Decrease In False Positive Rate Research Articles

Predicting Malignancy in Pediatric Thyroid Nodules: Early Experience With Machine Learning for Clinical Decision Support.

ObjectiveTo develop a machine learning tool to integrate clinical data for the prediction of non-benign thyroid cytology and histology.ContextPapillary thyroid carcinoma is the most common endocrine malignancy. Since most nodules are benign, the challenge for the clinician is to identify those most likely to harbor malignancy while limiting exposure to surgical risks among those with benign nodules.MethodsRandom forests (augmented to select features based on our clinical measure of interest), in conjunction with interpretable rule sets, were used on demographic, ultrasound, and biopsy data of thyroid nodules from children younger than 18 years at a tertiary pediatric hospital. Accuracy, false-positive rate (FPR), false-negative rate (FNR), and area under the receiver operator curve (AUROC) are reported.ResultsOur models predict nonbenign cytology and malignant histology better than historical outcomes. Specifically, we expect a 68.04% improvement in the FPR, 11.90% increase in accuracy, and 24.85% increase in AUROC for biopsy predictions in 67 patients (28 with benign and 39 with nonbenign histology). We expect a 23.22% decrease in FPR, 32.19% increase in accuracy, and 3.84% decrease in AUROC for surgery prediction in 53 patients (42 with benign and 11 with nonbenign histology). This improvement comes at the expense of the FNR, for which we expect 10.27% with malignancy would be discouraged from performing biopsy, and 11.67% from surgery. Given the small number of patients, these improvements are estimates and are not tested on an independent test set.ConclusionThis work presents a first attempt at developing an interpretable machine learning based clinical tool to aid clinicians. Future work will involve sourcing more data and developing probabilistic estimates for predictions.

Pulse oximetry screening for detection of congenital heart defects at 1646 m in Albuquerque, New Mexico.

To determine the false-positive rate of pulse oximetry screening at moderate altitude, presumed to be elevated compared with sea level values and assess change in false-positive rate with time. We retrospectively analysed 3548 infants in the newborn nursery in Albuquerque, New Mexico, (elevation 5400 ft) from July 2012 to October 2013. Universal pulse oximetry screening guidelines were employed after 24 hours of life but before discharge. Newborn babies between 36 and 36 6/7 weeks of gestation, weighing >2 kg and babies >37 weeks weighing >1.7 kg were included in the study. Log-binomial regression was used to assess change in the probability of false positives over time. Of the 3548 patients analysed, there was one true positive with a posteriorly-malaligned ventricular septal defect and an interrupted aortic arch. Of the 93 false positives, the mean pre- and post-ductal saturations were lower, 92 and 90%, respectively. The false-positive rate before April 2013 was 3.5% and after April 2013, decreased to 1.5%. There was a significant decrease in false-positive rate (p = 0.003, slope coefficient = -0.082, standard error of coefficient = 0.023) with the relative risk of a false positive decreasing at 0.92 (95% CI 0.88-0.97) per month. This is the first study in Albuquerque, New Mexico, reporting a high false-positive rate of 1.5% at moderate altitude at the end of the study in comparison to the false-positive rate of 0.035% at sea level. Implementation of the nationally recommended universal pulse oximetry screening was associated with a high false-positive rate in the initial period, thought to be from the combination of both learning curve and altitude. After the initial decline, it remained steadily elevated above sea level, indicating the dominant effect of moderate altitude.

Improved Merkle Hash Tree-Based One-Time Signature Scheme for Capability-Enhanced Security Enforcing Architecture for Named Data Networking

The concept of network caching is determined to be the potential requirement of named data networks (NDN) for enhancing the capabilities of the traditional IP networking. It is responsible for location independent data accesses and optimal bandwidth utilization in multi-path data dissemination. However, the network caching process in NDN introduces security challenges such as content cache poisoning, malicious injection or flooding of the packets and violation in accessing content packets. In this paper, an Improved Merkle Hash Tree-based one-time signature scheme for capability-enhanced security enforcing architecture (IMHT-OTSS-CSEA) is proposed for provisioning data authenticity in a distributed manner for leveraging the capabilities to inform the access privileges of the packets during the process of data dissemination. It is proposed for permitting the routers to verify the forwarded packets’ authenticity in NDN. It is capable in handling the issues that emerge from unsolicited packets during a flooding-based denial of service attacks by supporting the indispensable verification process in routers that confirms the timeliness of packets. The simulation experiments conducted using the open source CCNs platform and Planetlab confirmed a significant mean reduction in delay of 14.61%, superior to the benchmarked schemes. It is identified to minimize the delay incurred in generating bit vectors by a average margin of 13.06%, excellent to the baseline approaches. It also confirmed a mean increase in the true positive rate of 5.42%, a mean increase in the precision rate of 6.04%, decrease in false positive rate of 6.82% and increase in F-measure of 5.62% compared to the baseline approaches in the context of detecting content cache pollution attack respectively.

Iterative hard thresholding in genome-wide association studies: Generalized linear models, prior weights, and double sparsity.

BackgroundConsecutive testing of single nucleotide polymorphisms (SNPs) is usually employed to identify genetic variants associated with complex traits. Ideally one should model all covariates in unison, but most existing analysis methods for genome-wide association studies (GWAS) perform only univariate regression.ResultsWe extend and efficiently implement iterative hard thresholding (IHT) for multiple regression, treating all SNPs simultaneously. Our extensions accommodate generalized linear models, prior information on genetic variants, and grouping of variants. In our simulations, IHT recovers up to 30% more true predictors than SNP-by-SNP association testing and exhibits a 2–3 orders of magnitude decrease in false-positive rates compared with lasso regression. We also test IHT on the UK Biobank hypertension phenotypes and the Northern Finland Birth Cohort of 1966 cardiovascular phenotypes. We find that IHT scales to the large datasets of contemporary human genetics and recovers the plausible genetic variants identified by previous studies.ConclusionsOur real data analysis and simulation studies suggest that IHT can (i) recover highly correlated predictors, (ii) avoid over-fitting, (iii) deliver better true-positive and false-positive rates than either marginal testing or lasso regression, (iv) recover unbiased regression coefficients, (v) exploit prior information and group-sparsity, and (vi) be used with biobank-sized datasets. Although these advances are studied for genome-wide association studies inference, our extensions are pertinent to other regression problems with large numbers of predictors.

Comparing the diagnostic efficacy of full field digital mammography with digital breast tomosynthesis using BIRADS score in a tertiary cancer care hospital.

Introduction:Breast cancer is one of the leading cancers in females worldwide, and its incidence has been rising at an exponential pace in the last 10 years even in India. Mammography has been the mainstay for detection of breast cancer over decades and has gradually advanced from screen film to full-field digital mammography. Recently, tomosynthesis has evolved as an advanced imaging investigation for early diagnosis of breast lesions in both diagnostic and screening settings.Aim of Study:To compare and evaluate the impact of digital breast tomosynthesis (DBT) compared to full-field digital mammography (FFDM) in the interpretation of BIRADS score in both diagnostic and screening settings.Settings and Design:A 1-year prospective longitudinal study was conducted in the Department of Radio-diagnosis in our institute using Hologic Selenia Dimensions for mammography as well as tomosynthesis.Materials and Methods:One hundred women known or suspected (opportunistic screening) for breast cancer were evaluated either with FFDM alone or both FFDM and DBT. Sensitivity, specificity, positive predictive value, negative predictive value, and P value were used to assess the various diagnostic criteria in our study.Results:Addition of DBT to FFDM results in a statistically significant increase in the sensitivity, specificity, and positive predictive value, and a statistically significant decrease in the false positive rates. Similar results were noted in both diagnostic and screening cases. It was observed that, in most cases, i.e. a total of 47, DBT did not change the BIRADS scoring; however, its addition increased the diagnostic confidence. BIRADS was upgraded and downgraded in 14 and 31 cases, respectively, with the addition of DBT to FFDM. New lesions were seen with addition of DBT to FFDM in 8 cases.Conclusion:Addition of DBT to FFDM results in increase in sensitivity, specificity, positive predictive value, and a statistically significant decrease in false positive rates in both diagnostic and screening cases. As addition of tomosynthesis results in a significant decrease in recall rate, it should be added, at least, in all screening mammography programs.

A New Wavelet Based Spatio-temporal Method for Magnification of Subtle Motions in Video

Video magnification is a computational procedure to reveal subtle variations during video frames that are invisible to the naked eye. A new spatio-temporal method which makes use of connectivity based mapping of the wavelet sub-bands is introduced here for exaggerating of small motions during video frames. In this method, firstly the wavelet transformed frames are mapped to connectivity space and then decomposed into different spatial frequency bands by applying Laplacian Pyramid to determine the pixels having more chance to be a part of a movement. Finally each candidate is partially magnified based on its time history. The performance of the proposed method is evaluated on real videos which contain several subtle motions. Parameters for performance evaluation are presented and obtained results are compared with one of state-of-the-art video magnification methods. Increased true positive rate in parallel with simultaneous decrease in false positive rate confirm the effectiveness of the proposed method in amplifying subtle motions.

A New fuzzy level set method for lesion border detection in dermoscopy images

Accurate segmentation plays a vital role in automated analysis of dermoscopy images. A new method based on fuzzy level set method is introduced here for lesion detection in dermoscopy images. In this method, a hypothesis testing framework is defined first to separate lesions from skin and artifacts. Then the boundary of lesion is estimated by a decision function based on the level set energy minimization method which is driven by fuzzy connectedness concept. Performance is evaluated on real dermoscopy images which are captured from various lesions with different sizes and colors. Parameters for performance evaluation are presented and obtained results are compared with some other state-of-the-art lesion detection methods. Increased true positive rate in parallel with simultaneous decrease in false positive rate, Hammoude distance and Hausdorff distance confirm the effectiveness of proposed method for skin cancer detection.

Number of basis images effect on detection of root fractures in endodontically treated teeth using a cone beam computed tomography machine: an in vitro study

The objective of this study was to compare the accuracy of root fracture detection in endodontically treated teeth using scans acquired with a 180° rotation motion compared with a 360° after which the patient exposure and number of basis images are doubled. Sixty-six roots were collected and decoronated. All were treated endodontically. One-half of the roots were fractured, resulting in 2 root fragments which were then glued together. The roots were placed randomly in 8 prepared beef rib fragments. Five reviewers independently reviewed the scans twice, at different times. The specificity of the 360° scan was significantly higher than the 180° scan; doubling the basis images leads to a significant decrease in false-positive rates. Accuracy and sensitivity were not significantly different. Only the specificity is improved by the increased rotation and doubling of images. The accuracy and sensitivity are not improved.

Predicting unilateral prostate cancer on routine diagnostic biopsy: sextant vs extended

To compare the diagnostic properties of routine office-based sextant and extended biopsies for unilateral prostate cancer, as validated by final pathology, because focal therapy of prostate cancer is gaining acceptance as a viable treatment option and thus patient selection is of paramount consideration. We retrospectively analysed records of patients who had a radical prostatectomy (RP) for biopsy confirmed prostate cancer at our institution between 1990 and 2007. Records with incomplete data were excluded. Diagnostic properties for sextant and extended biopsies were calculated and compared for diagnostic accuracy, sensitivity, specificity, positive and negative predictive values (PPV, NPV) and false-positive and -negative rates. We identified 882 records (729 sextant, 153 extended biopsies) matching our criteria. Overall, unilateral prostate cancer was confirmed in 151 (16%) of pathological RP specimens. The sensitivity improved from 84.1% to 88.0% on sextant and extended biopsy, respectively. Similarly, the PPV increased from 21.9% to 27.2%, specificity from 37.1% to 53.9% (P < 0.05), and NPV from 91.8% to 95.8% (P < 0.05). These changes are reflected in the decrease in false-positive rates (from 62.9% to 46.1%) and false-negative rates (from 15.9% to 12.0%). The overall diagnostic accuracy increased from 49% on sextant to 59% on extended biopsy (P < 0.05). Taking more prostate biopsy cores improves the diagnostic properties for identifying unilateral prostate cancer. However, a 12-core biopsy is not an ideal diagnostic test to select patients for focal therapy, and should be interpreted in conjunction with imaging and clinical variables. Additional research should investigate the diagnostic gain associated with a further increase in the number of biopsy cores.

Effect of polymorphisms within probe–target sequences on olignonucleotide microarray experiments

Hybridization-based technologies, such as microarrays, rely on precise probe-target interactions to ensure specific and accurate measurement of RNA expression. Polymorphisms present in the probe–target sequences have been shown to alter probe- hybridization affinities, leading to reduced signal intensity measurements and resulting in false-positive results. Here, we characterize this effect on exon and gene expression estimates derived from the Affymetrix Exon Array. We conducted an association analysis between expression levels of probes, exons and transcripts and the genotypes of neighboring SNPs in 57 CEU HapMap individuals. We quantified the dependence of the effect of genotype on signal intensity with respect to the number of polymorphisms within target sequences, number of affected probes and position of the polymorphism within each probe. The effect of SNPs is quite severe and leads to considerable false-positive rates, particularly when the analysis is performed at the exon level and aimed at detecting alternative splicing events. Finally, we propose simple solutions, based on ‘masking’ probes, which are putatively affected by polymorphisms and show that such strategy results in a large decrease in false-positive rates, with a very modest reduction in coverage of the transcriptome.

Integrated modeling of the major events in the MHC class I antigen processing pathway

Rational design of epitope-driven vaccines is a key goal of immunoinformatics. Typically, candidate selection relies on the prediction of MHC-peptide binding only, as this is known to be the most selective step in the MHC class I antigen processing pathway. However, proteasomal cleavage and transport by the transporter associated with antigen processing (TAP) are essential steps in antigen processing as well. While prediction methods exist for the individual steps, no method has yet offered an integrated prediction of all three major processing events. Here we present WAPP, a method combining prediction of proteasomal cleavage, TAP transport, and MHC binding into a single prediction system. The proteasomal cleavage site prediction employs a new matrix-based method that is based on experimentally verified proteasomal cleavage sites. Support vector regression is used for predicting peptides transported by TAP. MHC binding is the last step in the antigen processing pathway and was predicted using a support vector machine method, SVMHC. The individual methods are combined in a filtering approach mimicking the natural processing pathway. WAPP thus predicts peptides that are cleaved by the proteasome at the C terminus, transported by TAP, and show significant affinity to MHC class I molecules. This results in a decrease in false positive rates compared to MHC binding prediction alone. Compared to prediction of MHC binding only, we report an increased overall accuracy and a lower rate of false positive predictions for the HLA-A*0201, HLA-B*2705, HLA-A*01, and HLA-A*03 alleles using WAPP. The method is available online through our prediction server at http://www-bs.informatik.uni-tuebingen.de/WAPP

Clinical and economic benefit of HPV-load testing in follow-up and management of women postcone biopsy for CIN2-3.

This study aimed to evaluate the clinical and economic implications of integrating human papilloma virus (HPV) load testing into the follow-up and management protocol of women postconisation for high-grade cervical intraepithelial neoplasia (CIN2–3). We evaluated 130 suitable women: 63 were screened biannually by Pap smears (‘conventional approach’) and 67 also had HPV-load testing (‘HPV approach’). More stringent criteria for undergoing colposcopy or reconisation were observed by the former group compared to the latter. Both approaches were analysed for cost effectiveness. There were 33 out of 67 (49.2%) colposcopic referrals and 24 out of 67 (35.8%) reconisation/hysterectomies with the ‘conventional approach’ compared to 9 out of 63 (14.2%) and 7 out of 63 (11.1%) with the ‘HPV approach’. Cervical intraepithelial neoplasia 2–3 residual disease was detected in 7 out of 67 (10.5%) and 7 out of 63 (11.1%) women. The ‘conventional approach’ had more negative colposcopic biopsies and more negative reconisation/hysterectomy histologies than the ‘HPV approach’. The respective cost per detection of one case of residual disease was US$3573 and US$3485. The ‘HPV approach’ required fewer colposcopic and reconisation procedures to detect one case of residual CIN2–3. Its higher positive predictive value than that of cytology provided a significant decrease in false positive rates and a reduction of US$88 per detected case.