Deep learning for healthcare applications based on physiological signals: A review.

Deep neural networks represent, nowadays, the most effective machine learning technology in biomedical domain. In this domain, the different areas of interest concern the Omics (study of the genome—genomics—and proteins—transcriptomics, proteomics, and metabolomics), bioimaging (study of biological cell and tissue), medical imaging (study of the human organs by creating visual representations), BBMI (study of the brain and body machine interface) and public and medical health management (PmHM). This paper reviews the major deep learning concepts pertinent to such biomedical applications. Concise overviews are provided for the Omics and the BBMI. We end our analysis with a critical discussion, interpretation and relevant open challenges.

Deep Learning in the Biomedical Applications: Recent and Future Status

Deep learning algorithms have achieved high performance accuracy in complex domains such as image classification, face recognition sentiment analysis, text classification, and speech understanding. Due to the nested non-linear structure of deep learning algorithms, these highly successful models are usually applied in a black-box manner, i.e., no information is provided about what exactly causes them to arrive at their predictions. The effectiveness of these systems is thus limited by the machine’s current inability to explain its decisions and actions to human users. Such a lack of transparency can be a major drawback. For instance, in medical applications the development of methods for visualizing, explaining, and interpreting deep learning models has recently attracted increasing attention. Explainable Machine Learning (XAI) or Interpretable Machine Learning (IML) programs aim to create a suite of machine learning techniques that produce more explainable models while maintaining the high level of accuracy. It also enables human users to understand, appropriately trust, and effectively manage the emerging generation of artificially intelligent partners. Our work summarizes recent developments in this field, and we present three classification tasks wherein we make use of LIME (Local Interpretable Model-Agnostic Explanations) to explain predictions of deep learning models. LIME attempts to make these complex models at least partly understandable by evaluating using three classification tasks. Our first evaluation is performed on natural language processing application for tweet data classification and our second evaluation is on biomedical signal classification cancer detection. Our third evaluation is on Windows PC malware classification in a cybersecurity domain. In all three case studies, the interpreted results are presented in terms of visualization.

Explainable Artificial Intelligence Applications in NLP, Biomedical, and Malware Classification: A Literature Review

Background: During last decade the use of ECG recordings in biometric recognition studies has increased. ECG characteristics made it suitable for subject identification: it is unique, present in all living individuals, and hard to forge. However, in spite of the great number of approaches found in literature, no agreement exists on the most appropriate methodology. This study aimed at providing a survey of the techniques used so far in ECG-based human identification. Specifically, a pattern recognition perspective is here proposed providing a unifying framework to appreciate previous studies and, hopefully, guide future research. Methods: We searched for papers on the subject from the earliest available date using relevant electronic databases (Medline, IEEEXplore, Scopus, and Web of Knowledge). The following terms were used in different combinations: electrocardiogram, ECG, human identification, biometric, authentication and individual variability. The electronic sources were last searched on 1st March 2015. In our selection we included published research on peer-reviewed journals, books chapters and conferences proceedings. The search was performed for English language documents. Results: 100 pertinent papers were found. Number of subjects involved in the journal studies ranges from 10 to 502, age from 16 to 86, male and female subjects are generally present. Number of analysed leads varies as well as the recording conditions. Identification performance differs widely as well as verification rate. Many studies refer to publicly available databases (Physionet ECG databases repository) while others rely on proprietary recordings making difficult them to compare. As a measure of overall accuracy we computed a weighted average of the identification rate and equal error rate in authentication scenarios. Identification rate resulted equal to 94.95 % while the equal error rate equal to 0.92 %. Conclusions: Biometric recognition is a mature field of research. Nevertheless, the use of physiological signals features, such as the ECG traits, needs further improvements. ECG features have the potential to be used in daily activities such as access control and patient handling as well as in wearable electronics applications. However, some barriers still limit its growth. Further analysis should be addressed on the use of single lead recordings and the study of features which are not dependent on the recording sites (e.g. fingers, hand palms). Moreover, it is expected that new techniques will be developed using fiducials and non-fiducial based features in order to catch the best of both approaches. ECG recognition in pathological subjects is also worth of additional investigations.

/pdf/individual-identification-via-electrocardiogram-analysis-1hm3xvuapg.pdf

Individual identification via electrocardiogram analysis

We perform a systematic review of ECG biometric databases in the literature.We compare the acquisition hardware used to acquire ECG biometric databases.We compare the acquisition protocols adopted by ECG biometric databases.We highlight that an exhaustive database for biometric studies still lacks. Computer-based biometric systems (CBBSs) individual recognition are expert and intelligent systems that are gaining increasing interest in many areas, such as securing financial systems, telecommunications and healthcare applications. The electrocardiogram (ECG) has been used as biometric feature for its low circumvention, large acceptability and uniqueness, thus being at the basis of several CBBSs. As ECG databases collected for clinical applications are not adequate for biometric applications, we have assisted to the development of other repositories of ECG, each one different from the others and highlighting certain issues of ECG-based biometric recognition. Through a systematic framework presented here, we quantitative analyse, evaluate and compare the acquisition hardware and the acquisition protocols of ECG databases available in literature and suited to develop CBBSs. Although the most recent ones, namely CYBHI and UofTDB, result the best for the acquisition hardware and the acquisition protocols, respectively, our survey shows that none is exhaustive for developing a robust and general enough CBBSs. The analysis also highlights the current lack of standardization in this field and the difficulty of performing an effective benchmarking activity. Since a publicly available database is essential for the research community in ECG-based CBBS to correctly assess the performance of existing algorithms or even commercial expert systems, we also discuss here the main features that an "optimal" repository for the intelligent application at hand.

ECG databases for biometric systems

Strategies were proposed for Electrocardiogram (ECG) based identification. Firstly, a selecting mechanism based on information entropy was used to obtain whole heart beat signal; Secondly, a Depth Neural Network (DNN) based on Denoising AutoEncoder (DAE) was adopted in feature selection unsupervised, by which, the robustness of the recognition system could be improved in recognizing. Finally, 98.10% and 95.67% recognition rate were obtained on self-collected calm and high pressure data sets respectively, and 94.39% rate on combined data sets of MIT arrhythmia database (mitdb) and self-collected data averagely.

ECG Based Identification by Deep Learning

Though modern ECG machine with digital-out has been applied for years, paper recordings are still chosen by medical organizations especially in China. But the recording paper is easily broken. These ECG data were necessarily to be extracted and keep the valuable ECG information as digital type for clinical information sharing, online diagnosing and ECG database establishing. A method based on K-means was proposed to extract ECG data from paper recordings. The ECG waveform and the background grid were separated well.105 patients' ECG paper recordings were adopted in the experiment. And the recordings are in different damage level, the paper are in different background color and made by different manufacturers. The result shows that ECG waveform can be extracted precisely and smoothly. The precision rate of RR interval, QRS interval, QT interval, ST slope, and R amplitude from ECG data which are digitalized by the approach in the paper could reach 99%.

http://cinc.org/archives/2011/pdf/0797.pdf

ECG waveform data extraction from paper ECG recordings by K-means method

Rule design is very important for active database system implementation. But, it is also very difficult for us because of lacking methodology and support. In the paper, active rule design is regarded as a whole process and identified to three steps: rule extraction, rule analysis, and rule update. Data mining technique is originally introduced into rule design by us to cope with the problems arisen in active semantic extraction, termination analysis of rules set, and rules update. Rule mining methods are adopted to extract active semantics, and the discovered rules are used to assist active rule specification. Data mining technique is integrated with the triggering graph to improve the accuracy of termination analysis. Finally, data mining technique is used to identify new semantics and determine which rules should be updated.

Data Mining Used in Rule Design for Active Database Systems

The invention provides a method for digitalizing a paper electrocardiogram In the method, a digital image processing technology is combined to rebuild and store a large number of clinical paper electrocardiograms The method comprises the following steps: scanning the paper electrocardiogram, and carrying out tilt correction on the grey level image of the obtained electrocardiogram; extracting an electrocardio (ECG) curve in the paper electrocardiogram; acquiring the time-voltage value of each discrete point on the curve; rebuilding an electrocardiogram curve and leading information; storing the time-voltage value of each discrete point in a database; and storing a rebuilt oscillogram in the database In the method, the possibility of adding symptom information of the clinically acquired paper electrocardiogram to a digital ECG information management system is ensured, thereby enriching a case bank The method is used for solving the problems that the paper electrocardiograms are easy to damage and lose (the electrocardiograms can not be recovered after being damaged or lost), are difficult to store, and easy to go wrong in trivial management; the method facilitates clinical analysis and scientific research, thus reducing the search time, and improving the efficiency; and the method can be applied to internet medical treatment and multiple expert consultation, thus improving the diagnosis quality

Method for digitalizing paper electrocardiogram

Baseline wander always exists along with ECG signal. It is a kind of noise and may interference the diagnosis of cardio diseases, especially for the automatic diagnosis. Most methods could eliminate baseline wander already, however be difficult to meet the requisition of low distortion. To solve this problem, a morphology algorithm based on 2-D flat structure element is proposed, where flat structure element is often employed in previous work. The structure element is designed according to the shape, amplitude, period of the ECG signal itself, for a more accurate approximating to the ECG waveforms. Moreover, such structure element is variable by the feedback of filtered waveforms, which could elevate its robust. This algorithm is tested with the data from 8 files of MIT/BIH arrhythmia database, which contains 8 different shapes in ST segment, covering most of the cardiac conditions. The results are estimated in the baseline elimination as well as the distortion induced by filtering on the P waveform, QRS wave group, and the ST segments of ECG signal. Compared with those arguments of several classical strategies, the signal to noise ratio after processed by morphology based on non-flat structure element reaches the highest among all methods, and the ratio of deformation lowest, which means that this algorithm could both reduce the baseline wander, and control the distortion effectively.

http://cinc.mit.edu/archives/2011/pdf/0817.pdf

A morphology algorithm based on 2-dimensional flat structure element on ECG baseline wander elimination

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Min Dai

Author Tools

Chat about Author