scholarly journals Manual Annotation of Time in Bed Using Free-Living Recordings of Accelerometry Data

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8442
Author(s):  
Esben Lykke Skovgaard ◽  
Jesper Pedersen ◽  
Niels Christian Møller ◽  
Anders Grøntved ◽  
Jan Christian Brønd
Keyword(s):  
Correlation Coefficients ◽  
Accelerometer Data ◽  
Manual Annotation ◽  
Rater Agreement ◽  
Sleep Diaries ◽  
Annotation Method ◽  
Time In Bed ◽  
Interclass Correlation ◽  
Novel Method

With the emergence of machine learning for the classification of sleep and other human behaviors from accelerometer data, the need for correctly annotated data is higher than ever. We present and evaluate a novel method for the manual annotation of in-bed periods in accelerometer data using the open-source software Audacity®, and we compare the method to the EEG-based sleep monitoring device Zmachine® Insight+ and self-reported sleep diaries. For evaluating the manual annotation method, we calculated the inter- and intra-rater agreement and agreement with Zmachine and sleep diaries using interclass correlation coefficients and Bland–Altman analysis. Our results showed excellent inter- and intra-rater agreement and excellent agreement with Zmachine and sleep diaries. The Bland–Altman limits of agreement were generally around ±30 min for the comparison between the manual annotation and the Zmachine timestamps for the in-bed period. Moreover, the mean bias was minuscule. We conclude that the manual annotation method presented is a viable option for annotating in-bed periods in accelerometer data, which will further qualify datasets without labeling or sleep records.

Chemometric Analysis for the Classification of some Groups of Drugs with Divergent Pharmacological Activity on the Basis of some Chromatographic and Molecular Modeling Parameters

2018 ◽  
Vol 21 (2) ◽  
pp. 125-137
Author(s):  
Jolanta Stasiak ◽  
Marcin Koba ◽  
Marcin Gackowski ◽  
Tomasz Baczek
Keyword(s):  
Correlation Analysis ◽  
Pharmacological Activity ◽  
Correlation Coefficients ◽  
Principal Component ◽  
Cardiovascular Drugs ◽  
New Drugs ◽  
Analgesic Drugs ◽  
Starting Point ◽  
Chromatographic Parameters

Aim and Objective: In this study, chemometric methods as correlation analysis, cluster analysis (CA), principal component analysis (PCA), and factor analysis (FA) have been used to reduce the number of chromatographic parameters (logk/logkw) and various (e.g., 0D, 1D, 2D, 3D) structural descriptors for three different groups of drugs, such as 12 analgesic drugs, 11 cardiovascular drugs and 36 “other” compounds and especially to choose the most important data of them. Material and Methods: All chemometric analyses have been carried out, graphically presented and also discussed for each group of drugs. At first, compounds’ structural and chromatographic parameters were correlated. The best results of correlation analysis were as follows: correlation coefficients like R = 0.93, R = 0.88, R = 0.91 for cardiac medications, analgesic drugs, and 36 “other” compounds, respectively. Next, part of molecular and HPLC experimental data from each group of drugs were submitted to FA/PCA and CA techniques. Results: Almost all results obtained by FA or PCA, and total data variance, from all analyzed parameters (experimental and calculated) were explained by first two/three factors: 84.28%, 76.38 %, 69.71% for cardiovascular drugs, for analgesic drugs and for 36 “other” compounds, respectively. Compounds clustering by CA method had similar characteristic as those obtained by FA/PCA. In our paper, statistical classification of mentioned drugs performed has been widely characterized and discussed in case of their molecular structure and pharmacological activity. Conclusion: Proposed QSAR strategy of reduced number of parameters could be useful starting point for further statistical analysis as well as support for designing new drugs and predicting their possible activity.

scholarly journals Interobserver agreement of the Paris and simplified classifications of superficial colonic lesions: a Western study

2021 ◽  
Vol 09 (03) ◽  
pp. E388-E394
Author(s):  
Francesco Cocomazzi ◽  
Marco Gentile ◽  
Francesco Perri ◽  
Antonio Merla ◽  
Fabrizio Bossa ◽  
...  
Keyword(s):  
Interobserver Agreement ◽  
Classification Systems ◽  
Sensitivity Analyses ◽  
Size Estimation ◽  
Rater Agreement ◽  
Staff Members ◽  
Video Clips ◽  
Paris Classification ◽  
Level Of Agreement

Abstract Background and study aims The Paris classification of superficial colonic lesions has been widely adopted, but a simplified description that subgroups the shape into pedunculated, sessile/flat and depressed lesions has been proposed recently. The aim of this study was to evaluate the accuracy and inter-rater agreement among 13 Western endoscopists for the two classification systems. Methods Seventy video clips of superficial colonic lesions were classified according to the two classifications, and their size estimated. The interobserver agreement for each classification was assessed using both Cohen k and AC1 statistics. Accuracy was taken as the concordance between the standard morphology definition and that made by participants. Sensitivity analyses investigated agreement between trainees (T) and staff members (SM), simple or mixed lesions, distinct lesion phenotypes, and for laterally spreading tumors (LSTs). Results Overall, the interobserver agreement for the Paris classification was substantial (κ = 0.61; AC1 = 0.66), with 79.3 % accuracy. Between SM and T, the values were superimposable. For size estimation, the agreement was 0.48 by the κ-value, and 0.50 by AC1. For single or mixed lesions, κ-values were 0.60 and 0.43, respectively; corresponding AC1 values were 0.68 and 0.57. Evaluating the several different polyp subtypes separately, agreement differed significantly when analyzed by the k-statistics (0.08–0.12) or the AC1 statistics (0.59–0.71). Analyses of LSTs provided a κ-value of 0.50 and an AC1 score of 0.62, with 77.6 % accuracy. The simplified classification outperformed the Paris classification: κ = 0.68, AC1 = 0.82, accuracy = 91.6 %. Conclusions Agreement is often measured with Cohen’s κ, but we documented higher levels of agreement when analyzed with the AC1 statistic. The level of agreement was substantial for the Paris classification, and almost perfect for the simplified system.

Multi-level Chunk-based Constituent-to-Dependency Treebank Transformation for Tibetan Dependency Parsing

2021 ◽  
Vol 20 (2) ◽  
pp. 1-12
Author(s):  
Shumin Shi ◽  
Dan Luo ◽  
Xing Wu ◽  
Congjun Long ◽  
Heyan Huang
Keyword(s):  
Language Processing ◽  
Manual Annotation ◽  
Syntactic Parsing ◽  
Dependency Parsing ◽  
Low Resource ◽  
Resource Setting ◽  
Dependency Tree ◽  
Low Resource Setting ◽  
Novel Method ◽  
Multi Level

Dependency parsing is an important task for Natural Language Processing (NLP). However, a mature parser requires a large treebank for training, which is still extremely costly to create. Tibetan is a kind of extremely low-resource language for NLP, there is no available Tibetan dependency treebank, which is currently obtained by manual annotation. Furthermore, there are few related kinds of research on the construction of treebank. We propose a novel method of multi-level chunk-based syntactic parsing to complete constituent-to-dependency treebank conversion for Tibetan under scarce conditions. Our method mines more dependencies of Tibetan sentences, builds a high-quality Tibetan dependency tree corpus, and makes fuller use of the inherent laws of the language itself. We train the dependency parsing models on the dependency treebank obtained by the preliminary transformation. The model achieves 86.5% accuracy, 96% LAS, and 97.85% UAS, which exceeds the optimal results of existing conversion methods. The experimental results show that our method has the potential to use a low-resource setting, which means we not only solve the problem of scarce Tibetan dependency treebank but also avoid needless manual annotation. The method embodies the regularity of strong knowledge-guided linguistic analysis methods, which is of great significance to promote the research of Tibetan information processing.

116 Behavioral Attention Raw Scores Best Differentiate Cognitive Resilience and Vulnerability to Sleep Loss

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A47-A48
Author(s):  
Erika Yamazaki ◽  
Tess Brieva ◽  
Courtney Casale ◽  
Caroline Antler ◽  
Namni Goel
Keyword(s):  
Correlation Coefficients ◽  
Response Speed ◽  
Sleep Loss ◽  
Vulnerable Groups ◽  
Average Performance ◽  
Psychomotor Vigilance Test ◽  
Time In Bed ◽  
Attention Performance ◽  
Optimal Approach ◽  
Psychomotor Vigilance

Abstract Introduction There are substantial, stable individual differences in cognitive performance resulting from sleep restriction (SR) and total sleep deprivation (TSD). The best method for defining cognitive resilience and vulnerability to sleep loss remains an unanswered, yet important question. To investigate this, we compared multiple approaches and cutoff thresholds to define resilience and vulnerability using the 10-minute Psychomotor Vigilance Test (PVT). Methods Forty-one healthy adults (ages 21-49; mean±SD, 33.9±8.9y; 18 females) participated in a 13-night experiment [2 baseline nights (10h-12h time-in-bed, TIB), 5 SR nights (4h TIB), 4 recovery nights (12h TIB), and 36h TSD]. The PVT was administered every 2h during wakefulness. PVT lapses (reaction time [RT]>500 ms) and 1/RT (response speed) were measured. Resilient and vulnerable groups were defined by three approaches: average performance during SR1-5, average performance change from baseline to SR1-5, and variance in performance during SR1-5. Within each approach, resilient/vulnerable groups were defined by +/- 1 standard deviation and by the top and bottom 12.5%, 20%, 25%, 33%, 50%. Bias-corrected and accelerated bootstrapped t-tests compared PVT performance between the resilient and vulnerable groups during baseline and SR1-5. Kendall’s tau correlations compared the ranking of individuals in each group. Results T-tests revealed that the resilient and vulnerable PVT lapses groups, defined by all three approaches, had significantly different mean PVT lapses at all cutoffs. Resilient and vulnerable PVT 1/RT groups, defined by raw scores and by change from baseline, had significantly different mean PVT 1/RT at all cutoffs. However, resilient/vulnerable PVT 1/RT groups defined by variance only differed at the 33% and 50% cutoffs. Notably, raw scores at baseline significantly differed between resilient/vulnerable groups for both PVT measures. Variance vs. raw scores and variance vs. change from baseline had the lowest correlation coefficients for both PVT measures. Conclusion Defining resilient and vulnerable groups by raw scores during SR1-5 produced the clearest differentiation between resilient and vulnerable groups at every cutoff threshold for PVT lapses and response speed. As such, we propose that using PVT raw score is the optimal approach to define resilient and vulnerable groups for behavioral attention performance during sleep loss. Support (if any) ONR Award No.N00014-11-1-0361;NIH UL1TR000003;NASA NNX14AN49G and 80NSSC20K0243;NIH R01DK117488

Converting Raw Accelerometer Data to Activity Counts Using Open-Source Code: Implementing a MATLAB Code in Python and R, and Comparing the Results to ActiLife

2021 ◽  
pp. 1-7
Author(s):  
Ruben Brondeel ◽  
Yan Kestens ◽  
Javad Rahimipour Anaraki ◽  
Kevin Stanley ◽  
Benoit Thierry ◽  
...  
Keyword(s):  
Open Source ◽  
Pearson Correlation ◽  
Vertical Axis ◽  
Accelerometer Data ◽  
Accelerometer Sensor ◽  
Interclass Correlation ◽  
Acceleration Data ◽  
The Right ◽  
Pearson Correlations ◽  
Closed Source

Background: Closed-source software for processing and analyzing accelerometer data provides little to no information about the algorithms used to transform acceleration data into physical activity indicators. Recently, an algorithm was developed in MATLAB that replicates the frequently used proprietary ActiLife activity counts. The aim of this software profile was (a) to translate the MATLAB algorithm into R and Python and (b) to test the accuracy of the algorithm on free-living data. Methods: As part of the INTErventions, Research, and Action in Cities Team, data were collected from 86 participants in Victoria (Canada). The participants were asked to wear an integrated global positioning system and accelerometer sensor (SenseDoc) for 10 days on the right hip. Raw accelerometer data were processed in ActiLife, MATLAB, R, and Python and compared using Pearson correlation, interclass correlation, and visual inspection. Results: Data were collected for a combined 749 valid days (>10 hr wear time). MATLAB, Python, and R counts per minute on the vertical axis had Pearson correlations with the ActiLife counts per minute of .998, .998, and .999, respectively. All three algorithms overestimated ActiLife counts per minute, some by up to 2.8%. Conclusions: A MATLAB algorithm for deriving ActiLife counts was implemented in R and Python. The different implementations provide similar results to ActiLife counts produced in the closed source software and can, for all practical purposes, be used interchangeably. This opens up possibilities to comparing studies using similar accelerometers from different suppliers, and to using free, open-source software.

scholarly journals A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data

2009 ◽  
Vol 56 (3) ◽  
pp. 871-879 ◽  
Author(s):  
Stephen J. Preece ◽  
John Yannis Goulermas ◽  
Laurence P. J. Kenney ◽  
David Howard
Keyword(s):  
Feature Extraction ◽  
Extraction Methods ◽  
Accelerometer Data

Comparing Computer-Derived and Human-Observed Scores for the Balance Error Scoring System

2016 ◽  
Vol 25 (2) ◽  
pp. 133-136 ◽  
Author(s):  
Jaclyn B. Caccese ◽  
Thomas W. Kaminski
Keyword(s):  
Athletic Training ◽  
Outcome Measures ◽  
Scoring System ◽  
Postural Stability ◽  
Correlation Coefficients ◽  
Current Standard ◽  
Interclass Correlation ◽  
Z Scores ◽  
Balance Error Scoring System ◽  
Balance Error

Context:The Balance Error Scoring System (BESS) is the current standard for assessing postural stability in concussed athletes on the sideline. However, research has questioned the objectivity and validity of the BESS, suggesting that while certain subcategories of the BESS have sufficient reliability to be used in evaluation of postural stability, the total score is not reliable, demonstrating limited interrater and intrarater reliability. Recently, a computerized BESS test was developed to automate scoring.Objective:To compare computerderived BESS scores with those taken from 3 trained human scorers.Design:Interrater reliability study.Setting:Athletic training room.Patients:NCAA Division I student athletes (53 male, 58 female; 19 ± 2 y, 168 ± 41 cm, 69 ± 4 kg).Interventions:Subjects were asked to perform the BESS while standing on the Tekscan (Boston, MA) MobileMat® BESS. The MobileMat BESS software displayed an error score at the end of each trial. Simultaneously, errors were recorded by 3 separate examiners. Errors were counted using the standard BESS scoring criteria.Main Outcome Measures:The number of BESS errors was computed for the 6 stances from the software and each of the 3 human scorers. Interclass correlation coefficients (ICCs) were used to compare errors for each stance scored by the MobileMat BESS software with each of 3 raters individually. The ICC values were converted to Fisher Z scores, averaged, and converted back into ICC values.Results:The double-leg, single-leg, and tandem-firm stances resulted in good agreement with human scorers (ICC = .999, .731, and .648). All foam stances resulted in fair agreement.Conclusions:Our results suggest that the MobileMat BESS is suitable for identifying BESS errors involving each of the 6 stances of the BESS protocol. Because the MobileMat BESS scores consistently and reliably, this system can be used with confidence by clinicians as an effective alternative to scoring the BESS.

scholarly journals Visual Analogue Scales as a Tool for Initial Assessment of Tinnitus Severity: Psychometric Evaluation in a Clinical Population

2018 ◽  
Vol 23 (4) ◽  
pp. 229-237 ◽  
Author(s):  
Danuta Raj-Koziak ◽  
Elzbieta Gos ◽  
Weronika Swierniak ◽  
Joanna J. Rajchel ◽  
Lucyna Karpiesz ◽  
...  
Keyword(s):  
Correlation Coefficients ◽  
Psychometric Evaluation ◽  
Clinical Population ◽  
Initial Assessment ◽  
Tinnitus Severity ◽  
Interclass Correlation ◽  
Bland Altman Method ◽  
Patient Reported ◽  
Brief Screening ◽  
Analogue Scales

The aim of this study was to evaluate the psychometric properties of patient-reported visual analogue scale (VAS) ratings. All of the participants (100 Polish-speaking adults) completed a Tinnitus Functional Index (TFI) once and a 4-component VAS twice over a period of 3 days. Spearman’s correlation coefficients between the VAS score and global TFI ranged from ρ = 0.52 for VAS-coping (VAS-C) to ρ = 0.81 for VAS-annoyance (VAS-A). Using the Bland-Altman method, the agreement ranged from 93% for VAS-A to 96% for VAS-distress (VAS-D). Interclass correlation coefficients ranged from 0.67 for VAS-C to 0.90 for VAS-A. The VAS cutoff points representing significant tinnitus severity ranged from 45 points for VAS-C to 66 points for VAS-D. VAS scales are a valid and reliable brief screening tool for obtaining quick information about tinnitus.

scholarly journals An in vitro Comparison of Root Canal Measurement in Permanent Teeth by Electronic Apex Locator, Conventional and Digital Radiography

2011 ◽  
Vol 2 (4) ◽  
pp. 312-315
Author(s):  
Alexander LNU ◽  
Musab Hamed Saeed ◽  
Nazil A Abtahl ◽  
A Praveen Pradeep
Keyword(s):  
Failure Rate ◽  
Digital Radiography ◽  
Root Canal ◽  
Correlation Coefficients ◽  
Conventional Radiography ◽  
Permanent Teeth ◽  
Radiographic Measurements ◽  
Interclass Correlation ◽  
Working Length ◽  
Electronic Apex Locator

ABSTRACT Introduction In endodontic treatment for permanent teeth, it is important to estimate the working length precisely. Currently, various methods are used in clinical practice for working length estimation. The objective of this study is to compare the accuracy of root canal length in permanent teeth determined by electronic apex locators, conventional and digital radiography. Materials and methods A total of 50 single rooted permanent teeth with mature apices were extracted for periodontal reasons and obtained from different sources without caries were studied. The radiographic measurements were done using paralleling technique. Electronic measurements were done next using third generation, DentAport ZX. Actual canal length of each tooth was measured using direct observation of the apical exit of the file. Measurements obtained from radiographic and electronic methods were compared to the actual tooth length. Interclass correlation coefficients and failure rate for each method and their combinations were calculated using STATA 12.0 software. Results The measurements obtained through all the three techniques showed high interclass correlation coefficients and excellent level of agreement. The failure rate of measurements obtained through conventional radiography, digital radiography and electronic apex locators was 38, 30 and 22% respectively. Combination of conventional radiography with electronic apex locator showed an accuracy of 90%, while combination of digital radiographs and electronic apex locators given an accuracy of 96%. Conclusion A combination of digital radiographic and apex locator methods for determining the root canal length in permanent teeth can be considered safe, reliable and precise.

scholarly journals Repeatability of a Dual-Scheimpflug Placido Disc Corneal Tomographer/Topographer in Eyes with Keratoconus

2020 ◽  
Author(s):  
Anne Poulsen ◽  
Diane Jang ◽  
Mahmood Khan ◽  
Zaina Nabil Al-Mohtaseb ◽  
Michael Chen ◽  
...  
Keyword(s):  
Image Quality ◽  
Spherical Aberration ◽  
Correlation Coefficients ◽  
Quality Metrics ◽  
Corneal Surgery ◽  
Image Quality Metrics ◽  
Interclass Correlation ◽  
Intrastromal Corneal Ring ◽  
History Of ◽  
Image Quality Metric

Purpose: To investigate the repeatability of a combined Dual-Scheimpflug placido disc corneal topographer (Zeimer Galilei G4) with respect to keratometric indices used to monitor progression of keratoconus (KCN). Methods: Patients with KCN were prospectively enrolled. For each eye lacking history of corneal surgery, 5 measurements were taken in succession. Eyes in which 3 or more measurements could be obtained (defined by the device's 4 image quality metrics) were included in the analysis. The repeatability limits (RL) and interclass correlation coefficients (ICC) were calculated for various parameters. Results: 32 eyes from 25 patients met all image quality metrics, and 54 eyes from 38 patients met at least 3/4 criteria (all except the placido image quality metric). RLs for key parameters when 4/4 or 3/4 image quality metrics were met included: 0.37 and 0.77 diopters (D) for steep simulated keratometry, 0.79 and 1.65 D for maximum keratometry, 13.80 and 13.88 degrees for astigmatism axis, 0.64 and 0.56 um for vertical coma magnitude, and 3.76 and 3.84 um for thinnest pachymetry, respectively. The ICCs for all parameters were excellent [above 0.87 except for spherical aberration (0.77)]. Conclusions: The dual-Scheimpflug placido disc corneal topographer is highly repeatable in quantifying parameters used in monitoring KCN. Excellent placido images are difficult to capture in eyes with KCN, but when available, increase the reliability of the measurements. The RLs may be especially helpful in detecting progression in mild KCN when interventions such as corneal cross-linking or intrastromal corneal ring segments are most beneficial.

Sign in / Sign up

Export Citation Format

Share Document