Search

This study explores the progress of chatbot technology, focusing on the aspect of error correction to enhance these smart conversational tools. Chatbots, powered by artificial intelligence (AI), are increasingly prevalent across industries such as customer service, healthcare, e-commerce, and education. Despite their use and increasing complexity, chatbots are prone to errors like misunderstandings, inappropriate responses, and factual inaccuracies. These issues can have an impact on user satisfaction and trust. This research provides an overview of chatbots, conducts an analysis of errors they encounter, and examines different approaches to rectifying these errors. These approaches include using data-driven feedback loops, involving humans in the learning process, and adjusting through learning methods like reinforcement learning, supervised learning, unsupervised learning, semi-supervised learning, and meta-learning. Through real life examples and case studies in different fields, we explore how these strategies are implemented. Looking ahead, we explore the different challenges faced by AI-powered chatbots, including ethical considerations and biases during implementation. Furthermore, we explore the transformative potential of new technological advancements, such as explainable AI models, autonomous content generation algorithms (e.g., generative adversarial networks), and quantum computing to enhance chatbot training. Our research provides information for developers and researchers looking to improve chatbot capabilities, which can be applied in service and support industries to effectively address user requirements. [ABSTRACT FROM AUTHOR]

As healthcare systems around the world face challenges such as escalating costs, limited access, and growing demand for personalized care, artificial intelligence (AI) is emerging as a key force for transformation. This review is motivated by the urgent need to harness AI's potential to mitigate these issues and aims to critically assess AI's integration in different healthcare domains. We explore how AI empowers clinical decision-making, optimizes hospital operation and management, refines medical image analysis, and revolutionizes patient care and monitoring through AI-powered wearables. Through several case studies, we review how AI has transformed specific healthcare domains and discuss the remaining challenges and possible solutions. Additionally, we will discuss methodologies for assessing AI healthcare solutions, ethical challenges of AI deployment, and the importance of data privacy and bias mitigation for responsible technology use. By presenting a critical assessment of AI's transformative potential, this review equips researchers with a deeper understanding of AI's current and future impact on healthcare. It encourages an interdisciplinary dialogue between researchers, clinicians, and technologists to navigate the complexities of AI implementation, fostering the development of AI-driven solutions that prioritize ethical standards, equity, and a patient-centered approach. [ABSTRACT FROM AUTHOR]

Fatigue limit states often govern the design of shear connectors in steel‐concrete composite bridges. AASHTO LRFD bridge design specifications provides a linear equation in a semi‐logarithmic S‐N curve for predicting the fatigue life of shear connectors. However, this equation can be too conservative in some cases, as supported by the available experimental data. In this paper, artificial intelligence (AI) was incorporated into the prediction of the fatigue life of shear connectors. Six different machine learning (ML) algorithms were considered for this purpose. The predictions of ML algorithms were compared both with the available experimental data and the equation provided by AASHTO. The results showed that the fatigue life predicted by ML methods is more accurate than that predicted by the current equation of AASHTO. The results of this study showed that AI can be a proper alternative to the existing methods for predicting the fatigue life of shear connectors. Highlights: AI was used for the first time to evaluate fatigue life of shear connectors in bridges.AI predicted fatigue life of shear connectors more accurately than the current methods.GPR and DT algorithms were the best algorithms for assessing fatigue life of connectors.The current equations in AASHTO for fatigue may need to be redeveloped based on AI. [ABSTRACT FROM AUTHOR]

Electrocardiography is the gold standard technique for detecting abnormal heart conditions. Automatic detection of electrocardiogram (ECG) abnormalities helps clinicians analyze the large amount of data produced daily by cardiac monitors. As thenumber of abnormal ECG samples with cardiologist-supplied labels required to train supervised machine learning models is limited, there is a growing need for unsupervised learning methods for ECG analysis. Unsupervised learning aims to partition ECG samples into distinct abnormality classes without cardiologist-supplied labels–a process referred to as ECG clustering. In addition to abnormality detection, ECG clustering has recently discovered inter and intra-individual patterns that reveal valuable information about the whole body and mind, such as emotions, mental disorders, and metabolic levels. ECG clustering can also resolve specific challenges facing supervised learning systems, such as the imbalanced data problem, and can enhance biometric systems. While several reviews exist on supervised ECG systems, a comprehensive review of unsupervised ECG analysis techniques is still lacking. This study reviews ECG clustering techniques developed mainly in the last decade. The focus will be on recent machine learning and deep learning algorithms and their practical applications. We critically review and compare these techniques, discuss their applications and limitations, and provide future research directions. This review provides further insights into ECG clustering and presents the necessary information required to adopt the appropriate algorithm for a specific application. [ABSTRACT FROM AUTHOR]

Objectives: Sleep apnea is the most common sleep disorder that leads to serious health complications if not treated early. Forecasting apnea occurrence ahead in time provides the opportunity to take appropriate actions to control and manage it. Methods: A novel framework for forecasting the occurrence of apnea from single-lead electrocardiogram (ECG) based on deep recurrent neural networks is proposed. ECG R-peak amplitudes and R-R intervals are extracted and aligned using power spectral analysis, and recurrent deep learning models are developed to extract the most predictive ECG features and forecast the occurrence of apnea. Results: The performance of the proposed approach was validated in forecasting apnea events up to five minutes in future on a dataset of 70 sleep recordings. A forecasting accuracy of up to 94.95% was achieved which was higher than the performance of conventional multilayer perceptron (p < 0.05) and other state-of-the-art techniques. Conclusions: The proposed deep learning approach was successful in forecasting the occurrence of sleep apnea from single-lead ECG. It can therefore be adopted in wearable sleep monitors for the management of sleep apnea. Our developed algorithms are publicly available on GitHub. [ABSTRACT FROM AUTHOR]

Background: Evaluating the risk of Alzheimer's disease (AD) in cognitively normal (CN) and patients with mild cognitive impairment (MCI) is extremely important. While MCI-to-AD progression risk has been studied extensively, few studies estimate CN-to-MCI conversion risk. The Cox proportional hazards (PH), a widely used survival analysis model, assumes a linear predictor-risk relationship. Generalizing the PH model to more complex predictor-risk relationships may increase risk estimation accuracy.Objective: The aim of this study was to develop a PH model using an Xgboost regressor, based on demographic, genetic, neuropsychiatric, and neuroimaging predictors to estimate risk of AD in patients with MCI, and the risk of MCI in CN subjects.Methods: We replaced the Cox PH linear model with an Xgboost regressor to capture complex interactions between predictors, and non-linear predictor-risk associations. We endeavored to limit model inputs to noninvasive and more widely available predictors in order to facilitate future applicability in a wider setting.Results: In MCI-to-AD (n = 882), the Xgboost model achieved a concordance index (C-index) of 84.5%. When the model was used for MCI risk prediction in CN (n = 100) individuals, the C-index was 73.3%. In both applications, the C-index was statistically significantly higher in the Xgboost in comparison to the Cox PH model.Conclusion: Using non-linear regressors such as Xgboost improves AD dementia risk assessment in CN and MCI. It is possible to achieve reasonable risk stratification using predictors that are relatively low-cost in terms of time, invasiveness, and availability. Future strategies for improving AD dementia risk estimation are discussed. [ABSTRACT FROM AUTHOR]

Peripheral arterial disease (PAD) is a progressing arterial disorder that is associated with significant morbidity and mortality. The conventional PAD detection methods are invasive, cumbersome, or require expensive equipment and highly trained technicians. Here, we propose a new automated, noninvasive, and easy-to-use method for the detection of PAD based on characterizing the arterial system by applying an external varying pressure using a cuff. The superposition of the internal arterial pressure and the externally applied pressure were measured and mathematically modeled as a function of cuff pressure. A feature-based learning algorithm was then designed to identify PAD patterns by analyzing the parameters of the derived mathematical models. Genetic algorithm and principal component analysis were employed to select the best predictive features distinguishing PAD patterns from normal. A RUSBoost ensemble model using neural network as the base learner was designed to diagnose PAD from genetic algorithm selected features. The proposed method was validated on data collected from 14 PAD patients and 19 healthy individuals. It achieved a high accuracy, sensitivity, and specificity of 91.4%, 90.0%, and 92.1%, respectively, in detecting PAD. The effect of age, a confounding factor that may have impacted our analyzes, was not considered in this study. The proposed method shows promise toward noninvasive and accurate detection of PAD and can be integrated into routine oscillometric blood pressure measurements. [ABSTRACT FROM AUTHOR]

Abstract: Impedance cardiography is the most common clinically validated, noninvasive method for determining the timing of the opening of the aortic valve, an important event used for measuring preejection period, which reflects sympathetic beta‐adrenergic influences on the heart. Automatic detection of the exact time of the opening of the aortic valve (B point on the impedance cardiogram) has proven to be challenging as its appearance varies between and within individuals and may manifest as a reversal, inflection, or rapid slope change of the thoracic impedance derivative's (dZ/dt) rapid rise. Here, a novel automatic algorithm is proposed for the detection of the B point by finding the main rapid rise of the dZ/dt signal, which is due to blood ejection. Several conditions based on zero crossings, minima, and maxima of the dZ/dt signal and its derivatives are considered to reject any unwanted noise and artifacts and select the true B‐point location. The detected B‐point locations are then corrected by modeling the B‐point time data using forward and reverse autoregressive models. The proposed algorithm is validated against expert‐detected B points and is compared with different conventional methods; it significantly outperforms them by at least 54% in mean error, 30% in mean absolute error, and 27% in standard deviation of error. This algorithm can be adopted in ambulatory studies requiring beat‐to‐beat evaluation of cardiac hemodynamic parameters over extended time periods where expert scoring is not feasible. [ABSTRACT FROM AUTHOR]

Noninvasive blood pressure (BP) measurement is an important tool for managing hypertension and cardiovascular disease. However, automated noninvasive BP measurement devices, which are usually based on the oscillometric method, do not always provide accurate estimation of BP. It has been found that change in arterial stiffness (AS) is an underlying mechanism of disagreement between an oscillometric BP monitor and a sphygmomanometer. This problem is addressed by incorporating parameters related to AS in the algorithm for BP measurement. Pulse transit time (PTT) is first used to estimate AS parameters, which are fixed into a model of the oscillometric envelope. This model can then be used to perform curve fitting to the measured signal using only four parameters: systolic BP, diastolic BP, mean BP, and lumen area at zero transmural pressure. The proposed technique is independent of the experimentally determined characteristic ratios that are commonly used in existing oscillometric methods. The accuracy of the proposed technique was evaluated by comparing with the same model without incorporation of AS, and with reference BP device measurements. The new method achieved standard deviation of error less than 8 mmHg and mean error less than 5 mmHg. The results show consistency with ANSI/AAMI SP-10 standard for noninvasive BP measurement techniques. [ABSTRACT FROM AUTHOR]

Objectives: The use of remote sensing technologies such as radar is gaining popularity as a technique for contactless detection of physiological signals and analysis of human motion. This paper presents a methodology for classifying different events in a collection of phase modulated continuous wave radar returns. The primary application of interest is to monitor inmates where the presence of human vital signs amidst different, interferences needs to be identified. Methods: A comprehensive set of features is derived through time and frequency domain analyses of the radar returns. The Bhattacharyya distance is used to preselect the features with highest class separability as the possible candidate features for use in the classification process. The uncorrelated linear discriminant analysis is performed to decorrelate, denoise, and reduce the dimension of the candidate feature set. Linear and quadratic Bayesian classifiers are designed to distinguish breathing, different human motions, and nonhuman motions. The performance of these classifiers is evaluated on a pilot dataset of radar returns that contained different events including breathing, stopped breathing, simple human motions, and movement of fan and water. Results: Our proposed pattern classification system achieved accuracies of up to $93$% in stationary subject detection, $90$% in stop-breathing detection, and $86$% in interference detection. Conclusion: Our proposed radar pattern recognition system was able to accurately distinguish the predefined events amidst interferences. Significance: Besides inmate monitoring and suicide attempt detection, this paper can be extended to other radar applications such as home-based monitoring of elderly people, apnea detection, and home occupancy detection. [ABSTRACT FROM AUTHOR]

Radar-based noncontact sensing of life sign signals is often used in safety and rescue missions during disasters such as earthquakes and avalanches and for home care applications. The radar returns obtained from a human target contain the breathing frequency along with its strong higher harmonics depending on the target’s posture. As a consequence, well understood, computationally efficient, and the most popular traditional FFT-based estimators that rely only on the strongest peak for estimates of breathing rates may be inaccurate. The paper proposes a solution for correcting the estimation errors of such single peak-based algorithms. The proposed method is based on using harmonically related comb filters over a set of all possible breathing frequencies. The method is tested on three subjects for different postures, for different distances between the radar and the subject, and for two different radar platforms: PN-UWB and phase modulated-CW (PM-CW) radars. Simplified algorithms more suitable for real-time implementation have also been proposed and compared using accuracy and computational complexity. The proposed breathing rate estimation algorithms provide a reduction of about 81% and 80% in the mean absolute error of breathing rates in comparison to the traditional FFT-based methods using strongest peak detection, for PN-UWB and PM-CW radars, respectively. [ABSTRACT FROM AUTHOR]

An accurate noninvasive estimation of mean arterial pressure (MAP) is of great importance in the evaluation of circulatory function and prognosis of some cardiovascular diseases. This paper proposes a novel oscillometric MAP estimation method based on the dependence of pulse transit time (PTT) on cuff pressure (CP). The PTT computed as the time interval between the electrocardiogram (ECG) R-peaks and the maximum slope points on the oscillometric pulses is mathematically modeled by considering the cuff-arm-artery system and the blood flow dynamics. It is then analytically shown that MAP can be approximated as the CP at which the PTT is maximum. Based on our theoretical findings, a new method of MAP estimation from simultaneous ECG and oscillometric blood pressure measurements is proposed. Our proposed method is validated with a pilot study in which 150 recordings from 10 subjects are analyzed. The reference MAP is computed from the systolic and diastolic pressures measured by the Food and Drug Administration-approved Omron HEM-790IT monitor using three different formulas given in the literature. The performance of our proposed method is compared with the maximum amplitude and zero-crossing methods in terms of mean error (ME), mean absolute error, and standard deviation of error (SDE). It is found that our proposed method achieves improvements of more than 20% in SDE compared with the maximum amplitude method and more than 50% in ME compared with the zero-crossing method. [ABSTRACT FROM PUBLISHER]

Oscillometry is a popular technique for automatic estimation of blood pressure (BP). However, most of the oscillometric algorithms rely on empirical coefficients for systolic and diastolic pressure evaluation that may differ in various patient populations, rendering the technique unreliable. A promising complementary technique for automatic estimation of BP, based on the dependence of pulse transit time (PTT) on cuff pressure (CP) (PTT–CP mapping), has been proposed in the literature. However, a theoretical grounding for this technique and a nonparametric BP estimation approach are still missing. In this paper, we propose a novel coefficient-free BP estimation method based on PTT–CP dependence. PTT is mathematically modeled as a function of arterial lumen area under the cuff. It is then analytically shown that PTT–CP mappings computed from various points on the arterial pulses can be used to directly estimate systolic, diastolic, and mean arterial pressure without empirical coefficients. Analytical results are cross-validated with a pilot investigation on ten healthy subjects where 150 simultaneous electrocardiogram and oscillometric BP recordings are analyzed. The results are encouraging whereby the mean absolute errors of the proposed method in estimating systolic and diastolic pressures are 5.31 and 4.51 mmHg, respectively, relative to the Food and Drug Administration approved Omron monitor. Our work thus shows promise toward providing robust and objective BP estimation in a variety of patients and monitoring situations. [ABSTRACT FROM PUBLISHER]

In this paper, we present a novel feature-based neural network (NN) approach for estimation of blood pressure (BP) from wrist oscillometric measurements. Unlike previous methods that use the raw oscillometric waveform envelope (OMWE) as input to the NN, in this paper, we propose to use features extracted from the envelope. The OMWE is mathematically modeled as a sum of two Gaussian functions. The optimum parameters of this model are found by minimizing the least squares error between the model and the OMWE using the Levenberg–Marquardt algorithm and are used as features. Two separate feed-forward NNs (FFNNs) are then designed to estimate the systolic and diastolic BPs using these features. The FFNNs are trained using the resilient backpropagation learning algorithm and tested on a data set of BP measurements recorded from 85 subjects. The performance is then compared with that of the conventional maximum amplitude algorithm, adaptive neuro-fuzzy inference system, and already published NN-based methods. It is found that the proposed approach achieves lower values of mean absolute error and standard deviation of error in the estimation of BP. In addition, the proposed approach has the following advantages: lower complexity with respect to the design parameters, smaller training data set, and lower computational load. [ABSTRACT FROM PUBLISHER]

Abstract: A traditional approach to segmentation of magnetic resonance (MR) images is the fuzzy c-means (FCM) clustering algorithm. The efficacy of FCM algorithm considerably reduces in the case of noisy data. In order to improve the performance of FCM algorithm, researchers have introduced a neighborhood attraction, which is dependent on the relative location and features of neighboring pixels. However, determination of degree of attraction is a challenging task which can considerably affect the segmentation results. This paper presents a study investigating the potential of genetic algorithms (GAs) and particle swarm optimization (PSO) to determine the optimum value of degree of attraction. The GAs are best at reaching a near optimal solution but have trouble finding an exact solution, while PSO’s-group interactions enhances the search for an optimal solution. Therefore, significant improvements are expected using a hybrid method combining the strengths of PSO with GAs, simultaneously. In this context, a hybrid GAs/PSO (breeding swarms) method is employed for determination of optimum degree of attraction. The quantitative and qualitative comparisons performed on simulated and real brain MR images with different noise levels demonstrate unprecedented improvements in segmentation results compared to other FCM-based methods. [Copyright &y& Elsevier]

Recently, the use of wavelet transform has led to significant advances in image denoising applications. Among wavelet-based denoising approaches, the Bayesian techniques give more accurate estimates. Considering interscale dependencies, these estimates become closer to the original image. In this context, the choice of an appropriate model for wavelet coefficients is an important issue. The performance can also be improved by estimating model parameters in a local neighborhood. In this paper, we propose the bivariate normal inverse Gaussian (NIG) distribution, which can model a wide range of heavy-tailed to less heavy-tailed processes, to model the local wavelet coefficients at adjacent scales. We will show that this new statistical model is superior to the conventional generalized Gaussian (GG) model. Then, a minimum mean square error-based (MMSE-based) Bayesian estimator is designed to effectively remove noise from wavelet coefficients. Exploiting this new statistical model in the dual-tree complex wavelet domain, we achieved state-of-the-art performance among related recent denoising approaches, both visually and in terms of peak signal-to-noise ratio (PSNR). [ABSTRACT FROM AUTHOR]

Oscillometry is the most common measurement method used in electronic blood pressure (BP) monitors. However, most of the existing oscillometric algorithms employ empirical ratios on the oscillometric waveform envelope (OMWE) to determine the systolic pressure (SP) and diastolic pressure (DP). As these algorithms do not consider the cardiovascular system parameters that may vary due to health conditions or age, the pressure estimates are not always reliable. In this paper, we develop a new mathematical model for the OMWE by incorporating an existing model of the cuff-arm-artery system. [ABSTRACT FROM PUBLISHER]

The pre‐ejection period (PEP) is a valid index of myocardial contractility and beta‐adrenergic sympathetic control of the heart defined as the time between electrical systole (ECG Q wave) to the initial opening of the aortic valve, estimated as the B point on the impedance cardiogram (ICG). B‐point detection accuracy can be severely impacted if ICG cardiac cycles corrupted by motion artifact, noise, or electrode displacement are included in the analyses. Here, we developed new algorithms to detect and exclude corrupted ICG cycles by analyzing their level of activity. PEP was then estimated and analyzed on ensemble‐averaged clean ICG cycles using an automatic algorithm previously developed by the authors for the detection of B point in awake individuals. We investigated the algorithms' performance relative to expert visual scoring on long‐duration data collected from 20 participants during overnight recordings, where the quality of ICG could be highly affected by movement artifacts and electrode displacements and the signal could also vary according to sleep stage and time of night. The artifact rejection algorithm achieved a high accuracy of 87% in detection of expert‐identified corrupted ICG cycles, including those with normal amplitude as well as out‐of‐range values, and was robust to different types and levels of artifact. Intraclass correlations for concurrent validity of the B‐point detection algorithm in different sleep stages and in‐bed wakefulness exceeded 0.98, indicating excellent agreement with the expert. The algorithms show promise toward sleep applications requiring accurate and reliable automatic measurement of cardiac hemodynamic parameters. The pre‐ejection period (PEP) is a valid index of sympathetic beta‐adrenergic influences upon the heart measured from the simultaneously recorded electrocardiogram and impedance cardiogram (ICG). PEP accuracy can be severely impacted if ICG cardiac cycles corrupted by motion artifact, noise, or electrode displacement are included in the analyses. Here, we developed new algorithms to automatically detect and exclude corrupted ICG cycles by analyzing their level of activity and evaluated the algorithms' performance on sleep data affected by noise and artifacts. The algorithms performed well and showed promise toward sleep applications requiring accurate and reliable automatic measurement of cardiac hemodynamic parameters. [ABSTRACT FROM AUTHOR]