Activity

In recent years, consumer-grade sensors that measure health relevant physiological signals have become widely available and are increasingly used by consumers and researchers alike. While this allows for multiple novel, potentially highly beneficial, large-scale health monitoring applications, quality of these data streams is oftentimes suboptimal. This makes alignment of different high-frequency data streams from multiple, non-connected sensors, a difficult task. In this work we describe a noise-robust framework to align high-frequency signals from different sensors, that share some underlying characteristic, obtained in a free-living, non-clinical, home environment. We demonstrate the approach on the basis of a single-lead, medical-grade, mobile electrocardiography device and a consumer-grade sleep sensor that allows for ballistocardiography. Both commercially available sensors measure the physiological process of a heartbeat. We show, on the basis of real-world data with multiple people and sensors, that the two highly noisy and sometimes dissimilar signals could in most cases be aligned with considerable precision. As a result, we could reduce mean heartbeat peak-to-peak difference by 58.1% on average and increase signal correlation by 0.40 on average.Failing to master handwriting, as in the case of Dysgraphia, has negative consequences on children’s lives. In early stage of development, Dysgraphia diagnosis is delayed and not easily achievable. Thus, the aim of this work is to propose a valid tool to anticipate Dysgraphia screening at a preliteracy age. We developed a tablet application to analyze characteristics altered in dysgraphic handwriting, such as rhythmical laws (isochrony and homothety), or a collection of kinematic and dynamic parameters (smoothness, pressure, frequency contents). To be suitable for the pre-literacy stage, possible alterations are investigated in symbol drawings. The app is tested on 104 preschoolers, both with normal (n=76) and delayed graphical abilities (n=28), reporting excellent acceptance. Some isochrony alterations were reported only for children with delayed graphical abilities. Moreover, kinematic and dynamic parameters are effective in discriminating between risk and norisk conditions. Indeed, the logistic classification adopted resulted in a 0.819 area under the precision-recall curve. These findings pave the way toward an early screening of future handwriting alteration, starting from a pre-literacy age.Speech analysis could help develop clinical tools for automatic detection of Alzheimer’s disease and monitoring of its progression. However, datasets containing both clinical information and spontaneous speech suitable for statistical learning are relatively scarce. In addition, speech data are often collected under different conditions, such as monologue and dialogue recording protocols. Therefore, there is a need for methods to allow the combination of these scarce resources. In this paper, we propose two feature extraction and representation models, based on neural networks and trained on monologue and dialogue data recorded in clinical settings. These models are evaluated not only for AD recognition, but also with respect to their potential to generalise across both datasets. They provide good results when trained and tested on the same data set (72.56% UAR for monologue data and 85.21% for dialogue). A decrease in UAR is observed in transfer training, where feature extraction models trained on dialogues provide better average UAR on monologues (63.72%) than the other way around (58.94%). When the choice of classifiers is independent of feature extraction, transfer from monologue models to dialogues result in a maximum UAR of 81.04% and transfer from dialogue features to monologue achieve a maximum UAR of 70.73%, evidencing the generalisability of the feature model.In clinical conversational applications, extracted entities tend to capture the main subject of a patient’s complaint, namely symptoms or diseases. However, they mostly fail to recognize the characterizations of a complaint such as the time, the onset, and the severity. For example, if the input is “I have a headache and it is extreme”, state-of-the-art models only recognize the main symptom entity – headache, but ignore the severity factor of extreme, that characterises headache. In this paper, we design a two-fold approach to detect the characterizations of entities like symptoms presented by general users in contexts where they would describe their symptoms to a clinician. We use Word2Vec and BERT models to encode clinical text given by the patients. We transform the output and re-frame the task as a multi-label classification problem. Finally, we combine the processed encodings with the Linear Discriminant Analysis (LDA) algorithm to classify the characterizations of the main entity. Experimental results demonstrate that our method achieves 40-50% improvement in the accuracy over the state-of-the-art models.DNA-Sequencing of tumor cells has revealed thousands of genetic mutations. However, cancer is caused by only some of them. Identifying mutations that contribute to tumor growth from neutral ones is extremely challenging and is currently carried out manually. This manual annotation is very cumbersome and expensive in terms of time and money. In this study, we introduce a novel method “NLP-SNPPred” to read scientific literature and learn the implicit features that cause certain variations to be pathogenic. Precisely, our method ingests the bio-medical literature and produces its vector representation via exploiting state of the art NLP methods like sent2vec, word2vec and tf-idf. These representations are then fed to machine learning predictors to identify the pathogenic versus neutral variations. Our best model (NLPSNPPred) trained on OncoKB and evaluated on several publicly available benchmark datasets, outperformed state of the art function prediction methods. CA-074 methyl ester ic50 Our results show that NLP can be used effectively in predicting functional impact of protein coding variations with minimal complementary biological features. Moreover, encoding biological knowledge into the right representations, combined with machine learning methods can help in automating manual efforts. A free to use web-server is available at http//www.nlp-snppred.cbrlab.org.