Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier

Optimized Machine Learning for the Early Detection of Polycystic Ovary Syndrome in Women

Polycystic ovary syndrome (PCOS) is a medical condition that impacts millions of women worldwide; however, due to a lack of public awareness, as well as the expensive testing involved in the identification of PCOS, 70% of cases go undiagnosed. Therefore, the primary objective of this study is to design an expert machine learning (ML) model for the early diagnosis of PCOS based on initial symptoms and health indicators; two datasets were amalgamated and preprocessed to accomplish this goal, resulting in a new symptomatic dataset with 12 attributes. An ensemble learning (EL) model, with seven base classifiers, and a deep learning (DL) model, as the meta-level classifier, are proposed. The hyperparameters of the EL model were optimized through the nature-inspired walrus optimization (WaO), cuckoo search optimization (CSO), and random search optimization (RSO) algorithms, leading to the WaOEL, CSOEL, and RSOEL models, respectively. The results obtained prove the supremacy of the designed WaOEL model over the other models, with a PCOS prediction accuracy of 92.8% and an area under the receiver operating characteristic curve (AUC) of 0.93; moreover, feature importance analysis, presented with random forest (RF) and Shapley additive values (SHAP) for positive PCOS predictions, highlights crucial clinical insights and the need for early intervention. Our findings suggest that patients with features related to obesity and high cholesterol are more likely to be diagnosed as PCOS positive. Most importantly, it is inferred from this study that early PCOS identification without expensive tests is possible with the proposed WaOEL, which helps clinicians and patients make better informed decisions, identify comorbidities, and reduce the harmful long-term effects of PCOS.

Overview of Wearable Healthcare Devices for Clinical Decision Support in the Prehospital Setting

Prehospital medical care is a major challenge for both civilian and military situations as resources are limited, yet critical triage and treatment decisions must be rapidly made. Prehospital medicine is further complicated during mass casualty situations or remote applications that require more extensive medical treatments to be monitored. It is anticipated on the future battlefield where air superiority will be contested that prolonged field care will extend to as much 72 h in a prehospital environment. Traditional medical monitoring is not practical in these situations and, as such, wearable sensor technology may help support prehospital medicine. However, sensors alone are not sufficient in the prehospital setting where limited personnel without specialized medical training must make critical decisions based on physiological signals. Machine learning-based clinical decision support systems can instead be utilized to interpret these signals for diagnosing injuries, making triage decisions, or driving treatments. Here, we summarize the challenges of the prehospital medical setting and review wearable sensor technology suitability for this environment, including their use with medical decision support triage or treatment guidance options. Further, we discuss recommendations for wearable healthcare device development and medical decision support technology to better support the prehospital medical setting. With further design improvement and integration with decision support tools, wearable healthcare devices have the potential to simplify and improve medical care in the challenging prehospital environment.

Accurate Arrhythmia Classification with Multi-Branch, Multi-Head Attention Temporal Convolutional Networks

Electrocardiogram (ECG) signals contain complex and diverse features, serving as a crucial basis for arrhythmia diagnosis. The subtle differences in characteristics among various types of arrhythmias, coupled with class imbalance issues in datasets, often hinder existing models from effectively capturing key information within these complex signals, leading to a bias towards normal classes. To address these challenges, this paper proposes a method for arrhythmia classification based on a multi-branch, multi-head attention temporal convolutional network (MB-MHA-TCN). The model integrates three convolutional branch layers with different kernel sizes and dilation rates to capture features across varying temporal scales. A multi-head self-attention mechanism dynamically allocates weights, integrating features and correlations from different branches to enhance the recognition capability for difficult-to-classify samples. Additionally, the temporal convolutional network employs multi-layer dilated convolutions to progressively expand the receptive field for extracting long-term dependencies. To tackle data imbalance, a novel data augmentation strategy is implemented, and focal loss is utilized to increase the weight of minority classes, while Bayesian optimization is employed to fine-tune the model's hyperparameters. The results from five-fold cross-validation on the MIT-BIH Arrhythmia Database demonstrate that the proposed method achieves an overall accuracy of 98.75%, precision of 96.60%, sensitivity of 97.21%, and F1 score of 96.89% across five categories of ECG signals. Compared to other studies, this method exhibits superior performance in arrhythmia classification, significantly improving the recognition rate of minority classes.

Towards a microRNA-based Johne's disease diagnostic predictive system: Preliminary results

BACKGROUND

Johne's disease, caused by Mycobacterium avium subspecies paratuberculosis (MAP), is a chronic enteritis that adversely affects welfare and productivity in cattle. Screening and subsequent removal of affected animals is a common approach for disease management, but efforts are hindered by low diagnostic sensitivity. Expression levels of small non-coding RNA molecules involved in gene regulation (microRNAs), which may be altered during mycobacterial infection, may present an alternative diagnostic method.

METHODS

The expression levels of 24 microRNAs affected by mycobacterial infection were measured in sera from MAP-positive (n = 66) and MAP-negative cattle (n = 65). They were then used within a machine learning approach to build an optimal classifier for MAP diagnosis.

RESULTS

The method provided 72% accuracy, 73% sensitivity and 71% specificity on average, with an area under the curve of 78%.

LIMITATIONS

Although control samples were collected from farms nominally MAP-free, the low sensitivity of current diagnostics means some animals may have been misclassified.

CONCLUSION

MicroRNA profiling combined with advanced predictive modelling enables rapid and accurate diagnosis of Johne's disease in cattle.

Machine learning allows expert level classification of intraoperative motor evoked potentials during neurosurgical procedures

OBJECTIVE

To develop and evaluate machine learning (ML) approaches for muscle identification using intraoperative motor evoked potentials (MEPs), and to compare their performance to human experts.

BACKGROUND

There is an unseized opportunity to apply ML analytic techniques to the world of intraoperative neuromonitoring (IOM). MEPs are the ideal candidates given the importance of their correct interpretation during a surgical operation to the brain or the spine. In this work, we develop and test a set of different ML models for muscle identification using intraoperative MEPs and compare their performance to human experts. In addition, we provide a review of the available literature on current ML applications to IOM data in neurosurgery.

METHODS

We trained and tested five different ML classifiers on a MEP database developed from six different muscles in patients who underwent brain or spinal cord surgery. MEPs were obtained by both transcranial (TES) and direct cortical stimulation (DCS) protocols. The models were evaluated within a single patient and on previously unseen patients, considering signals from TES and DCS both independently and mixed. Ten expert neurophysiologists classified a set of 50 randomly selected MEPs, and their performance was compared to the best performing model.

RESULTS

A total of 25.423 MEPs were included in the study. Random Forest proved to be the best performing model with 99 % accuracy in the single patient dataset task and a 78 %-94 % accuracy range on previously unseen patients. The model performance was maximized by representing MEPs as a set of features typically employed in signal processing compared to traditional neurophysiological parameters. The classification ability of the Random Forest model between six different muscles and across different MEP acquisition modalities (79 %) significantly exceeded that of human experts (mean 48 %).

CONCLUSIONS

Carefully selected ML models proved to have reliable capacity of extracting meaningful information to classify intraoperative MEPs using a limited number of features, proving robustness across patients and signal acquisition modalities, outperforming human experts, and with the potential to act as decision support systems to the IOM team. Such encouraging results lay the path to further explore the underlying nature of clinically important signals, with the aim to continue to produce useful applications to make surgeries safer and more efficient.

A diagnostic method for cardiomyopathy based on multimodal data

OBJECTIVES

Currently, a multitude of machine learning techniques are available for the diagnosis of hypertrophic cardiomyopathy (HCM) and dilated cardiomyopathy (DCM) by utilizing electrocardiography (ECG) data. However, these methods rely on digital versions of ECG data, while in practice, numerous ECG data still exist in paper form. As a result, the accuracy of the existing machine learning diagnostic models is suboptimal in practical scenarios. In order to enhance the accuracy of machine learning models for diagnosing cardiomyopathy, we propose a multimodal machine learning model capable of diagnosing both HCM and DCM.

METHODS

Our study employed an artificial neural network (ANN) for feature extraction from both the echocardiogram report form and biochemical examination data. Furthermore, a convolutional neural network (CNN) was utilized for feature extraction from the electrocardiogram (ECG). The resulting extracted features were subsequently integrated and inputted into a multilayer perceptron (MLP) for diagnostic classification.

RESULTS

Our multimodal fusion model achieved a precision of 89.87%, recall of 91.20%, F1 score of 89.13%, and precision of 89.72%.

CONCLUSIONS

Compared to existing machine learning models, our proposed multimodal fusion model has achieved superior results in various performance metrics. We believe that our method is effective.

Improving performance of classifiers for diagnosis of critical diseases to prevent COVID risk

The risk of developing COVID-19 and its variants may be higher in those with pre-existing health conditions such as thyroid disease, Hepatitis C Virus (HCV), breast tissue disease, chronic dermatitis, and other severe infections. Early and precise identification of these disorders is critical. A huge number of patients in nations like India require early and rapid testing as a preventative measure. The problem of imbalance arises from the skewed nature of data in which the instances from majority class are classified correct, while the minority class is unfortunately misclassified by many classifiers. When it comes to human life, this kind of misclassification is unacceptable. To solve the misclassification issue and improve accuracy in such datasets, we applied a variety of data balancing techniques to several machine learning algorithms. The outcomes are encouraging, with a considerable increase in accuracy. As an outcome of these proper diagnoses, we can make plans and take the required actions to stop patients from acquiring serious health issues or viral infections.

Machine learning prediction of postoperative unplanned 30-day hospital readmission in older adult

Background: Although unplanned hospital readmission is an important indicator for monitoring the perioperative quality of hospital care, few published studies of hospital readmission have focused on surgical patient populations, especially in the elderly. We aimed to investigate if machine learning approaches can be used to predict postoperative unplanned 30-day hospital readmission in old surgical patients.

Methods: We extracted demographic, comorbidity, laboratory, surgical, and medication data of elderly patients older than 65 who underwent surgeries under general anesthesia in West China Hospital, Sichuan University from July 2019 to February 2021. Different machine learning approaches were performed to evaluate whether unplanned 30-day hospital readmission can be predicted. Model performance was assessed using the following metrics: AUC, accuracy, precision, recall, and F1 score. Calibration of predictions was performed using Brier Score. A feature ablation analysis was performed, and the change in AUC with the removal of each feature was then assessed to determine feature importance.

Results: A total of 10,535 unique surgeries and 10,358 unique surgical elderly patients were included. The overall 30-day unplanned readmission rate was 3.36%. The AUCs of the six machine learning algorithms predicting postoperative 30-day unplanned readmission ranged from 0.6865 to 0.8654. The RF + XGBoost algorithm overall performed the best with an AUC of 0.8654 (95% CI, 0.8484–0.8824), accuracy of 0.9868 (95% CI, 0.9834–0.9902), precision of 0.3960 (95% CI, 0.3854–0.4066), recall of 0.3184 (95% CI, 0.259–0.3778), and F1 score of 0.4909 (95% CI, 0.3907–0.5911). The Brier scores of the six machine learning algorithms predicting postoperative 30-day unplanned readmission ranged from 0.3721 to 0.0464, with RF + XGBoost showing the best calibration capability. The most five important features of RF + XGBoost were operation duration, white blood cell count, BMI, total bilirubin concentration, and blood glucose concentration.

Conclusion: Machine learning algorithms can accurately predict postoperative unplanned 30-day readmission in elderly surgical patients.

Semi-Automatic Prostate Segmentation From Ultrasound Images Using Machine Learning and Principal Curve Based on Interpretable Mathematical Model Expression

Accurate prostate segmentation in transrectal ultrasound (TRUS) is a challenging problem due to the low contrast of TRUS images and the presence of imaging artifacts such as speckle and shadow regions. To address this issue, we propose a semi-automatic model termed Hybrid Segmentation Model (H-SegMod) for prostate Region of Interest (ROI) segmentation in TRUS images. H-SegMod contains two cascaded stages. The first stage is to obtain the vertices sequences based on an improved principal curve-based model, where a few radiologist-selected seed points are used as prior. The second stage is to find a map function for describing the smooth prostate contour based on an improved machine learning model. Experimental results show that our proposed model achieved superior segmentation results compared with several other state-of-the-art models, achieving an average Dice Similarity Coefficient (DSC), Jaccard Similarity Coefficient (Ω), and Accuracy (ACC) of 96.5%, 95.2%, and 96.3%, respectively.

Machine learning approaches for screening the risk of obstructive sleep apnea in the Taiwan population based on body profile

(a) Objective: Obstructive sleep apnea syndrome (OSAS) is typically diagnosed through polysomnography (PSG). However, PSG incurs high medical costs. This study developed new models for screening the risk of moderate-to-severe OSAS (apnea-hypopnea index, AHI ≥15) and severe OSAS (AHI ≥30) in various age groups and sexes by using anthropometric features in the Taiwan population.(b) Participants: Data were derived from 10,391 northern Taiwan patients who underwent PSG.(c) Methods: Patients' characteristics - namely age, sex, body mass index (BMI), neck circumference, and waist circumference - was obtained. To develop an age- and sex-independent model, various approaches - namely logistic regression, k-nearest neighbor, naive Bayes, random forest (RF), and support vector machine - were trained for four groups based on sex and age (men or women; aged <50 or ≥50 years). Dataset was separated independently (training:70%; validation: 10%; testing: 20%) and Cross-validated grid search was applied for model optimization. Models demonstrating the highest overall accuracy in validation outcomes for the four groups were used to predict the testing dataset.(d) Results: The RF models showed the highest overall accuracy. BMI was the most influential parameter in both types of OSAS severity screening models.(e) Conclusion: The established models can be applied to screen OSAS risk in the Taiwan population and those with similar craniofacial features.

A particle swarm optimization improved BP neural network intelligent model for electrocardiogram classification

BACKGROUND

As proven to reflect the work state of heart and physiological situation objectively, electrocardiogram (ECG) is widely used in the assessment of human health, especially the diagnosis of heart disease. The accuracy and reliability of abnormal ECG (AECG) decision depend to a large extent on the feature extraction. However, it is often uneasy or even impossible to obtain accurate features, as the detection process of ECG is easily disturbed by the external environment. And AECG got many species and great variation. What's more, the ECG result obtained after a long time past, which can not reach the purpose of early warning or real-time disease diagnosis. Therefore, developing an intelligent classification model with an accurate feature extraction method to identify AECG is of quite significance. This study aimed to explore an accurate feature extraction method of ECG and establish a suitable model for identifying AECG and the diagnosis of heart disease.

METHODS

In this research, the wavelet combined with four operations and adaptive threshold methods were applied to filter the ECG and extract its feature waves first. Then, a BP neural network (BPNN) intelligent model and a particle swarm optimization (PSO) improved BPNN (PSO-BPNN) intelligent model based on MIT-BIH open database was established to identify ECG. To reduce the complexity of the model, the principal component analysis (PCA) was used to minimize the feature dimension.

RESULTS

Wavelet transforms combined four operations and adaptive threshold methods were capable of ECG filtering and feature extraction. PCA can significantly deduce the modeling feature dimension to minimize the complexity and save classification time. The PSO-BPNN intelligent model was suitable for identifying five types of ECG and showed better effects while comparing it with the BPNN model.

CONCLUSION

In summary, it was further concluded that the PSO-BPNN intelligent model would be a suitable way to identify AECG and provide a tool for the diagnosis of heart disease.

Classification of ECG signals using multi-cumulants based evolutionary hybrid classifier

Every human being has a different electro-cardio-graphy (ECG) waveform that provides information about the well being of a human heart. Therefore, ECG waveform can be used as an effective identification measure in biometrics and many such applications of human identification. To achieve fast and accurate identification of human beings using ECG signals, a novel robust approach has been introduced here. The databases of ECG utilized during the experimentation are MLII, UCI repository arrhythmia and PTBDB databases. All these databases are imbalanced; hence, resampling techniques are helpful in making the databases balanced. Noise removal is performed with discrete wavelet transform (DWT) and features are obtained with multi-cumulants. This approach is mainly based on features extracted from the ECG data in terms of multi-cumulants. The multi-cumulants feature based ECG data is classified using kernel extreme learning machine (KELM). The parameters of multi-cumulants and KELM are optimized using genetic algorithm (GA). Excellent classification rate is achieved with 100% accuracy on MLII and UCI repository arrhythmia databases, and 99.57% on PTBDB database. Comparison with existing state-of-art approaches has also been performed to prove the efficacy of the proposed approach. Here, the process of classification in the proposed approach is named as evolutionary hybrid classifier.

An Intelligent Heartbeat Classification System Based on Attributable Features with AdaBoost+Random Forest Algorithm

Arrhythmia is a common cardiovascular disease that can threaten human life. In order to assist doctors in accurately diagnosing arrhythmia, an intelligent heartbeat classification system based on the selected optimal feature sets and AdaBoost + Random Forest model is developed. This system can acquire ECG signals through the Holter and transmit them to the cloud platform for preprocessing and feature extraction, and the features are input into AdaBoost + Random Forest for heartbeat classification. The analysis results are output in the form of reports. In this system, by comparing and analyzing the classification accuracy of different feature sets and classifiers, the optimal classification algorithm is obtained and applied to the system. The algorithm accuracy of the system is tested based on the MIT-BIH data set. The result shows that AdaBoost + Random Forest achieved 99.11% accuracy with optimal feature sets. The intelligent heartbeat classification system based on this algorithm has also achieved good results on clinical data.

Identification of Arrhythmia by Using a Decision Tree and Gated Network Fusion Model

In recent years, deep learning (DNN) based methods have made leapfrogging level breakthroughs in detecting cardiac arrhythmias as the cost effectiveness of arithmetic power, and data size has broken through the tipping point. However, the inability of these methods to provide a basis for modeling decisions limits clinicians' confidence on such methods. In this paper, a Gate Recurrent Unit (GRU) and decision tree fusion model, referred to as (T-GRU), was designed to explore the problem of arrhythmia recognition and to improve the credibility of deep learning methods. The fusion model multipathway processing time-frequency domain featured the introduction of decision tree probability analysis of frequency domain features, the regularization of GRU model parameters and weight control to improve the decision tree model output weights. The MIT-BIH arrhythmia database was used for validation. Results showed that the low-frequency band features dominated the model prediction. The fusion model had an accuracy of 98.31%, sensitivity of 96.85%, specificity of 98.81%, and precision of 96.73%, indicating its high reliability and clinical significance.

Comparison of machine learning techniques to predict unplanned readmission following total shoulder arthroplasty

BACKGROUND

Machine learning (ML) techniques have been shown to successfully predict postoperative complications for high-volume orthopedic procedures such as hip and knee arthroplasty and to stratify patients for risk-adjusted bundled payments. The latter has not been done for more heterogeneous, lower-volume procedures such as total shoulder arthroplasty (TSA) with equally limited discussion around strategies to optimize the predictive ability of ML algorithms. The purpose of this study was to (1) assess which of 5 ML algorithms best predicts 30-day readmission, (2) test select ML strategies to optimize the algorithms, and (3) report on which patient variables contribute most to risk prediction in TSA across algorithms.

METHODS

We identified 9043 patients in the American College of Surgeons National Surgical Quality Improvement Database who underwent primary TSA between 2011 and 2015. Predictors included demographics, comorbidities, laboratory data, and intraoperative variables. The outcome of interest was 30-day unplanned readmission. Five ML algorithms-support-vector machine (SVM), logistic regression, random forest (RF), an adaptive boosting algorithm, and neural network-were trained on the derivation cohort (2011-2014 TSA patients) to predict 30-day unplanned readmission rates. After training, weights for each respective model were fixed and the classifiers were evaluated on the 2015 TSA cohort to simulate a prospective evaluation. C-statistic and f1 scores were used to assess the performance of each classifier. After evaluation, features were removed independently to assess which features most affected classifier performance.

RESULTS

The derivation and validation cohorts comprised 5857 and 3186 primary TSA patients, respectively, with similar demographics, comorbidities, and 30-day unplanned readmission rates (2.9% vs. 2.7%). Of the ML algorithms, SVM performed the worst with a c-statistic of 0.54 and an f1-score of 0.07, whereas the random-forest classifier performed the best with the highest c-statistic of 0.74 and an f1-score of 0.18. In addition, SVM was most sensitive to loss of single features, whereas the performance of RF did not dramatically decrease after loss of single features. Within the trained RF classifier, 5 variables achieved weights >0.5 in descending order: high bilirubin (>1.9 mg/dL), age >65, race, chronic obstructive pulmonary disease, and American Society of Anesthesiologists' scores ≥3. In our validation cohort, we observed a 2.7% readmission rate. From this cohort, using the RF classifier we were then able to identify 436 high-risk patients with a predicted risk score >0.6, of whom 36 were readmitted (readmission rate of 8.2%).

CONCLUSION

Predictive analytics algorithms can achieve acceptable prediction of unplanned readmission for TSA with the RF classifier outperforming other common algorithms.

Extended Segmented Beat Modulation Method for Cardiac Beat Classification and Electrocardiogram Denoising

Beat classification and denoising are two challenging and fundamental operations when processing digital electrocardiograms (ECG). This paper proposes the extended segmented beat modulation method (ESBMM) as a tool for automatic beat classification and ECG denoising. ESBMM includes four main steps: (1) beat identification and segmentation into PQRS and TU segments; (2) wavelet-based time-frequency feature extraction; (3) convolutional neural network-based classification to discriminate among normal (N), supraventricular (S), and ventricular (V) beats; and (4) a template-based denoising procedure. ESBMM was tested using the MIT–BIH arrhythmia database available at Physionet. Overall, the classification accuracy was 91.5% while the positive predictive values were 92.8%, 95.6%, and 83.6%, for N, S, and V classes, respectively. The signal-to-noise ratio improvement after filtering was between 0.15 dB and 2.66 dB, with a median value equal to 0.99 dB, which is significantly higher than 0 (p < 0.05). Thus, ESBMM proved to be a reliable tool to classify cardiac beats into N, S, and V classes and to denoise ECG tracings.

Analyzing the Relevance of Peer Relationship, Learning Motivation, and Learning Effectiveness—Design Students as an Example

In a design department’s practice course there are often group exercises that include intensive interactions between students in the classroom or in the internship factory. In addition, students will deepen the interaction between peers due to course groupings or borrowing of model tools, etc. This study intended to carry out a differential analysis and discussion of the differences among design students from different backgrounds under the three factors of peer relationships, learning motivation, and learning effectiveness. The research method was based on literature analysis and a questionnaire survey, and the research objects were sophomores and seniors in four classes. Statistical analysis methods included the independent sample T-test, one-way ANOVA, and factor and cluster analysis, which were used to summarize different learning styles. The results showed that the students had significant differences of varying degrees in the three factor dimensions. Regarding gender, “care about classmates’ lives” in peer relationships scored higher for the females than the males, and the rest had no effect. Regarding educational system, “care about the classmates’ life” and “sharing life trivia” was included in peer relationships. “keep the enthusiasm in the course of learning” was included in the learning motivation. “recognition for self-directed learning” and “ability improvement” was included in learning effectiveness. The three factors all had significant differences, and the differences for full-time students were higher than for night school students. Regarding grade, there were significant differences in “friends will value my comments” and “sharing life trivia” in peer relationships, “understand course content” in learning motivation, and “data collection ability” and “understanding team member expertise” in learning effectiveness, and seniors scored higher than sophomores in these areas. In addition, the ANOVA and post-hoc tests revealed significant differences in learning the processes between different groups. In peer relationships, full-time seniors scored higher than the other groups; in learning motivation and learning effectiveness, full-time seniors scored higher than night school sophomores. In addition, the overall factors of the full-time seniors were higher than those of the other groups. In the analysis of different learning factors, under the premise of the variation of 58.975%, three factors were extracted by principal axis for analysis with Promax rotation. The different learning factors can be summarized in “emphasizing ability improvement”, “care about peer friendship”, and “careful and active learning”. Classification of learning styles under the three factor dimensions was based on two-stage cluster analysis to obtain two clustering results, including “enthusiastic and friendly” and “active and autonomous”. The results showed that the mastery of self-learning time and the learning experience performance have a key influence on the learning motivation and learning effectiveness of design students from different backgrounds. In addition, the results also showed a new opportunity for course improvement and teaching innovation at night schools. The final results of this study could be used as an important reference for research on peer relationships, learning motivation, and learning effectiveness in design education.

Time-Frequency Analysis of Photopic Negative Response in CRVO Patients

PURPOSE

The PhNR is driven by retinal ganglion cells (RGCs). Therefore, the function of RGCs could be objectively evaluated by analyzing the PhNR. The aim of this article is to determine the effect of central retinal vein occlusion (CRVO) on PhNR and RGCs performances.

METHODS

Seventeen patients with CRVO were included. Full-field photopic ERGs, including PhNR, were recorded and compared with the fellow normal eyes. ERG signals were analyzed based on the standard time-domain analyses of the PhNR as well as a continuous wavelet transform (CWT) to extract time-frequency components that correspond to the PhNR using MATLAB. We obtained the main frequencies and their occurrence time from CWT.

RESULTS

All a-wave, b-wave, and PhNR amplitudes of CRVO eyes showed a significant reduction compared to those of the fellow eyes (P < .01, P < .001, and P < .001, respectively). The peak times of a-wave, b-wave, and PhNR were increased significantly in the CRVO eyes (P = .04, P = .04, and P = .003, respectively). The dominant f₃ frequency, which corresponds to the PhNR in CRVO patients, showed a more significant decrease (P < .001) compared to other dominant frequencies (f₀, f₁, and f₂). The occurrence time of f₃ (t₃) was significantly higher in the CRVO eyes (P < .001). Time-domain of the PhNR was also affected in CRVO patients (P < .001).

CONCLUSION

CWT allows quantifications of ERG responses, especially for PhNR. The PhNR was severely affected in CRVO eyes implicating loss of RGCs. CWT might demonstrate the severity of CRVO more precisely and identify diagnostically significant changes of ERG waveforms that are not resolved when the analysis is only limited to the time-domain measurements.

Investigating Feature Selection and Random Forests for Inter-Patient Heartbeat Classification

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized beat-to-beat (R–R) intervals and features relative to the width of the ventricular depolarization waves (QRS complex) are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats, respectively. In comparison with other state-of-the-art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

EEG epileptic seizure detection and classification based on dual-tree complex wavelet transform and machine learning algorithms

The visual analysis of common neurological disorders such as epileptic seizures in electroencephalography (EEG) is an oversensitive operation and prone to errors, which has motivated the researchers to develop effective automated seizure detection methods. This paper proposes a robust automatic seizure detection method that can establish a veritable diagnosis of these diseases. The proposed method consists of three steps: (i) remove artifact from EEG data using Savitzky-Golay filter and multi-scale principal component analysis (MSPCA), (ii) extract features from EEG signals using signal decomposition representations based on empirical mode decomposition (EMD), discrete wavelet transform (DWT), and dual-tree complex wavelet transform (DTCWT) allowing to overcome the non-linearity and non-stationary of EEG signals, and (iii) allocate the feature vector to the relevant class ( i.e., seizure class "ictal" or free seizure class "interictal") using machine learning techniques such as support vector machine (SVM), k-nearest neighbor ( k-NN), and linear discriminant analysis (LDA). The experimental results were based on two EEG datasets generated from the CHB-MIT database with and without overlapping process. The results obtained have shown the effectiveness of the proposed method that allows achieving a higher classification accuracy rate up to 100% and also outperforms similar state-of-the-art methods.

Simultaneous ECG Heartbeat Segmentation and Classification with Feature Fusion and Long Term Context Dependencies

Arrhythmia detection by classifying ECG heartbeats is an important research topic for healthcare. Recently, deep learning models have been increasingly applied to ECG classification. Among them, most methods work in three steps: preprocessing, heartbeat segmentation and beat-wise classification. However, this methodology has two drawbacks. First, explicit heartbeat segmentation can undermine model simplicity and compactness. Second, beat-wise classification risks losing inter-heartbeat context information that can be useful to achieving high classification performance. Addressing these drawbacks, we propose a novel deep learning model that can simultaneously conduct heartbeat segmentation and classification. Compared to existing methods, our model is more compact as it does not require explicit heartbeat segmentation. Moreover, our model is more context-aware, for it takes into account the relationship between heartbeats. To achieve simultaneous segmentation and classification, we present a Faster R-CNN based model that has been customized to handle ECG data. To characterize inter-heartbeat context information, we exploit inverted residual blocks and a novel feature fusion subroutine that combines average pooling with max-pooling. Extensive experiments on the well-known MIT-BIH database indicate that our method can achieve competitive results for ECG segmentation and classification.

Identification of clinical and urine biomarkers for uncomplicated urinary tract infection using machine learning algorithms

Women with uncomplicated urinary tract infection (UTI) symptoms are commonly treated with empirical antibiotics, resulting in overuse of antibiotics, which promotes antimicrobial resistance. Available diagnostic tools are either not cost-effective or diagnostically sub-optimal. Here, we identified clinical and urinary immunological predictors for UTI diagnosis. We explored 17 clinical and 42 immunological potential predictors for bacterial culture among women with uncomplicated UTI symptoms using random forest or support vector machine coupled with recursive feature elimination. Urine cloudiness was the best performing clinical predictor to rule out (negative likelihood ratio [LR−] = 0.4) and rule in (LR+ = 2.6) UTI. Using a more discriminatory scale to assess cloudiness (turbidity) increased the accuracy of UTI prediction further (LR+ = 4.4). Urinary levels of MMP9, NGAL, CXCL8 and IL-1β together had a higher LR+ (6.1) and similar LR− (0.4), compared to cloudiness. Varying the bacterial count thresholds for urine culture positivity did not alter best clinical predictor selection, but did affect the number of immunological predictors required for reaching an optimal prediction. We conclude that urine cloudiness is particularly helpful in ruling out negative UTI cases. The identified urinary biomarkers could be used to develop a point of care test for UTI but require further validation.

Towards Real-Time Heartbeat Classification: Evaluation of Nonlinear Morphological Features and Voting Method

Abnormal heart rhythms are one of the significant health concerns worldwide. The current state-of-the-art to recognize and classify abnormal heartbeats is manually performed by visual inspection by an expert practitioner. This is not just a tedious task; it is also error prone and, because it is performed, post-recordings may add unnecessary delay to the care. The real key to the fight to cardiac diseases is real-time detection that triggers prompt action. The biggest hurdle to real-time detection is represented by the rare occurrences of abnormal heartbeats and even more are some rare typologies that are not fully represented in signal datasets; the latter is what makes it difficult for doctors and algorithms to recognize them. This work presents an automated heartbeat classification based on nonlinear morphological features and a voting scheme suitable for rare heartbeat morphologies. Although the algorithm is designed and tested on a computer, it is intended ultimately to run on a portable i.e., field-programmable gate array (FPGA) devices. Our algorithm tested on Massachusetts Institute of Technology- Beth Israel Hospital(MIT-BIH) database as per Association for the Advancement of Medical Instrumentation(AAMI) recommendations. The simulation results show the superiority of the proposed method, especially in predicting minority groups: the fusion and unknown classes with 90.4% and 100%.

Automatic detection of arrhythmia from imbalanced ECG database using CNN model with SMOTE

Timely prediction of cardiovascular diseases with the help of a computer-aided diagnosis system minimizes the mortality rate of cardiac disease patients. Cardiac arrhythmia detection is one of the most challenging tasks, because the variations of electrocardiogram(ECG) signal are very small, which cannot be detected by human eyes. In this study, an 11-layer deep convolutional neural network model is proposed for classification of the MIT-BIH arrhythmia database into five classes according to the ANSI-AAMI standards. In this CNN model, we designed a complete end-to-end structure of the classification method and applied without the denoising process of the database. The major advantage of the new methodology proposed is that the number of classifications will reduce and also the need to detect, and segment the QRS complexes, obviated. This MIT-BIH database has been artificially oversampled to handle the minority classes, class imbalance problem using SMOTE technique. This new CNN model was trained on the augmented ECG database and tested on the real dataset. The experimental results portray that the developed CNN model has better performance in terms of precision, recall, F-score, and overall accuracy as compared to the work mentioned in the literatures. These results also indicate that the best performance accuracy of 98.30% is obtained in the 70:30 train-test data set.

Positive and Negative Evidence Accumulation Clustering for Sensor Fusion: An Application to Heartbeat Clustering

In this work, a new clustering algorithm especially geared towards merging data arising from multiple sensors is presented. The algorithm, called PN-EAC, is based on the ensemble clustering paradigm and it introduces the novel concept of negative evidence. PN-EAC combines both positive evidence, to gather information about the elements that should be grouped together in the final partition, and negative evidence, which has information about the elements that should not be grouped together. The algorithm has been validated in the electrocardiographic domain for heartbeat clustering, extracting positive evidence from the heartbeat morphology and negative evidence from the distances between heartbeats. The best result obtained on the MIT-BIH Arrhythmia database yielded an error of 1.44%. In the St. Petersburg Institute of Cardiological Technics 12-Lead Arrhythmia Database database (INCARTDB), an error of 0.601% was obtained when using two electrocardiogram (ECG) leads. When increasing the number of leads to 4, 6, 8, 10 and 12, the algorithm obtains better results (statistically significant) than with the previous number of leads, reaching an error of 0.338%. To the best of our knowledge, this is the first clustering algorithm that is able to process simultaneously any number of ECG leads. Our results support the use of PN-EAC to combine different sources of information and the value of the negative evidence.

Wearable Sensors Reveal Menses-Driven Changes in Physiology and Enable Prediction of the Fertile Window: Observational Study

BACKGROUND

Previous research examining physiological changes across the menstrual cycle has considered biological responses to shifting hormones in isolation. Clinical studies, for example, have shown that women's nightly basal body temperature increases from 0.28 to 0.56 ˚C following postovulation progesterone production. Women's resting pulse rate, respiratory rate, and heart rate variability (HRV) are similarly elevated in the luteal phase, whereas skin perfusion decreases significantly following the fertile window's closing. Past research probed only 1 or 2 of these physiological features in a given study, requiring participants to come to a laboratory or hospital clinic multiple times throughout their cycle. Although initially designed for recreational purposes, wearable technology could enable more ambulatory studies of physiological changes across the menstrual cycle. Early research suggests that wearables can detect phase-based shifts in pulse rate and wrist skin temperature (WST). To date, previous work has studied these features separately, with the ability of wearables to accurately pinpoint the fertile window using multiple physiological parameters simultaneously yet unknown.

OBJECTIVE

In this study, we probed what phase-based differences a wearable bracelet could detect in users' WST, heart rate, HRV, respiratory rate, and skin perfusion. Drawing on insight from artificial intelligence and machine learning, we then sought to develop an algorithm that could identify the fertile window in real time.

METHODS

We conducted a prospective longitudinal study, recruiting 237 conception-seeking Swiss women. Participants wore the Ava bracelet (Ava AG) nightly while sleeping for up to a year or until they became pregnant. In addition to syncing the device to the corresponding smartphone app daily, women also completed an electronic diary about their activities in the past 24 hours. Finally, women took a urinary luteinizing hormone test at several points in a given cycle to determine the close of the fertile window. We assessed phase-based changes in physiological parameters using cross-classified mixed-effects models with random intercepts and random slopes. We then trained a machine learning algorithm to recognize the fertile window.

RESULTS

We have demonstrated that wearable technology can detect significant, concurrent phase-based shifts in WST, heart rate, and respiratory rate (all P<.001). HRV and skin perfusion similarly varied across the menstrual cycle (all P<.05), although these effects only trended toward significance following a Bonferroni correction to maintain a family-wise alpha level. Our findings were robust to daily, individual, and cycle-level covariates. Furthermore, we developed a machine learning algorithm that can detect the fertile window with 90% accuracy (95% CI 0.89 to 0.92).

CONCLUSIONS

Our contributions highlight the impact of artificial intelligence and machine learning's integration into health care. By monitoring numerous physiological parameters simultaneously, wearable technology uniquely improves upon retrospective methods for fertility awareness and enables the first real-time predictive model of ovulation.

Accurate and rapid screening model for potential diabetes mellitus

Background

Prediction or early diagnosis of diabetes is crucial for populations with high risk of diabetes.

Methods

In this study, we assessed the ability of five popular classifiers (J48, AdaboostM1, SMO, Bayes Net, and Naïve Bayes) to identify individuals with diabetes based on nine non-invasive and easily obtained clinical features, including age, gender, body mass index (BMI), hypertension, history of cardiovascular disease or stroke, family history of diabetes, physical activity, work stress, and salty food preference. A total of 4205 data entries were obtained from annual physical examination reports for adults in the Shengjing Hospital of China Medical University during January–April 2017. Weka data mining software was used to identify the best algorithm for diabetes classification.

Results

The results indicate that decision tree classifier J48 has the best performance (accuracy = 0.9503, precision = 0.950, recall = 0.950, F-measure = 0.948, and AUC = 0.964). The decision tree structure shows that age is the most significant feature, followed by family history of diabetes, work stress, BMI, salty food preference, physical activity, hypertension, gender, and history of cardiovascular disease or stroke.

Conclusions

Our study shows that decision tree analyses can be applied to screen individuals for early diabetes risk without the need for invasive tests. This procedure will be particularly useful in developing regions with high epidemiological risk and poor socioeconomic status, and enable clinical practitioners to rapidly screen patients for increased risk of diabetes. The key features in the tree structure could further facilitate diabetes prevention through targeted community interventions, which can potentially improve early diabetes diagnosis and reduce burdens on the healthcare system.

Automated Method for Discrimination of Arrhythmias Using Time, Frequency, and Nonlinear Features of Electrocardiogram Signals

We developed an automated approach to differentiate between different types of arrhythmic episodes in electrocardiogram (ECG) signals, because, in real-life scenarios, a software application does not know in advance the type of arrhythmia a patient experiences. Our approach has four main stages: (1) Classification of ventricular fibrillation (VF) versus non-VF segments—including atrial fibrillation (AF), ventricular tachycardia (VT), normal sinus rhythm (NSR), and sinus arrhythmias, such as bigeminy, trigeminy, quadrigeminy, couplet, triplet—using four image-based phase plot features, one frequency domain feature, and the Shannon entropy index. (2) Classification of AF versus non-AF segments. (3) Premature ventricular contraction (PVC) detection on every non-AF segment, using a time domain feature, a frequency domain feature, and two features that characterize the nonlinearity of the data. (4) Determination of the PVC patterns, if present, to categorize distinct types of sinus arrhythmias and NSR. We used the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database, Creighton University’s VT arrhythmia database, the MIT-BIH atrial fibrillation database, and the MIT-BIH malignant ventricular arrhythmia database to test our algorithm. Binary decision tree (BDT) and support vector machine (SVM) classifiers were used in both stage 1 and stage 3. We also compared our proposed algorithm’s performance to other published algorithms. Our VF detection algorithm was accurate, as in balanced datasets (and unbalanced, in parentheses) it provided an accuracy of 95.1% (97.1%), sensitivity of 94.5% (91.1%), and specificity of 94.2% (98.2%). The AF detection was accurate, as the sensitivity and specificity in balanced datasets (and unbalanced, in parentheses) were found to be 97.8% (98.6%) and 97.21% (97.1%), respectively. Our PVC detection algorithm was also robust, as the accuracy, sensitivity, and specificity were found to be 99% (98.1%), 98.0% (96.2%), and 98.4% (99.4%), respectively, for balanced and (unbalanced) datasets.

Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants

Arrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents absence of disease and the other fifteen classes represent electrocardiogram records of various subtypes of arrhythmias. The research is carried out on the dataset taken from the University of California at Irvine Machine Learning Data Repository. The dataset contains a large volume of feature dimensions which are reduced using wrapper based feature selection technique. For multiclass classification, support vector machine (SVM) based approaches including one-against-one (OAO), one-against-all (OAA), and error-correction code (ECC) are employed to detect the presence and absence of arrhythmias. The SVM method results are compared with other standard machine learning classifiers using varying parameters and the performance of the classifiers is evaluated using accuracy, kappa statistics, and root mean square error. The results show that OAO method of SVM outperforms all other classifiers by achieving an accuracy rate of 81.11% when used with 80/20 data split and 92.07% using 90/10 data split option.

A Statistical Classifier to Support Diagnose Meningitis in Less Developed Areas of Brazil

This paper describes the development of statistical classifiers to help diagnose meningococcal meningitis, i.e. the most sever, infectious and deadliest type of this disease. The goal is to find a mechanism able to determine whether a patient has this type of meningitis from a set of symptoms that can be directly observed in the earliest stages of this pathology. Currently, in Brazil, a country that is heavily affected by meningitis, all suspected cases require immediate hospitalization and the beginning of a treatment with invasive tests and medicines. This procedure, therefore, entails expensive treatments unaffordable in less developed regions. For this purpose, we have gathered together a dataset of 22,602 records of suspected meningitis cases from the Brazilian state of Bahia. Seven classification techniques have been applied from input data of nine symptoms and other information about the patient such as age, sex and the area they live in, and a 10 cross-fold validation has been performed. Results show that the techniques applied are suitable for diagnosing the meningococcal meningitis. Several indexes, such as precision, recall or ROC area, have been computed to show the accuracy of the models. All of them provide good results, but the best corresponds to the J48 classifier with a precision of 0.942 and a ROC area over 0.95. These results indicate that our model can indeed help lead to a non-invasive and early diagnosis of this pathology. This is especially useful in less developed areas, where the epidemiologic risk is usually high and medical expenses, sometimes, unaffordable.

Wavelet decomposition analysis in the two-flash multifocal ERG in early glaucoma: a comparison to ganglion cell analysis and visual field

PURPOSE

To further improve analysis of the two-flash multifocal electroretinogram (2F-mfERG) in glaucoma in regard to structure-function analysis, using discrete wavelet transform (DWT) analysis.

METHODS

Sixty subjects [35 controls and 25 primary open-angle glaucoma (POAG)] underwent 2F-mfERG. Responses were analyzed with the DWT. The DWT level that could best separate POAG from controls was compared to the root-mean-square (RMS) calculations previously used in the analysis of the 2F-mfERG. In a subgroup analysis, structure-function correlation was assessed between DWT, optical coherence tomography and automated perimetry (mf103 customized pattern) for the central 15°.

RESULTS

Frequency level 4 of the wavelet variance analysis (144 Hz, WVA-144) was most sensitive (p < 0.003). It correlated positively with RMS but had a better AUC. Positive relations were found between visual field, WVA-144 and GCIPL thickness. The highest predictive factor for glaucoma diagnostic was seen in the GCIPL, but this improved further by adding the mean sensitivity and WVA-144.

CONCLUSIONS

mfERG using WVA analysis improves glaucoma diagnosis, especially when combined with GCIPL and MS.

Investigating the effect of traditional Persian music on ECG signals in young women using wavelet transform and neural networks

Objective:

In the past few decades, several studies have reported the physiological effects of listening to music. The physiological effects of different music types on different people are different. In the present study, we aimed to examine the effects of listening to traditional Persian music on electrocardiogram (ECG) signals in young women.

Methods:

Twenty-two healthy females participated in this study. ECG signals were recorded under two conditions: rest and music. For each ECG signal, 20 morphological and wavelet-based features were selected. Artificial neural network (ANN) and probabilistic neural network (PNN) classifiers were used for the classification of ECG signals during and before listening to music.

Results:

Collected data were separated into two data sets train and test. Classification accuracies of 88% and 97% were achieved in train data sets using ANN and PNN, respectively. In addition, the test data set was employed for evaluating the classifiers, and classification rates of 84% and 93% were obtained using ANN and PNN, respectively.

Conclusion:

The present study investigated the effect of music on ECG signals based on wavelet transform and morphological features. The results obtained here can provide a good understanding on the effects of music on ECG signals to researchers.