False Positive Classifications Research Articles

Using autonomous recording units to identify and monitor western yellow‐billed cuckoo habitat

AbstractAutonomous recording units (ARUs) paired with signal classification software can be used to detect species‐specific calls, making them useful for evaluating patterns in avian occurrence and activity. However, classification of target signals is not always reliable and may be especially challenging for species that vocalize infrequently. We assessed the use of ARUs to identify and monitor habitat for a cryptic and federally threatened distinct population segment, the western yellow‐billed cuckoo (Coccyzus americanus) in mountainous xeroriparian drainages. Using Kaleidoscope Pro, we developed a call‐classifier and processed acoustic data collected in sites also surveyed using traditional human‐observer methods, applying the same spatial and temporal detection criteria to estimate breeding territories for each method. The classifier detected a total of 4,061 true positive calls at 4 sites, had an overall precision score of 0.07, recall score of 0.09, and F‐score (beta = 1) of 0.08, indicating high false positive and false negative classification rates. Our results were, however, consistent with other ARU studies of rare and cryptic species and ARUs estimated occupancy as effectively as human surveys with as little as 2 hours of daily recording. Total detections varied among sites, likely due to differences in cuckoo population densities and the interaction between topography and ARU detection space. Our results suggest that despite performance shortcomings of call‐classifiers, ARUs can be effective for monitoring cuckoos, with potential for providing higher resolution temporal and spatial information on activity and habitat use and may be particularly effective in remote locations where cuckoos often occur.

Combined Computed Coronary Tomography Angiography and Transcatheter Aortic Valve Implantation (TAVI) Planning Computed Tomography Reliably Detects Relevant Coronary Artery Disease Pre-TAVI.

Background: Before surgical or transcatheter aortic valve implantation (TAVI), coronary status evaluation is required. The role of combined computed coronary tomography angiography (cCTA) and TAVI planning CT in this context is not yet well elucidated. This study assessed whether relevant proximal coronary disease requiring coronary revascularization can be safely detected by combined cCTA and TAVI planning CT, including CT-derived fractional flow reserve (FFR) calculation in patients with severe aortic stenosis. Methods: This study analyzed patients with successful cCTA combined with TAVI planning CT using a 128-slice dual-source scanner. The detection via cCTA of relevant left main stem stenosis (>50%) or proximal coronary artery stenosis (>70%) was compared to invasive coronary angiography (ICA). Results: This study comprised 101 consecutive TAVI patients with a median age of 83 [77-86] years, a median STS score of 3.7 [2.4-6.1] and 54% of whom had known coronary artery disease. Of 15 patients with relevant coronary stenoses, 14 (93.3%) were detected with cCTA, while false positive results were found in 25 patients. Only in patients with previous percutaneous coronary stent implantation (PCI) were false positive rates (11/29) increased. In the subgroup without previous PCI, an improved classification performance of 87.5%, being mainly due to 11.1% false positive classifications, led to a negative predictive value of 98.5%. Conclusions: Combined cCTA and CT-FFR with TAVI planning CT via state-of-the-art scanners and protocols as a one-stop shop can replace routine ICA in patients prior to TAVI due to its safe detection of relevant coronary artery stenosis, although diagnostic performance of cCTA is only reduced in patients with coronary stents.

Weed resistance prediction: a random forest analysis based on field histories

Herbicide resistance has become a major issue in recent decades. Because diagnostics is still expensive, prediction models are helping to assess risks of resistance evolution. In this paper the influence of weed management on the evolution of resistance of the grass Alopecurus myosuroides Huds to ALS-inhibitors is investigated based on field history data from two regions, Hohenlohe in Germany and Champagne in France respectively. Champagne data also comprise information on Lolium spp. Using a random forest method variable importance and performance measures were obtained for a large number of single analyses allowing for a statistical analysis of the four performance measures, type I error, type II error, AUC and accuracy. It could be shown that acceptable predictions can be obtained for training data from Hohenlohe applied to Champagne and vice versa. It turned out that in nearly all analyses false negative classifications are more frequent than false positive classifications. Based on a combined training set of A.myosuroides samples from Hohenlohe and Champagne resistance status of Lolium spp. from the Champagne dataset can be predicted with a good accuracy. This suggest that resistance evolution to ALS-inhibitors of the two grasses are closely related. This work is a first step to set a simple herbicide resistance prediction tool to the users based on field history weed management data.

Improved rain event detection in commercial microwave link time series via combination with MSG SEVIRI data

Abstract. The most reliable areal precipitation estimation is usually generated via combinations of different measurements. Path-averaged rainfall rates can be derived from commercial microwave links (CMLs), where attenuation of the emitted radiation is strongly related to rainfall rate. CMLs can be combined with data from other rainfall measurements or can be used individually. They are available almost worldwide and often represent the only opportunity for ground-based measurement in data-scarce regions. However, deriving rainfall estimates from CML data requires extensive data processing. The separation of the attenuation time series into rainy and dry periods (rain event detection) is the most important step in this processing and has a high impact on the resulting rainfall estimates. In this study, we investigate the suitability of Meteosat Second Generation Spinning Enhanced Visible and InfraRed Imager (MSG SEVIRI) satellite data as an auxiliary-data-based (ADB) rain event detection method. We compare this method with two time-series-based (TSB) rain event detection methods. We used data from 3748 CMLs in Germany for 4 months in the summer of 2021 and data from the two SEVIRI-derived products PC and PC-Ph. We analyzed all rain event detection methods for different rainfall intensities, differences between day and night, and their influence on the performance of rainfall estimates from individual CMLs. The radar product RADKLIM-YW was used for validation. The results showed that both SEVIRI products are promising candidates for ADB rainfall detection, yielding only slightly worse results than the TSB methods, with the main advantage that the ADB method does not rely on extensive validation for different CML datasets. The main uncertainty of all methods was found for light rain. Slightly better results were obtained during the day than at night due to the reduced availability of SEVIRI channels at night. In general, the ADB methods led to improvements for CMLs performing comparatively weakly using TSB methods. Based on these results, combinations of ADB and TSB methods were developed by emphasizing their specific advantages. Compared to basic and advanced TSB methods, these combinations improved the Matthews correlation coefficient of the rain event detection from 0.49 (or 0.51) to 0.59 during the day and from 0.41 (or 0.50) to 0.55 during the night. Additionally, these combinations increased the number of true-positive classifications, especially for light rainfall compared to the TSB methods, and reduced the number of false negatives while only leading to a slight increase in false-positive classifications. Our results show that utilizing MSG SEVIRI data in CML data processing significantly increases the quality of the rain event detection step, in particular for CMLs which are challenging to process with TSB methods. While the improvement is useful even for applications in Germany, we see the main potential of using ADB methods in data-scarce regions like West Africa where extensive validation is not possible.

Exploration of Preliminary Objective Triage by Menopause Score and CA 125 Result Prior to Accelerating Fast-Track Booking for Suspected Ovarian Cancer-A Role for the Pathway Navigator?

The 28-days-to-diagnosis pathway is the current expected standard of care for women with symptoms of ovarian cancer in the UK. However, the anticipated conversion rate of symptoms to cancer is only 3%, and use of the pathway is increasing. A rapid triage at the moment of receipt of the referral might allow resources to be allocated more appropriately. In secondary care, multidisciplinary teams (MDTs) use the risk of malignancy index (RMI) score, (multiply menopausal status pre = 1 or post = 3 × ultrasound score = 0 - 3 × the CA 125 level), using a score of >200, to triage urgency and management in possible ovarian cancer cases. The most powerful determinant of the RMI score variables is CA 125 level, an objective number. Could a simple modification of the RMI score retain a high sensitivity for cancer whilst improving specificity and, consequently, decrease the morbidity of false-positive classification? To test this hypothesis, a retrospective evaluation of an ovarian two-week-wait telephone clinic of one consultant gynaecological oncologist was undertaken. Enquiry re menopause status was scored as one for pre- and three for postmenopausal or uncertain. CA 125 levels of >67 u/mL for premenopausal and >23 u/mL for postmenopausal women were used to precipitate urgent cross-sectional imaging requests and MDT opinions. These CA 125 cut thresholds were calculated using an assumption that the RMI imaging score, regardless of whether the result was available, could be three. We contemplate that women who did not exceed a provisional RMI score of >200 might be informed they are extremely unlikely to have cancer, removed from the malignancy tracker and appropriate follow-up arranged. One hundred and forty consecutive cases were analysed; 43% were deemed premenopausal and 57% postmenopausal. Twenty of the women had cancer, eighteen (90%) of whom had an RMI > 200. One hundred and twenty were benign, and only twenty-three (19%) classified as urgent cases in need of accelerated referral to imaging. In contrast, CA 125 > 35 u/mL, whilst retaining the sensitivity of 90%, misclassified 36 (30%) of the benign cases. It is possible that a telephone triage via a questionnaire determining menopausal status and the CA 125 result could offer a sensitivity for cancer of 90% and urgent expert review of under 20% of benign cases. This rapid initial telephone assessment could be presented by a trained pathway navigator, physician associate or nurse specialist. Substantial savings in NHS cancer services resources, anxieties all around and reduced patient morbidity may occur as a result.

Research of data mining methods for classification of imbalanced data sets

With the rapid development of information technology, which is widely used in all spheres of human life and activity, extremely large amounts of data have been accumulated today. By applying machine learning methods to this data, new practically useful knowledge can be obtained. The main goal of this paper is to study different machine learning methods for solving the classification problem and compare their efficiency and accuracy. A separate task is data pre-processing aimed at solving the problem of sample imbalance, as well as identifying the principal components that will be used to solve the classification problem. For this purpose, an information system for classifying the bankruptcy of a company with specified economic and financial characteristics was researched and developed. The study uses a dataset on the basis of which the efficiency and quality of application of several existing classification algorithms are evaluated. These classifiers are: conventional and linear Support Vector Machine, Extra Trees, Random Forest, Decision Tree, Logistic Regression, Multilayer perceptron Classifier, Gradient Boosting, Naive Bayes Classifier. For data pre-processing, we scaled the data, used the SMOTE method to get rid of the imbalance of the training sample, and performed principal component analysis and L1 regularisation. Principal component analysis allowed us to identify 15 principal components that have the greatest impact on classification accuracy and, accordingly, use them in the classification process. Analysing the results, we found that the best classifier was Random Forest with 95.9 % accuracy, and the worst was Naive Bayes with 85.1 %. To evaluate the quality of classification and select the best classifier, the Confusion matrix is used, which takes into account the number of true positive (TP) and true negative (TN) values, as well as the number of false negative (FN) and false positive (FP) classification results, and the values of such metrics as accuracy, precision, sensitivity, F1, and ROC. Accuracy is the percentage of correct answers given by the algorithm, while Recall is the number of TPs divided by the number of TPs plus the number of FNs. F1 indicates the balance between accuracy and sensitivity. Precision is the number of true positive predictions divided by the number of false positive and true negative predictions. ROC AUC is a tool for measuring performance for classification tasks at different thresholds. It shows how well a model can distinguish between classes. The conclusions present the main results of the study and indicate the main future direction of the work, namely, the study of classification results for other datasets and more efficient processing and analysis.

The Utility of Risk Factors to Define Complicated Staphylococcus aureus Bacteremia in a Setting With Low Methicillin-Resistant S. aureus Prevalence.

Recommended duration of antibiotic treatment of Staphylococcus aureus bacteremia (SAB) is frequently based on distinguishing uncomplicated and complicated SAB, and several risk factors at the onset of infection have been proposed to define complicated SAB. Predictive values of risk factors for complicated SAB have not been validated, and consequences of their use on antibiotic prescriptions are unknown. In a prospective cohort, patients with SAB were categorized as complicated or uncomplicated through adjudication (reference definition). Associations and predictive values of 9 risk factors were determined, compared with the reference definition, as was accuracy of Infectious Diseases Society of America (IDSA) criteria that include 4 risk factors, and the projected consequences of applying IDSA criteria on antibiotic use. Among 490 patients, 296 (60%) had complicated SAB. In multivariable analysis, persistent bacteremia (odds ratio [OR], 6.8; 95% confidence interval [CI], 3.9-12.0), community acquisition of SAB (OR, 2.9; 95% CI, 1.9-4.7) and presence of prosthetic material (OR, 2.3; 95% CI, 1.5-3.6) were associated with complicated SAB. Presence of any of the 4 risk factors in the IDSA definition of complicated SAB had a positive predictive value of 70.9% (95% CI, 65.5-75.9) and a negative predictive value of 57.5% (95% CI, 49.1-64.8). Compared with the reference, IDSA criteria yielded 24 (5%) false-negative and 90 (18%) false-positive classifications of complicated SAB. Median duration of antibiotic treatment of these 90 patients was 16 days (interquartile range, 14-19), all with favorable clinical outcome. Risk factors have low to moderate predictive value to identify complicated SAB and their use may lead to unnecessary prolonged antibiotic use.

Enhancing Anomaly Detection Models for Industrial Applications through SVM-Based False Positive Classification

Unsupervised anomaly detection models are crucial for the efficiency of industrial applications. However, frequent false alarms hinder the widespread adoption of unsupervised anomaly detection, especially in fault detection tasks. To this end, our research delves into the dependence of false alarms on the baseline anomaly detector by analyzing the high-response regions in anomaly maps. We introduce an SVM-based false positive classifier as a post-processing module, which identifies false alarms from positive predictions at the object level. Moreover, we devise a sample synthesis strategy that generates synthetic false positives from the trained baseline detector while producing synthetic defect patch features from fuzzy domain knowledge. Following comprehensive evaluations, we showcase substantial performance enhancements in two advanced out-of-distribution anomaly detection models, Cflow and Fastflow, across image and pixel-level anomaly detection performance metrics. Substantive improvements are observed in two distinct industrial applications, with notable instances of elevating the image-level F1-score from 46.15% to 78.26% in optimal scenarios and boosting pixel-level AUROC from 72.36% to 94.74%.

Detection of carbon nanotubes in bovine raw milk through Fourier transform Raman spectroscopy

The potential use of carbon-based methodologies for drug delivery and reproductive biology in cows raises concerns about residues in milk and food safety. This study aimed to assess the potential of Fourier transform Raman spectroscopy and discriminant analysis using partial least squares (PLS-DA) to detect functionalized multiwalled carbon nanotubes (MWCNT) in bovine raw milk. Oxidized MWCNT were diluted in milk at different concentrations from 25.00 to 0.01 µg/mL. Raman spectroscopy measurements and PLS-DA were performed to identify low concentrations of MWCNT in milk samples. The PLS-DA model was characterized by the analysis of the variable importance in projection (VIP) scores. All the training samples were correctly classified by the model, resulting in no false-positive or false-negative classifications. For test samples, only one false-negative result was observed, for 0.01 µg/mL MWCNT dilution. The association between Raman spectroscopy and PLS-DA was able to identify MWCNT diluted in milk samples up to 0.1 µg/mL. The PLS-DA model was built and validated using a set of test samples and spectrally interpreted based on the highest VIP scores. This allowed the identification of the vibrational modes associated with the D and G bands of MWCNT, as well as the milk bands, which were the most important variables in this analysis.

A - 184 Validity of the Infrequent Patterns of Performance Embedded Performance Validity Indicators in a Mixed Clinical Sample.

Novel performance validity tests (PVTs) for the Hopkins Verbal Learning Test-Revised (HVLT-R) and Brief Visuospatial Memory Test-Revised (BVMT-R), derived from infrequent patterns of performance (IPOP), were developed to examine invalid memory performance while reducing false positive misclassification. To examine their classification accuracy, these indicators were compared to several existing embedded PVTs in a mixed clinical sample. A chart review was completed for 75 adult outpatients (Mean Age = 52, Range = 19-85) referred to an academic medical center outpatient clinic for neuropsychological evaluation. Twenty-eight percent of the sample failed the Medical Symptom Validity Test (MSVT), which was used as the criterion to indicate invalid performance. Several established embedded validity indicators were calculated from HVLT-R and BVMT-R scores, including the recognition discrimination index (RDI) and percent retention (PR), as well as the Reliable Digit Span (RDS) validity indicator. Classification statistics, including sensitivity, specific, likelihood ratios, predictive values, and overall accuracy, were calculated and compared. The HVLT-R IPOP had a higher overall classification accuracy (72%) compared to the RDI indicator (68%) while maintaining excellent specificity (97%). The BVMT-R IPOP had identical classification accuracy (75%) compared to the RDI and PR indicators with very high specificity (96%). Both indicators were more accurate than RDS (72%). The HVLT-R and BVMT-R IPOP performance validity indicators produced adequate classification statistics when compared to existing embedded PVTs. Both indicators maintained excellent specificity, which is crucial in reducing false positive classification. Future research will focus on further examining the validity of these indicators in other clinical groups and known groups, including medico-legal populations.

Applications of Machine Learning and Neural Networks for FT-ICR Mass Measurements with SIPT

The single-ion Penning trap (SIPT) at the Low-Energy Beam Ion Trapping Facility has been developed to perform precision Penning trap mass measurements of single ions, ideal for the study of exotic nuclei available only at low rates at the Facility for Rare Isotope Beams (FRIB). Single-ion signals are very weak—especially if the ion is singly charged—and the few meaningful ion signals must be disentangled from an often larger noise background. A useful approach for simulating Fourier transform ion cyclotron resonance signals is outlined and shown to be equivalent to the established yet computationally intense method. Applications of supervised machine learning algorithms for classifying background signals are discussed, and their accuracies are shown to be ≈65% for the weakest signals of interest to SIPT. Additionally, a deep neural network capable of accurately predicting important characteristics of the ions observed by their image charge signal is discussed. Signal classification on an experimental noise dataset was shown to have a false-positive classification rate of 10.5%, and 3.5% following additional filtering. The application of the deep neural network to an experimental 85Rb+ dataset is presented, suggesting that SIPT is sensitive to single-ion signals. Lastly, the implications for future experiments are discussed.

Characterization and Quantification of Natural and Anthropogenic Titanium-Containing Particles Using Single-Particle ICP-TOFMS.

Titanium-containing nanoparticles (NPs) and submicrometer particles (μPs) in the environment can come from natural or anthropogenic sources. In this study, we investigate the use of single-particle inductively coupled plasma time-of-flight mass spectrometry (spICP-TOFMS) to measure and classify individual Ti-containing particles as either engineered (Ti-eng) or naturally occurring (Ti-nat) based on elemental composition and multielement mass ratios. We analyze mixtures of four Ti-containing particle types: anthropogenic food-grade TiO2 particles and particles from rutile, ilmenite, and biotite mineral samples. Through characterization of neat particle suspensions, we develop a decision-tree-based classification scheme to distinguish Ti-eng from Ti-nat particles and to classify individual Ti-nat particles by mineral type. Engineered TiO2 and rutile particles have the same major-element composition. To distinguish Ti-eng particles from rutile, we developed particle-type detection limits based on the average crustal abundance ratio of titanium to niobium. For our measurements, the average Ti mass needed to classify Ti-eng particles is 9.3 fg, which corresponds to a diameter of 211 nm for TiO2. From neat suspensions, we demonstrate classification rates of 55%, 32%, 75%, and 72% for Ti-eng, rutile, ilmenite, and biotite particles, respectively. Our classification approach minimizes false-positive classifications, with rates below 5% for all particle types. Individual Ti-eng particles can be accurately classified at the submicron size range, while the Ti-nat particles are classified in the nanoregime (diameter < 100 nm). Efficacy of our classification approach is demonstrated through the analysis of controlled mixtures of Ti-eng and Ti-nat and the analysis of natural streamwater spiked with Ti-eng particles. In control mixtures, Ti-eng particles can be measured and classified at particle-number concentrations (PNCs) 60-times lower than that of Ti-nat particles and across a PNC range of at least 3 orders of magnitude. In the streamwater sample, Ti-eng particles are classified at environmentally relevant PNCs that are 44-times lower than the background Ti-nat PNC and 2850-times lower than the total PNC.

Strategic incentives when implementing Dorfman testing with assortative matching

The Dorfman pooled testing scheme is a process in which individual specimens (e.g., blood, urine, swabs, etc.) are pooled and tested together; if the merged sample tests positive for infection, each specimen from the pool is tested individually. Through this procedure, laboratories can reduce the expected number of tests required to screen a population. The literature has often advocated in favor of using ordered partitions to screen the population, i.e., of pooling subjects with similar probability of infection together, as doing so simultaneously minimizes the expected number of tests, the expected number of false negatives, and the expected number of false positive classifications, provided that certain technical conditions hold. One potential limitation of using ordered partitions, however, is that they may incentivize some subjects to misreport their types to the tester. Indeed, if subjects wish to avoid being detected as infected, ordered partitions would incentivize them to falsely claim that they have a low probability of infection (assuming that pooled testing is subject to dilution effects). These incentives would disappear if subjects were matched randomly, regardless of their probability of infection. In this article, we derive conditions under which ordered partitions outperform matching subjects randomly, despite these incentives.

Pool testing with dilution effects and heterogeneous priors.

The Dorfman pooled testing scheme is a process in which individual specimens (e.g., blood, urine, swabs, etc.) are pooled and tested together; if the merged sample tests positive for infection, then each specimen from the pool is tested individually. Through this procedure, laboratories can reduce the expected number of tests required to screen the population, as individual tests are only carried out when the pooled test detects an infection. Several different partitions of the population can be used to form the pools. In this study, we analyze the performance of ordered partitions, those in which subjects with similar probability of infection are pooled together. We derive sufficient conditions under which ordered partitions outperform other types of partitions in terms of minimizing the expected number of tests, the expected number of false negatives, and the expected number of false positive classifications. These sufficient conditions can be easily verified in practical applications once the dilution effect has been estimated. We also propose a measure of equity and present conditions under which this measure is maximized by ordered partitions.

Use of a taxon-specific reference database for accurate metagenomics-based pathogen detection of Listeria monocytogenes in turkey deli meat and spinach

BackgroundThe reliability of culture-independent pathogen detection in foods using metagenomics is contingent on the quality and composition of the reference database. The inclusion of microbial sequences from a diverse representation of taxonomies in universal reference databases is recommended to maximize classification precision for pathogen detection. However, these sizable databases have high memory requirements that may be out of reach for some users. In this study, we aimed to assess the performance of a foodborne pathogen (FBP)-specific reference database (taxon-specific) relative to a universal reference database (taxon-agnostic). We tested our FBP-specific reference database's performance for detecting Listeria monocytogenes in two complex food matrices—ready-to-eat (RTE) turkey deli meat and prepackaged spinach—using three popular read-based DNA-to-DNA metagenomic classifiers: Centrifuge, Kraken 2 and KrakenUniq.ResultsIn silico host sequence removal led to substantially fewer false positive (FP) classifications and higher classification precision in RTE turkey deli meat datasets using the FBP-specific reference database. No considerable improvement in classification precision was observed following host filtering for prepackaged spinach datasets and was likely a consequence of a higher microbe-to-host sequence ratio. All datasets classified with Centrifuge using the FBP-specific reference database had the lowest classification precision compared to Kraken 2 or KrakenUniq. When a confidence-scoring threshold was applied, a nearly equivalent precision to the universal reference database was achieved for Kraken 2 and KrakenUniq. Recall was high for both reference databases across all datasets and classifiers. Substantially fewer computational resources were required for metagenomics-based detection of L. monocytogenes using the FBP-specific reference database, especially when combined with Kraken 2.ConclusionsA universal (taxon-agnostic) reference database is not essential for accurate and reliable metagenomics-based pathogen detection of L. monocytogenes in complex food matrices. Equivalent classification performance can be achieved using a taxon-specific reference database when the appropriate quality control measures, classification software, and analysis parameters are applied. This approach is less computationally demanding and more attainable for the broader scientific and food safety communities.

Neutral theory: applicability and neutrality of clinical study endpoints where a disease-specific instrument is available

BackgroundThere is a pressing need to improve the accuracy of rare disease clinical study endpoints. Neutral theory, first described here, can be used to assess the accuracy of endpoints and improve their selection in rare disease clinical studies, reducing the risk of patient misclassification.MethodsNeutral theory was used to assess the accuracy of rare disease clinical study endpoints and the resulting probability of false positive and false negative classifications at different disease prevalence rates. Search strings were extracted from the Orphanet Register of Rare Diseases using a proprietary algorithm to conduct a systematic review of studies published until January 2021. Overall, 11 rare diseases with one disease-specific disease severity scale (133 studies) and 12 rare diseases with more than one disease-specific disease severity scale (483 studies) were included. All indicators from clinical studies were extracted, and Neutral theory was used to calculate their match to disease-specific disease severity scales, which were used as surrogates for the disease phenotype. For those with more than one disease-severity scale, endpoints were compared with the first disease-specific disease severity scale and a composite of all later scales. A Neutrality score of > 1.50 was considered acceptable.ResultsAround half the clinical studies for half the rare diseases with one disease-specific disease severity score (palmoplantar psoriasis, achalasia, systemic lupus erythematosus, systemic sclerosis and Fournier’s gangrene) met the threshold for an acceptable match to the disease phenotype, one rare disease (Guillain-Barré syndrome) had one study with an acceptable match, and four diseases (Behcet’s syndrome, Creutzfeldt-Jakob disease, atypical hemolytic uremic syndrome and Prader-Willi syndrome) had no studies. Clinical study endpoints in almost half the rare diseases with more than one disease-specific DSS (acromegaly, amyotrophic lateral sclerosis, cystic fibrosis, Fabry disease and juvenile rheumatoid arthritis) were a better match to the composite, while endpoints in the remaining rare diseases (Charcot Marie Tooth disease, Gaucher disease Type I, Huntington’s disease, Sjogren’s syndrome and Tourette syndrome) were a worse match. Misclassifications varied with increasing disease prevalence.ConclusionsNeutral theory confirmed that disease-severity measurement needs improvement in rare disease clinical studies, especially for some diseases, and suggested that the potential for accuracy increases as the body of knowledge on a disease increases. Using Neutral theory to benchmark disease-severity measurement in rare disease clinical studies may reduce the risk of misclassification, ensuring that recruitment and treatment effect assessment optimise medicine adoption and benefit patients.

False-positive classification and associated factors in segmented macular layers and retinal nerve fiber layer analysis: Spectralis OCT deviation map study

The rates, patterns and associated factors for false-positive classification of deviation maps by Cirrus optical coherence tomography (OCT) have been reported. However, research on OCT layer-by-layer deviation maps is lacking. We aimed to determine the rates and associated factors for false-positive classification of segmented macular layers and retinal nerve fiber layer (RNFL) deviation maps of Spectralis OCT, and to identify false-positive patterns on segmented macular layers deviation maps. 118 healthy eyes of 118 normal participants who had undergone Spectralis OCT imaging were included. False-positive classification was determined by the area and location of yellow or red color-coded regions on the deviation map. The false-positive rates on the deviation maps were the highest on the ganglion cell layer map, followed by the inner plexiform layer, retinal layer, and RNFL maps. More myopic/less hyperopic refractive error was a factor significantly associated with higher false-positive classification on the RNFL deviation map, and three false-positive patterns were found on the segmented macular layers deviation maps. Spectralis OCT deviation maps should be interpreted carefully to avoid misdiagnosis, especially for eyes with higher degrees of myopic refractive error on the RNFL map, for which purpose, recognizing the characteristic false-positive patterns would be helpful in clinical practice.

Vectorial and topologically valid segmentation of forestry road networks from ALS data

Accurate information on road location is critical for forest management and conservation strategies. Road location data supports the analysis of road accessibility and usability and is a critical information layer for forest harvest, financial planning, wildfire suppression, and protection activities. The global expanse of forests, their remoteness, and difficulty to access have necessitated the development of automatic or semi-automatic remote sensing methodologies to map roads using passive optical imagery or Airborne Laser Scanning (ALS). Conventional automatic road mapping methods are raster-based and map roads as patches of disconnected pixels. This paper addresses the limitations of raster-based automatic forest road extraction and presents a method for producing a topologically accurate vectorial road network. Our method, presented as a fully documented and open-source software tool, uses metrics derived from an ALS point cloud to produce a raster of road conductivity. From this conductivity raster, the method “drives” the roads iteratively by detecting and following road intersections. We demonstrate the method’s efficacy using a road network in Quebec, Canada, where 96% of the roads in a binary raster, and 84% using our probability map, are vectorized properly from an ALS point cloud with 4% false positives. Our proposed method may significantly reduce the training requirements of machine learning techniques used to classify roads by being very robust to false positive and false negative classifications.

The use of copy number loads to designate mosaicism in blastocyst stage PGT-A cycles: fewer is better.

The use of copy number loads to designate mosaicism in blastocyst stage PGT-A cycles: fewer is better.

Semantic Segmentation of Metal Surface Defects and Corresponding Strategies

Facing the demand of industry for metal surface detection, this article addresses the segmentation of metal surface defects. Metal surface defect segmentation has many technical problems, such as serious imbalance in quantity and distribution, low contrast, and weak boundary information. To solve these problems, this article proposes a multi-scale attention feature fusion module, normalized mean square frequency category weight strategy, biased weight training sampling strategy, and category-boundary loss calculation strategy. The multi-scale attention feature fusion module fuses different levels of feature information to obtain defect features in images more effectively. The normalized mean square frequency category weight strategy suppresses the excessive weight of small defect categories and false positive classification. The biased weight training sampling strategy allocates different training frequencies to training samples and increases the attention to defect samples. The category-boundary loss calculation strategy imposes weights on the defect boundary and increases the attention to the boundary information. On four public datasets (Severstal, SD900, Magnetic-tile, and Crack), the proposed method achieves improvements of 7.8%, 4.0%, 18.4%, and 9.4% (absolute quantity), respectively, compared with the baseline method, while the calculation amount and number of parameters remain almost unchanged. Hence, our method ranks as state of the art.