Manual scoring of periodic limb movements in children: is it still necessary?

OBJECTIVE: Although manual scoring has been classically considered the gold standard to identify periodic leg movements (PLM), it is a very time consuming and expensive process, also subject to variability in interpretation. In the last decades, different authors have observed reasonably good agreement between automated PSG scoring algorithms and manual scoring in adults, according to established criteria. We aim to compare the automatic software analysis of our polysomnogram with the manual staging in children with sleep-disordered breathing. METHODS: We performed a semiautomatic method, in which an experienced technician watched the video recording and removed from the automatic analysis those movements that did not correspond to true candidate leg movement (LM). RESULTS: A total of 131 PSGs were studied; applying the established criteria, 65 children were diagnosed of obstructive sleep apnea, and 66 presented snoring but with no sleep apnea. The mean age was 6.7 years (±1.7) and twenty-five children (19.08 %) had a PLMI >5/h. Statistical differences were found not only for PLMI (manual: 2.20 (0.7, 4.1) vs automatic (6.4 (3.85,9.5); p < 0.001), but for almost of all indexes assessed between the automatic and the manual scoring analysis. The level of concordance was only moderate for PLM index (0.63 [0.51-0.72]); showing that, unlike the articles published in the adult population, automatic analysis is not accurate in children and, manually or semi-automatically analysis as ours need to be done. CONCLUSION: It seems that PLM detection algorithm might work accurately but, the real need would be a true LM detection algorithm.

Research and application of deep learning-based sleep staging: Data, modeling, validation, and clinical practice.

Over the past few decades, researchers have attempted to simplify and accelerate the process of sleep stage classification through various approaches; however, only a few such approaches have gained widespread acceptance. Artificial intelligence technology, particularly deep learning, is promising for earning the trust of the sleep medicine community in automated sleep-staging systems, thus facilitating its application in clinical practice and integration into daily life. We aimed to comprehensively review the latest methods that are applying deep learning for enhancing sleep staging efficiency and accuracy. Starting from the requisite "data" for constructing deep learning algorithms, we elucidated the current landscape of this domain and summarized the fundamental modeling process, encompassing signal selection, data pre-processing, model architecture, classification tasks, and performance metrics. Furthermore, we reviewed the applications of automated sleep staging in scenarios such as sleep-disorder screening, diagnostic procedures, and health monitoring and management. Finally, we conducted an in-depth analysis and discussion of the challenges and future in intelligent sleep staging, particularly focusing on large-scale sleep datasets, interdisciplinary collaborations, and human-computer interactions.

Scoring thermal limits in small insects using open-source, computer-assisted motion detection.

Scoring thermal tolerance traits live or with recorded video can be time consuming and susceptible to observer bias, and as with many physiological measurements, there can be trade-offs between accuracy and throughput. Recent studies show that automated particle tracking is a viable alternative to manually scoring videos, although some of the software options are proprietary and costly. In this study, we present a novel strategy for automated scoring of thermal tolerance videos by inferring motor activity with motion detection using an open-source Python command line application called DIME (detector of insect motion endpoint). We apply our strategy to both dynamic and static thermal tolerance assays, and our results indicate that DIME can accurately measure thermal acclimation responses, generally agrees with visual estimates of thermal limits, and can significantly increase throughput over manual methods.

Performance evaluation of the open-source Yet Another Spindle Algorithm sleep staging algorithm against gold standard manual evaluation of polysomnographic records in adolescence.

GOAL AND AIMS: To evaluate an automatic sleep scoring algorithm against manual polysomnography sleep scoring. FOCUS METHOD/TECHNOLOGY: Yet Another Spindle Algorithm automatic sleep staging algorithm. REFERENCE METHOD/TECHNOLOGY: Manual sleep scoring. SAMPLE: 327 nights (151 healthy adolescents), from the NCANDA study. DESIGN: Participants underwent one-to-three overnight polysomnography recordings, one consisting of an event-related-potential paradigm. CORE ANALYTICS: Epoch by Epoch and discrepancy analyses (Bland Altman plots) were conducted on the overall sample. ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES: Epoch by Epoch and discrepancy analysis were repeated separately on standard polysomnography nights and event-related potential nights. Regression models were estimated on age, sex, scorer, and site of recording, separately on standard polysomnography nights and event-related potential nights. CORE OUTCOMES: The Yet Another Spindle Algorithm sleep scoring algorithm's average sensitivity of 93.04% for Wake, 87.67% for N2, 84.46% for N3, 86.02% for rapid-eye-movement, and 40.39% for N1. Specificity was 96.75% for Wake, 97.31% for N1, 88.87% for N2, 97.99% for N3, and 97.70% for rapid-eye-movement. The Matthews Correlation Coefficient was highest in rapid-eye-movement sleep (0.85) while lowest in N1 (0.39). Cohen's Kappa mirrored Matthews Correlation Coefficient results. In Bland-Altman plots, the bias between Yet Another Spindle Algorithm and human scoring showed proportionality to the manual scoring measurement size. IMPORTANT ADDITIONAL OUTCOMES: Yet Another Spindle Algorithm performance was reduced in event-related-potential/polysomnography nights for N3 and rapid-eye-movement. According to the Matthews Correlation Coefficient, the Yet Another Spindle Algorithm performance was affected by younger age, male sex, recording sites, and scorers. CORE CONCLUSION: Results support the use of Yet Another Spindle Algorithm to score adolescents' polysomnography sleep records, possibly with classification outcomes supervised by an expert scorer.

Influence of computed tomography slice thickness on deep learning-based, automatic coronary artery calcium scoring software performance.

Background: The influence of computed tomography (CT) slice thickness on the accuracy of deep learning (DL)-based, automatic coronary artery calcium (CAC) scoring software has not been explored yet. Methods: This retrospective study included 844 subjects (477 men, mean age of 58.9±10.7 years) who underwent electrocardiogram (ECG)-gated CAC scoring CT scans with 1.5 and 3 mm slice thickness values between September 2013 and October 2020. Automatic CAC scoring was performed using DL-based software (3D patch-based U-Net architectures). Manual CAC scoring was set as the reference standard. The reliability of automatic CAC scoring was evaluated using intraclass correlation coefficients (ICCs) for both the 1.5 and 3 mm datasets. The agreement of CAC severity categories [Agatston score (AS) 0, 1-100, 101-400, >400] between automatic CAC scoring and the reference standard was analyzed using weighted kappa (κ) statistics for both 1.5 and 3 mm datasets. Results: The CAC scoring agreement between the automatic CAC scoring and reference standard was excellent (ICC 0.982 for 1.5 mm, 0.969 for 3 mm, respectively). The categorical agreement of CAC severity between two methods was excellent for both 1.5 and 3 mm scans, with better agreement for 3 mm scans (weighted κ: 0.851 and 0.961, 95% confidence intervals: 0.823-0.879 and 0.945-0.974, respectively). Conclusions: Automatic CAC scoring shows excellent agreement with the reference standard for both 1.5 and 3 mm scans but results in lower agreement in the CAC severity category for 1.5 mm scans.

Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis.

STUDY OBJECTIVES: We evaluated the validity of a squeeze-and-excitation and multiscaled fusion network (SE-MSCNN) using single-lead electrocardiogram (ECG) signals for obstructive sleep apnea detection and classification. METHODS: Overnight polysomnographic data from 436 participants at the Sleep Center of the First Affiliated Hospital of Sun Yat-sen University were used to generate a new FAH-ECG dataset comprising 260, 88, and 88 single-lead ECG signal recordings for training, validation, and testing, respectively. The SE-MSCNN was employed for detection of apnea-hypopnea events from the acquired ECG segments. Sensitivity, specificity, accuracy, and F1 scores were assigned to assess algorithm performance. We also used the SE-MSCNN to estimate the apnea-hypopnea index, classify obstructive sleep apnea severity, and compare the agreement between 2 sleep technicians. RESULTS: The SE-MSCNN's accuracy, sensitivity, specificity, and F1 score on the FAH-ECG dataset were 86.6%, 83.3%, 89.1%, and 0.843, respectively. Although slightly inferior to previously reported results using public datasets, it is superior to state-of-the-art open-source models. Furthermore, the SE-MSCNN had good agreement with manual scoring, such that the Spearman's correlations for the apnea-hypopnea index between the SE-MSCNN and 2 technicians were 0.93 and 0.94, respectively. Cohen's kappa scores in classifying the SE-MSCNN and the 2 sleep technicians were 0.72 and 0.78, respectively. CONCLUSIONS: In this study, we validated the use of the SE-MSCNN in a clinical environment, and despite some limitations the network appeared to meet the performance standards for generalizability. Therefore, updating algorithms based on single-lead ECG signals can facilitate the development of novel wearable devices for efficient obstructive sleep apnea screening. CITATION: Yue H, Li P, Li Y, et al. Validity study of a multiscaled fusion network using single-lead electrocardiogram signals for obstructive sleep apnea diagnosis. J Clin Sleep Med. 2023;19(6):1017-1025.

Validation of a wearable forehead sleep recorder against polysomnography in sleep staging and desaturation events in a clinical sample.

STUDY OBJECTIVES: Wearable sleep recording devices may be a helpful alternative method for polysomnography (PSG) due to their higher accessibility and comfort as well as lower cost, but their validities need to be examined. The aim of this study was to evaluate the accuracy of a novel single-channel, electroencephalography-based wearable forehead sleep recorder (UMindSleep) to assess sleep staging and oxygen desaturation. METHODS: Two hundred and three Chinese adults recruited from a sleep medicine center underwent an overnight study wearing UMindSleep and PSG simultaneously. Sleep parameters including sleep staging and oxygen desaturation index were compared between UMindSleep and PSG. RESULTS: A total of 195,349 valid epochs from 197 participants (171 with obstructive sleep apnea, 86.8%) were included in analyses of sleep staging. Sensitivities of UMindSleep compared to PSG were 79.7% for wake, 85.8% for light sleep, 79.4% for deep sleep, and 82.7% for rapid eye movement sleep. Specificities were 95.3% for wake, 83.4% for light sleep, 97.0% for deep sleep, and 96.8% for rapid eye movement sleep. Furthermore, the kappa agreements of 0.69-0.79 were indicative of a substantial agreement for sleep staging between UMindSleep and PSG. Sensitivity and specificity regarding oxygen desaturation index were 93.4% and 88.9%, yielding a kappa coefficient of 0.82. CONCLUSIONS: Our findings suggest that UMindSleep may serve as a feasible, accurate, and dependable device for screening of sleep disorders (eg, obstructive sleep apnea) and assessing sleep structure. CITATION: Chen X, Jin X, Zhang J, Ho KW, Wei Y, Cheng H. Validation of a wearable forehead sleep recorder against polysomnography in sleep staging and desaturation events in a clinical sample. J Clin Sleep Med. 2023;19(4):711-718.

Disease Incidence and Severity of Cercospora Leaf Spot in Sugar Beet Assessed by Multispectral Unmanned Aerial Images and Machine Learning.

Disease incidence (DI) and metrics of disease severity are relevant parameters for decision making in plant protection and plant breeding. To develop automated and sensor-based routines, a sugar beet variety trial was inoculated with Cercospora beticola and monitored with a multispectral camera system mounted to an unmanned aerial vehicle (UAV) over the vegetation period. A pipeline based on machine learning methods was established for image data analysis and extraction of disease-relevant parameters. Features based on the digital surface model, vegetation indices, shadow condition, and image resolution improved classification performance in comparison with using single multispectral channels in 12 and 6% of diseased and soil regions, respectively. With a postprocessing step, area-related parameters were computed after classification. Results of this pipeline also included extraction of DI and disease severity (DS) from UAV data. The calculated area under disease progress curve of DS was 2,810.4 to 7,058.8%.days for human visual scoring and 1,400.5 to 4,343.2%.days for UAV-based scoring. Moreover, a sharper differentiation of varieties compared with visual scoring was observed in area-related parameters such as area of complete foliage (AF), area of healthy foliage (AH), and mean area of lesion by unit of foliage ([Formula: see text]). These advantages provide the option to replace the laborious work of visual disease assessments in the field with a more precise, nondestructive assessment via multispectral data acquired by UAV flights.[Formula: see text] Copyright © 2023 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license.

Automatic SCOring of Atopic Dermatitis Using Deep Learning: A Pilot Study.

Atopic dermatitis (AD) is a chronic, itchy skin condition that affects 15-20% of children but may occur at any age. It is estimated that 16.5 million US adults (7.3%) have AD that initially began at age >2 years, with nearly 40% affected by moderate or severe disease. Therefore, a quantitative measurement that tracks the evolution of AD severity could be extremely useful in assessing patient evolution and therapeutic efficacy. Currently, SCOring Atopic Dermatitis (SCORAD) is the most frequently used measurement tool in clinical practice. However, SCORAD has the following disadvantages: (i) time consuming-calculating SCORAD usually takes about 7-10 minutes per patient, which poses a heavy burden on dermatologists and (ii) inconsistency-owing to the complexity of SCORAD calculation, even well-trained dermatologists could give different scores for the same case. In this study, we introduce the Automatic SCORAD, an automatic version of the SCORAD that deploys state-of-the-art convolutional neural networks that measure AD severity by analyzing skin lesion images. Overall, we have shown that Automatic SCORAD may prove to be a rapid and objective alternative method for the automatic assessment of AD, achieving results comparable with those of human expert assessment while reducing interobserver variability.

Variability of sleep stage scoring in late midlife and early old age.

Sleep stage scoring can lead to important inter-expert variability. Although likely, whether this issue is amplified in older populations, which show alterations of sleep electrophysiology, has not been thoroughly assessed. Algorithms for automatic sleep stage scoring may appear ideal to eliminate inter-expert variability. Yet, variability between human experts and algorithm sleep stage scoring in healthy older individuals has not been investigated. Here, we aimed to compare stage scoring of older individuals and hypothesized that variability, whether between experts or considering the algorithm, would be higher than usually reported in the literature. Twenty cognitively normal and healthy late midlife individuals' (61 ± 5 years; 10 women) night-time sleep recordings were scored by two experts from different research centres and one algorithm. We computed agreements for the entire night (percentage and Cohen's κ) and each sleep stage. Whole-night pairwise agreements were relatively low and ranged from 67% to 78% (κ, 0.54-0.67). Sensitivity across pairs of scorers proved lowest for stages N1 (8.2%-63.4%) and N3 (44.8%-99.3%). Significant differences between experts and/or algorithm were found for total sleep time, sleep efficiency, time spent in N1/N2/N3 and wake after sleep onset (p ≤ 0.005), but not for sleep onset latency, rapid eye movement (REM) and slow-wave sleep (SWS) duration (N2 + N3). Our results confirm high inter-expert variability in healthy aging. Consensus appears good for REM and SWS, considered as a whole. It seems more difficult for N3, potentially because human raters adapt their interpretation according to overall changes in sleep characteristics. Although the algorithm does not substantially reduce variability, it would favour time-efficient standardization.

Automatic, Qualitative Scoring of the Clock Drawing Test (CDT) Based on U-Net, CNN and Mobile Sensor Data.

The Clock Drawing Test (CDT) is a rapid, inexpensive, and popular screening tool for cognitive functions. In spite of its qualitative capabilities in diagnosis of neurological diseases, the assessment of the CDT has depended on quantitative methods as well as manual paper based methods. Furthermore, due to the impact of the advancement of mobile smart devices imbedding several sensors and deep learning algorithms, the necessity of a standardized, qualitative, and automatic scoring system for CDT has been increased. This study presents a mobile phone application, mCDT, for the CDT and suggests a novel, automatic and qualitative scoring method using mobile sensor data and deep learning algorithms: CNN, a convolutional network, U-Net, a convolutional network for biomedical image segmentation, and the MNIST (Modified National Institute of Standards and Technology) database. To obtain DeepC, a trained model for segmenting a contour image from a hand drawn clock image, U-Net was trained with 159 CDT hand-drawn images at 128 × 128 resolution, obtained via mCDT. To construct DeepH, a trained model for segmenting the hands in a clock image, U-Net was trained with the same 159 CDT 128 × 128 resolution images. For obtaining DeepN, a trained model for classifying the digit images from a hand drawn clock image, CNN was trained with the MNIST database. Using DeepC, DeepH and DeepN with the sensor data, parameters of contour (0-3 points), numbers (0-4 points), hands (0-5 points), and the center (0-1 points) were scored for a total of 13 points. From 219 subjects, performance testing was completed with images and sensor data obtained via mCDT. For an objective performance analysis, all the images were scored and crosschecked by two clinical experts in CDT scaling. Performance test analysis derived a sensitivity, specificity, accuracy and precision for the contour parameter of 89.33, 92.68, 89.95 and 98.15%, for the hands parameter of 80.21, 95.93, 89.04 and 93.90%, for the numbers parameter of 83.87, 95.31, 87.21 and 97.74%, and for the center parameter of 98.42, 86.21, 96.80 and 97.91%, respectively. From these results, the mCDT application and its scoring system provide utility in differentiating dementia disease subtypes, being valuable in clinical practice and for studies in the field.

Is the Nox-T3 device scoring algorithm accurate enough for the diagnosis of obstructive sleep apnea?

INTRODUCTION: Obstructive sleep apnea (OSA) is highly prevalent. Home sleep apnea testing (HSAT) for OSA is rapidly expanding because of its cost effectiveness in the diagnosis of OSA. Type 3 portable monitors are used for this purpose. In most cases, these devices contain an algorithm for automatic scoring of events. We propose to study the accuracy of the automatic scoring algorithm in our population in order to compare it with the manually edited scoring of Nox-T3®. MATERIAL AND METHODS: For five months, a prospective study was performed. Patients were randomly distributed to the available HSAT devices. We collected the data of patients who performed HSAT with Nox-T3®. We used normality plots, the Spearman correlation, the Wilcoxon signed-rank test, and Bland-Altman plots. RESULTS: The sample consisted of 283 participants. The average manual apnea and hypopnea index (AHI) was 23.7 ± 22.1 events/h. All manual scores (AHI, apnea index, hypopnea index, and oxygen desaturation index) had strong correlations with their respective automated scores. When AHI > 15 and AHI > 30 the difference between the values of this index (automatic and manual) was not statistically significant. Also, for AHI values > 15 the mean difference between the two scoring methods was 0.17 events/h. For AHI values > 30, this difference was - 1.23 events/h. CONCLUSIONS: When AHI is < 15, there may be a need for confirmation of automatic scores, especially in symptomatic patients with a high pretest probability of OSA. But, for patients with AHI > 15, automatic scores obtained from this device seem accurate enough to diagnose OSA in the correct clinical setting.

Strigolactone-Like Bioactivity via Parasitic Plant Germination Bioassay.

Strigolactones are a class of plant hormones involved in shoot branching, growth of symbiotic arbuscular mycorrhizal fungi, and germination of parasitic plant seeds. Assaying new molecules or compound exhibiting strigolactone-like activities is therefore important but unfortunately time-consuming and hard to implement because of the extremely low concentrations at which they are active. Seeds of parasite plants are natural integrator of these hormones since they can perceive molecule concentrations in the picomolar to nanomolar range stimulating their germination. Here we describe a simple and inexpensive method to evaluate the activity of these molecules by scoring the germination of parasitic plant seeds upon treatment with these molecules. Up to four molecules can be assayed from a single 96-well plate by this method. A comparison of SL-like bioactivities between molecules is done by determining the EC50 and the maximum percentage of germination.

Interrater sleep stage scoring reliability between manual scoring from two European sleep centers and automatic scoring performed by the artificial intelligence-based Stanford-STAGES algorithm.

STUDY OBJECTIVES: The objective of this study was to evaluate interrater reliability between manual sleep stage scoring performed in 2 European sleep centers and automatic sleep stage scoring performed by the previously validated artificial intelligence-based Stanford-STAGES algorithm. METHODS: Full night polysomnographies of 1,066 participants were included. Sleep stages were manually scored in Berlin and Innsbruck sleep centers and automatically scored with the Stanford-STAGES algorithm. For each participant, we compared (1) Innsbruck to Berlin scorings (INN vs BER); (2) Innsbruck to automatic scorings (INN vs AUTO); (3) Berlin to automatic scorings (BER vs AUTO); (4) epochs where scorers from Innsbruck and Berlin had consensus to automatic scoring (CONS vs AUTO); and (5) both Innsbruck and Berlin manual scorings (MAN) to the automatic ones (MAN vs AUTO). Interrater reliability was evaluated with several measures, including overall and sleep stage-specific Cohen's κ. RESULTS: Overall agreement across participants was substantial for INN vs BER (κ = 0.66 ± 0.13), INN vs AUTO (κ = 0.68 ± 0.14), CONS vs AUTO (κ = 0.73 ± 0.14), and MAN vs AUTO (κ = 0.61 ± 0.14), and moderate for BER vs AUTO (κ = 0.55 ± 0.15). Human scorers had the highest disagreement for N1 sleep (κN1 = 0.40 ± 0.16 for INN vs BER). Automatic scoring had lowest agreement with manual scorings for N1 and N3 sleep (κN1 = 0.25 ± 0.14 and κN3 = 0.42 ± 0.32 for MAN vs AUTO). CONCLUSIONS: Interrater reliability for sleep stage scoring between human scorers was in line with previous findings, and the algorithm achieved an overall substantial agreement with manual scoring. In this cohort, the Stanford-STAGES algorithm showed similar performances to the ones achieved in the original study, suggesting that it is generalizable to new cohorts. Before its integration in clinical practice, future independent studies should further evaluate it in other cohorts.

Patient-Ventilator Synchronization During Non-invasive Ventilation: A Pilot Study of an Automated Analysis System.

Background: Patient-ventilator synchronization during non-invasive ventilation (NIV) can be assessed by visual inspection of flow and pressure waveforms but it remains time consuming and there is a large inter-rater variability, even among expert physicians. SyncSmart™ software developed by Breas Medical (Mölnycke, Sweden) provides an automatic detection and scoring of patient-ventilator asynchrony to help physicians in their daily clinical practice. This study was designed to assess performance of the automatic scoring by the SyncSmart software using expert clinicians as a reference in patient with chronic respiratory failure receiving NIV. Methods: From nine patients, 20 min data sets were analyzed automatically by SyncSmart software and reviewed by nine expert physicians who were asked to score auto-triggering (AT), double-triggering (DT), and ineffective efforts (IE). The study procedure was similar to the one commonly used for validating the automatic sleep scoring technique. For each patient, the asynchrony index was computed by automatic scoring and each expert, respectively. Considering successively each expert scoring as a reference, sensitivity, specificity, positive predictive value (PPV), κ-coefficients, and agreement were calculated. Results: The asynchrony index assessed by SynSmart was not significantly different from the one assessed by the experts (18.9 ± 17.7 vs. 12.8 ± 9.4, p = 0.19). When compared to an expert, the sensitivity and specificity provided by SyncSmart for DT, AT, and IE were significantly greater than those provided by an expert when compared to another expert. Conclusions: SyncSmart software is able to score asynchrony events within the inter-rater variability. When the breathing frequency is not too high (<24), it therefore provides a reliable assessment of patient-ventilator asynchrony; AT is over detected otherwise.

Improving the accuracy of dose estimates from automatically scored dicentric chromosomes by accounting for chromosome number.

PURPOSE: The traditional workflow for biological dosimetry based on manual scoring of dicentric chromosomes is very time consuming. Especially for large-scale scenarios or for low-dose exposures, high cell numbers have to be analyzed, requiring alternative scoring strategies. Semi-automatic scoring of dicentric chromosomes provides an opportunity to speed up the standard workflow of biological dosimetry. Due to automatic metaphase and chromosome detection, the number of counted chromosomes per metaphase is variable. This can potentially introduce overdispersion and statistical methods for conventional, manual scoring might not be applicable to data obtained by automatic scoring of dicentric chromosomes, potentially resulting in biased dose estimates and underestimated uncertainties. The identification of sources for overdispersion enables the development of methods appropriately accounting for increased dispersion levels. MATERIALS AND METHODS: Calibration curves based on in vitro irradiated (137-Cs; 0.44 Gy/min) blood from three healthy donors were analyzed for systematic overdispersion, especially at higher doses (>2 Gy) of low LET radiation. For each donor, 12 doses in the range of 0-6 Gy were scored semi-automatically. The effect of chromosome number as a potential cause for the observed overdispersion was assessed. Statistical methods based on interaction models accounting for the number of detected chromosomes were developed for the estimation of calibration curves, dose and corresponding uncertainties. The dose estimation was performed based on a Bayesian Markov-Chain-Monte-Carlo method, providing high flexibility regarding the implementation of priors, likelihood and the functional form of the association between predictors and dicentric counts. The proposed methods were validated by simulations based on cross-validation. RESULTS: Increasing dose dependent overdispersion was observed for all three donors as well as considerable differences in dicentric counts between donors. Variations in the number of detected chromosomes between metaphases were identified as a major source for the observed overdispersion and the differences between donors. Persisting overdispersion beyond the contribution of chromosome number was modeled by a Negative Binomial distribution. Results from cross-validation suggested that the proposed statistical methods for dose estimation reduced bias in dose estimates, variability between dose estimates and improved the coverage of the estimated confidence intervals. However, the 95% confidence intervals were still slightly too permissive, suggesting additional unknown sources of apparent overdispersion. CONCLUSIONS: A major source for the observed overdispersion could be identified, and statistical methods accounting for overdispersion introduced by variations in the number of detected chromosomes were developed, enabling more robust dose estimation and quantification of uncertainties for semi-automatic counting of dicentric chromosomes.

Automatic, Qualitative Scoring of the Interlocking Pentagon Drawing Test (PDT) based on U-Net and Mobile Sensor Data.

We implemented a mobile phone application of the pentagon drawing test (PDT), called mPDT, with a novel, automatic, and qualitative scoring method for the application based on U-Net (a convolutional network for biomedical image segmentation) coupled with mobile sensor data obtained with the mPDT. For the scoring protocol, the U-Net was trained with 199 PDT hand-drawn images of 512ⅹ512 resolution obtained via the mPDT in order to generate a trained model, Deep5, for segmenting a drawn right or left pentagon. The U-Net was also trained with 199 images of 512ⅹ512 resolution to attain the trained model, DeepLock, for segmenting an interlocking figure. Here, the epochs were iterated until the accuracy was greater than 98% and saturated. The mobile senor data primarily consisted of x and y coordinates, timestamps, and touch-events of all the samples with a 20 ms sampling period. The velocities were then calculated using the primary sensor data. With Deep5, DeepLock, and the sensor data, four parameters were extracted. These included the number of angles (0-4 points), distance/intersection between the two drawn figures (0-4 points), closure/opening of the drawn figure contours (0-2 points), and tremors detected (0-1 points). The parameters gave a scaling of 11 points in total. The performance evaluation for the mPDT included 230 images from subjects and their associated sensor data. The results of the performance test indicated, respectively, a sensitivity, specificity, accuracy, and precision of 97.53%, 92.62%, 94.35%, and 87.78% for the number of angles parameter; 93.10%, 97.90%, 96.09%, and 96.43% for the distance/intersection parameter; 94.03%, 90.63%, 92.61%, and 93.33% for the closure/opening parameter; and 100.00%, 100.00%, 100.00%, and 100.00% for the detected tremor parameter. These results suggest that the mPDT is very robust in differentiating dementia disease subtypes and is able to contribute to clinical practice and field studies.

Exploring scoring methods for research studies: Accuracy and variability of visual and automated sleep scoring.

Sleep studies face new challenges in terms of data, objectives and metrics. This requires reappraising the adequacy of existing analysis methods, including scoring methods. Visual and automatic sleep scoring of healthy individuals were compared in terms of reliability (i.e., accuracy and stability) to find a scoring method capable of giving access to the actual data variability without adding exogenous variability. A first dataset (DS1, four recordings) scored by six experts plus an autoscoring algorithm was used to characterize inter-scoring variability. A second dataset (DS2, 88 recordings) scored a few weeks later was used to explore intra-expert variability. Percentage agreements and Conger's kappa were derived from epoch-by-epoch comparisons on pairwise and consensus scorings. On DS1 the number of epochs of agreement decreased when the number of experts increased, ranging from 86% (pairwise) to 69% (all experts). Adding autoscoring to visual scorings changed the kappa value from 0.81 to 0.79. Agreement between expert consensus and autoscoring was 93%. On DS2 the hypothesis of intra-expert variability was supported by a systematic decrease in kappa scores between autoscoring used as reference and each single expert between datasets (.75-.70). Although visual scoring induces inter- and intra-expert variability, autoscoring methods can cope with intra-scorer variability, making them a sensible option to reduce exogenous variability and give access to the endogenous variability in the data.

An automatic procedure that grades some facial skin structural signs: agreements and validation with clinical assessments made by dermatologists.

OBJECTIVE: To confirm the robustness and validity of an automatic scoring system, algorithm-based, that grades the severity of nine facial signs through "selfies" smartphones pictures taken by European Caucasian women through dermatological assessments. METHODS: 157 Caucasian women from three countries (France, Germany, Spain), of different ages (20-75 years), took one "selfie" image by the frontal camera of their smartphones whereas local dermatologists photographed them with the back camera of the same smartphone. The same nine facial signs of these subjects were initially graded by these local dermatologists, using referential Skin Aging Atlases. All 314 "selfies" images were then further automatically analyzed by the algorithm. The severity of facial signs (wrinkles, pigmentation, ptosis, skin folds etc.) were statistically compared to the assessments made by the three dermatologists, taken as ground truth. RESULTS: Highly significant coefficients of correlation (P < 0.001) were found in the three cohorts between the grades provided by the system and those from dermatologists in live. The back camera - of a better resolution than the frontal one - seems affording slightly more significant correlations. However, although significantly correlated, the signs of vascular disorders and cheek skin pores present some disparities that are likely linked to the technical diversity of smartphones or self-shootings, leading to lower coefficients of correlations. CONCLUSION: This automatic scoring system offers a promising approach in the harmonization of Dermatological assessments of skin facial signs and their changes with age or the follow up of anti-aging treatments.

OBJECTIF: De confirmer la validité et la solidité d'un système de scorage automatique qui quantifie la sévérité de neuf signes du visage à partir de photographies de type "selfies" prises par des femmes Caucasiennes Européennes d'âge différents. MÉTHODES: 157 femmes Caucasiennes de trois pays différents (France, Allemagne, Espagne), d'âges différents (20-75 ans) ont pris un « selfie¼ avec la caméra frontale de leur téléphone tandis que le dermatologue local les a photographiées à l'aide de la caméra dorsale du même appareil. Les neuf signes faciaux ciblés par le système de scorage automatique ont été préalablement évalués par trois dermatologues locaux, utilisant des Atlas référentiels du vieillissement cutané. Les 314 images obtenues furent ensuite analysées automatiquement par l'algorithme. Les sévérités des neuf signes (rides, ptose, plis, pigmentation...) ont été ensuite comparées à celles établies par les dermatologues, considérées comme références absolues. RÉSULTATS: De très significatifs coefficients de corrélation (P < 0.001) ont été trouvés dans les trois cohortes entre les scores fournis par le système et ceux issus des évaluations des dermatologues des visages durant la visite des volontaires. La caméra du dos des smartphones - de meilleure résolution que la frontale - semble fournir de légèrement meilleures significativités. Cependant, bien que significativement corrélés, les signes des désordres vasculaires et des pores cutanés des joues montrent quelques disparités, dues possiblement à la diversité technique des smartphones ou celle des prises de vue, conduisant à de plus faibles coefficients de corrélation. CONCLUSION: Ce système de quantification automatique semble offrir une approche prometteuse dans l'harmonisation des évaluations dermatologiques des signes faciaux et leurs modifications liées à l'âge et/ou le suivi de traitements à vocation antivieillissement cutané.

An Expert System for Quantification of Bradykinesia Based on Wearable Inertial Sensors.

Wearable sensors and advanced algorithms can provide significant decision support for clinical practice. Currently, the motor symptoms of patients with neurological disorders are often visually observed and evaluated, which may result in rough and subjective quantification. Using small inertial wearable sensors, fine repetitive and clinically important movements can be captured and objectively evaluated. In this paper, a new methodology is designed for objective evaluation and automatic scoring of bradykinesia in repetitive finger-tapping movements for patients with idiopathic Parkinson's disease and atypical parkinsonism. The methodology comprises several simple and repeatable signal-processing techniques that are applied for the extraction of important movement features. The decision support system consists of simple rules designed to match universally defined criteria that are evaluated in clinical practice. The accuracy of the system is calculated based on the reference scores provided by two neurologists. The proposed expert system achieved an accuracy of 88.16% for files on which neurologists agreed with their scores. The introduced system is simple, repeatable, easy to implement, and can provide good assistance in clinical practice, providing a detailed analysis of finger-tapping performance and decision support for symptom evaluation.