AUC Of ROC Curve Research Articles

ARE THE CAUSES OF ILIOPSOAS-RELATED GROIN PAIN IN TOTAL HIP ARTHROPLASTY AND HIP RESURFACING ARTHROPLASTY EQUIVALENT? A CASE-CONTROLLED INVESTIGATION USING A VALIDATED SIMULATION

Iliopsoas tendonitis occurs in up to 30% of patients after hip resurfacing arthroplasty (HRA) and is a common reason for revision. The primary purpose of this study was to validate our novel computational model for quantifying iliopsoas impingement in HRA patients using a case-controlled investigation. Secondary purpose was to compare these results with previously measured THA patients.We conducted a retrospective search in an experienced surgeon's database for HRA patients with iliopsoas tendonitis, confirmed via the active hip flexion test in supine, and control patients without iliopsoas tendonitis, resulting in two cohorts of 12 patients. The CT scans were segmented, landmarked, and used to simulate the iliopsoas impingement in supine and standing pelvic positions. Three discrete impingement values were output for each pelvic position, and the mean and maximum of these values were reported. Cup prominence was measured using a novel, nearest-neighbour algorithm.The mean cup prominence for the symptomatic cohort was 10.7mm and 5.1mm for the asymptomatic cohort (p << 0.01). The average standing mean impingement for the symptomatic cohort was 0.1mm and 0.0mm for the asymptomatic cohort (p << 0.01). The average standing maximum impingement for the symptomatic cohort was 0.2mm and 0.0mm for the asymptomatic cohort (p << 0.01). Impingement significantly predicted the probability of pain in logistic regression models and the simulation had a sensitivity of 92%, specificity of 91%, and an AUC ROC curve of 0.95.Using a case-controlled investigation, we demonstrated that our novel simulation could detect iliopsoas impingement and differentiate between the symptomatic and asymptomatic cohorts. Interestingly, the HRA patients demonstrated less impingement than the THA patients, despite greater cup prominence. In conclusion, this tool has the potential to be used preoperatively, to guide decisions about optimal cup placement, and postoperatively, to assist in the diagnosis of iliopsoas tendonitis.

An Empirical Study of Classification Models Using AUC-ROC Curve for Software Fault Predictions

Software bug prediction is the process of identifying software modules that are likely to have bugs by using some fundamental project resources before the real testing starts. Due to high cost in correcting the detected bugs, it is advisable to start predicting bugs at the early stage of development instead of at the testing phase. There are many techniques and approaches that can be used to build the prediction models, such as machine learning. We have studied nine different types of datasets and seven types of machine learning techniques have been identified. As for performance measures, both graphical and numerical measures are used to evaluate the performance of models. A few challenges exist when constructing a prediction model. In this study, we have narrowed down to nine different types of datasets and seven types of machine learning techniques have been identified. As for the performance measure, both graphical and numerical measures are used to evaluate the performance of the models. There are a few challenges in constructing the prediction model. Thus, more studies need to be carried out so that a well-formed result is obtained. We also provide a recommendation for future research based on the results we got from this study.

Risk factors for hyponatremia in acute exacerbation chronic obstructive pulmonary disease (AECOPD): a multicenter cross-sectional study

BackgroundHyponatremia is an independent predictor of poor prognosis, including increased mortality and readmission, in COPD patients. Identifying modifiable etiologies of hyponatremia may help reduce adverse events in patients with AECOPD. Therefore, the aim of this study was to explore the risk factors and underlying etiologies of hyponatremia in AECOPD patients.MethodsA total of 586 AECOPD patients were enrolled in this multicenter cross-sectional study. Finally, 323 had normonatremia, and 90 had hyponatremia. Demographics, underlying diseases, comorbidities, symptoms, and laboratory data were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to select potential risk factors, which were substituted into binary logistic regression to identify independent risk factors. Nomogram was built to visualize and validate binary logistics regression model.ResultsNine potential hyponatremia-associated variables were selected by LASSO regression. Subsequently, a binary logistic regression model identified that smoking status, rate of community-acquired pneumonia (CAP), anion gap (AG), erythrocyte sedimentation rate (ESR), and serum magnesium (Mg2+) were independent variables of hyponatremia in AECOPD patients. The AUC of ROC curve of nomogram was 0.756. The DCA curve revealed that the nomogram could yielded more clinical benefits if the threshold was between 10% and 52%.ConclusionsCollectively, our results showed that smoking status, CAP, AG, ESR, and serum Mg2+ were independently associated with hyponatremia in AECOPD patients. Then, these findings indicate that pneumonia, metabolic acidosis, and hypomagnesemia were the underlying etiologies of hyponatremia in AECOPD patients. However, their internal connections need further exploration.

Application of plasma donor-derived cell free DNA for lung allograft rejection diagnosis in lung transplant recipients

BackgroundDonor-derived cell-free DNA (dd-cfDNA) has been applied to monitor acute rejection (AR) in kidney and heart transplantation. This study was aimed to investigate the application of dd-cfDNA levels in the diagnosis of AR and chronic lung allograft dysfunction (CLAD) among the lung transplantation recipients (LTRs).MethodsOne hundred and seventy LTRs were enrolled at the First Affiliated Hospital of Guangzhou Medical University between 1 June 2015 and 30 March 2021. Patients were divided into 4 groups: stable group, AR group, infection group and CLAD group. The level of dd-cfDNA was analyzed using target region sequencing and the performance characteristics of dd-cfDNA for diagnosis of AR and CLAD were determined, respectively.ResultsKruskal–Wallis test showed that there were some significant differences in the level of dd-cfDNA (%) among the 4 groups, with p < 0.001. Among them, the level of dd-cfDNA (%) was highest (median 2.17, IQR [1.40–3.82]) in AR group, and higher in CLAD group (median 1.07, IQR [0.98–1.31]), but lower in infection group (median 0.71, IQR [0.57–1.07]) and lowest in stable group (median 0.71, IQR [0.61–0.84]). AUC-ROC curve analysis showed that the threshold of dd-cfDNA for AR was 1.17%, with sensitivity being 89.19% and specificity being 86.47%, and the optimal threshold of 0.89% was determined of CLAD, with sensitivity being 95.00% and specificity of 76.99%.ConclusionsPlasma dd-cfDNA could be a useful tool for the assessment of lung allograft rejection, including AR and CLAD, and holds promise as a noninvasive biomarker for “allograft injury” in both acute and chronic rejection following lung transplantation.

Feasibility study of automated cardiac motion quantification to assess left ventricular function in type 2 diabetes

The global incidence of diabetes and related complications is gradually increasing, with cardiovascular complications being the leading cause of death in the diabetic population. The purpose of this study was to examine left ventricular function in individuals with type 2 diabetes mellitus (T2D) and conduct a feasibility analysis using automated cardiac motion quantification (aCMQ) approach. A total of 150 T2D patients with a history of diabetes mellitus dating back more than 10 years were chosen, and we treated 87 patients with T2D that had been present for less than 15 years as group I, 63 patients with T2D that had been present for more than 15 years as group II, and 50 healthy volunteers as the control group. From the three groups, clinical information, conventional ultrasonography parameters, and mitral annular plane systolic excursion (MAPSE) parameters were gathered. aCMQ technique was used to collect longitudinal strain and circumferential strain in the left ventricle. Tissue motion mitral annular displacement technique (TMAD) in aCMQ was used to collect parameters related to TMAD, and cardiac motion quantification (CMQ) was used to collect two-dimensional global longitudinal strain (2D-GLS) to compare the degree of difference between the aforementioned three groups. The differences between longitudinal strain groups in aCMQ were all statistically significant and gradually decreased with increasing disease duration. Most TMAD parameters were lower in groups I and II than in the control group, and TMAD parameters gradually decreased with increasing disease duration. The results of the LV global longitudinal strain and 2D-GLS using Bland–Altman analyses showed high agreement between and within groups, Pearson correlation analysis showed a significant positive correlation (r = 0.18, P < 0.05), and the AUC of ROC curves predicting the value of left ventricular function in patients with T2D was 0.723 and 0.628, respectively. With significant positive correlations between MAPSE, s', and the majority of the TAMD parameters (P < 0.05), TAMD, MAPSE, and s' demonstrated high inter- and intra-group agreement using Bland–Altman analyses, and the three had predictive value in assessing left ventricular function in T2D patients by ROC curve. Reduced longitudinal strain and reduced mitral annular displacement were seen in patients with different disease stages of T2D, so the application of aCMQ and TAMD was effective in detecting altered left ventricular function in patients with T2D. aCMQ had higher value in predicting left ventricular function in patients with T2D compared to CMQ for overall longitudinal strain, and the software performed the depiction automatically, reducing manual errors. MAPSE parameters and s ' can replace the TMAD technique for assessing mitral annular motion and was simpler to perform, saving operational time.

Machine learning approach for quantitative biodosimetry of partial-body or total-body radiation exposures by combining radiation-responsive biomarkers

During a large-scale radiological event such as an improvised nuclear device detonation, many survivors will be shielded from radiation by environmental objects, and experience only partial-body irradiation (PBI), which has different consequences, compared with total-body irradiation (TBI). In this study, we tested the hypothesis that applying machine learning to a combination of radiation-responsive biomarkers (ACTN1, DDB2, FDXR) and B and T cell counts will quantify and distinguish between PBI and TBI exposures. Adult C57BL/6 mice of both sexes were exposed to 0, 2.0–2.5 or 5.0 Gy of half-body PBI or TBI. The random forest (RF) algorithm trained on ½ of the data reconstructed the radiation dose on the remaining testing portion of the data with mean absolute error of 0.749 Gy and reconstructed the product of dose and exposure status (defined as 1.0 × Dose for TBI and 0.5 × Dose for PBI) with MAE of 0.472 Gy. Among irradiated samples, PBI could be distinguished from TBI: ROC curve AUC = 0.944 (95% CI: 0.844–1.0). Mouse sex did not significantly affect dose reconstruction. These results support the hypothesis that combinations of protein biomarkers and blood cell counts can complement existing methods for biodosimetry of PBI and TBI exposures.

Automated Pneumonia Diagnosis using a 2D Deep Convolutional Neural Network with Chest X-Ray Images

Tiny air sacs in one or both lungs become inflamed as a result of the lung infection known as pneumonia. In order to provide the best possible treatment plan, pneumonia must be accurately and quickly diagnosed at initial stages. Nowadays, a chest X-ray is regarded as the most effective imaging technique for detecting pneumonia. However, performing chest X-ray analysis may be quite difficult and laborious. For this purpose, in this study we propose deep convolutional neural network (CNN) with 24 hidden layers to identify pneumonia using chest X-ray images. In order to get high accuracy of the proposed deep CNN we applied an image processing method as well as rescaling and data augmentation methods as shear_range, rotation, zooming, CLAHE, and vertical_flip. The proposed approach has been evaluated using different evaluation criteria and has demonstrat-ed 97.2%, 97.1%, 97.43%, 96%, 98.8% performance in terms of accuracy, precision, recall, F-score, and AUC-ROC curve. Thus, the applied deep CNN obtain a high level of performance in pneumonia detection. In general, the provided approach is intended to aid radiologists in making an accurate pneumonia diagnosis. Additionally, our suggested models could be helpful in the early detection of other chest-related illnesses such as COVID-19.

АНАЛИЗ АКТИВНОСТИ ЭРИТРОЦИТАРНОЙ АЦЕТИЛХОЛИНЭСТЕРАЗЫ

The aim of the study was to analyze the activity of erythrocyte acetylcholinesterase in puerperia with a complicated and physiological course of puerperia. A survey of 41 puerperas (mean age 26.5±2.1) who were hospitalized in the physiological department of the 3rd City Clinical Hospital named after E.V. Klumova, Minsk. All patients were divided into the following groups: 1st - 19 puerperas with a physiological course of labor and the postpartum period (mean age 25.2±2.3); 2nd - 22 puerperas with impaired contractile function of the uterus during childbirth and the postpartum period (mean age 27.0±2.2). The study of AChE activity in erythrocytes was carried out by the kinetic method using Cormay test kits (Poland) on an FP-900 biochemical analyzer (Finland). The results of the study allow us to consider the activity of acetylcholinesterase in erythrocytes, the echographic size of the uterine cavity according to sonography, and the level of uterine tone according to the hysterogram as significant markers of impaired labor contractile activity of the myometrium after childbirth. The threshold value of the size of the uterine cavity, the upward deviation from which indicates the formation of postpartum subinvolution of the uterus, was 15.3 mm at AUC 0.99±0.02 (p &lt; 0.001; HR 90.2%, DS 88.4%). The threshold value of the uterine tone, the downward deviation from which indicates a violation of the contractile function of the uterus in the puerperal, was 4.7 mm Hg. Art. at AUC 0.9±0.015 (p &lt; 0.001; HR 96.3%, DS 88.5%). The threshold point of AChE activity was 11745.4 U/l with an AUC ROC curve of 0.82±0.07 (p &lt; 0.001; PN 94.2%, DS 61.1%), which allows us to regard the studied parameter as a classifier physiological course of the postpartum period and postpartum subinvolution of the uterus. When choosing means of influencing postpartum subinvolution of the uterus, preference should be given to drugs and physiotherapeutic methods that have a stimulating effect on the contractile function of the uterus in order to eliminate the pathologically enlarged cavity and prevent the development of hemorrhagic and inflammatory complications.

Machine Learning Methods for Predicting Adverse Drug Reactions in Hospitalized Patients

Adverse Drug Reaction (ADR) in hospitalized patients have significant impacts on costs as well as on morbidity and mortality. A subset of ADR is preventable at the moment of prescribing. The use of supervised learning tools has been shown to be a good alternative to predict ADR, but more research is needed to make it a standard. A study was conducted to demonstrate how the use of machine learning methods can strengthen the ability to predict ADR in hospitalized patients. Binary classification models were constructed using three class balancing, feature selection and supervised learning approaches known as deep learning, random forest, and gradient boosting trees. Five-fold cross-validation and various evaluation metrics such as AUC, recall and F-measure were used to evaluate the models’ performance. Gradient boosting trees models was the approach that performed best, exhibiting a recall level of 78.3% and an ROC curve AUC of 0.81. Findings on attribute importance were also generated, which should thus prove useful in developing tools for clinical applications. Our predictive models’ results outperform those reported in the recent literature using traditional statistical methods. In this work we have shown the enormous potential of ML tools in this field and their great contribution to the development of information systems that use them.

A collaborative prediction approach to defend against amplified reflection and exploitation attacks

&lt;abstract&gt;&lt;p&gt;An amplified reflection and exploitation-based distributed denial of service (DDoS) attack allows an attacker to launch a volumetric attack on the target server or network. These attacks exploit network protocols to generate amplified service responses through spoofed requests. Spoofing the source addresses allows attackers to redirect all of the service responses to the victim's device, overwhelming it and rendering it unresponsive to legitimate users. Mitigating amplified reflection and exploitation attacks requires robust defense mechanisms that are capable of promptly identifying and countering the attack traffic while maintaining the availability and integrity of the targeted systems. This paper presents a collaborative prediction approach based on machine learning to mitigate amplified reflection and exploitation attacks. The proposed approach introduces a novel feature selection technique called closeness index of features (CIF) calculation, which filters out less important features and ranks them to identify reduced feature sets. Further, by combining different machine learning classifiers, a voting-based collaborative prediction approach is employed to predict network traffic accurately. To evaluate the proposed technique's effectiveness, experiments were conducted on CICDDoS2019 datasets. The results showed impressive performance, achieving an average accuracy, precision, recall and F1 score of 99.99%, 99.65%, 99.28% and 99.46%, respectively. Furthermore, evaluations were conducted by using AUC-ROC curve analysis and the Matthews correlation coefficient (MCC) statistical rate to analyze the approach's effectiveness on class imbalance datasets. The findings demonstrated that the proposed approach outperforms recent approaches in terms of performance. Overall, the proposed approach presents a robust machine learning-based solution to defend against amplified reflection and exploitation attacks, showcasing significant improvements in prediction accuracy and effectiveness compared to existing approaches.&lt;/p&gt;&lt;/abstract&gt;

Scoring of Professional Longevity of Patients with Arterial Hypertension of Military Personnel – the Participants of Modern Armed Conflicts

The prediction of ability for military service by the health of patients who are experienced (with war experience) military persons with arterial hypertension (AH) with existing comorbid pathology is an urgent issue of today and a component of national security. The objective: to analyze the of factors that influence on the prognosis of health service for the military service of patientsmilitary personnel with AH – the participants of anti-terrorist operation / operation of the united forces (ATO / OUF), taking into account the available comorbid pathology. Materials and methods. Medical card of 213 military personnel – ATO/OUF participants with AH and comorbid pathology were analyzed. The first group included medical cards of 126 patients with AH stage I, the second group – medical cards of 87 patients with AH stage II. Clinical and laboratory, instrumental methods of research and consultation of narrow specialists and cumulative CIRS disease scale, which provides a separate total assessment of the condition of each of the organ systems on the range of Likert scale were used. Results. During the study, the professional longevity was forecasted using program Statistica SSP 10.0 and the forecasting of professional longevity using IBM SPSS 23.0. The most important prognostic factors that affect the change in the category of suitability for military service for the health of patients with AH of military personnel – ATO/OUF participants with comorbid pathology were determined, namely: age, sum of points on the cumulative CIRS scale and stage of AH (87.0 –91.8 % of the correct classifications of generated artificial neural networks, the area index under the ROC-curve AUC 0.971–0,992). Conclusions. Based on the statistics obtained data in the construction and analysis of artificial neural networks, the “algorithm for predicting a category of suitability for military service for the health of patients with arterial hypertension of military personnel – ATO/OUF participants with comorbid pathology” was developed.

Type-II Diabetes Prediction by using Classification and Novel based Method (AWOD)

Type II diabetes is the deadliest disease. It must be identified early to be cured. Prediction models for detection systems typically use common parameters that might not be suitable for all individuals with various health conditions. As a result, this study suggests a way for diabetes type II prediction using variables that reflect individual health issues. More specifically, this work proposes a unique prediction method called Average Weighted Objective Distance (AWOD) based on the idea that the person has a variety of health states coming from a variety of individual characteristics, which is a need for an efficient prediction model. Using information gain to expose significant and inconsequential individual components with varying priorities, denoted by distinct weights (AWOD), modifies Weighted Objective Distance (WOD). To calculate AWOD, the data set is split into a training set and a testing set. The training set is utilized to establish all significant thresholds and constant values. In particular, binary classification issues with a small dataset are developed by AWOD. Two open-source datasets, Pima Indians Diabetes (First Dataset) and Mendeley Data for Diabetes (Second dataset) are examined to validate the suggested methodology. With machine learning-based prediction techniques like (K-Nearest Neighbors, Support Vector Machines, and Random Forest), the prediction performance for both datasets is compared, including statistical measures: Accuracy, Sensitivity, and specificity. The AUC-ROC curve graph reveals how well the model can differentiate across classes for all ML classifiers. The comparison findings demonstrated that the ML classifiers resulted in poor accuracy for the first Dataset. Although better for the second Dataset, the proposed method had greater accuracy than other machine learning based methods, with 95.26 percent and 99.01 percent for Datasets I and II, respectively.

Investigation of electrical and viscoelastic parameters of erythrocytes in patients with autoimmune gastritis

Patients with autoimmune gastritis (AIG) often have anemia of various origins . Hematological disorders usually portend severe atrophy , and in many cases , are the only indicators of the disease . Aim of the study was to investigate the electrical and viscoelastic parameters of erythrocytes in patients with AIG for their possible use in diagnostics . Material and methods . 73 patients with AIG ( mean age 55.3 ± 12.54 years ) and 38 people of the control group were examined . Electrical and viscoelastic parameters of erythrocytes were studied by dielectrophoresis . Results . Statistically significant decrease in the average cell diameter , the proportion of discocytes cells and an increase in the proportion of spherocytes , deformed forms were found in the group of patients with AIG in combination with Helicobaсter рylori (H. pylori , H.p .) infection compared with healthy individuals . Patients with AIG had significantly lower levels of amplitude of deformation , membrane capacity , dipole moment , speed of cell movement to the electrodes , polarizability at high frequencies of the electric field ( 106 , 0.5×106 Hz ), relative polarizability , and , conversely , higher values of membrane conductivity , aggregation , destruction indexes , summarized viscosity , rigidity , than those in the comparison group . Between groups of patients with and without H. pylori infection , differences were found in indicators reflecting the surface charge of erythrocytes – the speed of movement to the electrodes (p = 0.019), the dipole moment (p &lt; 0.001 ) and the state of the membranes – its capacity (p = 0.004). The diagnostic model , which includes three parameters of erythrocytes – the dipole moment , the speed of movement to the electrodes , the capacity of the cell membrane , provided high diagnostic accuracy of distinguishing AIG H.p . (+) and H.p . (–) – area under ROC curve AUC 0.925, sensitivity 92.4 %, specificity 89.7 %. Conclusions : Electrical and viscoelastic parameters of erythrocytes are promising in the diagnosis of AIG, including on the background of H. pylori infection .

Comparison of Novel Hybrid and Benchmark Machine Learning Algorithms to Predict Groundwater Potentiality: Case of a Drought-Prone Region of Medjerda Basin, Northern Tunisia

Water scarcity is a severe problem in Tunisia, particularly in the northern region crossed by the Medjerda River, where groundwater is a conjoint water resource that is increasingly exploited. The aim of this study is to delineate the groundwater potential zones (GWPZs) in the Lower Valley of the Medjerda basin by using single benchmark machine learning models based on artificial neural network (ANN), random forest (RF), and support vector regression (SVR), and by developing a novel hybrid method, NB-RF-SVR, to reach the highest accuracy of groundwater potential prediction. Each model produced a spatial groundwater potential map (GPM) with the input of 26 groundwater-related factors (GRF) selected by the frequency ratio model and 70% of the transmissivity training data. The models’ effectiveness was assessed using the AUC-ROC curve, sensitivity, specificity, MAE, and RMSE metric indicators. The validation findings revealed that all the models performed successfully for the GWPZ mapping, where the AUC values for the ANN, RF, SVR, and NB-RF-SVR models were estimated as 71%, 79%, 87%, and 92%, respectively. The relative importance of the GWPZs revealed that land use followed by geology and elevation were the most important factors. Finally, these outcomes can provide valuable information for decision makers to effectively manage groundwater in water-stressed regions.

Machine learning-based predictive risk models for 30-day and 1-year mortality in severe aortic stenosis patients undergoing transcatheter aortic valve implantation

BackgroundPredictive risk score for mortality plays an important role in the decision-making in patient selection and risk stratification for TAVI. Existing established predictive risk scores had poor discrimination performance in the prediction of mortality after the TAVI. ObjectivesThe present study aimed to develop machine learning-based predictive models for30-day and 1-year mortality in severe aortic stenosis patients undergoing TAVI. MethodsA total of 186 patients in a retrospective cohort study were analyzed. The models were fitted by a decision tree. Each model was tested in 100 iterations of 80:20 stratified random splitting into training/testing samples and 10-fold cross-validation. ResultsVariables that predict 30-day mortality are a set of factors driven mainly by height, chronic lung disease, STS score, preoperative LVEF, age, and preoperative LVOT VTI. Variables that predict 1-year mortality are a set of factors consisting of preoperative LVEF, STS score, heart rate, systolic blood pressure, home oxygen use, serum creatinine level, and preoperative LVOT Vmax. This decision tree-generated predictive models for 30-day and 1- year mortality provided the most precise accuracy of 0.97 and 0.90 with the AUC-ROC curves of 0.83 and 0.71 on 30-day and 1-year mortality on testing data and had better discrimination performance compared to the existing established TAVI predictive risk scores. ConclusionsThese machine learning models show excellent accuracy and have a better prediction for 30-day and 1-year mortality than the existing established TAVI predictive risk scores. A customized predictive model deems to be properly developed for better risk discrimination among cohorts.

Prediction of acute kidney injury after total aortic arch replacement with serum cystatin C and urine N-acetyl-β-d-glucosaminidase: A prospective observational study

BackgroundAcute kidney injury (AKI) after total aortic arch replacement (TAAR) is frequent and associated with adverse outcomes, whereas its early detection remains a challenge. Serum cystatin C (sCysC) and urinary N-acetyl-β-d-glucosaminidase (uNAG) are clinically available renal biomarkers, but their combination for AKI detection requires more evidence. This study aimed to assess the discriminative abilities of these biomarkers in AKI after TAAR. Materials and MethodsPatients undergoing TAAR were included in this prospective observational study. The AKI prediction model was developed and internal verificated, and the significance of each variable was analyzed by random forest (RF). Finally, the best predictive critical values of sCysC and uNAG were explored by the AUC-ROC curve. ResultsThe AUC-ROC of the prediction model was substantially enhanced by adding sCysC and uNAG (0.909 vs 0.844, p < 0.001), and the clinical utility and risk reclassification were significantly improved. Additionally, the RF showed that sCysC and uNAG ranked first and second. The AUC-ROC for each were 0.864 and 0.802 respectively, and the cut-off values were 1.395 mg/L and 31.90 U/g Cre respectively. ConclusionThe prediction model incorporating functional marker sCysC and tubular injury marker uNAG can improve the discriminative abilities of AKI after TAAR.

Comparison of five weaning indices in predicting successful weaning from mechanical ventilation

Introduction: Mechanical ventilation is a life-supporting modality used in patients with respiratory failure. Most patients are extubated early but weaning can be prolonged in some. Aim: Comparison of accuracy of prediction of success of a spontaneous breathing trial (SBT) using CORE, CROP, RSBI, RSBI rate and minute ventilation recovery. Methods: This is a prospective observational study. 62 adult patients admitted to Multidisciplinary Intensive Care Unit during April 2012 - January 2013 were studied. All patients, orotracheally intubated and mechanically ventilated for at least 24 hours and ready for weaning were enrolled. The patients underwent SBT using pressure support ventilation (5 – 8 cm H2O), PEEP of 5 - 8 cm H2O, and 40% oxygen. The weaning indices were measured at 30 min and correlated with weaning success. Results: The mean (± SD) age was 49.7 (± 18.3) years. There were 46 male and 16 female patients. The threshold values were as follows: CORE index: ≥ 6, CROP index: ≥ 13, RSBI &lt; 105 b/min/L, RSBI rate ≤ 20%. The sensitivity (%), specificity (%) and AUC of ROC curve were as follows: CORE (96, 66, 0.74), CROP (95, 33, 0.61), RSBI (89, 46, 0.2), RSBI rate (85, 28, 0.52) and minute ventilation recovery (higher than baseline minute ventilation at 25 min of rest on initial ventilator settings after 30 min of SBT) (n = 26) (92.3, 100, 0.93). Conclusion: CORE and RSBI are moderately accurate while CROP and RSBI rate are inaccurate. Minute ventilation recovery predicted weaning failure accurately.

Machine learning-supported interpretation of kidney graft elementary lesions in combination with clinical data

Interpretation of kidney graft biopsies using the Banff classification is still heterogeneous. In this study, extreme gradient boosting classifiers learned from two large training datasets (n=631 and 304 cases) where the "reference diagnoses" were not strictly defined following the Banff rules but from central reading by expert pathologists and further interpreted consensually by experienced transplant nephrologists, in light of the clinical context. In three external validation datasets (n=3744, 589, and 360), the classifiers yielded a mean ROC curve AUC (95%CI) of: 0.97 (0.92-1.00), 0.97 (0.96-0.97), and 0.95 (0.93-0.97) for antibody-mediated rejection (ABMR); 0.94 (0.91-0.96), 0.94 (0.92-0.95), and 0.91 (0.88-0.95) for T cell-mediated rejection; >0.96 (0.90-1.00) with all three for interstitial fibrosis-tubular atrophy. We also developed a classifier to discriminate active and chronic active ABMR with 95% accuracy. In conclusion, we built highly sensitive and specific artificial intelligence classifiers able to interpret kidney graft scoring together with a few clinical data and automatically diagnose rejection, with excellent concordance with the Banff rules and reference diagnoses made by a group of experts. Some discrepancies may point toward possible improvements that could be made to the Banff classification.

The Palliative Prognostic (PaP) Score without Clinical Evaluation Predicts Early Mortality among Advanced NSCLC Patients Treated with Immunotherapy.

Background: An acceptable risk-benefit ratio may encourage the prescription of immune checkpoint inhibitors (ICI) near the late stage of life. The lung immune prognostic index (LIPI) was validated in advanced non-small cell lung cancer (NSCLC) patients treated with ICIs. The palliative prognostic (PaP) score without clinical prediction of survival (PaPwCPS) predicts early mortality probability in terminal cancer patients. Methods: We performed a retrospective study including 182 deceased advanced NSCLC patients, treated with single-agent ICI at our Institution. Two prognostic categories of high and low mortality risk were identified through ROC curve analysis for PaPwCPS and LIPI scores. Results: Most were >65 years of age (68.3%) and received second-line ICI (61.2%). A total of 29 (15.9%) and 131 (72.0%) patients died within 30 and 90 days from treatment start, respectively. A total of 81 patients (44.5%) received ICI during the last month of life. Baseline PaPwCPS and LIPI scores were assessable for 78 patients. The AUC of ROC curves was significantly increased for PaPwCPS as compared with LIPI score for both 30-day and 90-day mortality. A high PaPwCPS score was associated in multivariate analysis with increased 30-day (HR 2.69, p = 0.037) and 90-day (HR 4.01, p < 0.001) mortality risk. A high LIPI score was associated with increased 90-day mortality risk (p < 0.001). Conclusion: We found a tendency towards ICI prescription near the late stage of life. The PaPwCPS score was a reliable predictor of 30- and 90-day mortality.

Clinical usefulness of cerebrospinal fluid biomarkers in Alzheimer's disease.

Alzheimer's disease (AD) is a complex disease that shares clinical features with other dementias. It is important to establish a specific and reliable diagnosis. Nowadays, AD diagnosis is based on cerebrospinal fluid (CSF) biomarkers. However, the corresponding cut-offs differ amongst studies. This study aims to evaluate the CSF biomarkers in the AD differential diagnosis. Clinical relevant biomarkers (amyloid β42 (Aβ42), t-Tau, p-Tau, amyloid β40 (Aβ40), neurofilament light chain (NfL)) were determined in CSF samples from participants classified as AD (n=124) and non-AD (n=148) patients from the Neurology Unit. They were included and evaluated consecutively (August 2018-October 2020). The clinical utility of these biomarkers was evaluated by AUC-ROC curves and the corresponding cut-off points were defined. The results showed satisfactory accuracy (AUC-ROC 0.91 for Aβ42, 0.890 for t-Tau and 0.933 for p-Tau); whilst Aβ40 and NfL did not show good discriminatory capacity (AUC-ROC 0.557 and 0.738, respectively). The ratios Aβ42/Aβ40 and t-Tau/Aβ42 improved the diagnosis indices of each individual biomarker, with AUC-ROC of 0.980 and 0.971, respectively. Also, elevated levels of NfL were found in the frontotemporal dementia group compared with the other participant groups. The ratio Aβ42/Aβ40 showed the highest discriminating capacity between AD and non-AD patients and might be useful in clinical practice. Regarding NfL, it is not a specific biomarker for AD; however, it might be helpful for the differential diagnosis of frontotemporal dementia. Nevertheless, further analysis in an external cohort is required in order to validate these results.