True Negative Ratio Research Articles

Personalized algorithmic pricing decision support tool for health insurance: The case of stratifying gestational diabetes mellitus into two groups

We propose a personalized algorithmic decision support (PADS) tool, facilitating premium pricing for pregnant women by accounting for the risk of gestational diabetes mellitus (GDM). The insurance premium with PADS is derived from true negative and positive ratios of machine learning algorithms. Hybrid sampling with uniform designs improves ML algorithm performance under unbalanced data. Feature selection approaches guarantee the accuracy and interpretability of the prediction models. PADS reduces the premium for most patients with a lower risk of GDM. A smaller fraction of patients will pay more premiums under PADS; however, they can benefit from an earlier GDM diagnosis.

Image Processing for Automatic Cell Nucleus Segmentation Using Super pixel and Clustering Methods on Histopathological Images

On a daily basis, it appears that the number of cancer cases and cancer-related deaths are increasing. Early detection and treatment of the malignant region are critical for successful treatment. Early detection of sick cells is made possible with the use of computer-assisted programmes, which are then diagnosed by experienced pathologists due to their efforts. Using computer-aided programmes, this research found that cell nuclei could be automatically detected in high-resolution histopathological images using global segmentation methods such as k-Means and Fuzzy C Means and algorithms from superpixel segmentation methods such as SLIC, Quick-shift, Felzenszwalb, Watershed, and ERS. Using high-quality histopathology pictures, the researchers discovered that the k-means and FCM algorithms performed significantly better than the baseline techniques in the study. In terms of precision, the Quickshift and SLIC approaches produced superior outcomes. The K-means and FCM algorithms perform best in the F-M test, and the true negative ratio is more successful in the Quickshift and SLIC methods than in the F-M test.

Deep-fading hole avoidance for secure region detection using channel state information

One of the critical challenges in many wireless systems is the deep fading hole problem where signals interfere destructively to create an abrupt change in signal amplitude due to multipath fading. In this work, we tackle this challenge in the context of secure region detection (SRD) problem. Specifically, we propose SHARD, a novel hole avoidance technique that analyzes channel state information (CSI) to significantly improve the accuracy of CSI-based SRD. SHARD identifies potential fading holes in CSI amplitude, and removes an unreliable portion of data while utilizing the remaining unaffected part. To compensate for the loss of information, we define phase-distance for reliable use of time-varying CSI phase, and neighboring reference points are utilized for accurate matching. Our real-world experiments show that SHARD can achieve a near-perfect 99.96% true-negative ratio (successfully rejecting devices not in the secure region) and an excellent true-positive of 98.01% for practical usage, significantly better than state-of-the-art prior work. We believe our ideas can be generalized to many RF-based localization systems to mitigate the deep fading hole problem and improve their accuracy.

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms.

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

TinyML-Based Concept System Used to Analyze Whether the Face Mask Is Worn Properly in Battery-Operated Conditions

As the COVID-19 pandemic emerged, everyone’s attention was brought to the topic of the health and safety of the entire human population. It has been proven that wearing a face mask can help limit the spread of the virus. Despite the enormous efforts of people around the world, there still exists a group of people that wear face masks incorrectly. In order to provide the best level of safety for everyone, face masks must be worn correctly, especially indoors, for example, in shops, cinemas and theaters. As security guards can only handle a limited area of the frequently visited objects, intelligent sensors can be used. In order to mount them on the shelves in the shops or near the cinema cash register queues, they need to be capable of battery operation. This restricts the sensor to be as energy-efficient as possible, in order to prolong the battery life of such devices. The cost is also a factor, as cheaper devices will result in higher accessibility. An interesting and quite novel approach that can answer all these challenges is a TinyML system, that can be defined as a combination of two concepts: Machine Learning (ML) and Internet of Things (IoT). The TinyML approach enables the usage of ML algorithms on boards equipped with low-cost, low-power microcontrollers without sacrificing the classifier quality. The main goal of this paper is to propose a battery-operated TinyML system that can be used for verification whether the face mask is worn properly. To this end, we carefully analyze several ML approaches to find the best method for the considered task. After detailed analysis of computation and memory complexity as well as after some preliminary experiments, we propose to apply the K-means algorithm with carefully designed filters and a sliding window technique, since this method provides high accuracy with the required energy-efficiency for the considered classification problem related to verification of using the face mask. The STM32F411 chip is selected as the best microcontroller for the considered task. Next, we perform wide experiments to verify the proposed ML framework implemented in the selected hardware platform. The obtained results show that the developed ML-system offers satisfactory performance in terms of high accuracy and lower power consumption. It should be underlined that the low-power aspect makes it possible to install the proposed system in places without the access to power, as well as reducing the carbon footprint of AI-focused industry which is not negligible. Our proposed TinyML system solution is able to deliver very high-quality metric values with accuracy, True Positive Ratio (TPR), True Negative Ratio (TNR), precision and recall being over 96% for masked face classification while being able to reach up to 145 days of uptime using a typical 18650 battery with capacity of 2500 mAh and nominal voltage of 3.7 V. The results are obtained using a STM32F411 microcontroller with 100 MHz ARM Cortex M4, which proves that execution of complex computer vision tasks is possible on such low-power devices. It should be noted that the STM32F411 microcontroller draws only 33 mW during operation.

Comparison of Various Classification Techniques for Prediction of the Agriculture Production Based on Different Parameters Rainfall, Temperature

The classification techniques based on various machine learning techniques are having use for the Big data analysis. This will be useful in identifying the classification and then finally the prediction which will be useful for the decision managers for having quality decisions. There are various types of supervised and unsupervised learning techniques which are having capabilities in the terms of driving the analysis. This analysis will be useful for having identification of relationship between the various attributes which is required to device the analysis. There are various supervised learning techniques which are useful to drive the analysis. These techniques are SVM, Logistic regression, KNN, Naïve Bayes, Tree, Neural network. The relative comparison of this technique is done in the terms of various parameters for example AUC, CA, F1, Recall and precision. The accuracy in the terms of AUC, CA is highest for the Naïve Bayes. This shows the Naïve Bayes is having higher true positives, true negative ratio. The proposed technique is having higher accuracy of 81% which is far above than all the remaining techniques. The confusion matrix for the Naïve Bayes is having true positive count as 729, true negative at 103. This shows that the true positive and true negative count is far above for this technique compared to the other techniques.

Severity assessment of COVID-19 using CT image features and laboratory indices

The coronavirus disease 2019 (COVID-19) is now a global pandemic. Tens of millions of people have been confirmed with infection, and also more people are suspected. Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of chest CT images increases rapidly, manual severity assessment becomes a labor-intensive task, delaying appropriate isolation and treatment. In this paper, a study of automatic severity assessment for COVID-19 is presented. Specifically, chest CT images of 118 patients (age 46.5 ± 16.5 years, 64 male and 54 female) with confirmed COVID-19 infection are used, from which 63 quantitative features and 110 radiomics features are derived. Besides the chest CT image features, 36 laboratory indices of each patient are also used, which can provide complementary information from a different view. A random forest (RF) model is trained to assess the severity (non-severe or severe) according to the chest CT image features and laboratory indices. Importance of each chest CT image feature and laboratory index, which reflects the correlation to the severity of COVID-19, is also calculated from the RF model. Using three-fold cross-validation, the RF model shows promising results: 0.910 (true positive ratio), 0.858 (true negative ratio) and 0.890 (accuracy), along with AUC of 0.98. Moreover, several chest CT image features and laboratory indices are found to be highly related to COVID-19 severity, which could be valuable for the clinical diagnosis of COVID-19.

A Method for Human Facial Image Annotation on Low Power Consumption Autonomous Devices.

This paper proposes a classifier designed for human facial feature annotation, which is capable of running on relatively cheap, low power consumption autonomous microcomputer systems. An autonomous system is one that depends only on locally available hardware and software—for example, it does not use remote services available through the Internet. The proposed solution, which consists of a Histogram of Oriented Gradients (HOG) face detector and a set of neural networks, has comparable average accuracy and average true positive and true negative ratio to state-of-the-art deep neural network (DNN) architectures. However, contrary to DNNs, it is possible to easily implement the proposed method in a microcomputer with very limited RAM memory and without the use of additional coprocessors. The proposed method was trained and evaluated on a large 200,000 image face data set and compared with results obtained by other researchers. Further evaluation proves that it is possible to perform facial image attribute classification using the proposed algorithm on incoming video data captured by an RGB camera sensor of the microcomputer. The obtained results can be easily reproduced, as both the data set and source code can be downloaded. Developing and evaluating the proposed facial image annotation algorithm and its implementation, which is easily portable between various hardware and operating systems (virtually the same code works both on high-end PCs and microcomputers using the Windows and Linux platforms) and which is dedicated for low power consumption devices without coprocessors, is the main and novel contribution of this research.

A Dynamic and Combined Phishing Detection Technique

With the quick advancement of web applications, internet users are spending more and more time with these applications .They utilize the benefits of the internet in doing all the day-to-day chores from reading newspaper to grocery shopping .This makes them prone to various kinds of cyber-attacks such as phishing , password attack , malwares etc...Phishing is one of the most common cyber-attack which is made by the attackers to take the users’ delicate data . In phishing attack the users are first tempted with attractive offers and are then redirected to illegitimate (phishing) websites which ask for their credentials .In spite of the alert and awareness spread against these types of cyber-attacks , people continue to fall prey and get affected .The attackers have evolved with time and craft the attacks in such a way that the phishing websites and emails may seem real .Many systems and algorithms have been developed to predict phishing attacks .However ,the achievement rate of phishing attacks stays high and it’s detection is prone towards high true negative and false positive ratio. Therefore ,to deal with this conundrum we are putting forward a generalized algorithm for phishing detection with improved accuracy.

AppPerm Analyzer: Malware Detection System Based on Android Permissions and Permission Groups

Besides the applications aimed at increasing the efficiency of the Android mobile devices, also many malicious applications, millions of Android malware according to various security company reports, are being developed and uploaded into the application stores. In order to detect those applications, a malicious Android application detection system based on permission and permission groups namely, AppPerm Analyzer has been developed. The AppPerm Analyzer software extracts the manifest and code permissions of analyzed applications, creates duple and triple permission groups from them, calculates risk scores of these permissions and permission groups according to their usage rates in malicious and benign applications and calculates the total risk score of the analyzed application. After training the software with 7776 applications in total, it is tested with 1664 benign and 1664 malicious applications. In the tests, AppPerm Analyzer detected malicious applications with an accuracy of 96.19% at most. At this point, sensitivity (true-positive ratio) is 95.50% and specificity (true-negative ratio) is 96.88%. If a false-positive ratio up to 10% is accepted, the sensitivity increases to 99.04%.

Asset restructuring performance prediction for failure firms

AbstractThis study aims to forecast asset restructuring performance for failing public firms and to test the effectiveness of different strategies of assets restructuring by using ten models, including: standalone models of multivariate discriminant analysis (MDA), logistic regression (Logit), probit, case‐based reasoning (CBR), support vector machine (SVM), and their bagged ensembles. Moreover, this study proposes a knowledge base by collecting positive and negative samples and uses random down‐sampling method to pair success samples with failure samples in order to focus more on real‐happened failure samples when forming a balanced data set. After variables filtering process, ten financial ratios, covering aspects of debt‐paying, risk level, development, and operating abilities, are identified as significantly efficient predictors. The following empirical results are found, namely (a) adopting more means of asset restructuring leads to a higher chance for performance improvement; (b) equity transfer, asset stripping, and asset acquisition are the three most commonly used means, and the last two are among the most efficient means; (c) compared to the other 9 models, SVM has the most balanced prediction performance in terms of total accuracy, true positive ratio, and true negative ratio; and (d) predicting a failing event of achieving performance improvement with asset restructuring is more difficult than predicting a successful event, which needs more focus with the state‐of‐the‐art models.

A holistic multi-objective optimization design procedure for ensemble member generation and selection

In the last few years, machine learning techniques have been successfully applied to solve engineering problems. However, owing to certain complexities found in real-world problems, such as class imbalance, classical learning algorithms may not reach a prescribed performance. There can be situations where a good result on different conflicting objectives is desirable, such as true positive and true negative ratios, or it is important to balance model’s complexity and prediction score. To solve such issues, the application of multi-objective optimization design procedures can be used to analyze various trade-offs and build more robust machine learning models. Thus, the creation of ensembles of predictive models using such procedures is addressed in this work. First, a set of diverse predictive models is built by employing a multi-objective evolutionary algorithm. Next, a second multi-objective optimization step selects the previous models as ensemble members, resulting on several non-dominated solutions. A final multi-criteria decision making stage is applied to rank and visualize the resulting ensembles. To analyze the proposed methodology, two different experiments are conducted for binary classification. The first case study is a famous classification problem through which the proposed procedure is illustrated. The second one is a challenging real-world problem related to water quality monitoring, where the proposed procedure is compared to four classical ensemble learning algorithms. Results on this second experiment show that the proposed technique is able to create robust ensembles that can outperform other ensemble methods. Overall, the authors conclude that the proposed methodology for ensemble generation creates competitive models for real-world engineering problems.

Automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms.

The analysis of cell characteristics from high-resolution digital histopathological images is the standard clinical practice for the diagnosis and prognosis of cancer. Yet, it is a rather exhausting process for pathologists to examine the cellular structures manually in this way. Automating this tedious and time-consuming process is an emerging topic of the histopathological image-processing studies in the literature. This paper presents a two-stage segmentation method to obtain cellular structures in high-dimensional histopathological images of renal cell carcinoma. First, the image is segmented to superpixels with simple linear iterative clustering (SLIC) method. Then, the obtained superpixels are clustered by the state-of-the-art clustering-based segmentation algorithms to find similar superpixels that compose the cell nuclei. Furthermore, the comparison of the global clustering-based segmentation methods and local region-based superpixel segmentation algorithms are also compared. The results show that the use of the superpixel segmentation algorithm as a pre-segmentation method improves the performance of the cell segmentation as compared to the simple single clustering-based segmentation algorithm. The true positive ratio (TPR), true negative ratio (TNR), F-measure, precision, and overlap ratio (OR) measures are utilized as segmentation performance evaluation. The computation times of the algorithms are also evaluated and presented in the study. Graphical Abstract The visual flowchart of the proposed automatic cell segmentation in histopathological images via two-staged superpixel-based algorithms.

Validating a Predictive Atlas of Tumor Shrinkage for Adaptive Radiotherapy of Locally Advanced Lung Cancer

To cross-validate and expand a predictive atlas that can estimate geometric patterns of lung tumor shrinkage during radiation therapy using data from 2 independent institutions and to model its integration into adaptive radiation therapy (ART) for enhanced dose escalation. Data from 22 patients at a collaborating institution were obtained to cross-validate an atlas, originally created with 12 patients, for predicting patterns of tumor shrinkage during radiation therapy. Subsequently, the atlas was expanded by integrating all 34 patients. Each study patient was selected via a leave-one-out scheme and was matched with a subgroup of the remaining 33 patients based on similarity measures of tumor volume and surroundings. The spatial distribution of residual tumor was estimated by thresholding the superimposed shrinkage patterns in the subgroup. A Bayesian method was also developed to recalibrate the prediction using the tumor observed on the midcourse images. Finally, in a retrospective predictive treatment planning (PTP) study, at the initial planning stage, the predicted residual tumors were escalated to the highest achievable dose while maintaining the original prescription dose to the remainder of the tumor. The PTP approach was compared isotoxically to ART that replans with midcourse imaging and to PTP-ART with the recalibrated prediction. Predictive accuracy (true positive plus true negative ratios based on predicted and actual residual tumor) were comparable across institutions, 0.71 versus 0.73, and improved to 0.74 with an expanded atlas including 2 institutions. Recalibration further improved accuracy to 0.76. PTP increased the mean dose to the actual residual tumor by an averaged 6.3Gy compared to ART. A predictive atlas found to perform well across institutions and benefit from more diversified shrinkage patterns and tumor locations. Elevating tumoricidal dose to the predicted residual tumor throughout the entire treatment course could improve the efficacy and efficiency of treatment compared to ART with midcourse replanning.

Comparison of Three Segmentation Methods for Breast Ultrasound Images based on Level Set and Morphological Operations

Breast cancer is one of the major causes of death among women all over the world. The most frequently used diagnosis tool to detect breast cancer is ultrasound. However, to segment the breast ultrasound images is a difficult thing. Some studies show that the active contour models have been proved to be the most successful methods for medical image segmentation. The level set method is a class of curve evolution methods based on the geometric active contour model. Morphological operation describes a range of image processing technique that deal with the shape of features in an image. Morphological operations are applied to remove imperfections that introduced during segmentation. In this paper, we have evaluated three level set methods that combined with morphological operations to segment the breast lesions. The level set methods that used in our research are the Chan Vese (C-V) model, the Selective Binary and Gaussian Filtering Regularized Level Set (SBGFRLS) model and the Distance Regularized Level Set Evolution (DRLSE) model. Furthermore, to evaluate the method, we compared the segmented breast lesion that obtained by each method with the lesion that obtained manually by radiologists. The evaluation is done by four metrics: Dice Similarity Coefficient (DSC), True-Positive Ratio (TPR), True-Negative Ratio (TNR), and Accuracy (ACC). Our experimental results with 30 breast ultrasound images showed that the C-V model that combined with morphological operations have better performance than the other two methods according to mean value of DSC metrics.

Life-threatening false alarm rejection in ICU: using the rule-based and multi-channel information fusion method

False alarm (FA) rates as high as 86% have been reported in intensive care unit monitors. High FA rates decrease quality of care by slowing staff response times while increasing patient burdens and stresses. In this study, we proposed a rule-based and multi-channel information fusion method for accurately classifying the true or false alarms for five life-threatening arrhythmias: asystole (ASY), extreme bradycardia (EBR), extreme tachycardia (ETC), ventricular tachycardia (VTA) and ventricular flutter/fibrillation (VFB). The proposed method consisted of five steps: (1) signal pre-processing, (2) feature detection and validation, (3) true/false alarm determination for each channel, (4) ‘real-time’ true/false alarm determination and (5) ‘retrospective’ true/false alarm determination (if needed). Up to four signal channels, that is, two electrocardiogram signals, one arterial blood pressure and/or one photoplethysmogram signal were included in the analysis. Two events were set for the method validation: event 1 for ‘real-time’ and event 2 for ‘retrospective’ alarm classification. The results showed that 100% true positive ratio (i.e. sensitivity) on the training set were obtained for ASY, EBR, ETC and VFB types, and 94% for VTA type, accompanied by the corresponding true negative ratio (i.e. specificity) results of 93%, 81%, 78%, 85% and 50% respectively, resulting in the score values of 96.50, 90.70, 88.89, 92.31 and 64.90, as well as with a final score of 80.57 for event 1 and 79.12 for event 2. For the test set, the proposed method obtained the score of 88.73 for ASY, 77.78 for EBR, 89.92 for ETC, 67.74 for VFB and 61.04 for VTA types, with the final score of 71.68 for event 1 and 75.91 for event 2.

A novel image recuperation approach for diagnosing and ranking retinopathy disease level using diabetic fundus image.

Retinal fundus images are widely used in diagnosing and providing treatment for several eye diseases. Prior works using retinal fundus images detected the presence of exudation with the aid of publicly available dataset using extensive segmentation process. Though it was proved to be computationally efficient, it failed to create a diabetic retinopathy feature selection system for transparently diagnosing the disease state. Also the diagnosis of diseases did not employ machine learning methods to categorize candidate fundus images into true positive and true negative ratio. Several candidate fundus images did not include more detailed feature selection technique for diabetic retinopathy. To apply machine learning methods and classify the candidate fundus images on the basis of sliding window a method called, Diabetic Fundus Image Recuperation (DFIR) is designed in this paper. The initial phase of DFIR method select the feature of optic cup in digital retinal fundus images based on Sliding Window Approach. With this, the disease state for diabetic retinopathy is assessed. The feature selection in DFIR method uses collection of sliding windows to obtain the features based on the histogram value. The histogram based feature selection with the aid of Group Sparsity Non-overlapping function provides more detailed information of features. Using Support Vector Model in the second phase, the DFIR method based on Spiral Basis Function effectively ranks the diabetic retinopathy diseases. The ranking of disease level for each candidate set provides a much promising result for developing practically automated diabetic retinopathy diagnosis system. Experimental work on digital fundus images using the DFIR method performs research on the factors such as sensitivity, specificity rate, ranking efficiency and feature selection time.

Application and Development of Review Criteria on Sysmex XT-2100 in Chinese at a Large Third-Grade Class-A Hospital

Hematology analysis is an essential component of patient assessment and used in screening, diagnosis, and the planning of care. The objective of the study was to find out the suitable hematology review criteria for large scale general hospitals in China via the analysis of experimental data from Sysmex XE-2100 hematology analyzer. A total 1486 blood samples were detected with the Sysmes XE-2100. Based on hematology review criteria suggested by international consensus group and a positive smear finding new optimal review rules were determined. With the International Article 41 Review Rules, the true positive ratio (TP), the false positive ratio (FP), the true negative ratio (TN), and the false negative ratio (FN) was 14.0% (208/1486), 31.49% (468/1486) 52.42% (779/1486), and 2.09% (31/1486), respectively. With the help of Laboman 4.2 software (the Sysmex Corporation), 19 rules for review of automated CBC and WBC differential were set up. With our review rules, the TP, FP, TN, and FN was 13.86% (206/1486), 25.17% (374/1486), 58.75% (873/1486) and 2.22% (33/1486), respectively. The review rules were validated, the FN was 0.96%, blasts and immature cells were not omitted. The review criteria can be developed in light of the rules of the International Consensus Group for Hematology Review, but should be improved depending on different laboratory's requirements.

Review criteria for automated complete blood count and WBC differential analysis by Sysmex XE-2100 hematology analyzer

Objective To find out suitable hematology review criteria for Chinese population via analysis of experimental data from Sysmex XE-2100 hematology analyzer. Methods The total 3 594 patient samples were randomly detected in three hospitals respectively with automated hematology analyzer XE-2100 and blood smear was reviewed including observation of cell morphology and manual WBC differential analysis. Base on hematology review criteria suggested by international consensus group, we evaluated true positive ratio(TP), false positive ratio (FP), true negative ratio (TN) and false negative ratio (FN) as well as prevalence for smear review, we finalized optimal program. Results According to the items of International Consensus Review Rules and Slide Review Rule proposed by international hematology expert group, TP, FP, TN and FN were 14.02% (504/ 3 594), 32.67% ( 1 174/3 594), 51.47% ( 1 850/3 594) and 1.84% (66/3 594), respectively. Because reference range of Chinese peripheral blood was different from Western people and 3 594 specimen data were analyzed by using revised review criteria ( Chapter Ⅷ ) and microscopic smear review. The TP, FP, TN and FN were 12.33% (443/3 594), 21.01% (755/3 594), 63.44% (2 280/ 3 594) and 3.23% (116/3 594) accordingly. On basis of above 41 items of International Consensus Review Rules, performance, characteristic of XE-2100 and Chinese laboratory situation, we put forward criteria for slide review following automated CBC and WBC differential analysis in XE-2100 hematology analyzer, which was more suitable for population in China. The validation result demonstrated that no blast cell and immature cell was missed. Conclusions It's very important in establishing applied criteria for slide review following automated CBC and WBC differential analysis to assure quality of hematology results. It can enhance work efficiency and reduce unnecessary labor consuming. The criteria should be improved in laboratory practice. Key words: Blood cell count; Leukocyte count; Diagnostic equipment; Autoanalysis; Specimen handling; Evaluation studies

Accuracy of multidetector spiral computed tomography in detecting significant coronary stenosis in patient populations with differing pre-test probabilities of disease

To investigate the clinical impact of multidetector computed tomography (MDCT) in patients with a low versus a high pre-test likelihood of coronary artery disease (CAD). A cohort of 120 patients with suspected CAD, scheduled for conventional coronary angiography, underwent MDCT. Using the American Heart Association (AHA)/American College of Cardiology (ACC) guidelines, the population was divided into two groups: patients with a low (group 1) and a high (group 2) likelihood of CAD. Analysis of all segments showed a high feasibility (92%), and a patient based-model showed excellent sensitivity and negative predictive values (NPV; both 100%) and acceptable specificity and positive predictive values (PPV; 86 and 90%, respectively), with an accuracy of 94%. Using MDCT in patients with lower pre-test likelihoods of CAD, according to the ACC/AHA guidelines, the accuracy remained high (93%); conversely, in patient groups with a high prevalence of CAD, a non-significant reduction in accuracy (85%) occurred using MDCT. Particularly, MDCT can be used effectively to exclude a diagnosis of CAD because of its high sensitivity and NPV (100%), but shows a significant reduction in specificity (58%). This reduction was due to an increase in the false-positive:true-negative ratio because of the higher percentage of calcified plaque (a relative but non-significant increase in false positives), and the high prevalence of CAD (significant reduction in true negatives). No differences were found between MDCT and quantitative coronary angiography (QCA) concerning the number of vessels narrowed. Because of its excellent sensitivity and specificity in patients with a low pre-test likelihood of CAD, MDCT could be helpful in clinical decision-making in this population.