Speech analysis as a tool for detection and monitoring of medical conditions: a review (Preprint)

2020 ◽  
Author(s):  
Mariusz Ziolko
Keyword(s):  
Machine Learning ◽  
Meta Analysis ◽  
Voice Quality ◽  
Medical Diagnostics ◽  
Mass Scale ◽  
The State ◽  
Machine Learning Algorithms ◽  
Speech Analysis ◽  
Future Research ◽  
Voice Analysis

BACKGROUND Speech is the main direct means of transmitting information between people. It also carries additional information depending on the state of the speaker: physical features, emotions, psychosocial traits and health conditions. Studying voice features is straightforward, does not require significant investment and can be carried out on a mass scale. However, speech analysis can only be used for initial diagnosis. The outcome of such a pre-diagnosis should indicate the need for standard medical tests. Although speech analysis is currently rarely used in medical diagnostics, it can enable earlier diagnosis and more effective treatment of patients. OBJECTIVE This paper is a systematic review and meta-analysis of recent advancements in using voice analysis for diagnosis and monitoring of some diseases. The goal of this article is to present and compare recent approaches to using speech and voice analysis as biomarkers of diseases. The article takes into account metabolic, respiratory, cardiovascular, endocrine and nervous system disorders. METHODS Articles published between 2010-2019 were selected from PubMed and ISCA Archive, using keywords ‘voice’ and ‘speech’ and respective disorder names. Further selection was performed to identify studies that assessed voice quality quantitatively in selected disorders by acoustic voice analysis (not only perceptual assessment). Information was extracted from each paper in order to compare various aspects of datasets, speech parameters, methods of analysis applied and results obtained. Each chapter starts with a medical description of how each disorder affects voice and contains a summary of different processing approaches, and is supplemented by tables comparing various investigations. Additional diagrams were prepared to illustrate general tendencies and to compare advancements in the state-of-the-art across the analyzed groups of diseases. RESULTS Over 90 research papers were reviewed and over 40 databases were summarized. Basic acoustic parameters which are significantly correlated with each given disorder were developed for cardiovascular, metabolic and endocrine diseases, as well as schizophrenia and amyotrophic lateral sclerosis. The affective and neurodegenerative disorders are well investigated and the majority of papers contain automatic voice recognition and machine learning methods. The main sources of problems were identified and some recommendation for future research were set. CONCLUSIONS Speech analysis is a promising tool for pre-diagnosis of certain disorders. Advanced computerized voice analysis and machine learning algorithms, and the widespread availability of smartphones, means that a diagnosis may be presented during the patient’s appointment with their physician, and even during a telephone conversation.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

scholarly journals Determination of Significant Features for Building an Efficient Heart Disease Prediction System

2019 ◽  
Vol 8 (2) ◽  
pp. 4499-4504
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Prediction Model ◽  
Prediction Models ◽  
Heart Diseases ◽  
Medical Diagnostics ◽  
Medical Data ◽  
Machine Learning Algorithms ◽  
Prediction System ◽  
Early Stages

Heart diseases are responsible for the greatest number of deaths all over the world. These diseases are usually not detected in early stages as the cost of medical diagnostics is not affordable by a majority of the people. Research has shown that machine learning methods have a great capability to extract valuable information from the medical data. This information is used to build the prediction models which provide cost effective technological aid for a medical practitioner to detect the heart disease in early stages. However, the presence of some irrelevant and redundant features in medical data deteriorates the competence of the prediction system. This research was aimed to improve the accuracy of the existing methods by removing such features. In this study, brute force-based algorithm of feature selection was used to determine relevant significant features. After experimenting rigorously with 7528 possible combinations of features and 5 machine learning algorithms, 8 important features were identified. A prediction model was developed using these significant features. Accuracy of this model is experimentally calculated to be 86.4%which is higher than the results of existing studies. The prediction model proposed in this study shall help in predicting heart disease efficiently.

An integrated review on machine learning approaches for heart disease prediction: Direction towards future research gaps

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Fathima Aliyar Vellameeran ◽  
Thomas Brindha
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Prediction Models ◽  
Machine Learning Algorithms ◽  
Future Research ◽  
Disease Prediction ◽  
Learning Approaches ◽  
Research Papers ◽  
Using Data ◽  
Intelligent Methods

Abstract Objectives To make a clear literature review on state-of-the-art heart disease prediction models. Methods It reviews 61 research papers and states the significant analysis. Initially, the analysis addresses the contributions of each literature works and observes the simulation environment. Here, different types of machine learning algorithms deployed in each contribution. In addition, the utilized dataset for existing heart disease prediction models was observed. Results The performance measures computed in entire papers like prediction accuracy, prediction error, specificity, sensitivity, f-measure, etc., are learned. Further, the best performance is also checked to confirm the effectiveness of entire contributions. Conclusions The comprehensive research challenges and the gap are portrayed based on the development of intelligent methods concerning the unresolved challenges in heart disease prediction using data mining techniques.

Forecasting the Market with Machine Learning Algorithms: An Application of NMC-BERT-LSTM-DQN-X Algorithm in Quantitative Trading

2022 ◽  
Vol 16 (4) ◽  
pp. 1-22
Author(s):  
Chang Liu ◽  
Jie Yan ◽  
Feiyue Guo ◽  
Min Guo
Keyword(s):  
Machine Learning ◽  
Stock Market ◽  
Mean Square Error ◽  
Short Term Memory ◽  
The State ◽  
Machine Learning Algorithms ◽  
Future Market ◽  
Mean Square ◽  
Market Data ◽  
Market Trends

Although machine learning (ML) algorithms have been widely used in forecasting the trend of stock market indices, they failed to consider the following crucial aspects for market forecasting: (1) that investors’ emotions and attitudes toward future market trends have material impacts on market trend forecasting (2) the length of past market data should be dynamically adjusted according to the market status and (3) the transition of market statutes should be considered when forecasting market trends. In this study, we proposed an innovative ML method to forecast China's stock market trends by addressing the three issues above. Specifically, sentimental factors (see Appendix [1] for full trans) were first collected to measure investors’ emotions and attitudes. Then, a non-stationary Markov chain (NMC) model was used to capture dynamic transitions of market statutes. We choose the state-of-the-art (SOTA) method, namely, Bidirectional Encoder Representations from Transformers ( BERT ), to predict the state of the market at time t , and a long short-term memory ( LSTM ) model was used to estimate the varying length of past market data in market trend prediction, where the input of LSTM (the state of the market at time t ) was the output of BERT and probabilities for opening and closing of the gates in the LSTM model were based on outputs of the NMC model. Finally, the optimum parameters of the proposed algorithm were calculated using a reinforced learning-based deep Q-Network. Compared to existing forecasting methods, the proposed algorithm achieves better results with a forecasting accuracy of 61.77%, annualized return of 29.25%, and maximum losses of −8.29%. Furthermore, the proposed model achieved the lowest forecasting error: mean square error (0.095), root mean square error (0.0739), mean absolute error (0.104), and mean absolute percent error (15.1%). As a result, the proposed market forecasting model can help investors obtain more accurate market forecast information.

Machine Learning

2012 ◽  
pp. 13-22 ◽  
Author(s):  
João Gama ◽  
André C.P.L.F. de Carvalho
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Text Processing ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Background Information ◽  
Future Research ◽  
Personal View ◽  
Learning Techniques ◽  
Future Research Directions

Machine learning techniques have been successfully applied to several real world problems in areas as diverse as image analysis, Semantic Web, bioinformatics, text processing, natural language processing,telecommunications, finance, medical diagnosis, and so forth. A particular application where machine learning plays a key role is data mining, where machine learning techniques have been extensively used for the extraction of association, clustering, prediction, diagnosis, and regression models. This text presents our personal view of the main aspects, major tasks, frequently used algorithms, current research, and future directions of machine learning research. For such, it is organized as follows: Background information concerning machine learning is presented in the second section. The third section discusses different definitions for Machine Learning. Common tasks faced by Machine Learning Systems are described in the fourth section. Popular Machine Learning algorithms and the importance of the loss function are commented on in the fifth section. The sixth and seventh sections present the current trends and future research directions, respectively.

Machine Learning

2011 ◽  
pp. 2462-2468 ◽  
Author(s):  
João Gama ◽  
André C.P.L.F. de Carvalho
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Text Processing ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Background Information ◽  
Future Research ◽  
Personal View ◽  
Learning Techniques ◽  
Future Research Directions

Machine learning techniques have been successfully applied to several real world problems in areas as diverse as image analysis, Semantic Web, bioinformatics, text processing, natural language processing,telecommunications, finance, medical diagnosis, and so forth. A particular application where machine learning plays a key role is data mining, where machine learning techniques have been extensively used for the extraction of association, clustering, prediction, diagnosis, and regression models. This text presents our personal view of the main aspects, major tasks, frequently used algorithms, current research, and future directions of machine learning research. For such, it is organized as follows: Background information concerning machine learning is presented in the second section. The third section discusses different definitions for Machine Learning. Common tasks faced by Machine Learning Systems are described in the fourth section. Popular Machine Learning algorithms and the importance of the loss function are commented on in the fifth section. The sixth and seventh sections present the current trends and future research directions, respectively.

scholarly journals Linear Support Vector Machines for Prediction of Student Performance in School-Based Education

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Nalindren Naicker ◽  
Timothy Adeliyi ◽  
Jeanette Wing
Keyword(s):  
Machine Learning ◽  
Support Vector Machines ◽  
Student Performance ◽  
State Of The Art ◽  
Learning Algorithms ◽  
The State ◽  
Machine Learning Algorithms ◽  
Superior Performance ◽  
Support Vector ◽  
Vector Machines

Educational Data Mining (EDM) is a rich research field in computer science. Tools and techniques in EDM are useful to predict student performance which gives practitioners useful insights to develop appropriate intervention strategies to improve pass rates and increase retention. The performance of the state-of-the-art machine learning classifiers is very much dependent on the task at hand. Investigating support vector machines has been used extensively in classification problems; however, the extant of literature shows a gap in the application of linear support vector machines as a predictor of student performance. The aim of this study was to compare the performance of linear support vector machines with the performance of the state-of-the-art classical machine learning algorithms in order to determine the algorithm that would improve prediction of student performance. In this quantitative study, an experimental research design was used. Experiments were set up using feature selection on a publicly available dataset of 1000 alpha-numeric student records. Linear support vector machines benchmarked with ten categorical machine learning algorithms showed superior performance in predicting student performance. The results of this research showed that features like race, gender, and lunch influence performance in mathematics whilst access to lunch was the primary factor which influences reading and writing performance.

scholarly journals Classification of Children’s Sitting Postures Using Machine Learning Algorithms

2018 ◽  
Vol 8 (8) ◽  
pp. 1280 ◽  
Author(s):  
Yong Kim ◽  
Youngdoo Son ◽  
Wonjoon Kim ◽  
Byungki Jin ◽  
Myung Yun
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Monitoring System ◽  
Multinomial Logistic Regression ◽  
Learning Algorithms ◽  
Feedback System ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Future Research ◽  
Support Vector

Sitting on a chair in an awkward posture or sitting for a long period of time is a risk factor for musculoskeletal disorders. A postural habit that has been formed cannot be changed easily. It is important to form a proper postural habit from childhood as the lumbar disease during childhood caused by their improper posture is most likely to recur. Thus, there is a need for a monitoring system that classifies children’s sitting postures. The purpose of this paper is to develop a system for classifying sitting postures for children using machine learning algorithms. The convolutional neural network (CNN) algorithm was used in addition to the conventional algorithms: Naïve Bayes classifier (NB), decision tree (DT), neural network (NN), multinomial logistic regression (MLR), and support vector machine (SVM). To collect data for classifying sitting postures, a sensing cushion was developed by mounting a pressure sensor mat (8 × 8) inside children’s chair seat cushion. Ten children participated, and sensor data was collected by taking a static posture for the five prescribed postures. The accuracy of CNN was found to be the highest as compared with those of the other algorithms. It is expected that the comprehensive posture monitoring system would be established through future research on enhancing the classification algorithm and providing an effective feedback system.

scholarly journals Survey on Machine Learning Algorithms Enhancing the Functional Verification Process

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2688
Author(s):  
Khaled A. Ismail ◽  
Mohamed A. Abd El Ghany
Keyword(s):  
Machine Learning ◽  
Test Generation ◽  
Machine Learning Algorithms ◽  
Future Research ◽  
Functional Verification ◽  
Functional Requirements ◽  
Comprehensive Overview ◽  
Bug Detection ◽  
Coverage Metrics ◽  
Verification Process

The continuing increase in functional requirements of modern hardware designs means the traditional functional verification process becomes inefficient in meeting the time-to-market goal with sufficient level of confidence in the design. Therefore, the need for enhancing the process is evident. Machine learning (ML) models proved to be valuable for automating major parts of the process, which have typically occupied the bandwidth of engineers; diverting them from adding new coverage metrics to make the designs more robust. Current research of deploying different (ML) models prove to be promising in areas such as stimulus constraining, test generation, coverage collection and bug detection and localization. An example of deploying artificial neural network (ANN) in test generation shows 24.5× speed up in functionally verifying a dual-core RISC processor specification. Another study demonstrates how k-means clustering can reduce redundancy of simulation trace dump of an AHB-to-WHISHBONE bridge by 21%, thus reducing the debugging effort by not having to inspect unnecessary waveforms. The surveyed work demonstrates a comprehensive overview of current (ML) models enhancing the functional verification process from which an insight of promising future research areas is inferred.

scholarly journals Accuracy of Machine Learning Algorithms for the Diagnosis of Autism Spectrum Disorder: Systematic Review and Meta-Analysis of Brain Magnetic Resonance Imaging Studies

10.2196/14108 ◽  
2019 ◽  
Vol 6 (12) ◽  
pp. e14108 ◽  
Author(s):  
Sun Jae Moon ◽  
Jinseub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Magnetic Resonance Imaging ◽  
Machine Learning ◽  
Systematic Review ◽  
Magnetic Resonance ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Resonance Imaging ◽  
Accuracy Measures

Background In the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, their application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder (ASD). However, given their complexity and potential clinical implications, there is an ongoing need for further research on their accuracy. Objective This study aimed to perform a systematic review and meta-analysis to summarize the available evidence for the accuracy of machine learning algorithms in diagnosing ASD. Methods The following databases were searched on November 28, 2018: MEDLINE, EMBASE, CINAHL Complete (with Open Dissertations), PsycINFO, and Institute of Electrical and Electronics Engineers Xplore Digital Library. Studies that used a machine learning algorithm partially or fully for distinguishing individuals with ASD from control subjects and provided accuracy measures were included in our analysis. The bivariate random effects model was applied to the pooled data in a meta-analysis. A subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false-negative, and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw Summary Receiver Operating Characteristics curves, and obtain the area under the curve (AUC) and partial AUC (pAUC). Results A total of 43 studies were included for the final analysis, of which a meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural magnetic resonance imaging (sMRI) subgroup meta-analysis (12 samples with 1776 participants) showed a sensitivity of 0.83 (95% CI 0.76-0.89), a specificity of 0.84 (95% CI 0.74-0.91), and AUC/pAUC of 0.90/0.83. A functional magnetic resonance imaging/deep neural network subgroup meta-analysis (5 samples with 1345 participants) showed a sensitivity of 0.69 (95% CI 0.62-0.75), specificity of 0.66 (95% CI 0.61-0.70), and AUC/pAUC of 0.71/0.67. Conclusions The accuracy of machine learning algorithms for diagnosis of ASD was considered acceptable by few accuracy measures only in cases of sMRI use; however, given the many limitations indicated in our study, further well-designed studies are warranted to extend the potential use of machine learning algorithms to clinical settings. Trial Registration PROSPERO CRD42018117779; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=117779

Sign in / Sign up

Export Citation Format

Share Document