scholarly journals Deep learning algorithm helps to standardise ATS/ERS spirometric acceptability and usability criteria

2020 ◽  
pp. 2000603 ◽  
Author(s):  
Nilakash Das ◽  
Kenneth Verstraete ◽  
Sanja Stanojevic ◽  
Marko Topalovic ◽  
Jean-Marie Aerts ◽  
...  
Keyword(s):  
Quality Control ◽  
Deep Learning ◽  
Learning Algorithm ◽  
High Sensitivity ◽  
Current Approach ◽  
Deep Learning Algorithm ◽  
Volume Curve ◽  
Flow Volume Curve ◽  
Shapley Values ◽  
Quality Control Criteria

RationaleWhile ATS/ERS quality control criteria for spirometry include several quantitative limits, it also requires manual visual inspection. The current approach is time consuming and leads to high inter-technician variability. We propose a deep learning approach called convolutional neural network (CNN), to standardise spirometric manoeuvre acceptability and usability.Methods and methodsIn 36 873 curves from the national health and nutritional examination survey (NHANES) USA 2011–12, technicians labelled 54% of curves as meeting ATS/ERS 2005 acceptability criteria with satisfactory start and end of test but identified 93% of curves with a usable FEV1. We processed raw data into images of maximal expiratory flow-volume curve (MEFVC), calculated ATS/ERS quantifiable criteria, and developed CNNs to determine manoeuvre acceptability and usability on 90% of the curves. The models were tested on the remaining 10% of curves. We calculated Shapley values to interpret the models.ResultsIn the test set (N=3738), CNN showed an accuracy of 87% for acceptability and 92% for usability, with the latter demonstrating a high sensitivity (92%) and specificity (96%). They were significantly superior (p<0.0001) to ATS/ERS quantifiable rule-based models. Shapley interpretation revealed MEFVC<1 s (MEFVC pattern within first second of exhalation) and plateau in volume-time were most important in determining acceptability, while MEFVC<1 s entirely determined usability.ConclusionThe CNNs identified relevant attributes in spirometric curves to standardise ATS/ERS manoeuvre acceptability and usability recommendations, and further provides individual manoeuvre feedback. Our algorithm combines the visual experience of skilled technicians and ATS/ERS quantitative rules in automating the critical phase of spirometry quality control.

scholarly journals A64 Viral sequence classification using deep learning algorithms

2019 ◽  
Vol 5 (Supplement_1) ◽  
Author(s):  
David Nieuwenhuijse ◽  
Bas Oude Munnink ◽  
My Phan ◽  
Marion Koopmans
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Learning Algorithms ◽  
High Sensitivity ◽  
Current Approach ◽  
Metagenomic Sequencing ◽  
Public Health Importance ◽  
Short Reads ◽  
Deep Learning Algorithm ◽  
High Threat

Abstract Sewage samples have a high potential benefit for surveillance of circulating pathogens because they are easy to obtain and reflect population-wide circulation of pathogens. These type of samples typically contain a great diversity of viruses. Therefore, one of the main challenges of metagenomic sequencing of sewage for surveillance is sequence annotation and interpretation. Especially for high-threat viruses, false positive signals can trigger unnecessary alerts, but true positives should not be missed. Annotation thus requires high sensitivity and specificity. To better interpret annotated reads for high-threat viruses, we attempt to determine how classifiable they are in a background of reads of closely related low-threat viruses. As an example, we attempted to distinguish poliovirus reads, a virus of high public health importance, from other enterovirus reads. A sequence-based deep learning algorithm was used to classify reads as either polio or non-polio enterovirus. Short reads were generated from 500 polio and 2,000 non-polio enterovirus genomes as a training set. By training the algorithm on this dataset we try to determine, on a single read level, which short reads can reliably be labeled as poliovirus and which cannot. After training the deep learning algorithm on the generated reads we were able to calculate the probability with which a read can be assigned to a poliovirus genome or a non-poliovirus genome. We show that the algorithm succeeds in classifying the reads with high accuracy. The probability of assigning the read to the correct class was related to the location in the genome to which the read mapped, which conformed with our expectations since some regions of the genome are more conserved than others. Classifying short reads of high-threat viral pathogens seems to be a promising application of sequence-based deep learning algorithms. Also, recent developments in software and hardware have facilitated the development and training of deep learning algorithms. Further plans of this work are to characterize the hard-to-classify regions of the poliovirus genome, build larger training databases, and expand on the current approach to other viruses.

Real-world application of Spirometry Quality Control Deep-Learning Algorithm

2021 ◽  
Author(s):  
Sanja Stanojevic ◽  
Pippa Powell ◽  
Graham Hall ◽  
Marko Topalovic ◽  
Nilakash Das ◽  
...  
Keyword(s):  
Quality Control ◽  
Deep Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Deep Learning Algorithm ◽  
Real World Application

scholarly journals Area under the expiratory flow-volume curve: predicted values by regression and deep learning methods and recommendations for clinical practice

2021 ◽  
Vol 8 (1) ◽  
pp. e000925
Author(s):  
Octavian C Ioachimescu ◽  
José A Ramos ◽  
Michael Hoffman ◽  
James K Stoller
Keyword(s):  
Deep Learning ◽  
Clinical Practice ◽  
Learning Algorithm ◽  
Flow Volume ◽  
Additional Tool ◽  
Volume Curve ◽  
Simple Regression Model ◽  
Flow Volume Curve ◽  
Expiratory Flow ◽  
Simple Regression

BackgroundIn spirometry, the area under expiratory flow-volume curve (AEX-FV) was found to perform well in diagnosing and stratifying physiologic impairments, potentially lessening the need for complex lung volume testing. Expanding on prior work, this study assesses the accuracy and the utility of several models of estimating AEX-FV based on forced vital capacity (FVC) and several instantaneous flows. These models could be incorporated in regular spirometry reports, especially when actual AEX-FV measurements are not available.MethodsWe analysed 4845 normal spirometry tests, performed on 3634 non-smoking subjects without known respiratory disease or complaints. Estimated AEX-FV was computed based on FVC and several flows: peak expiratory flow, isovolumic forced expiratory flow at 25%, 50% and 75% of FVC (FEF25, FEF50 and FEF75, respectively). The estimations were based on simple regression with and without interactions, by optimised regression models and by a deep learning algorithm that predicted the response surface of AEX-FV without interference from any predictor collinearities or normality assumption violations.ResultsMedian/IQR of actual square root of AEX-FV was 3.8/3.1–4.5 L2/s. The per cent of variance (R2) explained by the models selected was very high (>0.990), the effect of collinearities was negligible and the use of deep learning algorithms likely unnecessary for regular or routine pulmonary function testing laboratory usage.ConclusionsIn the absence of actual AEX-FV, a simple regression model without interactions between predictors or use of optimisation techniques can provide a reasonable estimation for clinical practice, thus making AEX-FV an easily available additional tool for interpreting spirometry.

scholarly journals SalaciaML: A Deep Learning Approach for Supporting Ocean Data Quality Control

2021 ◽  
Vol 8 ◽  
Author(s):  
Sebastian Mieruch ◽  
Serdar Demirel ◽  
Simona Simoncelli ◽  
Reiner Schlitzer ◽  
Steffen Seitz
Keyword(s):  
Quality Control ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Learning Approach ◽  
Data Quality Control ◽  
Deep Learning Algorithm ◽  
Mediterranean Regions ◽  
Control Procedures ◽  
Data Collections ◽  
Automated Quality Control

We present a skillful deep learning algorithm for supporting quality control of ocean temperature measurements, which we name SalaciaML according to Salacia the roman goddess of sea waters. Classical attempts to algorithmically support and partly automate the quality control of ocean data profiles are especially helpful for the gross errors in the data. Range filters, spike detection, and data distribution checks remove reliably the outliers and errors in the data, still wrong classifications occur. Various automated quality control procedures have been successfully implemented within the main international and EU marine data infrastructures (WOD, CMEMS, IQuOD, SDN) but their resulting data products are still containing data anomalies, bad data flagged as good and vice-versa. They also include visual inspection of suspicious measurements, which is a time consuming activity, especially if the number of suspicious data detected is large. A deep learning approach could highly improve our capabilities to quality assess big data collections and contemporary reducing the human effort. Our algorithm SalaciaML is meant to complement classical automated quality control procedures in supporting the time consuming visually inspection of data anomalies by quality control experts. As a first approach we applied the algorithm to a large dataset from the Mediterranean Sea. SalaciaML has been able to detect correctly more than 90% of all good and/or bad data in 11 out of 16 Mediterranean regions.

scholarly journals Radiation-Induced Pneumonitis in the Era of the COVID-19 Pandemic: Artificial Intelligence for Differential Diagnosis

Cancers ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1960
Author(s):  
Francesco Maria Giordano ◽  
Edy Ippolito ◽  
Carlo Cosimo Quattrocchi ◽  
Carlo Greco ◽  
Carlo Augusto Mallio ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
High Sensitivity ◽  
Low Risk ◽  
Control Group ◽  
Significance Threshold ◽  
Deep Learning Algorithm ◽  
Risk Probability

(1) Aim: To test the performance of a deep learning algorithm in discriminating radiation therapy-related pneumonitis (RP) from COVID-19 pneumonia. (2) Methods: In this retrospective study, we enrolled three groups of subjects: pneumonia-free (control group), COVID-19 pneumonia and RP patients. CT images were analyzed by mean of an artificial intelligence (AI) algorithm based on a novel deep convolutional neural network structure. The cut-off value of risk probability of COVID-19 was 30%; values higher than 30% were classified as COVID-19 High Risk, and values below 30% as COVID-19 Low Risk. The statistical analysis included the Mann–Whitney U test (significance threshold at p < 0.05) and receiver operating characteristic (ROC) curve, with fitting performed using the maximum likelihood fit of a binormal model. (3) Results: Most patients presenting RP (66.7%) were classified by the algorithm as COVID-19 Low Risk. The algorithm showed high sensitivity but low specificity in the detection of RP against COVID-19 pneumonia (sensitivity = 97.0%, specificity = 2%, area under the curve (AUC = 0.72). The specificity increased when an estimated COVID-19 risk probability cut-off of 30% was applied (sensitivity 76%, specificity 63%, AUC = 0.84). (4) Conclusions: The deep learning algorithm was able to discriminate RP from COVID-19 pneumonia, classifying most RP cases as COVID-19 Low Risk.

Sign in / Sign up

Export Citation Format

Share Document