Objectives: This study is aimed to achieve the rapid optimization of the input feature subset that satisfies the expert's point of view and enhance the prediction performance of the early prediction model for fatty liver disease (FLD). Methods: We explore a large-scale and high-dimension dataset coming from a northern Taipei Health Screening Center in Taiwan, and the dataset includes data of 12,707 male and 10,601 female patients processed from around 500,000 records from year 2009 to 2016. We propose three eigenvector-based feature selections taking the Intersection of Union (IoU) and the Coverage to determine the sub-optimal subset of features with the highest IoU and the Coverage automatically, use various long short-term memory (LSTM) related classifiers for FLD prediction, and evaluate the model performance by the test accuracy and the Area Under the Receiver Operating Characteristic Curve (AUROC). Results: Our eigenvector-based feature selection EFS- TW has the highest IOU and the Coverage and the shortest total computing time. For comparison, the highest IOU, the Coverage, and computing time are 30.56%, 45.83% and 260 seconds for female, and that of a benchmark, sequential forward selection (SFS), are 9.09%, 16.67% and 380,350 seconds. The AUROC with LSTM, biLSTM, Gated Recurrent Unit (GRU), Stack-LSTM, Stack-biLSTM are 0.85, 0.86, 0.86, 0.86 and 0.87 for male, and all 0.9 for female, respectively. Conclusion: Our method explores a large-scale and high-dimension FLD dataset, implements three efficient and automatic eigenvector-based feature selections, and develops the model for early prediction of FLD efficiently.

Background: To parse free text medical notes into structured data such as disease names, drugs, procedures, and other important medical information first, it is necessary to detect medical entities. It is important for an Electronic Medical Record (EMR) to have structured data with semantic interoperability to serve as a seamless communication platform whenever a patient migrates from one physician to another. However, in free text notes, medical entities are often expressed using informal abbreviations. An informal abbreviation is a non-standard or undetermined abbreviation, made in diverse writing styles, which may burden the semantic interoperability between EMR systems. Therefore, a detection of informal abbreviations is required to tackle this issue. Objectives: We attempt to achieve highly reliable detection of informal abbreviations made in diverse writing styles. Methods: In this study, we apply the Long Short-Term Memory (LSTM) model to detect informal abbreviations in free text medical notes. Additionally, we use sliding windows to tackle the limited data issue and sample generator for the imbalance class issue, while introducing additional pre-trained features (bag of words and word2vec vectors) to the model.Results: The LSTM model was able to detect informal abbreviations with precision of 93.6%, recall of 57.6%, and F1-score of 68.9%. Conclusion: Our method was able to recognize informal abbreviations using small data set with high precision. The detection can be used to recognize informal abbreviations in real-time while the physician is typing it and raise appropriate indicators for the informal abbreviation meaning confirmation, thus increase the semantic interoperability.

• MeSH
• automatizované zpracování dat metody   MeSH
• data management metody   statistika a číselné údaje   MeSH
• deep learning * MeSH
• elektronické zdravotní záznamy MeSH
• interoperabilita zdravotnických informací MeSH
• správnost dat MeSH
• zkratky jako téma * MeSH
• Publikační typ
• práce podpořená grantem MeSH

The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.

• MeSH
• artefakty MeSH
• datové soubory jako téma MeSH
• deep learning * MeSH
• elektroencefalografie klasifikace   přístrojové vybavení   metody   MeSH
• lidé MeSH
• ROC křivka MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• pozorovací studie MeSH
• práce podpořená grantem MeSH
• Research Support, N.I.H., Extramural MeSH
• validační studie MeSH

In this paper, we propose an integrated biologically inspired visual collision avoidance approach that is deployed on a real hexapod walking robot. The proposed approach is based on the Lobula giant movement detector (LGMD), a neural network for looming stimuli detection that can be found in visual pathways of insects, such as locusts. Although a superior performance of the LGMD in the detection of intercepting objects has been shown in many collision avoiding scenarios, its direct integration with motion control is an unexplored topic. In our work, we propose to utilize the LGMD neural network for visual interception detection with a central pattern generator (CPG) for locomotion control of a hexapod walking robot that are combined in the controller based on the long short-term memory (LSTM) recurrent neural network. Moreover, we propose self-supervised learning of the integrated controller to autonomously find a suitable setting of the system using a realistic robotic simulator. Thus, individual neural networks are trained in a simulation to enhance the performance of the controller that is then experimentally verified with a real hexapod walking robot in both collision and interception avoidance scenario and navigation in a cluttered environment.

• MeSH
• chování zvířat fyziologie   MeSH
• chůze fyziologie   MeSH
• kobylky fyziologie   MeSH
• neuronové sítě MeSH
• řízené strojové učení MeSH
• robotika přístrojové vybavení   MeSH
• učení vyhýbat se fyziologie   MeSH
• zvířata MeSH
• Check Tag
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

Background: In most of Taiwan's medical institutions, congestion is a serious problem for emergency departments. Due to a lack of hospital beds, patients spend more time in emergency retention zones, which make it difficult to detect cardiac arrest. Objective: We seek to develop a Drug Early Warning Scoring Model (DEWSM), including drug injections and vital signs as these research important features. We use it to predict cardiac arrest in emergency departments via drug classification and medical experts' suggestion. Methods: We propose this new model for detecting cardiac arrest via drug classification and by using a sliding window, and apply learning-based algorithms to time-series data for a DEWSM. To evaluate the proposed model, we use the area under the receiver operating characteristic curve (AUROC). Results: We identify the two important drug predictors: bits (intravenous therapy), and replenishers and regulators of water and electrolytes (fluid and electrolyte supplement). Weverify feature selection, in which accounting for drugs to improve the accuracy and demonstrate that thus accounting for the drugs significantly affects prediction. Also, we show that CPR events can be predicted four hours before the event. Conclusion: Our study used a sliding window to account for dynamic time-series data consisting of the patient's vital signs and drug injections. The experimental results of adding the drug injections were better than only vital signs. In addition, we using LSTM method as the main processing time series data, it was the bases for comparison of this research.

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

• MeSH
• algoritmy MeSH
• COVID-19 * diagnóza   MeSH
• elektrokardiografie metody   MeSH
• fibrilace síní * diagnóza   MeSH
• kontrola infekčních nemocí MeSH
• lidé MeSH
• strojové učení MeSH
• umělá inteligence MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

• MeSH
• hodnocení výsledků zdravotní péče MeSH
• kvalita zdravotní péče MeSH
• poskytování zdravotní péče MeSH
• rozvojové země MeSH
• ukazatele kvality zdravotní péče MeSH

• Konspekt
• Veřejné zdraví a hygiena
• NLK Obory
• veřejné zdravotnictví
• NLK Publikační typ
• publikace WHO