate were comparable to those reported in two meta-analyses of PI-RADS v2.1, with no significant differences in sensitivity and specificity (p > 0.05). ConclusionThe evaluated AI tool demonstrated high diagnostic performance in identifying and grading prostate lesions, with results comparable to those reported in meta-analyses of expert readers using PI-RADS v2.1. Its ability to standardize evaluations and potentially reduce variability underscores its potential as a valuable adjunct in the prostate cancer diagnostic pathway. The high accuracy of mdprostate, particularly in ruling out prostate cancers, highlights its clinical utility by reducing workload and enhancing patient outcomes.

A Machine Learning Approach to Determine Risk Factors for Respiratory Bacterial/Fungal Coinfection in Critically Ill Patients with Influenza and SARS-CoV-2 Infection: A Spanish Perspective.

Background: Bacterial/fungal coinfections (COIs) are associated with antibiotic overuse, poor outcomes such as prolonged ICU stay, and increased mortality. Our aim was to develop machine learning-based predictive models to identify respiratory bacterial or fungal coinfections upon ICU admission. Methods: We conducted a secondary analysis of two prospective multicenter cohort studies with confirmed influenza A (H1N1)pdm09 and COVID-19. Multiple logistic regression (MLR) and random forest (RF) were used to identify factors associated with BFC in the overall population and in each subgroup (influenza and COVID-19). The performance of these models was assessed by the area under the ROC curve (AUC) and out-of-bag (OOB) methods for MLR and RF, respectively. Results: Of the 8902 patients, 41.6% had influenza and 58.4% had SARS-CoV-2 infection. The median age was 60 years, 66% were male, and the crude ICU mortality was 25%. BFC was observed in 14.2% of patients. Overall, the predictive models showed modest performances, with an AUC of 0.68 (MLR) and OOB 36.9% (RF). Specific models did not show improved performance. However, age, procalcitonin, CRP, APACHE II, SOFA, and shock were factors associated with BFC in most models. Conclusions: Machine learning models do not adequately predict the presence of co-infection in critically ill patients with pandemic virus infection. However, the presence of factors such as advanced age, elevated procalcitonin or CPR, and high severity of illness should alert clinicians to the need to rule out this complication on admission to the ICU.