Heart Sound Abnormality Detection From Multi-Institutional Collaboration: Introducing a Federated Learning Framework.

OBJECTIVE: Early diagnosis of cardiovascular diseases is a crucial task in medical practice. With the application of computer audition in the healthcare field, artificial intelligence (AI) has been applied to clinical non-invasive intelligent auscultation of heart sounds to provide rapid and effective pre-screening. However, AI models generally require large amounts of data which may cause privacy issues. Unfortunately, it is difficult to collect large amounts of healthcare data from a single centre. METHODS: In this study, we propose federated learning (FL) optimisation strategies for the practical application in multi-centre institutional heart sound databases. The horizontal FL is mainly employed to tackle the privacy problem by aligning the feature spaces of FL participating institutions without information leakage. In addition, techniques based on deep learning have poor interpretability due to their "black-box" property, which limits the feasibility of AI in real medical data. To this end, vertical FL is utilised to address the issues of model interpretability and data scarcity. CONCLUSION: Experimental results demonstrate that, the proposed FL framework can achieve good performance for heart sound abnormality detection by taking the personal privacy protection into account. Moreover, using the federated feature space is beneficial to balance the interpretability of the vertical FL and the privacy of the data. SIGNIFICANCE: This work realises the potential of FL from research to clinical practice, and is expected to have extensive application in the federated smart medical system.

Learning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models.

Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade. Nevertheless, lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset. However, inconsistent standards on data collection, annotation, and partition are still restraining a fair and efficient comparison between different works. To this line, we introduced and benchmarked a first version of the Heart Sounds Shenzhen (HSS) corpus. Motivated and inspired by the previous works based on HSS, we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study. First, we segmented the heart sound recording into shorter recordings (10 s), which makes it more similar to the human auscultation case. Second, we redefined the classification tasks. Besides using the 3 class categories (normal, moderate, and mild/severe) adopted in HSS, we added a binary classification task in this study, i.e., normal and abnormal. In this work, we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies, which are reproducible by using open-source toolkits. Last but not least, we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.

STOP1-regulated SMALL AUXIN UP RNA55 (SAUR55) is involved in proton/malate co-secretion for Al tolerance in Arabidopsis.

Proton (H+) release is linked to aluminum (Al)-enhanced organic acids (OAs) excretion from the roots under Al rhizotoxicity in plants. It is well-reported that the Al-enhanced organic acid excretion mechanism is regulated by SENSITIVE TO PROTON RHIZOTOXICITY1 (STOP1), a zinc-finger TF that regulates major Al tolerance genes. However, the mechanism of H+ release linked to OAs excretion under Al stress has not been fully elucidated. Recent physiological and molecular-genetic studies have implicated the involvement of SMALL AUXIN UP RNAs (SAURs) in the activation of plasma membrane H+-ATPases for stress responses in plants. We hypothesized that STOP1 is involved in the regulation of Al-responsive SAURs, which may contribute to the co-secretion of protons and malate under Al stress conditions. In our transcriptome analysis of the roots of the stop1 (sensitive to proton rhizotoxicity1) mutant, we found that STOP1 regulates the transcription of one of the SAURs, namely SAUR55. Furthermore, we observed that the expression of SAUR55 was induced by Al and repressed in the STOP1 T-DNA insertion knockout (KO) mutant (STOP1-KO). Through in silico analysis, we identified a functional STOP1-binding site in the promoter of SAUR55. Subsequent in vitro and in vivo studies confirmed that STOP1 directly binds to the promoter of SAUR55. This suggests that STOP1 directly regulates the expression of SAUR55 under Al stress. We next examined proton release in the rhizosphere and malate excretion in the T-DNA insertion KO mutant of SAUR55 (saur55), in conjunction with STOP1-KO. Both saur55 and STOP1-KO suppressed rhizosphere acidification and malate release under Al stress. Additionally, the root growth of saur55 was sensitive to Al-containing media. In contrast, the overexpressed line of SAUR55 enhanced rhizosphere acidification and malate release, leading to increased Al tolerance. These associations with Al tolerance were also observed in natural variations of Arabidopsis. These findings demonstrate that transcriptional regulation of SAUR55 by STOP1 positively regulates H+ excretion via PM H+-ATPase 2 which enhances Al tolerance by malate secretion from the roots of Arabidopsis. The activation of PM H+-ATPase 2 by SAUR55 was suggested to be due to PP2C.D2/D5 inhibition by interaction on the plasma membrane with its phosphatase. Furthermore, RNAi-suppression of NtSTOP1 in tobacco shows suppression of rhizosphere acidification under Al stress, which was associated with the suppression of SAUR55 orthologs, which are inducible by Al in tobacco. It suggests that transcriptional regulation of Al-inducible SAURs by STOP1 plays a critical role in OAs excretion in several plant species as an Al tolerance mechanism.

Speech Features as Predictors of Momentary Depression Severity in Patients With Depressive Disorder Undergoing Sleep Deprivation Therapy: Ambulatory Assessment Pilot Study.

BACKGROUND: The use of mobile devices to continuously monitor objectively extracted parameters of depressive symptomatology is seen as an important step in the understanding and prevention of upcoming depressive episodes. Speech features such as pitch variability, speech pauses, and speech rate are promising indicators, but empirical evidence is limited, given the variability of study designs. OBJECTIVE: Previous research studies have found different speech patterns when comparing single speech recordings between patients and healthy controls, but only a few studies have used repeated assessments to compare depressive and nondepressive episodes within the same patient. To our knowledge, no study has used a series of measurements within patients with depression (eg, intensive longitudinal data) to model the dynamic ebb and flow of subjectively reported depression and concomitant speech samples. However, such data are indispensable for detecting and ultimately preventing upcoming episodes. METHODS: In this study, we captured voice samples and momentary affect ratings over the course of 3 weeks in a sample of patients (N=30) with an acute depressive episode receiving stationary care. Patients underwent sleep deprivation therapy, a chronotherapeutic intervention that can rapidly improve depression symptomatology. We hypothesized that within-person variability in depressive and affective momentary states would be reflected in the following 3 speech features: pitch variability, speech pauses, and speech rate. We parametrized them using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) from open-source Speech and Music Interpretation by Large-Space Extraction (openSMILE; audEERING GmbH) and extracted them from a transcript. We analyzed the speech features along with self-reported momentary affect ratings, using multilevel linear regression analysis. We analyzed an average of 32 (SD 19.83) assessments per patient. RESULTS: Analyses revealed that pitch variability, speech pauses, and speech rate were associated with depression severity, positive affect, valence, and energetic arousal; furthermore, speech pauses and speech rate were associated with negative affect, and speech pauses were additionally associated with calmness. Specifically, pitch variability was negatively associated with improved momentary states (ie, lower pitch variability was linked to lower depression severity as well as higher positive affect, valence, and energetic arousal). Speech pauses were negatively associated with improved momentary states, whereas speech rate was positively associated with improved momentary states. CONCLUSIONS: Pitch variability, speech pauses, and speech rate are promising features for the development of clinical prediction technologies to improve patient care as well as timely diagnosis and monitoring of treatment response. Our research is a step forward on the path to developing an automated depression monitoring system, facilitating individually tailored treatments and increased patient empowerment.

Automated Cough Sound Analysis for Detecting Childhood Pneumonia.

Pneumonia is one of the leading causes of death in children. Prompt diagnosis and treatment can help prevent these deaths, particularly in resource poor regions where deaths due to pneumonia are highest. Clinical symptom-based screening of childhood pneumonia yields excessive false positives, highlighting the necessity for additional rapid diagnostic tests. Cough is a prevalent symptom of acute respiratory illnesses and the sound of a cough can indicate the underlying pathological changes resulting from respiratory infections. In this study, we propose a fully automated approach to evaluate cough sounds to distinguish pneumonia from other acute respiratory diseases in children. The proposed method involves cough sound denoising, cough sound segmentation, and cough sound classification. The denoising algorithm utilizes multi-conditional spectral mapping with a multilayer perceptron network while the segmentation algorithm detects cough sounds directly from the denoised audio waveform. From the segmented cough signal, we extract various handcrafted features and feature embeddings from a pretrained deep learning network. A multilayer perceptron is trained on the combined feature set for detecting pneumonia. The method we propose is evaluated using a dataset comprising cough sounds from 173 children diagnosed with either pneumonia or other acute respiratory diseases. On average, the denoising algorithm improved the signal-to-noise ratio by 44%. Furthermore, a sensitivity and specificity of 91% and 86%, respectively, is achieved in cough segmentation and 82% and 71%, respectively, in detecting childhood pneumonia using cough sounds alone. This demonstrates its potential as a rapid diagnostic tool, such as using smartphone technology.

Somatisation Disorder Detection via Speech: Introducing a Self-Supervised Learning Model.

With the depressive psychiatric disorders becoming more common, people are gradually starting to take it seriously. Somatisation disorders, as a general mental disorder, are rarely accurately identified in clinical diagnosis for its specific nature. In the previous work, speech recognition technology has been successfully applied to the task of identifying somatisation disorders on the Shenzhen Somatisation Speech Corpus. Nevertheless, there is still a scarcity of labels for somatisation disorder speech database. The current mainstream approaches in the speech recognition heavily rely on the well labelled data. Compared to supervised learning, self-supervised learning is able to achieve the same or even better recognition results while reducing the reliance on labelled samples. Moreover, self-supervised learning can generate general representations without the need for human hand-crafted features depending on the different recognition tasks. To this end, we apply self-supervised learning pre-trained models to solve few-labelled somatisation disorder speech recognition. In this study, we compare and analyse the results of three self-supervised learning models (contrastive predictive coding, wav2vec and wav2vec 2.0). The best result of wav2vec 2.0 model achieves 77.0 % unweighted average recall and is significantly better than CPC (p < .005), performing better than the benchmark of the supervised learning model.Clinical relevance- This work proposed a self-supervised learning model to resolve the few-labelled SD speech data, which can be well used for helping psychiatrists with clinical assistant to diagnosis. With this model, psychiatrists no longer need to spend a lot of time labelling SD speech data.

Less is More: A Novel Feature Extraction Method for Heart Sound Classification via Fractal Transformation.

Cardiovascular diseases (CVDs) are the leading cause of death globally. Heart sound signal analysis plays an important role in clinical detection and physical examination of CVDs. In recent years, auxiliary diagnosis technology of CVDs based on the detection of heart sound signals has become a research hotspot. The detection of abnormal heart sounds can provide important clinical information to help doctors diagnose and treat heart disease. We propose a new set of fractal features - fractal dimension (FD) - as the representation for classification and a Support Vector Machine (SVM) as the classification model. The whole process of the method includes cutting heart sounds, feature extraction, and classification of abnormal heart sounds. We compare the classification results of the heart sound waveform (time domain) and the spectrum (frequency domain) based on fractal features. Finally, according to the better classification results, we choose the fractal features that are most conducive for classification to obtain better classification performance. The features we propose outperform the widely used features significantly (p < .05 by one-tailed z-test) with a much lower dimension.Clinical relevance-The heart sound classification model based on fractal provides a new time-frequency analysis method for heart sound signals. A new effective mechanism is proposed to explore the relationship between the heart sound acoustic properties and the pathology of CVDs. As a non-invasive diagnostic method, this work could supply an idea for the preliminary screening of cardiac abnormalities through heart sounds.

Detecting Childhood Pneumonia Using Handcrafted and Deep Learning Cough Sound Features and Multilayer Perceptron.

Pneumonia is one of the leading causes of morbidity and mortality in children. This is especially true in resource poor regions lacking diagnostic facilities, bringing about the need for rapid diagnostic tests for pneumonia. Cough is a common symptom of acute respiratory diseases, including pneumonia, and the sound of cough can be indicative of the pathological variations caused by respiratory infections. As such, in this paper we study objective cough sound evaluation for differentiating between pneumonia and other acute respiratory diseases. We use a dataset of 491 cough sounds from 173 children diagnosed either as having pneumonia or other acute respiratory diseases. We extract features which describe the temporal, spectral, and cepstral characteristics of the cough sound. These features are combined with feature embeddings from a pretrained deep learning network and used to train a multilayer perceptron for classification. The proposed method achieves a sensitivity and specificity of 84% and 73% respectively in differentiating between pneumonia and other acute respiratory diseases using cough sounds alone.

Cutting Weights of Deep Learning Models for Heart Sound Classification: Introducing a Knowledge Distillation Approach.

Cardiovascular diseases (CVDs) are the number one cause of death worldwide. In recent years, intelligent auxiliary diagnosis of CVDs based on computer audition has become a popular research field, and intelligent diagnosis technology is increasingly mature. Neural networks used to monitor CVDs are becoming more complex, requiring more computing power and memory, and are difficult to deploy in wearable devices. This paper proposes a lightweight model for classifying heart sounds based on knowledge distillation, which can be deployed in wearable devices to monitor the heart sounds of wearers. The network model is designed based on Convolutional Neural Networks (CNNs). Model performance is evaluated by extracting Mel Frequency Cepstral Coefficients (MFCCs) features from the PhysioNet/CinC Challenge 2016 dataset. The experimental results show that knowledge distillation can improve a lightweight network's accuracy, and our model performs well on the test set. Especially, when the knowledge distillation temperature is 7 and the weight α is 0.1, the accuracy is 88.5 %, the recall is 83.8 %, and the specificity is 93.6 %.Clinical relevance- A lightweight model of heart sound classification based on knowledge distillation can be deployed on various hardware devices for timely monitoring and feedback of the physical condition of patients with CVDs for timely provision of medical advice. When the model is deployed on the medical instruments of the hospital, the condition of severe and hospitalised patients can be timely fed back and clinical treatment advice can be provided to the clinicians.

How does Music Affect Your Brain? A Pilot Study on EEG and Music Features for Automatic Analysis.

Music can effectively induce specific emotion and usually be used in clinical treatment or intervention. The electroencephalogram can help reflect the impact of music. Previous studies showed that the existing methods achieved relatively good performance in predicting emotion response to music. However, these methods tend to be time consuming and expensive due to their complexity. To this end, this study proposes a grey wolf optimiser-based method to predict the induced emotion through fusing electroencephalogram features and music features. Experimental results show that, the proposed method can reach a promising performance for predicting emotional response to music and outperform the alternative method. In addition, we analyse the relationship between the music features and electroencephalogram features and the results demonstrate that, musical timbre features are significantly related to the electroencephalogram features.Clinical relevance- This study targets the automatic prediction of the human response to music. It further explores the correlation between EEG features and music features aiming to provide the basis for the extension to the application of music. The grey wolf optimiser-based method proposed in this study could supply a promising avenue for the emotion prediction as induced by music.

[Detection and Application of Allostatic Load through Internet of Things Measurements].

Allostatic load refers to a vulnerable state of the nervous system caused by chronic or repeated exposure to challenges of daily life (e.g., psychological stressors) and considered to indicate risk of a transition to pathological state. In this paper, we first introduce a traditional method of assessing allostatic load that utilizes multiple biomarkers. Next, we demonstrate the potential of the Internet of Things (IoT) data sampling method to detect and control the vulnerable state in daily life.

The transcription factors, STOP1 and TCP20, are required for root system architecture alterations in response to nitrate deficiency.

Nitrate distribution in soils is often heterogeneous. Plants have adapted to this by modifying their root system architecture (RSA). Previous studies showed that NITRATE-TRANSPORTER1.1 (NRT1.1), which also transports auxin, helps inhibit lateral root primordia (LRP) emergence in nitrate-poor patches, by preferentially transporting auxin away from the LRP. In this study, we identified the regulatory system for this response involving the transcription factor (TF), SENSITIVE-TO-PROTON-RHIZOTOXICITY1 (STOP1), which is accumulated in the nuclei of LRP cells under nitrate deficiency and directly regulates Arabidopsis NRT1.1 expression. Mutations in STOP1 mimic the root phenotype of the loss-of-function NRT1.1 mutant under nitrate deficiency, compared to wild-type plants, including increased LR growth and higher DR5promoter activity (i.e., higher LRP auxin signaling/activity). Nitrate deficiency-induced LR growth inhibition was almost completely reversed when STOP1 and the TF, TEOSINTE-BRANCHED1,-CYCLOIDEA,-PCF-DOMAIN-FAMILY-PROTEIN20 (TCP20), a known activator of NRT1.1 expression, were both mutated. Thus, the STOP1-TCP20 system is required for activation of NRT1.1 expression under nitrate deficiency, leading to reduced LR growth in nitrate-poor regions. We found this STOP1-mediated system is more active as growth media becomes more acidic, which correlates with reductions in soil nitrate as the soil pH becomes more acidic. STOP1 has been shown to be involved in RSA modifications in response to phosphate deficiency and increased potassium uptake, hence, our findings indicate that root growth regulation in response to low availability of the major fertilizer nutrients, nitrogen, phosphorus and potassium, all involve STOP1, which may allow plants to maintain appropriate root growth under the complex and varying soil distribution of nutrients.

Identifying languages in a novel dataset: ASMR-whispered speech.

Introduction: The Autonomous Sensory Meridian Response (ASMR) is a combination of sensory phenomena involving electrostatic-like tingling sensations, which emerge in response to certain stimuli. Despite the overwhelming popularity of ASMR in the social media, no open source databases on ASMR related stimuli are yet available, which makes this phenomenon mostly inaccessible to the research community; thus, almost completely unexplored. In this regard, we present the ASMR Whispered-Speech (ASMR-WS) database. Methods: ASWR-WS is a novel database on whispered speech, specifically tailored to promote the development of ASMR-like unvoiced Language Identification (unvoiced-LID) systems. The ASMR-WS database encompasses 38 videos-for a total duration of 10 h and 36 min-and includes seven target languages (Chinese, English, French, Italian, Japanese, Korean, and Spanish). Along with the database, we present baseline results for unvoiced-LID on the ASMR-WS database. Results: Our best results on the seven-class problem, based on segments of 2s length, and on a CNN classifier and MFCC acoustic features, achieved 85.74% of unweighted average recall and 90.83% of accuracy. Discussion: For future work, we would like to focus more deeply on the duration of speech samples, as we see varied results with the combinations applied herein. To enable further research in this area, the ASMR-WS database, as well as the partitioning considered in the presented baseline, is made accessible to the research community.

The Voice of the Body: Why AI Should Listen to It and an Archive.

The sound generated by body carries important information about our health status physically and psychologically. In the past decades, we have witnessed a plethora of successes achieved in the field of body sound analysis. Nevertheless, the fundamentals of this young field are still not well established. In particular, publicly accessible databases are rarely developed, which dramatically restrains a sustainable research. To this end, we are launching and continuously calling for participation from the global scientific community to contribute to the Voice of the Body (VoB) archive. We aim to build an open access platform to collect the well-established body sound databases in a well standardized way. Moreover, we hope to organize a series of challenges to promote the development of audio-driven methods for healthcare via the proposed VoB. We believe that VoB can help break the walls between different subjects toward an era of Medicine 4.0 enriched by audio intelligence.

The Effects of Objective Push-Type Sleep Feedback on Habitual Sleep Behavior and Momentary Symptoms in Daily Life: mHealth Intervention Trial Using a Health Care Internet of Things System.

BACKGROUND: Sleep is beneficial for physical and mental health. Several mobile and wearable sleep-tracking devices have been developed, and personalized sleep feedback is the most common functionality among these devices. To date, no study has implemented an objective push-type feedback message and investigated the characteristics of habitual sleep behavior and diurnal symptoms when receiving sleep feedback. OBJECTIVE: We conducted a mobile health intervention trial to examine whether sending objective push-type sleep feedback changes the self-reported mood, physical symptoms, and sleep behavior of Japanese office workers. METHODS: In total, 31 office workers (mean age 42.3, SD 7.9 years; male-to-female ratio 21:10) participated in a 2-arm intervention trial from November 30 to December 19, 2020. The participants were instructed to indicate their momentary mood and physical symptoms (depressive mood, anxiety, stress, sleepiness, fatigue, and neck and shoulder stiffness) 5 times a day using a smartphone app. In addition, daily work performance was rated once a day after work. They were randomly assigned to either a feedback or control group, wherein they did or did not receive messages about their sleep status on the app every morning, respectively. All participants wore activity monitors on their nondominant wrists, through which objective sleep data were registered on the web on a server. On the basis of the estimated sleep data on the server, personalized sleep feedback messages were generated and sent to the participants in the feedback group using the app. These processes were fully automated. RESULTS: Using hierarchical statistical models, we examined the differences in the statistical properties of sleep variables (sleep duration and midpoint of sleep) and daily work performance over the trial period. Group differences in the diurnal slopes for mood and physical symptoms were examined using a linear mixed effect model. We found a significant group difference among within-individual residuals at the midpoint of sleep (expected a posteriori for the difference: -15, 95% credible interval -26 to -4 min), suggesting more stable sleep timing in the feedback group. However, there were no significant group differences in daily work performance. We also found significant group differences in the diurnal slopes for sleepiness (P<.001), fatigue (P=.002), and neck and shoulder stiffness (P<.001), which was largely due to better scores in the feedback group at wake-up time relative to those in the control group. CONCLUSIONS: This is the first mobile health study to demonstrate that objective push-type sleep feedback improves sleep timing of and physical symptoms in healthy office workers. Future research should incorporate specific behavioral instructions intended to improve sleep habits and examine the effectiveness of these instructions.

Altered distribution of resting periods of daily locomotor activity in patients with delayed sleep phase disorder.

Delayed sleep phase disorder (DSPD) and mood disorders have a close relationship. However, the shared mechanisms by DSPD and mood disorders have not been well-elucidated. We previously found that micro-fluctuations in human behaviors are organized by robust statistical laws (behavioral organization), where the cumulative distributions of resting and active period durations take a power-law distribution form and a stretched exponential functional form, respectively. Further, we found that the scaling exponents of resting period distributions significantly decreased in major depressive disorder (MDD). In this study, we hypothesized that DSPD had similar characteristics of the altered behavioral organization to that of MDD. Locomotor activity data were acquired for more than 1 week from 17 patients with DSPD and 17 age- and gender-matched healthy participants using actigraphy. We analyzed the cumulative distributions of resting and active period durations in locomotor activity data and subsequently derived fitting parameters of those distributions. Similar to patients with MDD, we found that resting period distributions took a power-law form over the range of 2-100 min, with significantly lower values of scaling exponents γ in patients with DSPD compared with healthy participants. The shared alteration in γ suggests the existence of similar pathophysiology between DSPD and MDD.

Heart Sound Classification based on Residual Shrinkage Networks.

Heart sound classification is one of the non-invasive methods for early detection of the cardiovascular diseases (CVDs), the leading cause for deaths. In recent years, Computer Audition (CA) technology has become increasingly sophisticated, auxiliary diagnosis technology of heart disease based on CA has become a popular research area. This paper proposes a deep Convolutional Neural Network (CNN) model for heart sound classification. To improve the classification accuracy of heart sound, we design a classification algorithm combining classical Residual Network (ResNet) and Long Short-Term Memory (LSTM). The model performance is evaluated in the PhysioNet/CinC Challenges 2016 datasets using a 2D time-frequency feature. We extract the four features from different filter-bank coefficients, including Filterbank (Fbank), Mel-Frequency Spectral Coefficients (MFSCs), and Mel-Frequency Cepstral Coefficients (MFCCs). The experimental results show the MFSCs feature outperforms the other features in the proposed CNN model. The proposed model performs well on the test set, particularly the F1 score of 84.3 % - the accuracy of 84.4 %, the sensitivity of 84.3 %, and the specificity of 85.6 %. Compared with the classical ResNet model, an accuracy of 4.9 % improvement is observed in the proposed model.

A Federated Learning Paradigm for Heart Sound Classification.

Cardiovascular diseases (CVDs) have been ranked as the leading cause for deaths. The early diagnosis of CVDs is a crucial task in the medical practice. A plethora of efforts were given to the automated auscultation of heart sound, which leverages the power of computer audition to develop a cheap, non-invasive method that can be used at any time and anywhere for measuring the status of the heart. Nevertheless, previous works ignore an important factor, namely, the privacy of the user data. On the one hand, learnt models are always hungry for bigger data. On the other hand, it can be difficult to protect personal private information when collecting such large amount of data. In this dilemma, we propose a federated learning (FL) framework for the heart sound classification task. To the best of our knowledge, this is the first time to introduce FL to this field. We conducted multiple experiments, analysed the impact of data distribution across collaborative institutions on model quality and learning patterns, and verified the feasibility and effectiveness of FL based on real data. Non- independent identically distributed (Non-IID) data and model quality can be effectively improved by adding a strategy of globally sharing data.

Correlation of Scoring Systems with the Requirement of an External Ventricular Drain in Intraventricular Hemorrhage.

BACKGROUND: External ventricular drainage (EVD) is required to resolve acute hydrocephalus associated with intraventricular hemorrhage (IVH). The correlation of scoring systems of IVH with indications for EVD for acute hydrocephalus related to IVH is currently unknown. METHODS: We identified 213 hypertensive patients with IVH and divided them into 2 groups according to treatment method: 187 patients receiving blood pressure control alone and 26 patients undergoing EVD. The following patients were excluded: pediatric patients, patients undergoing intracranial hematoma removal, patients with fetal status, and patients without sufficient clinical data. We compared the Glasgow Coma Scale score, Graeb score, LeRoux score, Evans index, and bicaudate index values between the 2 groups and determined the prognostication accuracy of each scoring system. RESULTS: There were significant differences in all 4 scoring systems between the 2 groups (P < 0.001). The cutoff values (sensitivity and specificity) of each scoring system were as follows: Glasgow Coma Scale, 8 (65.4%, 87.7%); Graeb score, 6 (80.8%, 75.4%); LeRoux score, 9 (80.8%, 76.5%); Evans index, 0.245 (80.8%, 67.9%); and bicaudate index, 0.186 (76.9%, 76.5%). The value of the area under the curve of each scoring system (95% confidence interval) was as follows: Glasgow Coma Scale, 0.806 (0.705-0.907); Graeb score, 0.852 (0.779-0.925); LeRoux score, 0.875 (0.812-0.937); Evans index, 0.788 (0.702-0.875); and bicaudate index, 0.778 (0.673-0.883). CONCLUSIONS: The LeRoux score is better for identifying patients with IVH who are more likely to have EVD.

Sequence-based evaluation of promoter context for prediction of transcription start sites in Arabidopsis and rice.

Genes are transcribed from transcription start sites (TSSs), and their position in a genome is strictly controlled to avoid mis-expression of undesired regions. In this study, we designed and developed a methodology for the evaluation of promoter context, which detects proximal promoter regions from - 200 to - 60 bp relative to a TSS, in Arabidopsis and rice genomes. The method positively evaluates spacer sequences and Regulatory Element Groups, but not core promoter elements like TATA boxes, and is able to predict the position of a TSS within a width of 200 bp. An important feature of the evaluation/prediction method is its independence of the core promoter elements, which was demonstrated by successful prediction of all the TATA, GA, and coreless types of promoters without notable differences in the accuracy of prediction. The positive relationship identified between the evaluation scores and gene expression levels suggests that this method is useful for the evaluation of promoter maturity.