test accuracy
Recently Published Documents





Rajeev Kumar Gupta ◽  
Nilesh Kunhare ◽  
Rajesh Kumar Pateriya ◽  
Nikhlesh Pathik

The novel Covid-19 is one of the leading cause of death worldwide in the year 2020 and declared as a pandemic by world health organization (WHO). This virus affecting all countries across the world and 5 lakh people die as of June 2020 due to Covid-19. Due to the highly contagious nature, early detection of this virus plays a vital role to break Covid chain. Recent studies done by China says that chest CT and X-Ray image may be used as a preliminary test for Covid detection. Deep learning-based CNN model can use to detect Coronavirus automatically from the chest X-rays images. This paper proposed a transfer learning-based approach to detect Covid disease. Due to the less number of Covid chest images, we are using a pre-trained model to classify X-ray images into Covid and Normal class. This paper presents the comparative study of a various pre-trained model like VGGNet-19, ResNet50 and Inception_ResNet_V2. Experiment results show that Inception_ResNet_V2 gives the better result as compare to VGGNet and ResNet model with training and test accuracy of 99.26 and 94, respectively.

Ratna Patil ◽  
Sharvari Tamane ◽  
Shitalkumar Adhar Rawandale ◽  
Kanishk Patil

<p>Diabetes mellitus is a chronic disease that affects many people in the world badly. Early diagnosis of this disease is of paramount importance as physicians and patients can work towards prevention and mitigation of future complications. Hence, there is a necessity to develop a system that diagnoses type 2 diabetes mellitus (T2DM) at an early stage. Recently, large number of studies have emerged with prediction models to diagnose T2DM. Most importantly, published literature lacks the availability of multi-class studies. Therefore, the primary objective of the study is development of multi-class predictive model by taking advantage of routinely available clinical data in diagnosing T2DM using machine learning algorithms. In this work, modified mayfly-support vector machine is implemented to notice the prediabetic stage accurately. To assess the effectiveness of proposed model, a comparative study was undertaken and was contrasted with T2DM prediction models developed by other researchers from last five years. Proposed model was validated over data collected from local hospitals and the benchmark PIMA dataset available on UCI repository. The study reveals that modified Mayfly-SVM has a considerable edge over metaheuristic optimization algorithms in local as well as global searching capabilities and has attained maximum test accuracy of 94.5% over PIMA.</p>

2022 ◽  
Vol 11 (1) ◽  
Yuelun Zhang ◽  
Siyu Liang ◽  
Yunying Feng ◽  
Qing Wang ◽  
Feng Sun ◽  

Abstract Background Systematic review is an indispensable tool for optimal evidence collection and evaluation in evidence-based medicine. However, the explosive increase of the original literatures makes it difficult to accomplish critical appraisal and regular update. Artificial intelligence (AI) algorithms have been applied to automate the literature screening procedure in medical systematic reviews. In these studies, different algorithms were used and results with great variance were reported. It is therefore imperative to systematically review and analyse the developed automatic methods for literature screening and their effectiveness reported in current studies. Methods An electronic search will be conducted using PubMed, Embase, ACM Digital Library, and IEEE Xplore Digital Library databases, as well as literatures found through supplementary search in Google scholar, on automatic methods for literature screening in systematic reviews. Two reviewers will independently conduct the primary screening of the articles and data extraction, in which nonconformities will be solved by discussion with a methodologist. Data will be extracted from eligible studies, including the basic characteristics of study, the information of training set and validation set, and the function and performance of AI algorithms, and summarised in a table. The risk of bias and applicability of the eligible studies will be assessed by the two reviewers independently based on Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Quantitative analyses, if appropriate, will also be performed. Discussion Automating systematic review process is of great help in reducing workload in evidence-based practice. Results from this systematic review will provide essential summary of the current development of AI algorithms for automatic literature screening in medical evidence synthesis and help to inspire further studies in this field. Systematic review registration PROSPERO CRD42020170815 (28 April 2020).

BMC Medicine ◽  
2022 ◽  
Vol 20 (1) ◽  
Jane P. Daniels ◽  
Emily Dixon ◽  
Alicia Gill ◽  
Jon Bishop ◽  
Mark Wilks ◽  

Abstract Background Mother-to-baby transmission of group B Streptococcus (GBS) is the main cause of early-onset infection. We evaluated whether, in women with clinical risk factors for early neonatal infection, the use of point-of-care rapid intrapartum test to detect maternal GBS colonisation reduces maternal antibiotic exposure compared with usual care, where antibiotics are administered due to those risk factors. We assessed the accuracy of the rapid test in diagnosing maternal GBS colonisation, against the reference standard of selective enrichment culture. Methods We undertook a parallel-group cluster randomised trial, with nested test accuracy study and microbiological sub-study. UK maternity units were randomised to a strategy of rapid test (GeneXpert GBS system, Cepheid) or usual care. Within units assigned to rapid testing, vaginal-rectal swabs were taken from women with risk factors for vertical GBS transmission in established term labour. The trial primary outcome was the proportion of women receiving intrapartum antibiotics to prevent neonatal early-onset GBS infection. The accuracy of the rapid test was compared against the standard of selective enrichment culture in diagnosing maternal GBS colonisation. Antibiotic resistance profiles were determined in paired maternal and infant samples. Results Twenty-two maternity units were randomised and 20 were recruited. A total of 722 mothers (749 babies) participated in rapid test units; 906 mothers (951 babies) were in usual care units. There was no evidence of a difference in the rates of intrapartum antibiotic prophylaxis (relative risk 1.16, 95% CI 0.83 to 1.64) between the rapid test (41%, 297/716) and usual care (36%, 328/906) units. No serious adverse events were reported. The sensitivity and specificity measures of the rapid test were 86% (95% CI 81 to 91%) and 89% (95% CI 85 to 92%), respectively. Babies born to mothers who carried antibiotic-resistant Escherichia coli were more likely to be colonised with antibiotic-resistant strains than those born to mothers with antibiotic-susceptible E. coli. Conclusion The use of intrapartum rapid test to diagnose maternal GBS colonisation did not reduce the rates of antibiotics administered for preventing neonatal early-onset GBS infection than usual care, although with considerable uncertainty. The accuracy of the rapid test is within acceptable limits. Trial registration ISRCTN74746075. Prospectively registered on 16 April 2015

2022 ◽  
Vol 2022 (1) ◽  
Jing Lin ◽  
Laurent L. Njilla ◽  
Kaiqi Xiong

AbstractDeep neural networks (DNNs) are widely used to handle many difficult tasks, such as image classification and malware detection, and achieve outstanding performance. However, recent studies on adversarial examples, which have maliciously undetectable perturbations added to their original samples that are indistinguishable by human eyes but mislead the machine learning approaches, show that machine learning models are vulnerable to security attacks. Though various adversarial retraining techniques have been developed in the past few years, none of them is scalable. In this paper, we propose a new iterative adversarial retraining approach to robustify the model and to reduce the effectiveness of adversarial inputs on DNN models. The proposed method retrains the model with both Gaussian noise augmentation and adversarial generation techniques for better generalization. Furthermore, the ensemble model is utilized during the testing phase in order to increase the robust test accuracy. The results from our extensive experiments demonstrate that the proposed approach increases the robustness of the DNN model against various adversarial attacks, specifically, fast gradient sign attack, Carlini and Wagner (C&W) attack, Projected Gradient Descent (PGD) attack, and DeepFool attack. To be precise, the robust classifier obtained by our proposed approach can maintain a performance accuracy of 99% on average on the standard test set. Moreover, we empirically evaluate the runtime of two of the most effective adversarial attacks, i.e., C&W attack and BIM attack, to find that the C&W attack can utilize GPU for faster adversarial example generation than the BIM attack can. For this reason, we further develop a parallel implementation of the proposed approach. This parallel implementation makes the proposed approach scalable for large datasets and complex models.

2022 ◽  
Vol 12 (2) ◽  
pp. 717
Sahar Alwadei ◽  
Ashraf Farahat ◽  
Moataz Ahmed ◽  
Harry D. Kambezidis

Data from a moderate resolution imaging spectroradiometer instrument onboard the Terra satellite along with a radiative transfer model and a machine learning technique were integrated to predict direct solar irradiance on a horizontal surface over the Arabian Peninsula (AP). In preparation for building appropriate residual network (ResNet) prediction models, we conducted some exploratory data analysis (EDA) and came to some conclusions. We noted that aerosols in the atmosphere correlate with solar irradiance in the eastern region of the AP, especially near the coastlines of the Arabian Gulf and the Sea of Oman. We also found low solar irradiance during March 2016 and March 2017 in the central (~20% less) and eastern regions (~15% less) of the AP, which could be attributed to the high frequency of dust events during those months. Compared to other locations in the AP, high solar irradiance was recorded in the Rub Al Khali desert during winter and spring. The effect of major dust outbreaks over the AP during March 2009 and March 2012 was also noted. The EDA indicated a correlation between high aerosol loading and a decrease in solar irradiance. The analysis showed that the Rub Al Khali desert is one of the best locations in the AP to harvest solar radiation. The analysis also showed the ResNet prediction model achieves high test accuracy scores, indicated by a mean absolute error of ~0.02, a mean squared error of ~0.005, and an R2 of 0.99.

2022 ◽  
Vol 12 (1) ◽  
Jeewoo Yoon ◽  
Jinyoung Han ◽  
Junseo Ko ◽  
Seong Choi ◽  
Ji In Park ◽  

AbstractCentral serous chorioretinopathy (CSC) is the fourth most common retinopathy and can reduce quality of life. CSC is assessed using optical coherence tomography (OCT), but deep learning systems have not been used to classify CSC subtypes. This study aimed to build a deep learning system model to distinguish CSC subtypes using a convolutional neural network (CNN). We enrolled 435 patients with CSC from a single tertiary center between January 2015 and January 2020. Data from spectral domain OCT (SD-OCT) images of the patients were analyzed using a deep CNN. Five-fold cross-validation was employed to evaluate the model’s ability to discriminate acute, non-resolving, inactive, and chronic atrophic CSC. We compared the performances of the proposed model, Resnet-50, Inception-V3, and eight ophthalmologists. Overall, 3209 SD-OCT images were included. The proposed model showed an average cross-validation accuracy of 70.0% (95% confidence interval [CI], 0.676–0.718) and the highest test accuracy was 73.5%. Additional evaluation in an independent set of 104 patients demonstrated the reliable performance of the proposed model (accuracy: 76.8%). Our model could classify CSC subtypes with high accuracy. Thus, automated deep learning systems could be useful in the classification and management of CSC.

2022 ◽  
pp. 096228022110651
Mohammed Baragilly ◽  
Brian Harvey Willis

Tailored meta-analysis uses setting-specific knowledge for the test positive rate and disease prevalence to constrain the possible values for a test's sensitivity and specificity. The constrained region is used to select those studies relevant to the setting for meta-analysis using an unconstrained bivariate random effects model (BRM). However, sometimes there may be no studies to aggregate, or the summary estimate may lie outside the plausible or “applicable” region. Potentially these shortcomings may be overcome by incorporating the constraints in the BRM to produce a constrained model. Using a penalised likelihood approach we developed an optimisation algorithm based on co-ordinate ascent and Newton-Raphson iteration to fit a constrained bivariate random effects model (CBRM) for meta-analysis. Using numerical examples based on simulation studies and real datasets we compared its performance with the BRM in terms of bias, mean squared error and coverage probability. We also determined the ‘closeness’ of the estimates to their true values using the Euclidian and Mahalanobis distances. The CBRM produced estimates which in the majority of cases had lower absolute mean bias and greater coverage probability than the BRM. The estimated sensitivities and specificity for the CBRM were, in general, closer to the true values than the BRM. For the two real datasets, the CBRM produced estimates which were in the applicable region in contrast to the BRM. When combining setting-specific data with test accuracy meta-analysis, a constrained model is more likely to yield a plausible estimate for the sensitivity and specificity in the practice setting than an unconstrained model.

2022 ◽  
Vol 12 (1) ◽  
Teruhiko Terasawa ◽  
Satoyo Hosono ◽  
Seiju Sasaki ◽  
Keika Hoshi ◽  
Yuri Hamashima ◽  

AbstractTo compare all available accuracy data on screening strategies for identifying cervical intraepithelial neoplasia grade ≥ 2 in healthy asymptomatic women, we performed a systematic review and network meta-analysis. MEDLINE and EMBASE were searched up to October 2020 for paired-design studies of cytology and testing for high-risk genotypes of human papillomavirus (hrHPV). The methods used included a duplicate assessment of eligibility, double extraction of quantitative data, validity assessment, random-effects network meta-analysis of test accuracy, and GRADE rating. Twenty-seven prospective studies (185,269 subjects) were included. The combination of cytology (atypical squamous cells of undetermined significance or higher grades) and hrHPV testing (excepting genotyping for HPV 16 or 18 [HPV16/18]) with the either-positive criterion (OR rule) was the most sensitive/least specific, whereas the same combination with the both-positive criterion (AND rule) was the most specific/least sensitive. Compared with standalone cytology, non-HPV16/18 hrHPV assays were more sensitive/less specific. Two algorithms proposed for primary cytological testing or primary hrHPV testing were ranked in the middle as more sensitive/less specific than standalone cytology and the AND rule combinations but more specific/less sensitive than standalone hrHPV testing and the OR rule combination. Further research is needed to assess these results in population-relevant outcomes at the program level.

Sign in / Sign up

Export Citation Format

Share Document