Listening like a speech-training app: Expert and non-expert listeners' goodness ratings of children's speech.

Speech training apps are being developed that provide automatic feedback concerning children's production of known target words, as a score on a 1-5 scale. However, this 'goodness' scale is still poorly understood. We investigated listeners' ratings of 'how many stars the app should provide as feedback' on children's utterances, and whether listener agreement is affected by clinical experience and/or access to anchor stimuli. In addition, we explored the association between goodness ratings and clinical measures of speech accuracy; the Percentage of Consonants Correct (PCC) and the Percentage of Phonemes Correct (PPC). Twenty speech-language pathologists and 20 non-expert listeners participated; half of the listeners in each group had access to anchor stimuli. The listeners rated 120 words, collected from children with and without speech sound disorder. Concerning reliability, intra-rater agreement was generally high, whereas inter-rater agreement was moderate. Access to anchor stimuli was associated with higher agreement, but only for non-expert listeners. Concerning the association between goodness ratings and the PCC/PPC, correlations were moderate for both listener groups, under both conditions. The results indicate that the task of rating goodness is difficult, regardless of clinical experience, and that access to anchor stimuli is insufficient for achieving reliable ratings. This raises concerns regarding the 1-5 rating scale as the means of feedback in speech training apps. More specific listener instructions, particularly regarding the intended context for the app, are suggested in collection of human ratings underlying the development of speech training apps. Until then, alternative means of feedback should be preferred.

Graph semantic similarity-based automatic assessment for programming exercises.

This paper proposes an algorithm for the automatic assessment of programming exercises. The algorithm assigns assessment scores based on the program dependency graph structure and the program semantic similarity, but does not actually need to run the student's program. By calculating the node similarity between the student's program and the teacher's reference programs in terms of structure and program semantics, a similarity matrix is generated and the optimal similarity node path of this matrix is identified. The proposed algorithm achieves improved computational efficiency, with a time complexity of O ( n 2 ) for a graph with n nodes. The experimental results show that the assessment algorithm proposed in this paper is more reliable and accurate than several comparison algorithms, and can be used for scoring programming exercises in C/C++, Java, Python, and other languages.

Automatic assessment of atherosclerotic plaque features by intracoronary imaging: a scoping review.

Background: The diagnostic performance and clinical validity of automatic intracoronary imaging (ICI) tools for atherosclerotic plaque assessment have not been systematically investigated so far. Methods: We performed a scoping review including studies on automatic tools for automatic plaque components assessment by means of optical coherence tomography (OCT) or intravascular imaging (IVUS). We summarized study characteristics and reported the specifics and diagnostic performance of developed tools. Results: Overall, 42 OCT and 26 IVUS studies fulfilling the eligibility criteria were found, with the majority published in the last 5 years (86% of the OCT and 73% of the IVUS studies). A convolutional neural network deep-learning method was applied in 71% of OCT- and 34% of IVUS-studies. Calcium was the most frequent plaque feature analyzed (26/42 of OCT and 12/26 of IVUS studies), and both modalities showed high discriminatory performance in testing sets [range of area under the curve (AUC): 0.91-0.99 for OCT and 0.89-0.98 for IVUS]. Lipid component was investigated only in OCT studies (n = 26, AUC: 0.82-0.86). Fibrous cap thickness or thin-cap fibroatheroma were mainly investigated in OCT studies (n = 8, AUC: 0.82-0.94). Plaque burden was mainly assessed in IVUS studies (n = 15, testing set AUC reported in one study: 0.70). Conclusion: A limited number of automatic machine learning-derived tools for ICI analysis is currently available. The majority have been developed for calcium detection for either OCT or IVUS images. The reporting of the development and validation process of automated intracoronary imaging analyses is heterogeneous and lacks critical information. Systematic Review Registration: Open Science Framework (OSF), https://osf.io/nps2b/.Graphical AbstractCentral Illustration.

Characterization of Surgical Movements As a Training Tool for Improving Efficiency.

INTRODUCTION: Surgical experience is often reflected by efficient, fluid, and well-calculated movements. For a new trainee, learning these characteristics is possible only by observation as there is no quantification system to define these factors. We analyzed surgeons' hand movements with different experience levels to characterize their movements according to experience. METHODS: Hand motions were recorded by an inertial measurement unit (IMU) mounted on the hands of the surgeons during a simulated surgical procedure. IMU data provided acceleration and Eulerian angles: yaw, roll, and pitch corresponding to hand motions as radial/ulnar deviation, pronation/supination, and extension/flexion, respectively. These variables were graphically depicted and compared between three surgeons. RESULTS: Participants were assigned to three groups based on years of surgical experience: group 1: >15 y; group 2: 3-10 y; and group 3: 0-1 y. Visualization of the roll motion, being the main motion during suturing, showed the clear difference in fluidity and regularity of the movements between the groups, showing minimal wasted movements for group 1. The angle of the roll motion, measured at the minimum, midpoint, and maximum points was significantly different between the groups. As expected, the experienced group completed the procedure first; however, the acceleration was not different between the groups. CONCLUSIONS: Surgeons' hand movements can be easily characterized and quantified by an IMU device for automatic assessment of surgical skills. These characteristics graphically visualize a surgeon's regularity, fluidity, economy, and efficiency. The characteristics of an experienced surgeon can serve as a training model and as a reference tool for trainees.

Automatic Segmentation and Assessment of Valvular Regurgitations with Color Doppler Echocardiography Images: A VABC-UNet-Based Framework.

This study investigated the automatic segmentation and classification of mitral regurgitation (MR) and tricuspid regurgitation (TR) using a deep learning-based method, aiming to improve the efficiency and accuracy of diagnosis of valvular regurgitations. A VABC-UNet model was proposed consisting of VGG16 encoder, U-Net decoder, batch normalization, attention block and deepened convolution layer based on the U-Net backbone. Then, a VABC-UNet-based assessment framework was established for automatic segmentation, classification, and evaluation of valvular regurgitations. A total of 315 color Doppler echocardiography images of MR and/or TR in an apical four-chamber view were collected, including 35 images in the test dataset and 280 images in the training dataset. In comparison with the classic U-Net and VGG16-UNet models, the segmentation performance of the VABC-UNet model was evaluated via four metrics: Dice, Jaccard, Precision, and Recall. According to the features of regurgitation jet and atrium, the regurgitation could automatically be classified into MR or TR, and evaluated to mild, moderate, moderate-severe, or severe grade by the framework. The results show that the VABC-UNet model has a superior performance in the segmentation of valvular regurgitation jets and atria to the other two models and consequently a higher accuracy of classification and evaluation. There were fewer pseudo- and over-segmentations by the VABC-UNet model and the values of the metrics significantly improved (p < 0.05). The proposed VABC-UNet-based framework achieves automatic segmentation, classification, and evaluation of MR and TR, having potential to assist radiologists in clinical decision making of the regurgitations in valvular heart diseases.

Automatic Assessment of Transcatheter Aortic Valve Implantation Results on Four-Dimensional Computed Tomography Images Using Artificial Intelligence.

Transcatheter aortic valve implantation (TAVI) is a procedure to treat severe aortic stenosis. There are several clinical concerns related to potential complications after the procedure, which demand the analysis of computerized tomography (CT) scans after TAVI to assess the implant's result. This work introduces a novel, fully automatic method for the analysis of post-TAVI 4D-CT scans to characterize the prosthesis and its relationship with the patient's anatomy. The method enables measurement extraction, including prosthesis volume, center of mass, cross-sectional area (CSA) along the prosthesis axis, and CSA difference between the aortic root and prosthesis, all the variables studied throughout the cardiac cycle. The method has been implemented and evaluated with a cohort of 13 patients with five different prosthesis models, successfully extracting all the measurements from each patient in an automatic way. For Allegra patients, the mean of the obtained inner volume values ranged from 10,798.20 mm3 to 18,172.35 mm3, and CSA in the maximum diameter plane varied from 396.35 mm2 to 485.34 mm2. The implantation of this new method could provide information of the important clinical value that would contribute to the improvement of TAVI, significantly reducing the time and effort invested by clinicians in the image interpretation process.

D-STGCNT: A Dense Spatio-Temporal Graph Conv-GRU Network based on transformer for assessment of patient physical rehabilitation.

This paper tackles the challenge of automatically assessing physical rehabilitation exercises for patients who perform the exercises without clinician supervision. The objective is to provide a quality score to ensure correct performance and achieve desired results. To achieve this goal, a new graph-based model, the Dense Spatio-Temporal Graph Conv-GRU Network with Transformer, is introduced. This model combines a modified version of STGCN and transformer architectures for efficient handling of spatio-temporal data. The key idea is to consider skeleton data respecting its non-linear structure as a graph and detecting joints playing the main role in each rehabilitation exercise. Dense connections and GRU mechanisms are used to rapidly process large 3D skeleton inputs and effectively model temporal dynamics. The transformer encoder's attention mechanism focuses on relevant parts of the input sequence, making it useful for evaluating rehabilitation exercises. The evaluation of our proposed approach on the KIMORE and UI-PRMD datasets highlighted its potential, surpassing state-of-the-art methods in terms of accuracy and computational time. This resulted in faster and more accurate learning and assessment of rehabilitation exercises. Additionally, our model provides valuable feedback through qualitative illustrations, effectively highlighting the significance of joints in specific exercises.

A Wearable Artificial Intelligence Feedback Tool (Wrist Angel) for Treatment and Research of Obsessive Compulsive Disorder: Protocol for a Nonrandomized Pilot Study.

BACKGROUND: Obsessive compulsive disorder (OCD) in youth is characterized by behaviors, emotions, physiological reactions, and family interaction patterns. An essential component of therapy involves increasing awareness of the links among thoughts, emotions, behaviors, bodily sensations, and family interactions. An automatic assessment tool using physiological signals from a wearable biosensor may enable continuous symptom monitoring inside and outside of the clinic and support cognitive behavioral therapy for OCD. OBJECTIVE: The primary aim of this study is to evaluate the feasibility and acceptability of using a wearable biosensor to monitor OCD symptoms. The secondary aim is to explore the feasibility of developing clinical and research tools that can detect and predict OCD-relevant internal states and interpersonal processes with the use of speech and behavioral signals. METHODS: Eligibility criteria for the study include children and adolescents between 8 and 17 years of age diagnosed with OCD, controls with no psychiatric diagnoses, and one parent of the participating youths. Youths and parents wear biosensors on their wrists that measure pulse, electrodermal activity, skin temperature, and acceleration. Patients and their parents mark OCD episodes, while control youths and their parents mark youth fear episodes. Continuous, in-the-wild data collection will last for 8 weeks. Controlled experiments designed to link physiological, speech, behavioral, and biochemical signals to mental states are performed at baseline and after 8 weeks. Interpersonal interactions in the experiments are filmed and coded for behavior. The films are also processed with computer vision and for speech signals. Participants complete clinical interviews and questionnaires at baseline, and at weeks 4, 7, and 8. Feasibility criteria were set for recruitment, retention, biosensor functionality and acceptability, adherence to wearing the biosensor, and safety related to the biosensor. As a first step in learning the associations between signals and OCD-related parameters, we will use paired t tests and mixed effects models with repeated measures to assess associations between oxytocin, individual biosignal features, and outcomes such as stress-rest and case-control comparisons. RESULTS: The first participant was enrolled on December 3, 2021, and recruitment closed on December 31, 2022. Nine patient dyads and nine control dyads were recruited. Sixteen participating dyads completed follow-up assessments. CONCLUSIONS: The results of this study will provide preliminary evidence for the extent to which a wearable biosensor that collects physiological signals can be used to monitor OCD severity and events in youths. If we find the study to be feasible, further studies will be conducted to integrate biosensor signals output into machine learning algorithms that can provide patients, parents, and therapists with actionable insights into OCD symptoms and treatment progress. Future definitive studies will be tasked with testing the accuracy of machine learning models to detect and predict OCD episodes and classify clinical severity. TRIAL REGISTRATION: ClinicalTrials.gov NCT05064527; https://clinicaltrials.gov/ct2/show/NCT05064527. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/45123.

Feasibility and reproducibility of semi-automated longitudinal strain analysis: a comparative study with conventional manual strain analysis.

BACKGROUND: Conventional approach to myocardial strain analysis relies on a software designed for the left ventricle (LV) which is complex and time-consuming and is not specific for right ventricular (RV) and left atrial (LA) assessment. This study compared this conventional manual approach to strain evaluation with a novel semi-automatic analysis of myocardial strain, which is also chamber-specific. METHODS: Two experienced observers used the AutoStrain software and manual QLab analysis to measure the LV, RV and LA strains in 152 healthy volunteers. Fifty cases were randomly selected for timing evaluation. RESULTS: No significant differences in LV global longitudinal strain (LVGLS) were observed between the two methods (-21.0% ± 2.5% vs. -20.8% ± 2.4%, p = 0.230). Conversely, RV longitudinal free wall strain (RVFWS) and LA longitudinal strain during the reservoir phase (LASr) measured by the semi-automatic software differed from the manual analysis (RVFWS: -26.4% ± 4.8% vs. -31.3% ± 5.8%, p < 0.001; LAS: 48.0% ± 10.0% vs. 37.6% ± 9.9%, p < 0.001). Bland-Altman analysis showed a mean error of 0.1%, 4.9%, and 10.5% for LVGLS, RVFWS, and LASr, respectively, with limits of agreement of -2.9,2.6%, -8.1,17.9%, and -12.3,33.3%, respectively. The semi-automatic method had a significantly shorter strain analysis time compared with the manual method. CONCLUSIONS: The novel semi-automatic strain analysis has the potential to improve efficiency in measurement of longitudinal myocardial strain. It shows good agreement with manual analysis for LV strain measurement.

Usefulness of automatic assessment for longitudinal strain to diagnose wild-type transthyretin amyloid cardiomyopathy.

Background: Left ventricular (LV) apical sparing by transthoracic echocardiography (TTE) has not been widely accepted to diagnose transthyretin amyloid cardiomyopathy (ATTR-CM), because it is time consuming and requires a level of expertise. We hypothesized that automatic assessment may be the solution for these problems. Methods-and-Results: We enrolled 63 patients aged ≥70 years who underwent 99mTc-labeled pyrophosphate (99mTc-PYP) scintigraphy on suspicion of ATTR-CM and performed TTE by EPIQ7G, and had enough information for two-dimensional speckle tracking echocardiography at Kumamoto University Hospital from January 2016 to December 2019. LV apical sparing was described as a high relative apical longitudinal strain (LS) index (RapLSI). Measurement of LS was repeated using the same apical images with three different measurement packages as follows: (1) full-automatic assessment, (2) semi-automatic assessment, and (3) manual assessment. The calculation time for full-automatic assessment (14.7 ± 1.4 sec/patient) and semi-automatic assessment (66.7 ± 14.4 sec/patient) were significantly shorter than that for manual assessment (171.2 ± 59.7 sec/patient) (p < 0.01 for both). Receiver operating characteristic curve analysis showed that the area under curve of the RapLSI evaluated by full-automatic assessment for predicting ATTR-CM was 0.70 (best cut-off point; 1.14 [sensitivity 63%, specificity 81%]), by semi-automatic assessment was 0.85 (best cut-off point; 1.00 [sensitivity, 66%; specificity, 100%]) and by manual assessment was 0.83 (best cut-off point; 0.97 [sensitivity, 72%; specificity, 97%]). Conclusion: There was no significant difference between the diagnostic accuracy of RapLSI estimated by semi-automatic assessment and that estimated by manual assessment. Semi-automatically assessed RapLSI is useful to diagnose ATTR-CM in terms of rapidity and diagnostic accuracy.

Gradient boosting DD-MLP Net: An ensemble learning model using near-infrared spectroscopy to classify after-stroke dyskinesia degree during exercise.

This study aims to develop an automatic assessment of after-stroke dyskinesias degree by combining machine learning and near-infrared spectroscopy (NIRS). Thirty-five subjects were divided into five stages (healthy, patient: Brunnstrom stages 3, 4, 5, 6). NIRS was used to record the muscular hemodynamic responses from bilateral femoris (biceps brachii) muscles during passive and active upper (lower) limbs circular exercise. We used the D-S evidence theory to conduct feature information fusion and established a Gradient Boosting DD-MLP Net model, combining the dendrite network and multilayer perceptron, to realize automatic dyskinesias degree evaluation. Our model classified the upper limb dyskinesias with high accuracy: 98.91% under the passive mode and 98.69% under the active mode, and classified the lower limb dyskinesias with high accuracy: 99.45% and 99.63% under the passive and active modes, respectively. Our model combined with NIRS has great potential in monitoring the after-stroke dyskinesias degree and guiding rehabilitation training.

Machine Learning Based on Computed Tomography Pulmonary Angiography in Evaluating Pulmonary Artery Pressure in Patients with Pulmonary Hypertension.

BACKGROUND: Right heart catheterization is the gold standard for evaluating hemodynamic parameters of pulmonary circulation, especially pulmonary artery pressure (PAP) for diagnosis of pulmonary hypertension (PH). However, the invasive and costly nature of RHC limits its widespread application in daily practice. PURPOSE: To develop a fully automatic framework for PAP assessment via machine learning based on computed tomography pulmonary angiography (CTPA). MATERIALS AND METHODS: A machine learning model was developed to automatically extract morphological features of pulmonary artery and the heart on CTPA cases collected between June 2017 and July 2021 based on a single center experience. Patients with PH received CTPA and RHC examinations within 1 week. The eight substructures of pulmonary artery and heart were automatically segmented through our proposed segmentation framework. Eighty percent of patients were used for the training data set and twenty percent for the independent testing data set. PAP parameters, including mPAP, sPAP, dPAP, and TPR, were defined as ground-truth. A regression model was built to predict PAP parameters and a classification model to separate patients through mPAP and sPAP with cut-off values of 40 mm Hg and 55 mm Hg in PH patients, respectively. The performances of the regression model and the classification model were evaluated by analyzing the intraclass correlation coefficient (ICC) and the area under the receiver operating characteristic curve (AUC). RESULTS: Study participants included 55 patients with PH (men 13; age 47.75 ± 14.87 years). The average dice score for segmentation increased from 87.3% ± 2.9 to 88.2% ± 2.9 through proposed segmentation framework. After features extraction, some of the AI automatic extractions (AAd, RVd, LAd, and RPAd) achieved good consistency with the manual measurements. The differences between them were not statistically significant (t = 1.222, p = 0.227; t = -0.347, p = 0.730; t = 0.484, p = 0.630; t = -0.320, p = 0.750, respectively). The Spearman test was used to find key features which are highly correlated with PAP parameters. Correlations between pulmonary artery pressure and CTPA features show a high correlation between mPAP and LAd, LVd, LAa (r = 0.333, p = 0.012; r = -0.400, p = 0.002; r = -0.208, p = 0.123; r = -0.470, p = 0.000; respectively). The ICC between the output of the regression model and the ground-truth from RHC of mPAP, sPAP, and dPAP were 0.934, 0.903, and 0.981, respectively. The AUC of the receiver operating characteristic curve of the classification model of mPAP and sPAP were 0.911 and 0.833. CONCLUSIONS: The proposed machine learning framework on CTPA enables accurate segmentation of pulmonary artery and heart and automatic assessment of the PAP parameters and has the ability to accurately distinguish different PH patients with mPAP and sPAP. Results of this study may provide additional risk stratification indicators in the future with non-invasive CTPA data.

Validation of an automatic scoring system for the assessment of hock burn in broiler.

This study aimed to develop and validate a camera vision score that could detect macroscopic alterations of the hock, to identify errors and to assess possible factors that could influence the assessment. Two hundred hocks in the first (calibration) phase and 500 hocks in the second (validation) phase were collected at slaughter, visually assessed, placed back into the evisceration line and assessed by a camera system with 2 software systems. The size of the alteration in percent (%) measured by the camera system was evaluated ("camera score", CS). Additionally, temperature, humidity, and light intensities were measured. In the calibration phase, threshold values of camera scores for respective macro scores were defined and performance measures evaluated. In the validation phase, the generated threshold values were validated, occurring errors, as well as possible impacts of climatic factors analyzed. The results showed that the generated thresholds predict the camera score values at which the respective macro score has the highest probability of appearance. Small hock burn lesions ≤0.5 cm have the highest probability at a camera score of ≥0.2 (original CS) or ≥0.1 (updated CS), and lesions >0.5 cm have the highest probability at a camera score of ≥0.7 (original CS) or ≥1.1 (updated CS). Large lesions (>0.5 cm) are more reliably identified by the system than small lesions. The risks of errors in assessing reference areas and lesions showed a correct identification of lesions to be the most probable result even if the reference area is not correctly identified. The probability of a correct identification of lesions by the camera system was slightly higher (not significant) with the updated software (risk = 0.66 [0.62-0.70]) than with the original software (risk = 0.63 [0.58-0.67]). Automatic assessment systems at slaughter could be adjusted to the presented threshold values to classify hock burn lesions. Software adaptations can improve the performance measures of diagnosis and reduce the probability of errors.

Footpad Monitoring: Reliability of an Automated System to Assess Footpad Dermatitis in Turkeys (Meleagris gallopavo) During Slaughter.

Footpad dermatitis (FPD) is an indicator of animal welfare in turkeys, giving evidence of the animals' physical integrity and providing information on husbandry management. Automated systems for assessing FPD at slaughter can present a useful tool for objective data collection. However, using automated systems requires that they reliably assess the incidence. In this study, the feet of turkeys were scored for FPD by both an automated camera system and a human observer, using a five-scale score. The observer reliability between both was calculated (Krippendorff's alpha). The results were not acceptable, with an agreement coefficient of 0.44 in the initial situation. Therefore, pictures of 3,000 feet scored by the automated system were evaluated systematically to detect deficiencies. The reference area (metatarsal footpad) was not detected correctly in 55.0% of the feet, and false detections of the alteration on the footpad (FPD) were found in 32.9% of the feet. In 41.3% of the feet, the foot was not presented straight to the camera. According to these results, the algorithm of the automated system was modified, aiming to improve color detection and the distinction of the metatarsal footpad from the background. Pictures of the feet, now scored by the modified algorithm, were evaluated again. Observer reliability could be improved (Krippendorff's alpha = 0.61). However, detection of the metatarsal footpad (50.9% incorrect detections) and alterations (27.0% incorrect detections) remained a problem. We found that the performance of the camera system was affected by the angle at which the foot was presented to the camera (skew/straight; p < 0.05). Furthermore, the laterality of the foot (left/right) was found to have a significant effect (p < 0.001). We propose that the latter depends on the slaughter process. This study also highlights a high variability in observer reliability of human observers. Depending on the respective target parameter, the reliability coefficient (Krippendorff's alpha) ranged from 0.21 to 0.82. This stresses the importance of finding an objective alternative. Therefore, it was concluded that the automated detection system could be appropriate to reliably assess FPD at the slaughterhouse. However, there is still room to improve the existing method, especially when using FPD as a welfare indicator.

A new basic thoracoscopic surgical skill training and assessment system using automatic scoring techniques.

PURPOSE: We report a new thoracoscopic surgical skill training and assessment system with automatic scoring techniques, the Huaxi Intelligent Thoracoscopic Skill Training and Assessment (HITSTA) system. We also evaluated the discriminative ability of this system compared to our conventional scoring method at our institution. METHODS: We retrospectively collected training data of thoracic board-certified thoracic surgeons at West China Hospital, Sichuan University from January 1, 2018 to January 1, 2019. Surgeons were assessed by HITSTA system and human examiners simultaneously. Total scores were summed from 3 tasks (grasping with delivery, pattern cutting, and suture with knot). Bland-Altman analysis was used to test agreement of scores made by HITSTA system (automatic scoring) and human examiners (manual scoring). Differentiation ability was also compared between the two scoring methods. RESULTS: Thirty-nine surgeons were recruited. Scores made by HITSTA system and human examiners were not consistent. For suture with knot, automatic scoring method could detect the score differences between different training status (trained: 26.92 ± 12.04, untrained: 19.85 ± 11.12; p = 0.026) and training duration (< 10 h: 20.67 ± 15.23, ≥ 10 h: 31.92 ± 5.56; p = 0.003). For total scores, automatic scoring approach could discriminate between different training status (trained: 71.90 ± 12.63; untrained: 61.41 ± 13.87; p = 0.016) and training duration (< 10 h: 65.23 ± 15.31; ≥ 10 h 77.23 ± 6.94; p = 0.046). CONCLUSION: HITSTA system could discriminate the different levels of thoracoscopic surgical skills better than the traditional manual scoring method. Larger prospective studies are warranted to validate the differentiation ability of HITSTA system.

Risk of bias assessment in preclinical literature using natural language processing.

We sought to apply natural language processing to the task of automatic risk of bias assessment in preclinical literature, which could speed the process of systematic review, provide information to guide research improvement activity, and support translation from preclinical to clinical research. We use 7840 full-text publications describing animal experiments with yes/no annotations for five risk of bias items. We implement a series of models including baselines (support vector machine, logistic regression, random forest), neural models (convolutional neural network, recurrent neural network with attention, hierarchical neural network) and models using BERT with two strategies (document chunk pooling and sentence extraction). We tune hyperparameters to obtain the highest F1 scores for each risk of bias item on the validation set and compare evaluation results on the test set to our previous regular expression approach. The F1 scores of best models on test set are 82.0% for random allocation, 81.6% for blinded assessment of outcome, 82.6% for conflict of interests, 91.4% for compliance with animal welfare regulations and 46.6% for reporting animals excluded from analysis. Our models significantly outperform regular expressions for four risk of bias items. For random allocation, blinded assessment of outcome, conflict of interests and animal exclusions, neural models achieve good performance; for animal welfare regulations, BERT model with a sentence extraction strategy works better. Convolutional neural networks are the overall best models. The tool is publicly available which may contribute to the future monitoring of risk of bias reporting for research improvement activities.

Adolescents with borderline personality disorder show a higher response to stress but a lack of self-perception: Evidence through affective computing.

Stress reactivity is a complex phenomenon associated with multiple and multimodal expressions and functions. Herein, we hypothesized that compared with healthy controls (HCs), adolescents with borderline personality disorder (BPD) would exhibit a stronger response to stressors and a deficit in self-perception of stress due to their lack of insight. Twenty adolescents with BPD and 20 matched HCs performed a socially evaluated mental arithmetic test to induce stress. We assessed self- and heteroperception using both human ratings and affective computing-based methods for the automatic extraction of 39 behavioral features (2D + 3D video recording) and 62 physiological features (Nexus-10 recording). Predictions were made using machine learning. In addition, salivary cortisol was measured. Human ratings showed that adolescents with BPD experienced more stress than HCs. Human ratings and automated machine learning indicated opposite results regarding self- and heteroperceived stress in adolescents with BPD compared to HCs. Adolescents with BPD had higher levels of heteroperceived stress than self-perceived stress. Similarly, affective computing achieved better classification for heteroperceived stress. HCs had an opposite profile; they had higher levels of self-perceived stress, and affective computing reached a better classification for self-perceived stress. We conclude that adolescents with BPD are more sensitive to stress and show a lack of self-perception (or insight). In terms of clinical implications, our affective computing measures may help distinguish hetero- vs. self-perceptions of stress in natural settings and may offer external feedback during therapeutic interaction.

Advance in Automatic Assessment of Motor Function for Patients with Stroke (review) / 中国康复理论与实践

There were some disadvantages such as low efficiency and strong subjectivity for scale-based assessment for motor dysfunction after stroke. Recently, automatic assessment approaches based on sensor technology and machine learning were developed, which can be used for motor function assessment of stroke patients in terms of motion control, balance, gait and range of motion, etc.

Automatic Assessment of Tone Quality in Violin Music Performance.

The automatic assessment of music performance has become an area of increasing interest due to the growing number of technology-enhanced music learning systems. In most of these systems, the assessment of musical performance is based on pitch and onset accuracy, but very few pay attention to other important aspects of performance, such as sound quality or timbre. This is particularly true in violin education, where the quality of timbre plays a significant role in the assessment of musical performances. However, obtaining quantifiable criteria for the assessment of timbre quality is challenging, as it relies on consensus among the subjective interpretations of experts. We present an approach to assess the quality of timbre in violin performances using machine learning techniques. We collected audio recordings of several tone qualities and performed perceptual tests to find correlations among different timbre dimensions. We processed the audio recordings to extract acoustic features for training tone-quality models. Correlations among the extracted features were analyzed and feature information for discriminating different timbre qualities were investigated. A real-time feedback system designed for pedagogical use was implemented in which users can train their own timbre models to assess and receive feedback on their performances.

Computer-based evaluation of Alzheimer's disease and mild cognitive impairment patients during a picture description task.

INTRODUCTION: We present a methodology to automatically evaluate the performance of patients during picture description tasks. METHODS: Transcriptions and audio recordings of the Cookie Theft picture description task were used. With 25 healthy elderly control (HC) samples and an information coverage measure, we automatically generated a population-specific referent. We then assessed 517 transcriptions (257 Alzheimer's disease [AD], 217 HC, and 43 mild cognitively impaired samples) according to their informativeness and pertinence against this referent. We extracted linguistic and phonetic metrics which previous literature correlated to early-stage AD. We trained two learners to distinguish HCs from cognitively impaired individuals. RESULTS: Our measures significantly (P < .001) correlated with the severity of the cognitive impairment and the Mini-Mental State Examination score. The classification sensitivity was 81% (area under the curve of receiver operating characteristics = 0.79) and 85% (area under the curve of receiver operating characteristics = 0.76) between HCs and AD and between HCs and AD and mild cognitively impaired, respectively. DISCUSSION: An automated assessment of a picture description task could assist clinicians in the detection of early signs of cognitive impairment and AD.