Improved Discrimination Performance Research Articles

Colocalization of Cancer-Associated Biomarkers on Single Extracellular Vesicles for Early Detection of Cancer

Detection of cancer early, when it is most treatable, remains a significant challenge due to the lack of diagnostic methods sufficiently sensitive to detect nascent tumors. Early-stage tumors are small relative to their tissue of origin, heterogeneous, and infrequently manifest in clinical symptoms. Detection of their presence is made more difficult by a lack of abundant tumor-specific indicators (i.e., protein biomarkers, circulating tumor DNA, etc.) that would enable detection using a non-invasive diagnostic assay. To overcome these obstacles, we have developed a liquid biopsy assay that interrogates circulating extracellular vesicles (EVs) to detect tumor-specific biomarkers colocalized on the surface of individual EVs. We demonstrate the technical feasibility of this approach in human cancer cell line-derived EVs where we show strong correlations between assay signal and cell line gene/protein expression for the ovarian cancer-associated biomarkers BST2, FOLR1, and MUC1. Furthermore, we demonstrate that detecting distinct colocalized biomarkers on the surface of EVs significantly improves discrimination performance relative to single biomarker measurements. Using this approach, we observe promising discrimination of high-grade serous ovarian cancer versus benign ovarian masses and healthy women in a proof-of-concept clinical study.

Dynamic and Transdiagnostic Risk Calculator Based on Natural Language Processing for the Prediction of Psychosis in Secondary Mental Health Care: Development and Internal-External Validation Cohort Study

BackgroundAutomatic transdiagnostic risk calculators can improve the detection of individuals at risk of psychosis. However, they rely on assessment at a single point in time and can be refined with dynamic modeling techniques that account for changes in risk over time. MethodsWe included 158,139 patients (5007 events) who received a first index diagnosis of a nonorganic and nonpsychotic mental disorder within electronic health records from the South London and Maudsley National Health Service Foundation Trust between January 1, 2008, and October 8, 2021. A dynamic Cox landmark model was developed to estimate the 2-year risk of developing psychosis according to the TRIPOD (Transparent Reporting of a multivariate prediction model for Individual Prognosis or Diagnosis) statement. The dynamic model included 24 predictors extracted at 9 landmark points (baseline, 0, 6, 12, 24, 30, 36, 42, and 48 months): 3 demographic, 1 clinical, and 20 natural language processing–based symptom and substance use predictors. Performance was compared with a static Cox regression model with all predictors assessed at baseline only and indexed via discrimination (C-index), calibration (calibration plots), and potential clinical utility (decision curves) in internal-external validation. ResultsThe dynamic model improved discrimination performance from baseline compared with the static model (dynamic: C-index = 0.9; static: C-index = 0.87) and the final landmark point (dynamic: C-index = 0.79; static: C-index = 0.76). The dynamic model was also significantly better calibrated (calibration slope = 0.97–1.1) than the static model at later landmark points (≥24 months). Net benefit was higher for the dynamic than for the static model at later landmark points (≥24 months). ConclusionsThese findings suggest that dynamic prediction models can improve the detection of individuals at risk for psychosis in secondary mental health care settings.

Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models

ObjectiveClass imbalance is sometimes considered a problem when developing clinical prediction models and assessing their performance. To address it, correction strategies involving manipulations of the training dataset, such as random undersampling or oversampling, are frequently used. The aim of this article is to illustrate the consequences of these class imbalance correction strategies on clinical prediction models’ internal validity in terms of calibration and discrimination performances. MethodsWe used both heuristic intuition and formal mathematical reasoning to characterize the relations between conditional probabilities of interest and probabilities targeted when using random undersampling or oversampling. We propose a plug-in estimator that represents a natural correction for predictions obtained from models that have been trained on artificially balanced datasets (“naïve” models). We conducted a Monte Carlo simulation with two different data generation processes and present a real-world example using data from the International Stroke Trial database to empirically demonstrate the consequences of applying random resampling techniques for class imbalance correction on calibration and discrimination (in terms of Area Under the ROC, AUC) for logistic regression and tree-based prediction models. ResultsAcross our simulations and in the real-world example, calibration of the naïve models was very poor. The models using the plug-in estimator generally outperformed the models relying on class imbalance correction in terms of calibration while achieving the same discrimination performance. ConclusionRandom resampling techniques for class imbalance correction do not generally improve discrimination performance (i.e., AUC), and their use is hard to justify when aiming at providing calibrated predictions. Improper use of such class imbalance correction techniques can lead to suboptimal data usage and less valid risk prediction models.

Harmonizing multisite data with the ComBat method for enhanced Parkinson's disease diagnosis via DAT-SPECT.

Dopamine transporter single-photon emission computed tomography (DAT-SPECT) is a crucial tool for evaluating patients with Parkinson's disease (PD). However, its implication is limited by inter-site variability in large multisite clinical trials. To overcome the limitation, a conventional prospective correction method employs linear regression with phantom scanning, which is effective yet available only in a prospective manner. An alternative, although relatively underexplored, involves retrospective modeling using a statistical method known as "combatting batch effects when combining batches of gene expression microarray data" (ComBat). We analyzed DAT-SPECT-specific binding ratios (SBRs) derived from 72 healthy older adults and 81 patients with PD registered in four clinical sites. We applied both the prospective correction and the retrospective ComBat correction to the original SBRs. Next, we compared the performance of the original and two corrected SBRs to differentiate the PD patients from the healthy controls. Diagnostic accuracy was assessed using the area under the receiver operating characteristic curve (AUC-ROC). The original SBRs were 6.13 ± 1.54 (mean ± standard deviation) and 2.03 ± 1.41 in the control and PD groups, respectively. After the prospective correction, the mean SBRs were 6.52 ± 1.06 and 2.40 ± 0.99 in the control and PD groups, respectively. After the retrospective ComBat correction, the SBRs were 5.25 ± 0.89 and 2.01 ± 0.73 in the control and PD groups, respectively, resulting in substantial changes in mean values with fewer variances. The original SBRs demonstrated fair performance in differentiating PD from controls (Hedges's g = 2.76; AUC-ROC = 0.936). Both correction methods improved discrimination performance. The ComBat-corrected SBR demonstrated comparable performance (g = 3.99 and AUC-ROC = 0.987) to the prospectively corrected SBR (g = 4.32 and AUC-ROC = 0.992) for discrimination. Although we confirmed that SBRs fairly discriminated PD from healthy older adults without any correction, the correction methods improved their discrimination performance in a multisite setting. Our results support the utility of harmonization methods with ComBat for consolidating SBR-based diagnosis or stratification of PD in multisite studies. Nonetheless, given the substantial changes in the mean values of ComBat-corrected SBRs, caution is advised when interpreting them.

Daily Activities of Elder Adults Using Optimized Deep Learning Model in China

The health and happiness of seniors can be influenced by the design of public spaces and buildings. Planning for age-friendly communities requires taking into account the wide variety of daily activities and public facility consumption among older persons. Yet, conventional approaches fall short when it comes to providing comprehensive, objective measures of the actions of the elderly. This research proposes an attention-based recognition approach by decomposing neural network outputs into class-dependent features using dictionary learning to improve discrimination performance. This research aimed to develop an empirical typology of activity of daily living (ADL) and its connection to health in China's ageing population. A deep learning-based model was rummaged to categorise the contributors in the Chinese Longitudinal Healthy Longevity Study (CLHLS) into subgroups based on their abilities with ADL. To be more precise, the study trains a category-based recognition network (CRN) by superimposing a basic but effective specific recognition encoding (SRE) unit on top of convolutional layers. In order to encode attention maps for each class, the SRE module uses the feature maps produced by the Convolutional Neural Networks (CNN) to learn a class-specific vocabulary. Class-wise adaptive feature refining is achieved by multiplying these attention maps by the input features. In this case, a gazelle optimization algorithm (GOA) handles the hyper-parameter tuning process of the proposed model. This case study is the first of its kind in a dense metropolitan region, and it uses objective measurements to evaluate the activity spaces of the elderly. This research provides empirical data for the promotion of healthy ageing in urban areas.

Improving Neutron-gamma discrimination in CLYC with Gaussian mixture model

Neutron and gamma discrimination is a common issue in neutron detection. Cs 2 LiYCl 6:Ce (CLYC) crystal, with its unique core-to-valence luminescence (CVL) mechanism for gamma rays, has excellent capability for neutron-gamma discrimination. This paper proposes a new preprocessing method called constant fraction alignment (CFA), based on the fast rise and slow decay characteristics of CLYC, to effectively improve discrimination performance. Unsupervised classification methods that do not require training data have a great advantage since pure neutron sources are difficult to obtain. As an unsupervised clustering method, Gaussian mixture model (GMM) is used to achieve neutron-gamma discrimination of data detected by CLYC, and the impact of different parameters on GMM results is studied. When the input dimension is high, GMM not only requires significantly more time but also reduces precision, so dimensionality reduction is necessary. Principal component analysis (PCA) is a commonly used dimensionality reduction method, and through analysis, it is found that using the first three components of PCA as inputs achieves the best performance. In the GMM solving process, selecting different covariance matrices based on data types can reduce running time while maintaining high accuracy. Diagonal mode is the most suitable according to comparison. Based on the same dataset, the accuracy of GMM is higher than that of charge comparison method and k-means++, with an accuracy of 99.96% for 252 Cf source and a false alarm rate as low as 0.01% for 137 Cs source.

A multi-channel framework based Local Binary Pattern with two novel local feature descriptors for texture classification

Local binary pattern (LBP) has been widely used in various application fields, including object detection, texture analysis, and remote sensing. To improve discrimination performance, many LBP-based methods have been proposed for extracting different local feature information for texture classification. However, current LBP-based algorithms typically describe local features at a single sampling scale, but some significant and discriminative texture feature information is contained between different scales. Therefore, the lack of capability to extract cross-scale features can lead to losing critical texture features. Moreover, low-frequency texture information should be accorded great importance in texture classification. Additionally, if the diversity and validity of local feature extraction are lacking, the effectiveness of classification capability suffers. To address these issues, (1) we propose a completed cross-scale Local binary pattern (ccsLBP) operator to extract cross-scale texture features. (2) A mean-filtered Local binary pattern (LBPmf) operator is presented to highlight the important low-frequency texture information of texture images. (3) We build a high-performing multi-channel framework based Local binary pattern (MC-LBP) for texture classification, which combines complementary features extracted by LBP, ccsLBP, and LBPmf hybridly to form a final feature vector of the texture image. The effectiveness of the proposed MC-LBP framework is verified on 6 representative texture databases, and the experimental results demonstrate its state-of-art texture classification performance.

Improved discrimination performance of Cs2LaLiBr6 single crystal detector with doping Y

The Cs2LaLiBr6 scintillation crystals doped with Y element (CLLB:Y) using non-stoichiometric raw material were grown by the vertical Bridgman method to improve the poor neutron/gamma discrimination performance of Cs2LiLaBr6:Ce (CLLB:Ce) crystals in elpasolite scintillation crystals. An excess of 100% LiBr raw material during crystal growth was added to prevent the incongruent melting phenomenon. XRD and TG-DSC measurements revealed that the Y-doped CLLB:Y scintillation crystal was successfully grown. The successful doping of the Y element was confirmed by EDS mapping and XRF in the meantime. At 0.662 MeV, the crystal has an energy resolution of 5.2%, with a fast decay component of 0.2∼0.23 μs and a slow decay component of 2.3∼2.5 μs. The CLLB:Y’s light output is approximately 67% of the CLLB:Ce, while its discrimination performance is significantly superior. 1.64 is the discrimination figure of merit for the charge comparison method. Single crystals can achieve complete neutron detection, improving neutron measurement and application.

Improving the performance of A-Not A sensory discrimination ratings by modifying sample presentation probability

Sensory discrimination analysis based on signal detection theory (SDT) deals with measuring small sensory differences between samples required for various business objectives, including quality control, reformulation, cost reduction, and product development. Variants of the A-Not A test designs have been used for SDT analysis using sensory panels to measure the sensory differences between a reference and multiple test products because they are economical and sensitive for such multiple product comparisons. On the other hand, the test protocols of conducting the A-Not A ratings affect the test performance and data quality. The present study examined the effects of equal sample presentation probability between reference vs test samples (0.5 reference presentation probability, 0.5 RPP) with and without informing a panel of RPP on the test performance of A-Not A and A-Not AR ratings using a reference with three test products. SDT analyses including the novel d'Rec analysis were used to examine these effects. The overall experiment consisted of three protocols: Control – 0.25 RPP without informing; Modified-1 protocol – 0.5 RPP without informing; Modified-2 protocol – 0.5 RPP with informing of the RPP. Compared to the Control, the Modified-1 protocol employing 0.5 RPP without informing improved discrimination performance significantly (higher d′ values) for the A-Not A ratings. Compared with the A-Not A ratings, the effects of the Modified-1 protocol were reduced for the A-Not AR ratings, showing the effects of reminders assisting the evaluations. The test instructions providing information of 0.5 RPP were inefficient. It shifted the panel’s middle decision criteria (c0) close to zero but did not improve the discrimination performance better than the Control. Overall, the efficiency of 0.5 RPP was confirmed using sensory panels for both A-Not A and A-Not A ratings, and it was shown that the novel d'Rec analysis is an efficient way to study the reasons for changes in a panel’s performance and diagnose the sensory data quality obtained from sensory panels.

Independent response modulation of visual cortical neurons by attentional and behavioral states

Sensory processing is influenced by cognitive and behavioral states, but how these states interact to modulate responses of individual neurons is unknown. We trained mice in a visual discrimination task wherein they attended to different locations within a hemifield while running or sitting still, enabling us to examine how visual responses are modulated by spatial attention and running behavior. We found that spatial attention improved discrimination performance and strengthened visual responses of excitatory neurons in the primary visual cortex whose receptive fields overlapped with the attended location. Although individual neurons were modulated by both spatial attention and running, the magnitudes of these influences were not correlated. While running-dependent modulation was stable across days, attentional modulation was dynamic, influencing individual neurons to different degrees after repeated changes in attentional states. Thus, despite similar effects on neural responses, spatial attention and running act independently with different dynamics, implying separable mechanisms for their implementation.

Refining the Lung Allocation Score Models Fails to Improve Discrimination Performance

As broader geographic sharing is implemented in lung transplant allocation through the Composite Allocation Score (CAS) system, models predicting waitlist and posttransplant (PT) survival will become more important in determining access to organs. How well do CAS survival models perform, and can discrimination performance be improved with alternative statistical models or machine learning approaches? Scientific Registry for Transplant Recipients (SRTR) data from 2015-2020 were used to build seven waitlist (WL) and data from 2010-2020 to build similar PT models. These included the (I) current lung allocation score (LAS)/CAS model; (II) re-estimated WL-LAS/CAS model; (III) model II incorporating nonlinear relationships; (IV) random survival forests model; (V) logistic model; (VI) linear discriminant analysis; and (VII) gradient-boosted tree model. Discrimination performance was evaluated at 1, 3, and 6months on the waiting list and 1, 3, and 5 years PT. Area under the curve (AUC) values were estimated across subgroups. WL model performance was similar across models with the greatest discrimination in the baseline cohort (AUC 0.93) and declined to 0.87-0.89 for 3-month and 0.84-0.85 for 6-month predictions and further diminished for residual cohorts. Discrimination performance for PT models ranged from AUC 0.58-0.61 and remained stable with increasing forecasting times but was slightly worse for residual cohorts. WL and PT variability in AUC was greatest for individuals with Medicaid insurance. Use of alternative modeling strategies and contemporary cohorts did not improve performance of models determining access to lung transplant.

Effect of Transcranial Electrical Stimulation over the Posterior Parietal Cortex on Tactile Spatial Discrimination Performance

The intraparietal sulcus region, which is part of the posterior parietal cortex (PPC), has been shown to play an important role in discriminating object shapes using the fingers. Transcranial random noise stimulation (tRNS) and anodal transcranial pulsed current stimulation (tPCS) are noninvasive strategies widely used to modulate neural activity in cortical regions. Therefore, we investigated the effects of tRNS and anodal tPCS applied to left or right PPC on the tactile discrimination performance of the right index finger in 20 neurologically healthy subjects. A grating orientation task (GOT) was performed before and immediately after delivering tRNS (stimulus frequency 0.1–640 Hz) in Experiment 1 or anodal tPCS (pulse width 50 ms and inter-pulse interval 5 ms) in Experiment 2. Performing tRNS over the right PPC significantly improved discrimination performance on the GOT. Subjects were classified into low and high baseline performance groups. Conducting tRNS over the left PPC significantly reduced the GOT discrimination performance in the high-performance group. By contrast, anodal tPCS delivered to the PPC of the left and right hemispheres had no significant effect on the tactile GOT discrimination performance of the right hand. We show that transcranial electric stimulation over the PPC may improve tactile perception but the effect depends on stimulus modality, parameters, and on the stimulated hemisphere.

The thrombodynamic ratio as a predictor of 28-day mortality in sepsis patients

BackgroundThe thrombodynamic ratio (TDR) as a composite thromboelastography (TEG) parameter, has been proven to be valuable in multiple diseases. However, the association between TDR and mortality in sepsis has not been studied. MethodsOne hundred forty-one patients were enrolled in this retrospectively study. TEG was performed immediately at admission. Two cox proportional hazards models were developed for the prediction of 28-day mortality. The C statistic, continuous net reclassification index (cNRI) and integrated discriminatory index (IDI) were calculated to compare the discrimination performance of clinical models with and without the TDR value. The integrated calibration index (ICI) and E50 were calculated to compare the calibration. ResultsPatients with lower TDR were more likely to have organ impairments and increased 28-day mortality. The TDR value improved discrimination performance in both Model 1 (C statistic, 0.745 vs 0.735; cNRI 19.4%, p = 0.044; IDI 5.6%, p = 0.012) and Model 2 (C statistic, 0.761 vs 0.751; IDI, 5.1%, p = 0.012). Compared to the calibration curve of Model 1 without TDR, addition of TDR displayed better calibration (ICI, 0.023; E50, 0.021). ConclusionTDR value significantly predicts 28-day mortality in patients with sepsis and could improve the discrimination and calibration performance of clinical prediction models.

Habitat Imaging-Based 18F-FDG PET/CT Radiomics for the Preoperative Discrimination of Non-small Cell Lung Cancer and Benign Inflammatory Diseases.

PurposeTo propose and evaluate habitat imaging-based 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) radiomics for preoperatively discriminating non-small cell lung cancer (NSCLC) and benign inflammatory diseases (BIDs).MethodsThree hundred seventeen 18F-FDG PET/CT scans were acquired from patients who underwent aspiration biopsy or surgical resection. All volumes of interest (VOIs) were semiautomatically segmented. Each VOI was separated into variant subregions, namely, habitat imaging, based on our adapted clustering-based habitat generation method. Radiomics features were extracted from these subregions. Three feature selection methods and six classifiers were applied to construct the habitat imaging-based radiomics models for fivefold cross-validation. The radiomics models whose features extracted by conventional habitat-based methods and nonhabitat method were also constructed. For comparison, the performances were evaluated in the validation set in terms of the area under the receiver operating characteristic curve (AUC). Pairwise t-test was applied to test the significant improvement between the adapted habitat-based method and the conventional methods.ResultsA total of 1,858 radiomics features were extracted. After feature selection, habitat imaging-based 18F-FDG PET/CT radiomics models were constructed. The AUC of the adapted clustering-based habitat radiomics was 0.7270 ± 0.0147, which showed significantly improved discrimination performance compared to the conventional methods (p <.001). Furthermore, the combination of features extracted by our adaptive habitat imaging-based method and non-habitat method showed the best performance than the other combinations.ConclusionHabitat imaging-based 18F-FDG PET/CT radiomics shows potential as a biomarker for discriminating NSCLC and BIDs, which indicates that the microenvironmental variations in NSCLC and BID can be captured by PET/CT.

The neural basis for violations of Weber’s law in self-motion perception

A prevailing view is that Weber's law constitutes a fundamental principle of perception. This widely accepted psychophysical law states that the minimal change in a given stimulus that can be perceived increases proportionally with amplitude and has been observed across systems and species in hundreds of studies. Importantly, however, Weber's law is actually an oversimplification. Notably, there exist violations of Weber's law that have been consistently observed across sensory modalities. Specifically, perceptual performance is better than that predicted from Weber's law for the higher stimulus amplitudes commonly found in natural sensory stimuli. To date, the neural mechanisms mediating such violations of Weber's law in the form of improved perceptual performance remain unknown. Here, we recorded from vestibular thalamocortical neurons in rhesus monkeys during self-motion stimulation. Strikingly, we found that neural discrimination thresholds initially increased but saturated for higher stimulus amplitudes, thereby causing the improved neural discrimination performance required to explain perception. Theory predicts that stimulus-dependent neural variability and/or response nonlinearities will determine discrimination threshold values. Using computational methods, we thus investigated the mechanisms mediating this improved performance. We found that the structure of neural variability, which initially increased but saturated for higher amplitudes, caused improved discrimination performance rather than response nonlinearities. Taken together, our results reveal the neural basis for violations of Weber's law and further provide insight as to how variability contributes to the adaptive encoding of natural stimuli with continually varying statistics.

A VGGNet-like approach for classifying and segmenting coal dust particles with overlapping regions

The Automatic extraction of coal particles characteristics has great importance in smart mine construction for security planning and disaster prevention. Traditional approaches, including visual interpretation, which requires manually outlining textures to describe particles, provide unclear texture characteristics due to the complexity of low-contrast grey particle imagery. Thus, a novel feature learning approach with a simplified VGGNet-like network is investigated to learn the characteristic details of complex spatial particle sample image sets. The sample data information includes 2000 particle images of four scenes acquired from a coal preparation plant. First, the particle overlapping regions are located by the detected feature points. Then particle swarms are separated with positioning-labels by their discriminative characteristics. Afterwards, feature classification by fully connected layers and image segmentation with up-sampling module introduced are realized based on improved VGGNet. Furthermore, particle sizes are evaluated over the hybrid particle distribution by characteristic learning. The experimental results demonstrate that, under the proper conditions, improved discrimination performance can be achieved by the proposed approach compared with that of other state-of-the-art approaches. The extraction performance can indeed be an effective reference to determine the particle size distribution (i.e., the granulometric analysis) of the sampled particulate.

Discrimination Improvement Through Undesirable Feedback in Coupling Object Manipulation Tasks.

Subjective effort can significantly affect the ability of humans to act optimally in dynamic manipulation tasks. In a previous study, we designed a complex object coupling manipulation task that required tight performance and induced high cognitive workload. We hypothesize that strong-effort-related physiological reactivity during the dynamic manipulation task improves the user performance in an undesired task feedback situation. To test this hypothesis, using the motor intentions' discrimination from electroencephalogram (EEG) measurements, we evaluate the effort expended by 20 participants in a controlling task with constraints involving complex coupling objects. Specifically, the finer motor decisions are obtained from the controlling information in EEG by using two fingers from the same hand rather than two hands. The motor intention is decoded from a task-dependent EEG through a regularized discriminant analysis, and the area under the curve is [Formula: see text]. Furthermore, we compare the undesired and desired task feedback conditions along with the individual's effort dynamic adjustment, and investigate whether the undesired task feedback improved the discrimination of the motor activities. A stronger effort to attain the desired feedback state corresponds to improved motor activity discrimination from the EEG in the undesired task feedback scenario. The differences in the brain activities under the undesired and desired task feedback conditions are analyzed using brain-network-based topographical scalp maps. Our experiment provides preliminary evidence that inducing strong effort can improve discrimination performance during highly demanding tasks. This finding can advance our understanding of human attention, potentially improve the accuracy of intention recognition, and may inspire better EEG acquisition contexts.

Machine-learning analysis of contrast-enhanced computed tomography radiomics predicts patients with hepatocellular carcinoma who are unsuitable for initial transarterial chemoembolization monotherapy: A multicenter study

IntroductionDue to the high heterogeneity of hepatocellular carcinoma (HCC), patients with non-advanced disease who are unsuitable for initial transarterial chemoembolization (TACE) monotherapy may have the potential to develop extrahepatic spread or vascular invasion. We aimed to develop and independently validate a radiomics-based model for predicting which patients will develop extrahepatic spread or vascular invasion after initial TACE monotherapy (EVIT). Materials and methodsThis retrospective study included 256 HCC patients (training set: n = 136; testing set: n = 120) who underwent TACE as initial therapy between April 2007 and June 2018. Clinicoradiological predictors were selected using multivariate logistic regression and a clinicoradiological model was constructed. The radiomic features were extracted from contrast-enhanced computed tomography (CT) images and a radiomics signature was constructed based on a machine learning algorithm. A combined model integrated clinicoradiological predictor and radiomics signature was developed. The predictive performance of the two models was evaluated and compared based on its discrimination, calibration, and clinical usefulness. ResultsIn the training set, 34 (25.0%) patients were confirmed to have EVIT, whereas 26 (21.7%) patients in the testing set had EVIT. When the radiomics signature was added, the combined model showed improved discrimination performance compared to the clinicoradiological model (area under the curves [AUCs] 0.911 vs. 0.772 in the training set; AUCs 0.847 vs. 0.746 in the testing set) and could divide HCC patients into three strata of low, intermediate, or high risk in the two sets. Decision curve analysis demonstrated that the two models were clinically useful, and the combined model provided greater benefits for discriminating patients than the clinicoradiological model. ConclusionsThis study presents a model that integrates clinicoradiological predictors and CT-based radiomics signature that could provide a preoperative individualized prediction of EVIT in patients with HCC.

Statistical approaches using longitudinal biomarkers for disease early detection: A comparison of methodologies.

Early detection of clinical outcomes such as cancer may be predicted using longitudinal biomarker measurements. Tracking longitudinal biomarkers as a way to identify early disease onset may help to reduce mortality from diseases like ovarian cancer that are more treatable if detected early. Two disease risk prediction frameworks, the shared random effects model (SREM) and the pattern mixture model (PMM) could be used to assess longitudinal biomarkers on disease early detection. In this article, we studied the discrimination and calibration performances of SREM and PMM on disease early detection through an application to ovarian cancer, where early detection using the risk of ovarian cancer algorithm (ROCA) has been evaluated. Comparisons of the above three approaches were performed via analyses of the ovarian cancer data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial. Discrimination was evaluated by the time-dependent receiver operating characteristic curve and its area, while calibration was assessed using calibration plot and the ratio of observed to expected number of diseased subjects. The out-of-sample performances were calculated via using leave-one-out cross-validation, aiming to minimize potential model overfitting. A careful analysis of using the biomarker cancer antigen 125 for ovarian cancer early detection showed significantly improved discrimination performance of PMM as compared with SREM and ROCA, nevertheless all approaches were generally well calibrated. Robustness of all approaches was further investigated in extensive simulation studies. The improved performance of PMM relative to ROCA is in part due to the fact that the biomarker measurements were taken at a yearly interval, which is not frequent enough to reliably estimate the changepoint or the slope after changepoint in cases under ROCA.

Ironic efficiency in automation-aided signal detection

Decision makers often make poor use of the information provided by an automated signal detection aid; recent studies have found that participants assisted by an automated aid fell well short of best-possible sensitivity levels. The present study tested the generalisability of this finding over varying levels of aid reliability. Participants performed a binary signal detection task either unaided or with assistance from a decision aid that was 60%, 85%, or 96%-reliable. Assistance from a highly reliable aid (85% or 96%) improved discrimination performance, while assistance from a low-reliability aid (60%) did not. Because their ideal strategy is to place less weight on less reliable cues, however, the decision makers’ tendency to disuse the aid became more appropriate as the aid’s reliability declined. Automation-aided efficiency was thus near to optimal when the aid was close to chance but became highly inefficient, ironically, as the aid’s reliability increased. Practitioner Summary: Investigating operators’ automation-aided information integration strategies allows human factors practitioners to predict the level of performance the operator will attain. Ironically, in an aided signal detection task, performance when assisted by a highly reliable aid is far less efficient than that obtained when assisted by a far less reliable aid. Abbreviations: OW: optimal weighting; UW: uniform weighting; CC: contingent criterion; BD: best decides; CF: coin flip; PM: probability matching; HDI: highest density interval; MCMC: markov chain monte carlo; HR: hit rate; FAR: false alarm rate