An efficient diagnosis system for Parkinson's disease using kernel-based extreme learning machine with subtractive clustering features weighting approach

Assessing the reproducibility of machine-learning-based biomarker discovery in Parkinson's disease

Feature selection and machine learning algorithms can be used to analyze Single Nucleotide Polymorphisms (SNPs) data and identify potential disease biomarkers. Reproducibility of identified biomarkers is critical for them to be useful for clinical research; however, genotyping platforms and selection criteria for individuals to be genotyped affect the reproducibility of identified biomarkers. To assess biomarkers reproducibility, we collected five SNPs datasets from the database of Genotypes and Phenotypes (dbGaP) and explored several data integration strategies. While combining datasets can lead to a reduction in classification accuracy, it has the potential to improve the reproducibility of potential biomarkers. We evaluated the agreement among different strategies in terms of the SNPs that were identified as potential Parkinson's disease (PD) biomarkers. Our findings indicate that, on average, 93% of the SNPs identified in a single dataset fail to be identified in other datasets. However, through dataset integration, this lack of replication is reduced to 62%. We discovered fifty SNPs that were identified at least twice, which could potentially serve as novel PD biomarkers. These SNPs are indirectly linked to PD in the literature but have not been directly associated with PD before. These findings open up new potential avenues of investigation.

A review of machine learning and deep learning algorithms for Parkinson's disease detection using handwriting and voice datasets

Parkinson's Disease (PD) is a prevalent neurodegenerative disorder with significant clinical implications. Early and accurate diagnosis of PD is crucial for timely intervention and personalized treatment. In recent years, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as promis-ing tools for improving PD diagnosis. This review paper presents a detailed analysis of the current state of ML and DL-based PD diagnosis, focusing on voice, handwriting, and wave spiral datasets. The study also evaluates the effectiveness of various ML and DL algorithms, including classifiers, on these datasets and highlights their potential in enhancing diagnostic accuracy and aiding clinical decision-making. Additionally, the paper explores the identifi-cation of biomarkers using these techniques, offering insights into improving the diagnostic process. The discussion encompasses different data formats and commonly employed ML and DL methods in PD diagnosis, providing a comprehensive overview of the field. This review serves as a roadmap for future research, guiding the development of ML and DL-based tools for PD detection. It is expected to benefit both the scientific community and medical practitioners by advancing our understanding of PD diagnosis and ultimately improving patient outcomes.

Has machine learning over-promised in healthcare? A critical analysis and a proposal for improved evaluation, with evidence from Parkinson’s disease

Adoption of artificial intelligence (AI) by the medical community has long been anticipated, endorsed by a stream of machine learning literature showcasing AI systems that yield extraordinary performance. However, many of these systems are likely over-promising and will under-deliver in practice. One key reason is the community's failure to acknowledge and address the presence of inflationary effects in the data. These simultaneously inflate evaluation performance and prevent a model from learning the underlying task, thus severely misrepresenting how that model would perform in the real world. This paper investigated the impact of these inflationary effects on healthcare tasks, as well as how these effects can be addressed. Specifically, we defined three inflationary effects that occur in medical data sets and allow models to easily reach small training losses and prevent skillful learning. We investigated two data sets of sustained vowel phonation from participants with and without Parkinson's disease, and revealed that published models which have achieved high classification performances on these were artificially enhanced due to the inflationary effects. Our experiments showed that removing each inflationary effect corresponded with a decrease in classification accuracy, and that removing all inflationary effects reduced the evaluated performance by up to 30%. Additionally, the performance on a more realistic test set increased, suggesting that the removal of these inflationary effects enabled the model to better learn the underlying task and generalize. Source code is available at https://github.com/Wenbo-G/pd-phonation-analysis under the MIT license.

Postmortem submersion interval estimation of cadavers recovered from freshwater based on gut microbial community succession

Microbial community succession during decomposition has been proven to be a useful tool for postmortem interval (PMI) estimation. Numerous studies have shown that the intestinal microbial community presented chronological changes after death and was stable in terrestrial corpses with different causes of death. However, the postmortem pattern of intestinal microbial community succession in cadavers retrieved from water remains unclear. For immersed corpses, the postmortem submersion interval (PMSI) is a useful indicator of PMI. To provide reliable estimates of PMSI in forensic investigations, we investigated the gut microbial community succession of corpses submersed in freshwater and explored its potential application in forensic investigation. In this study, the intestinal microbial community of mouse submersed in freshwater that died of drowning or CO2 asphyxia (i.e., postmortem submersion) were characterized by 16S rDNA amplification and high-throughput sequencing, followed by bioinformatic analyses. The results demonstrated that the chronological changes in intestinal bacterial communities were not different between the drowning and postmortem submersion groups. α-diversity decreased significantly within 14 days of decomposition in both groups, and the β-diversity bacterial community structure ordinated chronologically, inferring the functional pathway and phenotype. To estimate PMSI, a regression model was established by random forest (RF) algorithm based on the succession of postmortem microbiota. Furthermore, 15 genera, including Proteus, Enterococcus, and others, were selected as candidate biomarkers to set up a concise predicted model, which provided a prediction of PMSI [MAE (± SE) = 0.818 (± 0.165) d]. Overall, our present study provides evidence that intestinal microbial community succession would be a valuable marker to estimate the PMSI of corpses submerged in an aquatic habitat.

Analysis of Parkinson's Disease Using an Imbalanced-Speech Dataset by Employing Decision Tree Ensemble Methods

Parkinson's disease (PD) currently affects approximately 10 million people worldwide. The detection of PD positive subjects is vital in terms of disease prognostics, diagnostics, management and treatment. Different types of early symptoms, such as speech impairment and changes in writing, are associated with Parkinson disease. To classify potential patients of PD, many researchers used machine learning algorithms in various datasets related to this disease. In our research, we study the dataset of the PD vocal impairment feature, which is an imbalanced dataset. We propose comparative performance evaluation using various decision tree ensemble methods, with or without oversampling techniques. In addition, we compare the performance of classifiers with different sizes of ensembles and various ratios of the minority class and the majority class with oversampling and undersampling. Finally, we combine feature selection with best-performing ensemble classifiers. The result shows that AdaBoost, random forest, and decision tree developed for the RUSBoost imbalanced dataset perform well in performance metrics such as precision, recall, F1-score, area under the receiver operating characteristic curve (AUROC) and the geometric mean. Further, feature selection methods, namely lasso and information gain, were used to screen the 10 best features using the best ensemble classifiers. AdaBoost with information gain feature selection method is the best performing ensemble method with an F1-score of 0.903.

Detecting Parkinson's Disease through Gait Measures Using Machine Learning

Parkinson’s disease (PD) is one of the most common long-term degenerative movement disorders that affects the motor system. This progressive nervous system disorder affects nearly one million Americans, and more than 20,000 new cases are diagnosed each year. PD is a chronic and progressive painful neurological disorder and usually people with PD live 10 to 20 years after being diagnosed. PD is diagnosed based on the identification of motor signs of bradykinesia, rigidity, tremor, and postural instability. Though several attempts have been made to develop explicit diagnostic criteria, this is still largely unrevealed. In this manuscript, we aim to build a classifier with gait data from Parkinson patients and healthy controls using machine learning methods. The classifier could help facilitate a more accurate and cost-effective diagnostic method. The input to our algorithm is the Gait in Parkinson’s Disease dataset published on PhysioNet containing force sensor data as the measurement of gait from 92 healthy subjects and 214 patients with idiopathic Parkinson’s Disease. Different machine learning methods, including logistic regression, SVM, decision tree, KNN were tested to output a predicted classification of Parkinson patients and healthy controls. Baseline models including frequency domain method can reach similar performance and may be another good approach for the PD diagnostics.

Lipidomics Prediction of Parkinson's Disease Severity: A Machine-Learning Analysis

BACKGROUND

The role of the lipidome as a biomarker for Parkinson's disease (PD) is a relatively new field that currently only focuses on PD diagnosis.

OBJECTIVE

To identify a relevant lipidome signature for PD severity markers.

METHODS

Disease severity of 149 PD patients was assessed by the Unified Parkinson's Disease Rating Scale (UPDRS) and the Montreal Cognitive Assessment (MoCA). The lipid composition of whole blood samples was analyzed, consisting of 517 lipid species from 37 classes; these included all major classes of glycerophospholipids, sphingolipids, glycerolipids, and sterols. To handle the high number of lipids, the selection of lipid species and classes was consolidated via analysis of interrelations between lipidomics and disease severity prediction using the random forest machine-learning algorithm aided by conventional statistical methods.

RESULTS

Specific lipid classes dihydrosphingomyelin (dhSM), plasmalogen phosphatidylethanolamine (PEp), glucosylceramide (GlcCer), dihydro globotriaosylceramide (dhGB3), and to a lesser degree dihydro GM3 ganglioside (dhGM3), as well as species dhSM(20:0), PEp(38:6), PEp(42:7), GlcCer(16:0), GlcCer(24:1), dhGM3(22:0), dhGM3(16:0), and dhGB3(16:0) contribute to PD severity prediction of UPDRS III score. These, together with age, age at onset, and disease duration, also contribute to prediction of UPDRS total score. We demonstrate that certain lipid classes and species interrelate differently with the degree of severity of motor symptoms between men and women, and that predicting intermediate disease stages is more accurate than predicting less or more severe stages.

CONCLUSION

Using machine-learning algorithms and methodologies, we identified lipid signatures that enable prediction of motor severity in PD. Future studies should focus on identifying the biological mechanisms linking GlcCer, dhGB3, dhSM, and PEp with PD severity.

Feature selection and machine learning methods for optimal identification and prediction of subtypes in Parkinson's disease

OBJECTIVES

The present work focuses on assessment of Parkinson's disease (PD), including both PD subtype identification (unsupervised task) and prediction (supervised task). We specifically investigate optimal feature selection and machine learning algorithms for these tasks.

METHODS

We selected 885 PD subjects as derived from longitudinal datasets (years 0-4; Parkinson's Progressive Marker Initiative), and investigated 981 features including motor, non-motor, and imaging features (SPECT-based radiomics features extracted using our standardized SERA software). Two different hybrid machine learning systems (HMLS) were constructed and applied to the data in order to select optimal combinations in both tasks: (i) identification of subtypes in PD (unsupervised-clustering), and (ii) prediction of these subtypes in year 4 (supervised-classification). From the original data based on years 0 (baseline) and 1, we created new datasets as inputs to the prediction task: (i,ii) CSD0 and CSD01: cross-sectional datasets from year 0 only and both years 0 & 1, respectively; (iii) TD01: timeless dataset from both years 0 & 1. In addition, PD subtype in year 4 was considered as outcome. Finally, high score features were derived via ensemble voting based on their prioritizations from feature selector algorithms (FSAs).

RESULTS

In clustering task, the most optimal combinations (out of 981) were selected by individual FSAs to enable high correlation compared to using all features (arriving at 547). In prediction task, we were able to select optimal combinations, resulting in an accuracy >90% only for timeless dataset (TD01); there, we were able to select the most optimal combination using 77 features, directly selected by FSAs. In both tasks, however, using combination of only high score features from ensemble voting did not enable acceptable performances, showing optimal feature selection via individual FSAs to be more effective.

CONCLUSION

Combining non-imaging information with SPECT-based radiomics features, and optimal utilization of HMLSs, can enable robust identification of subtypes as well as appropriate prediction of these subtypes in PD patients. Moreover, use of timeless dataset, beyond cross-sectional datasets, enabled predictive accuracies over 90%. Overall, we showed that radiomics features extracted from SPECT images are important in clustering as well as prediction of PD subtypes.

Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson's Disease Detection

As a neurodegenerative disorder, Parkinson’s disease (PD) affects the nerve cells of the human brain. Early detection and treatment can help to relieve the symptoms of PD. Recent PD studies have extracted the features from vocal disorders as a harbinger for PD detection, as patients face vocal changes and impairments at the early stages of PD. In this study, two hybrid models based on a Support Vector Machine (SVM) integrating with a Principal Component Analysis (PCA) and a Sparse Autoencoder (SAE) are proposed to detect PD patients based on their vocal features. The first model extracted and reduced the principal components of vocal features based on the explained variance of each feature using PCA. For the first time, the second model used a novel Deep Neural Network (DNN) of an SAE, consisting of multiple hidden layers with L1 regularization to compress the vocal features into lower-dimensional latent space. In both models, reduced features were fed into the SVM as inputs, which performed classification by learning hyperplanes, along with projecting the data into a higher dimension. An F1-score, a Mathews Correlation Coefficient (MCC), and a Precision-Recall curve were used, along with accuracy to evaluate the proposed models due to highly imbalanced data. With its highest accuracy of 0.935, F1-score of 0.951, and MCC value of 0.788, the probing results show that the proposed model of the SAE-SVM surpassed not only the former model of the PCA-SVM and other standard models including Multilayer Perceptron (MLP), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbor (KNN), and Random Forest (RF), but also surpassed two recent studies using the same dataset. Oversampling and balancing the dataset with SMOTE boosted the performance of the models.

Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature

Diagnosis of Parkinson's disease (PD) is commonly based on medical observations and assessment of clinical signs, including the characterization of a variety of motor symptoms. However, traditional diagnostic approaches may suffer from subjectivity as they rely on the evaluation of movements that are sometimes subtle to human eyes and therefore difficult to classify, leading to possible misclassification. In the meantime, early non-motor symptoms of PD may be mild and can be caused by many other conditions. Therefore, these symptoms are often overlooked, making diagnosis of PD at an early stage challenging. To address these difficulties and to refine the diagnosis and assessment procedures of PD, machine learning methods have been implemented for the classification of PD and healthy controls or patients with similar clinical presentations (e.g., movement disorders or other Parkinsonian syndromes). To provide a comprehensive overview of data modalities and machine learning methods that have been used in the diagnosis and differential diagnosis of PD, in this study, we conducted a literature review of studies published until February 14, 2020, using the PubMed and IEEE Xplore databases. A total of 209 studies were included, extracted for relevant information and presented in this review, with an investigation of their aims, sources of data, types of data, machine learning methods and associated outcomes. These studies demonstrate a high potential for adaptation of machine learning methods and novel biomarkers in clinical decision making, leading to increasingly systematic, informed diagnosis of PD.

Using a deep recurrent neural network with EEG signal to detect Parkinson's disease

Background

Parkinson's disease (PD) gradually degrades the functionality of the brain. Because of its relevance to the abnormality of the brain, electroencephalogram (EEG) signal is used for the early detection of this disease. This paper introduces a novel computer-aided diagnosis method to detect PD, which is an efficient deep learning method based on a pooling-based deep recurrent neural network (PDRNN). Therefore, the purpose of this study is to detect Parkinson's disease based on deep recurrent neural network of EEG signal.

Methods

The EEG signals of 20 patients with Parkinson's disease and 20 healthy people in Henan Provincial People's Hospital (People's Hospital of Zhengzhou University) were examined, and a PDRNN learning method was applied on the dataset for managing the demand of the traditional feature presentation step.

Results

The suggested DPRNN network gives the precision, sensitivity and specificity of 88.31%, 84.84% and 91.81%, respectively. Nevertheless, 11.28% of the healthy cases are wrongly categorized in Parkinson class. Also, 11.49% percent of Parkinson cases are classified wrongly in the healthy class.

Conclusions

The experimental model has high efficiency and can be used as a reliable tool for clinical PD detection. In future research, more cases should be used to test and develop the proposed model.

Identification of arthropathy and myopathy of the temporomandibular syndrome by biomechanical facial features

Background

Temporomandibular disorders (TMDs) are pathological conditions affecting the temporomandibular joint and/or masticatory muscles. The current diagnosis of TMDs is complex and multi-factorial, including questionnaires, medical testing and the use of diagnostic methods, such as computed tomography and magnetic resonance imaging. The evaluation, like the mandibular range of motion, needs the experience of the professional in the field and as such, there is a probability of human error when diagnosing TMD. The aim of this study is therefore to develop a method with infrared cameras, using the maximum range of motion of the jaw and four types of classifiers to help professionals to classify the pathologies of the temporomandibular joint (TMJ) and related muscles in a quantitative way, thus helping to diagnose and follow up on TMD.

Methods

Forty individuals were evaluated and diagnosed using the diagnostic criteria for temporomandibular disorders (DC/TMD) scale, and divided into three groups: 20 healthy individuals (control group CG), 10 individuals with myopathies (MG), 10 individuals with arthropathies (AG). A quantitative assessment was carried out by motion capture. The TMJ movement was captured with camera tracking markers mounted on the face and jaw of each individual. Data was exported and analyzed using a custom-made software. The data was used to identify and place each participant into one of three classes using the K-nearest neighbor (KNN), Random Forest, Naïve Bayes and Support Vector Machine algorithms.

Results

Significant precision and accuracy (over 90%) was reached by KNN when classifying the three groups. The other methods tested presented lower values of sensitivity and specificity.

Conclusion

The quantitative TMD classification method proposed herein has significant precision and accuracy over the DC/TMD standards. However, this should not be used as a standalone tool but as an auxiliary method for diagnostic TMDs.

A new fruit fly optimization algorithm enhanced support vector machine for diagnosis of breast cancer based on high-level features

BACKGROUND

It is of great clinical significance to develop an accurate computer aided system to accurately diagnose the breast cancer. In this study, an enhanced machine learning framework is established to diagnose the breast cancer. The core of this framework is to adopt fruit fly optimization algorithm (FOA) enhanced by Levy flight (LF) strategy (LFOA) to optimize two key parameters of support vector machine (SVM) and build LFOA-based SVM (LFOA-SVM) for diagnosing the breast cancer. The high-level features abstracted from the volunteers are utilized to diagnose the breast cancer for the first time.

RESULTS

In order to verify the effectiveness of the proposed method, 10-fold cross-validation method is used to make comparison among the proposed method, FOA-SVM (model based on original FOA), PSO-SVM (model based on original particle swarm optimization), GA-SVM (model based on genetic algorithm), random forest, back propagation neural network and SVM. The main novelty of LFOA-SVM lies in the combination of FOA with LF strategy that enhances the quality for FOA, thus improving the convergence rate of the FOA optimization process as well as the probability of escaping from local optimal solution.

CONCLUSIONS

The experimental results demonstrate that the proposed LFOA-SVM method can beat other counterparts in terms of various performance metrics. It can very well distinguish malignant breast cancer from benign ones and assist the doctor with clinical diagnosis.

Classifying Parkinson's Disease Based on Acoustic Measures Using Artificial Neural Networks

In recent years, neural networks have become very popular in all kinds of prediction problems. In this paper, multiple feed-forward artificial neural networks (ANNs) with various configurations are used in the prediction of Parkinson’s disease (PD) of tested individuals, based on extracted features from 26 different voice samples per individual. Results are validated via the leave-one-subject-out (LOSO) scheme. Few feature selection procedures based on Pearson’s correlation coefficient, Kendall’s correlation coefficient, principal component analysis, and self-organizing maps, have been used for boosting the performance of algorithms and for data reduction. The best test accuracy result has been achieved with Kendall’s correlation coefficient-based feature selection, and the most relevant voice samples are recognized. Multiple ANNs have proven to be the best classification technique for diagnosis of PD without usage of the feature selection procedure (on raw data). Finally, a neural network is fine-tuned, and a test accuracy of 86.47% was achieved.

Authenticity identification and classification of Rhodiola species in traditional Tibetan medicine based on Fourier transform near-infrared spectroscopy and chemometrics analysis

Rhodiola is an increasingly widely used traditional Tibetan medicine and traditional Chinese medicine in China. The composition profiles of bioactive compounds are somewhat jagged according to different species, which makes it crucial to identify authentic Rhodiola species accurately so as to ensure clinical application of Rhodiola. In this paper, a nondestructive, rapid, and efficient method in classification of Rhodiola was developed by Fourier transform near-infrared (FT-NIR) spectroscopy combined with chemometrics analysis. A total of 160 batches of raw spectra were obtained from four different species of Rhodiola by FT-NIR, such as Rhodiola crenulata, Rhodiola fastigiata, Rhodiola kirilowii, and Rhodiola brevipetiolata. After excluding the outliers, different performances of 3 sample dividing methods, 12 spectral preprocessing methods, 2 wavelength selection methods, and 2 modeling evaluation methods were compared. The results indicated that this combination was superior than others in the authenticity identification analysis, which was FT-NIR combined with sample set partitioning based on joint x-y distances (SPXY), standard normal variate transformation (SNV) + Norris-Williams (NW) + 2nd derivative, competitive adaptive reweighted sampling (CARS), and kernel extreme learning machine (KELM). The accuracy (ACCU), sensitivity (SENS), and specificity (SPEC) of the optimal model were all 1, which showed that this combination of FT-NIR and chemometrics methods had the optimal authenticity identification performance. The classification performance of the partial least squares discriminant analysis (PLS-DA) model was slightly lower than KELM model, and PLS-DA model results were ACCU = 0.97, SENS = 0.93, and SPEC = 0.98, respectively. It can be concluded that FT-NIR combined with chemometrics analysis has great potential in authenticity identification and classification of Rhodiola, which can provide a valuable reference for the safety and effectiveness of clinical application of Rhodiola.

Constrained Optimization-Based Extreme Learning Machines with Bagging for Freezing of Gait Detection

The Internet-of-Things (IoT) is a paradigm shift from slow and manual approaches to fast and automated systems. It has been deployed for various use-cases and applications in recent times. There are many aspects of IoT that can be used for the assistance of elderly individuals. In this paper, we detect the presence or absence of freezing of gait in patients suffering from Parkinson’s disease (PD) by using the data from body-mounted acceleration sensors placed on the legs and hips of the patients. For accurate detection and estimation, constrained optimization-based extreme learning machines (C-ELM) have been utilized. Moreover, in order to enhance the accuracy even further, C-ELM with bagging (C-ELMBG) has been proposed, which uses the characteristics of least squares support vector machines. The experiments have been carried out on the publicly available Daphnet freezing of gait dataset to verify the feasibility of C-ELM and C-ELMBG. The simulation results show an accuracy above 90% for both methods. A detailed comparison with other state-of-the-art statistical learning algorithms such as linear discriminate analysis, classification and regression trees, random forest and state vector machines is also presented where C-ELM and C-ELMBG show better performance in all aspects, including accuracy, sensitivity, and specificity.

The Omics Revolution Continues: The Maturation of High-Throughput Biological Data Sources

OBJECTIVE

 The aim is to provide a comprehensive review of state-of-the art omics approaches, including proteomics, metabolomics, cell-free DNA, and patient cohort matching algorithms in precision oncology.

METHODS

 In the past several years, the cancer informatics revolution has been the beneficiary of a data explosion. Different complementary omics technologies have begun coming into their own to provide a more nuanced view of the patient-tumor interaction beyond that of DNA alterations. A combined approach is beneficial to the patient as nearly all new cancer therapeutics are designed with an omics biomarker in mind. Proteomics and metabolomics provide us with a means of assaying in real-time the response of the tumor to treatment. Circulating cell-free DNA may allow us to better understand tumor heterogeneity and interactions with the host genome.

RESULTS

 Integration of increasingly available omics data increases our ability to segment patients into smaller and smaller cohorts, thereby prompting a shift in our thinking about how to use these omics data. With large repositories of patient omics-outcomes data being generated, patient cohort matching algorithms have become a dominant player.

CONCLUSIONS

 The continued promise of precision oncology is to select patients who are most likely to benefit from treatment and to avoid toxicity for those who will not. The increased public availability of omics and outcomes data in patients, along with improved computational methods and resources, are making precision oncology a reality.

Detecting Parkinson's disease from sustained phonation and speech signals

This study investigates signals from sustained phonation and text-dependent speech modalities for Parkinson’s disease screening. Phonation corresponds to the vowel /a/ voicing task and speech to the pronunciation of a short sentence in Lithuanian language. Signals were recorded through two channels simultaneously, namely, acoustic cardioid (AC) and smart phone (SP) microphones. Additional modalities were obtained by splitting speech recording into voiced and unvoiced parts. Information in each modality is summarized by 18 well-known audio feature sets. Random forest (RF) is used as a machine learning algorithm, both for individual feature sets and for decision-level fusion. Detection performance is measured by the out-of-bag equal error rate (EER) and the cost of log-likelihood-ratio. Essentia audio feature set was the best using the AC speech modality and YAAFE audio feature set was the best using the SP unvoiced modality, achieving EER of 20.30% and 25.57%, respectively. Fusion of all feature sets and modalities resulted in EER of 19.27% for the AC and 23.00% for the SP channel. Non-linear projection of a RF-based proximity matrix into the 2D space enriched medical decision support by visualization.

Can a Smartphone Diagnose Parkinson Disease? A Deep Neural Network Method and Telediagnosis System Implementation

Parkinson's disease (PD) is primarily diagnosed by clinical examinations, such as walking test, handwriting test, and MRI diagnostic. In this paper, we propose a machine learning based PD telediagnosis method for smartphone. Classification of PD using speech records is a challenging task owing to the fact that the classification accuracy is still lower than doctor-level. Here we demonstrate automatic classification of PD using time frequency features, stacked autoencoders (SAE), and K nearest neighbor (KNN) classifier. KNN classifier can produce promising classification results from useful representations which were learned by SAE. Empirical results show that the proposed method achieves better performance with all tested cases across classification tasks, demonstrating machine learning capable of classifying PD with a level of competence comparable to doctor. It concludes that a smartphone can therefore potentially provide low-cost PD diagnostic care. This paper also gives an implementation on browser/server system and reports the running time cost. Both advantages and disadvantages of the proposed telediagnosis system are discussed.

A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method

Heart disease is one of the most common diseases in the world. The objective of this study is to aid the diagnosis of heart disease using a hybrid classification system based on the ReliefF and Rough Set (RFRS) method. The proposed system contains two subsystems: the RFRS feature selection system and a classification system with an ensemble classifier. The first system includes three stages: (i) data discretization, (ii) feature extraction using the ReliefF algorithm, and (iii) feature reduction using the heuristic Rough Set reduction algorithm that we developed. In the second system, an ensemble classifier is proposed based on the C4.5 classifier. The Statlog (Heart) dataset, obtained from the UCI database, was used for experiments. A maximum classification accuracy of 92.59% was achieved according to a jackknife cross-validation scheme. The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques.