A Detection Method With Antiinterference for Infrared Maritime Small Target

Much of the research into multipath detectionand mitigation has not considered the carrier phase delaybetween the line of sight (LOS) and reflected signals. Anew variable referred to as early late phase (ELP) hasrecently been proposed to exploit this phase difference. Ithas been found that in a receiver tracking the L1 GPSsignal, the probability of detecting multipath is lower whenthe carrier phase difference between the LOS and areflected signal is an integer multiple of p. Since thepseudorange error caused by the multipath’s presence is thehighest in this case, we propose to exploit the coexistenceof another GPS civilian signal, the L2C. We present ananalysis of ELP for the L1 and L2C signals, and a com-bination of both, for detecting multipath. The multipathdetection performance has been compared using probabil-ities of false alarm and detection. An ideal algorithmshould have lower probability of false alarm and higherprobability of detection. However, it has been found thatusing dual-frequency ELP increases both probabilities.Thus, receiver operator characteristics (ROC) curves, andthe area under the ROC curves, have been used for effec-tive comparison. It has been found that the L2C signalindividually gives worse performance than L1 because ofits weaker signal strength. However, the combination of L1and L2C gives the best overall performance, and thus it canbe claimed that ELP using dual-frequency receivers is amore effective approach for detecting multipath.Keywords Multipath GPS L2C ELP Dual-frequency receiverIntroductionThe last decade or so has seen an increase in applicationsof GPS in urban and indoor applications, which hasencouraged extensive research activity in the field ofmultipath detection and mitigation. Algorithms widelycited are narrow correlators (Dierendonck et al. 1992),double-difference residuals (DDR) (Townsend and Fenton1994), the vision correlator (Fenton and Jones 2005) andthe multipath estimating delay locked loop (MEDLL)(Townsend et al. 2000). Since a reflected signal reachesthe receiver by a relatively longer path, it is delayed intime and also has a carrier phase difference with respectto the line of sight (LOS) signal (Hatch et al. 2007;Mubarak and Dempster 2008). The above algorithms (andmany others) only use the magnitude of the correlatoroutputs and hence do not exploit this phase difference. Anew parameter, called the ‘‘early late phase (ELP)’’, hasrecently been proposed for multipath detection and esti-mation (Mubarak and Dempster 2007). ELP is the phasedifference between the early and late correlator outputs,where the phase of a correlator output is equal to theinverse tangent of the Q-channel output divided by theI-channel output. It is higher in the presence of multipathand has been shown to be a useful discriminator to detectthe presence of multipath (Mubarak 2008).This paper first provides a brief description of ELP,followed by its analysis in the presence of multipath for theL1 and L2C signals, and the combination of both. Multi-path detection performance is then compared using prob-abilities of false alarm and detection. ROC curves and the

ABSTRACTAimAcute appendicitis is one of the most common surgical emergencies in children and differentiating uncomplicated appendicitis from complicated is crucial. Our aim was to examine accuracy of preoperative C‐reactive protein (CRP) combined with imaging findings in identifying patients with uncomplicated outcome.MethodsWe retrospectively examined 1520 patients treated for acute appendicitis at the Helsinki University Children's Hospital during 2013–2023. Receiver operating characteristics (ROC) curves and areas under the ROC curves (AUROC) were used to estimate optimal CRP cutoff values with maximum sum of sensitivity and specificity for predicting uncomplicated outcomes in patients with uncomplicated imaging findings.ResultsAmong the 1149 included patients, preoperative imaging included ultrasound examination (98.6%), MRI (9.8%), and/or CT (2.1%). In total, 314 (27.3%) patients had a complicated outcome with higher preoperative CRP levels (133 ± 83 mg/L) compared to patients with uncomplicated outcomes (47.2 ± 46.3 mg/L, p < 0.001). In patients with uncomplicated imaging findings, the optimal CRP cutoff was 58 mg/L with AUROC 0.819 (95% CI 0.78–0.86), 85.7% sensitivity, and 90.0% specificity. Using CRP cutoff ≤ 58 mg/L, only 20 of 450 patients with uncomplicated imaging findings had a complicated outcome.ConclusionWith CRP cutoff ≤ 58 mg/L and uncomplicated imaging findings, only a minority (4.4%) of children with acute appendicitis had a complicated outcome.

In this paper we propose a combination of the AdaBoost and random forests algorithms for constructing a breast cancer survivability prediction model. We use random forests as a weak learner of AdaBoost for selecting the high weight instances during the boosting process to improve accuracy, stability and to reduce overfitting problems. The capability of this hybrid method is evaluated using basic performance measurements (e.g., accuracy, sensitivity, and specificity), Receiver Operating Characteristic (ROC) curve and Area Under the receiver operating characteristic Curve (AUC). Experimental results indicate that the proposed method outperforms a single classifier and other combined classifiers for the breast cancer survivability prediction.

In power distribution fault data, the percentage of faults with different causes could be very different and varies from region to region. This data imbalance issue seriously affects the performance evaluation of fault diagnosis algorithms. Due to the limitations of conventional accuracy (ACC) and geometric mean (G-mean) measures, this paper discusses the application of Receiver Operating Characteristic (ROC) curves in evaluating distribution fault diagnosis performance. After introducing how to obtain ROC curves, Artificial Neural Networks (ANN), Logistic Regression (LR), Support Vector Machines (SVM), Artificial Immune Recognition Systems (AIRS), and K-Nearest Neighbor (KNN) algorithm are compared using ROC curves and Area Under the Curve (AUC) on real-world fault datasets from Progress Energy Carolinas. Experimental results show that AIRS performs best most of the time and ANN is potentially a good algorithm with a proper decision threshold.

Background The prevalence of atrial fibrillation (AF), the most common type of cardiac arrhythmia, has increased globally. AF is also the leading cardiac factor for several cardiovascular and cerebrovascular events. Early prediction and treatment of AF prevents major cardiovascular and cerebrovascular events. Purpose Our objective is to predict AF risk within 7-years follow-up using only twelve basic factors and applying machine learning (ML) models. Methods Data from the German epidemiological trial on ankle brachial index (getABI) were utilized in this work. GetABI includes 6,457 patients with mean age of 72.53 years. 3,985 individuals were assessed for AF of which 393 patients suffered from AF at 7-years follow-up. The feature selection was initially done manually, ending up in 45 features. The 10 best features were extracted from this dataset according to the SHAP (SHapley Additive exPlanations) values. The final features were body mass index, sensitive CRP, cholesterol, LDL-cholesterol, troponin I, NT-pro-BNP, glomerular filtration rate, ratio of triglycerides and HDL-cholesterol, gamma-GT, heart rate, including age and sex as major factors. The handling of missing values was achieved by SimpleImputer, estimating the mean values. XGBoost and Random Forest predicted AF. Logistic Regression was also used as a baseline model. The data were split into training and test set and ML models were applied for 100 iterative runs, extracting results with mean values. Results XGBoost was the most accurate model, predicting the AF with 71.19 % mean accuracy, 66.37 % mean sensitivity and 75.61 % mean specificity. Figure 1 depicts the performance of all models. Additionally, Receiver Operating Characteristic Curve (ROC) and Area Under Curve (AUC) for each model are presented in Figure 2. XGBoost also outperformed all the others models, achieving the highest mean AUC value, equal to 70.99 %. Contrariwise, logistic regression had the lowest overall performance. Conclusion ML models, specifically XGBoost, achieved accurate AF prediction in 3,985 individuals utilizing only twelve clinical-routine data.Evaluation results of each used model.ROC curve and AUC value of each model.

Objective To investigate the changes and significance of pro-adrenomedullin (pro-ADM) in neonatal infection and to analyze its value in predicting the severity of the infection. Methods From April to December in 2007, data from 356 neonates admitted to our hospital were included in the study. Patients were divided into non-infection group (n=160), mild infection group (n= 114) and severe infection group (n = 82). Plasma levels of pro-ADM were determined with chemiluminescence immunoassay. Procalcitonin (PCT) and C-reactive protein (CRP) levels were measured also. Cut-off value, sensitivity and specificity of pro-ADM in diagnosing infection were calculated by receiver operator characteristic curve(ROC) and area under the ROC curve(AUC) ,then compared with those of CRP. One way ANOVA and Wilcoxon test were applied as the statistical methods. Results The level of pro-ADM in severe infection group were (2. 079±1. 195) nmol/L, higher than that of mild infection group and non-infection group [(1. 025 ±0. 421) nmol/L and (0. 853±0. 488) nmol/L](P<0. 01). Infection was the independent influencing factor of pro-ADM level (r=0. 78, P<0. 01). Pro-ADM showed better diagnostic efficiency compared to CRP with the sensitivity of 71. 95% and the specificity of 87. 23%. The level of pro-ADM in critically infected neonates was (2. 498 ±1. 140) nmol/L, significantly higher than that of non-critically infected neonates [1.810±1.162) nmol/L] among those in the severe infection group (P<0. 05) , while PCT showed no significant difference. Conclusions The level of pro-ADM increases in neonates with infection, especially those with severe infection. Pro-ADM has potential value in early diagnosis of severe infection and severity assessment in infected newborns. Key words: Protein precursors; Adrenomedullin; Infant, newborn; Sepsis

A contaminated binormal model for ROC data: Part I. Some interesting examples of binormal degeneracy

Backgroundβ-synuclein (β-syn), mainly expressed in central nerve system, is one of the biomarkers in cerebrospinal fluid (CSF) and blood for synaptic damage, which has been reported to be elevated in CSF and blood of the patients of prion diseases (PrDs).MethodsWe analyzed 314 CSF samples from patients in China National Surveillance for CJD. The diagnostic groups of the 223 patients with PrDs included sporadic Creutzfeldt-Jacob disease (sCJD), genetic CJD (gCJD), fatal familial insomnia (FFI) and Gerstmann-Straussler-Scheinker (GSS). 91 patients with non-PrDs comprised Alzheimer’s disease (AD), Parkinson's disease (PD), viral encephalitis (VE) or autoimmune encephalitis (AE) were enrolled in the control groups. The CSF β-syn levels were measured by a commercial microfluidic ELISA. The Mann–Whitney U test and Kruskal–Wallis H test were employed to analyze two or more sets of continuous variables. Multiple linear regression was also performed to evaluate the factors for CSF β-syn levels. Receiver operating characteristics (ROC) curves and area under the curve (AUC) values were used to assess the diagnostic performance of β-syn.ResultsThe median of β-syn levels (2074 pg/ml; IQR: 691 to 4332) of all PrDs was significantly higher than that of non-PrDs group (504 pg/ml; IQR: 126 to 3374). The CSF β-syn values in the cohorts of sCJD, T188K-gCJD, E200K-gCJD and P102L-GSS were remarkably higher than that of the group of AD + PD, but similar as that of the group of VE + AE. The elevated CSF β-syn in sCJD and gCJD cases was statistically associated with CSF 14-3-3 positive and appearance of mutism. ROC curve analysis identified satisfied performance for distinguishing from AD + PD, with high AUC values in sCJD (0.7640), T188K-gCJD (0.8489), E200K-gCJD (0.8548), P102L-GSS (0.7689) and D178N-FFI (0.7210), respectively.ConclusionOur data here indicate that CSF β-syn is a potential biomarker for distinguishing PrDs (gCJD, sCJD and GSS) from AD and PD, but is much less efficient from VE and AE. These findings have critical implications for early diagnosis and monitoring of synaptic integrity in prion diseases.

The fact that lung cancer continues to be the leading cause of cancer-related death around the world emphasizes how important it is to improve diagnostic methods. Using computed tomography (CT) images and deep learning techniques, the goal of this study is to improve the classification of lung cancer. EfficientNetB1 and Inception V3 are two well-known convolutional neural network (CNN) architectures that we compare the performance of our modified ResNet50 architecture against in order to determine how well it performs in the classification of lung nodules. Analyzing the effects of various preprocessing and hyperparameter optimization methods on model performance is one of our research objectives. Another is to determine how well these models improve diagnostic accuracy. An extensive collection of CT images with annotated lung nodule classifications make up the utilized dataset. To ensure accurate model training and improve image quality, a rigorous preprocessing pipeline is used. Using the Keras Sequential framework, the models are trained with optimal dropout rates and L2 regularization to prevent overfitting. Metrics like accuracy, loss, and confusion matrices are used to evaluate model performance. A comprehensive evaluation of the model's sensitivity and specificity across various thresholds is also provided by means of the Free-Response Receiver Operating Characteristic (FROC) curve and Area Under the Curve (AUC) values. The adjusted ResNet50 model showed prevalent order exactness, accomplishing a precision of 98.1% and an AUC of 0.97, in this way beating different models in the review. EfficientNetB1 had an accuracy of 96.4 percent and an AUC of 0.94, while Inception V3 had an accuracy of 95.8 percent and an AUC of 0.93, as a comparison. Based on these findings, it appears that the accuracy of lung cancer detection from CT images can be significantly improved by combining specialized preprocessing and training methods with advanced CNN architectures. With potential implications for clinical practice and future research directions, this study offers a promising strategy for increasing lung cancer diagnostic accuracy.

AimsThis study aimed to identify the optimal human chorionic gonadotropin (hCG) ratio in predicting etoposide, methotrexate, dactinomycin, cyclophosphamide, and vincristine resistance in women diagnosed with high‐risk gestational trophoblastic neoplasia (GTN) and to compare the chemoresistant disease detection rate by using the optimal hCG ratio and traditional criteria.MethodsSeventy‐six women with primary high‐risk GTN treated with etoposide, methotrexate, dactinomycin, cyclophosphamide, and vincristine in a tertiary‐care center were included. The hCG ratio was determined by its serum pretreatment level divided by that before each cycle of chemotherapy. The traditional criteria for chemoresistance included plateau or rising of hCG or presence of new metastasis. The optimal hCG ratio was determined using receiver operating characteristics (ROC) curve analysis.ResultsAmong the specificities of 90%, 92.5%, and 95%, the 90% specificity yielded the best ROC curve. At 90% specificity, the best area under curve value was at the fourth cycle with 75% sensitivity. The hCG ratio at the fourth cycle was 31.92. Using the ratio at the fourth cycle, chemoresistant disease was detected in six out of eight patients, compared to one in the traditional criteria. When combining the two diagnostic tools, the cumulative detection rate in the fourth cycle was 10/12 (83.3%) of total drug resistance. Among patients who developed drug resistance at the fourth cycle or thereafter, the use of the ratio at the fourth cycle could diagnose chemoresistance approximately two cycles earlier than that with the traditional criteria.ConclusionsA hCG ratio of <31.9 at the fourth cycle should be considered a high‐risk for etoposide, methotrexate, dactinomycin, cyclophosphamide, and vincristine resistance and may need second‐line chemotherapy. The ratio increases the detection rate of resistance to these drugs more than the traditional criteria.

Reliability and Validity of the Mandarin Version of the Voice-Related Quality of Life (MV-RQOL) Measure

Receiver Operating Characteristic (ROC) curves are used to describe and compare the accuracy of diagnostic test or the ability of a continuous biomarker in discriminating between the subjects into healthy or diseased cases in medical field. The most familiar form of ROC curve is Bi-normal (Gaussian) ROC curve model, which assumes that the test scores or a monotone transformation of the test scores are from two normal populations (i.e. healthy and diseased). It may not be true all the time, it may violate the assumptions of normal distribution in some situations and also we cannot adopt the model as it is when the sample size is small. In this paper, we have proposed ROC curve model for Rayleigh distribution which can be used even when sample size is small. The properties of Bi-Rayleigh ROC model are studied and Area Under the ROC Curve (AUC) are derived. The proposed model is supported by real life example as well as simulation studies. The confidence interval for the population parameter is studied with simulation studies of varying sample sizes. It is found that Bi-Rayleigh ROC model provides better accuracy of classification than the conventional bi-normal ROC model. In the ROC model section, Bi-Rayleigh ROC model and its AUC are derived and its properties are discussed. In application section, two real life example viz. Head trauma data and Multiple Sclerosis data were used for the proposed model and then these are compared with the conventional bi- normal model. In the simulation section, simulation studies have been carried out for different values of parameters to support the Bi-Rayleigh ROC model. In the last section, the confidence intervals for the parameter σi, i=0,1 are discussed for real life example and simulated data sets. II. ROC MODEL AND AREA UNDER THE CURVE Let the scores (S) be a random variable in healthy (H) and diseased (D) populations respectively. The ROC curve is plotted over values of threshold value (t) and is given by y(t) = h (x(t)) where x(t) is the False positive rate which is given by x(t) = P(S>t|H) and y(t) is True positive rate which is given by y(t) = P (S>t|D) The general functional form of ROC can be represented as

624 Background: The Preoperative Aspects and Dimensions Used for Anatomical Classification (PADUA) score is a validated predictor of a patient’s perioperative outcomes following partial nephrectomy. The use of a fully automated, unbiased and time sensitive PADUA scoring system is a novel concept that may help circumvent PADUA’s widespread adoptability. We sought to automate the scoring of preoperative computed tomography scans (CT) using a machine-learning-generated PADUA score (P-AI). In doing so, we aimed to compare P-AI’s ability to predict meaningful perioperative and oncologic outcomes as compared to human generated PADUA scores using both categorical (P-H) and continuous variables (P-AI+). Methods: 300 patients with pre-operative CT scans were identified from a cohort of 544 consecutive patients undergoing surgical extirpation for suspected renal cancer at a single institution. A deep neural network approach was used to automatically segment kidneys and tumors and geometric algorithms were developed to estimate each component of PADUA based on the segmented regions (P-AI). Tumors were also manually scored by medical personnel blinded to the P-AI (P-H). The ability of P-AI and P-AI+ to predict meaningful perioperative and oncologic outcomes was compared to P-H using logistic regression and receiver operating characteristics (ROC) curve analyses and areas under the curve (AUC). Results: Median age was 60 years, 40% were female. Median tumor size was 4.2 cm, 91.3% had malignant tumors, including 27% and 37% with high-stage and high-grade, respectively. Both P-AI and P-H were able to predict the need for partial nephrectomy (p &lt; 0.001). From an oncologic standpoint, P-AI and P-H were able to predict meaningful oncologic outcomes including the presence of malignancy, high grade and high stage disease (p &lt; 0.004) although the ROC curves were not different from one another). Interestingly, when each PADUA component was left as a continuous rather than ordinal variables (P-AI+), this automated continuous score was able to predict surgical type (AUC 0.88), presence of malignancy (AUC 0.67), indolent tumors (AUC 0.79) and high grade (AUC 0.77)/high stage disease (AUC 0.82), better than both P-AI and P-H. Conclusions: When viewed along a continuous spectrum, AI generated PADUA scores (P-AI+) yields predictive surgical and oncologic outcomes superior to both categorical AI and human generated PADUA scores. If nephrometry can be calculated automatically, there is no longer a need to simplify the equations and the use of an AI generated PADUA scoring system, provides a reliable estimate of meaningful outcomes in a manner that is time sensitive and superior to human expert evaluation. Further prospective work and reproducibility from other centers is encouraged.

Risk Prediction Model for Survival of Wait List Patients on Axial CF-LVAD: A UNOS Database Analysis

Non-alcoholic fatty liver disease (NAFLD) is the most common chronic liver disease worldwide. India and other developing countries are witnessing an unprecedented rise in the prevalence of NAFLD. As part of population-level strategy, at primary healthcare, an efficient risk stratification is crucial to ensure appropriate and timely referral of individuals who require care at secondary and tertiary levels. The present study was conducted to assess the diagnostic performance of two non-invasive risk scores, fibrosis-4 (FIB-4), and NAFLD fibrosis score (NFS), in Indian patients of biopsy-proven NAFLD. We conducted a retrospective analysis of biopsy-proven NAFLD patients that reported to our center between 2009 and 2015. Clinical and laboratory data were collected and two non-invasive fibrosis scores, NFS and FIB-4 score, were calculated using the original formulas. Liver biopsy was utilized as gold standard for diagnosis of NAFLD, diagnostic performance was determined by plotting receiver operator characteristic (ROC) curves and area under the ROC curve (AUROC) was calculated for each score. The mean age of 272 patients included was 40 (11.85) years and 187 (79.24%) were men. We found that the AUROCs for FIB-4 score (0.634) was higher for any degree of fibrosis as compared to NFS (0.566). The AUROC for FIB-4 for advanced liver fibrosis was 0.640 (.550-.730). The performance of the scores for advanced liver fibrosis was comparable with overlapping confidence intervals for both scores. The present study found an average performance of FIB-4 and NFS risk scores for detecting advanced liver fibrosis in Indian population. This study highlights the need for devising novel context-specific risk scores for efficient risk stratification of NAFLD patients in India.