Healthcare analytics (New York, N.Y.)最新文献

{"title":"Optimized early fusion of handcrafted and deep learning descriptors for voice pathology detection and classification","authors":"Roohum Jegan,&nbsp;R. Jayagowri","doi":"10.1016/j.health.2024.100369","DOIUrl":"10.1016/j.health.2024.100369","url":null,"abstract":"<div><div>This study presents an automated noninvasive voice disorder detection and classification approach using an optimized fusion of modified glottal source estimation and deep transfer learning neural network descriptors. A new set of modified descriptors based on a glottal source estimator and pre-trained Inception-ResNet-v2 convolutional neural network-based features are proposed for the speech disorder detection and classification task. The modified feature set is obtained using mel-cepstral coefficients, harmonic model, phase discrimination means, distortion deviation descriptors, conventional wavelet, and glottal source estimation features. Early descriptor-level fusion is employed in this study for performance enhancement-however, the fusion results in higher feature vector dimensionality. A nature-inspired slime mould algorithm is utilized to remove redundant and select the best discriminating features. Finally, the classification is performed using the K-nearest neighbor (KNN) classifier. The proposed algorithm was evaluated using extensive experiments with different feature combinations, with and without feature selection, and with two popular datasets: the Arabic Voice Pathology Database (AVPD) and the Saarbrucken Voice Database (SVD). We show that the proposed optimized fusion method attained an enhanced voice pathology detection accuracy of 98.46%, encompassing a wide spectrum of voice disorders on the SVD database. Furthermore, compared to traditional handcrafted and deep neural network-based techniques, the proposed method demonstrates competitive performance with fewer features.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100369"},"PeriodicalIF":0.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142742998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep neural network model with spectral correlation function for electrocardiogram classification and diagnosis of atrial fibrillation","authors":"Sara Mihandoost","doi":"10.1016/j.health.2024.100370","DOIUrl":"10.1016/j.health.2024.100370","url":null,"abstract":"<div><div>Atrial Fibrillation (AF) is a common type of irregular heartbeat, and early detection can significantly improve treatment outcomes and prognoses. Single-lead Electrocardiogram (ECG) devices are under extensive scrutiny for monitoring patients' heart health worldwide. Standardized ECG signal monitoring has demonstrated a significant reduction in mortality rates associated with severe cardiovascular diseases. However, the automatic detection method for AF requires significant improvement. This study presents a novel approach that utilizes the cyclostationary analysis of ECG signals, uncovering a spectral hidden periodicity between the QRS-T (the main wave components representing electrical activity in the heart) complexes of the ECG signal through the Spectral Correlation Function (SCF). To validate the proposed method's performance, the single ECG's SCF coefficients are applied to the Convolutional Recurrent Neural Network (CRNN), which consists of convolutional and long short-term memory (LSTM) layers, on the 2017 PhysioNet challenge dataset. The obtained results demonstrate that the proposed approach efficiently represents ECG signals through SCF coefficients, leading to the accurate detection of AF with an average accuracy of 92.76% and an average F1-score of 89.1%.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100370"},"PeriodicalIF":0.0,"publicationDate":"2024-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142699625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An ensemble convolutional neural network model for brain stroke prediction using brain computed tomography images","authors":"Most. Jannatul Ferdous,&nbsp;Rifat Shahriyar","doi":"10.1016/j.health.2024.100368","DOIUrl":"10.1016/j.health.2024.100368","url":null,"abstract":"<div><div>A stroke is a potentially fatal brain attack that causes an interruption in the blood supply to the brain. As a result, brain cells start to die due to a lack of oxygen and nutrients. After a stroke, every minute is critical. A million or more brain cells perish every minute during a stroke. The prompt identification of a stroke can prevent lasting brain damage or even save the patient’s life. Doctors advise computed tomography (CT) images of the brain for earlier stroke detection. If doctors delay CT diagnosis or may make erroneous diagnoses, this can be life-threatening. For that reason, an automatic diagnosis of stroke from a brain CT scan image will be beneficial for stroke patients. This study moderates three pre-trained convolutional neural network (CNN) models named Inceptionv3, MobileNetv2, and Xception by updating the top layer of those models using the transfer-learning technique based on CT images of the brain. A new ensemble convolutional neural network (ENSNET) model is proposed for automatic brain stroke prediction from brain CT scan images. ENSNET is the average of two improved CNN models named InceptionV3 and Xception. We have relied on the following metrics: accuracy, precision, recall, f1-score, confusion matrix, accuracy versus epoch, loss versus epoch, and the receiver operating characteristic (ROC) curve to assess performance matrices. The accuracy of the moderated Inceptionv3 is 97.48%, the moderated MobileNetv2 is 83.29%, and the moderated Xception is 96.11%. Nonetheless, the suggested ensemble model ENSNET performs better than the other models when it comes to the diagnosis of stroke from brain CT scans, providing 98.86% accuracy, 97.71% precision, 98.46% recall, 98.08% f1-score, and 98.74% area under the ROC curve(AUC). Therefore, the proposed model ENSNET can detect strokes from computed tomography images of the brain more successfully than other models.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100368"},"PeriodicalIF":0.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hierarchical Bayesian approach for identifying socioeconomic factors influencing self-rated health in Japan","authors":"Makoto Nakakita ,&nbsp;Teruo Nakatsuma","doi":"10.1016/j.health.2024.100367","DOIUrl":"10.1016/j.health.2024.100367","url":null,"abstract":"<div><div>This study identifies socioeconomic factors that potentially influence self-rated health (SRH), an important indicator of health status, in the Japanese population. We used a panel data logit model to simultaneously estimate the effects of personal attributes, living environment, and social conditions. To achieve a stable estimation of the panel data logit model, we applied hierarchical Bayesian modeling and the Markov Chain Monte Carlo (MCMC) method to obtain its estimation. Furthermore, we used the ancillary-sufficiency interweaving strategy (ASIS) algorithm to improve the efficiency of the MCMC method for the panel data logit model. The results indicate that SRH within the Japanese population is affected by demographic and socioeconomic factors (e.g., age, marital status, educational background, and employment status) and daily habits such as frequency of drinking alcohol. We also obtained results that differed from previous studies in the research literature. Differences in the national character among countries may be reflected in these results. Since SRH is a subjective measure of health status and often differs from actual health status, it is crucial to remove the influences of the national character on SRH in evaluating the actual health status of individuals within a population. The study findings provide important insights into addressing these factors to understand SRH in the Japanese context better.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100367"},"PeriodicalIF":0.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142537361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An electrocardiogram signal classification using a hybrid machine learning and deep learning approach","authors":"Faramarz Zabihi ,&nbsp;Fatemeh Safara ,&nbsp;Behrouz Ahadzadeh","doi":"10.1016/j.health.2024.100366","DOIUrl":"10.1016/j.health.2024.100366","url":null,"abstract":"<div><div>An electrocardiogram (ECG) is a diagnostic tool that captures the electrical activity of the heart. Any irregularity in the heart's electrical system is referred to as an arrhythmia, which can be identified through the analysis of ECG signals. Timely diagnosis of cardiac arrhythmias is crucial in order to mitigate their potentially harmful consequences. However, manual analysis of ECG signals is time-consuming and prone to inaccuracies. Therefore, researchers have developed medical decision support systems that utilize machine learning techniques to automate the analysis of ECG signals. In this study, we propose a novel method for classifying ECG signals into four distinct types of heartbeats: normal, supraventricular, ventricular, and fusion. Our method consists of two subsystems that integrate both machine learning and deep learning approaches. The first subsystem uses a residual network block to extract features from the input ECG signal, followed by an LSTM network for learning and classification of these features. The second subsystem uses several feature extraction methods and a random forest to classify the ECG signals. Furthermore, it employs a Synthetic Minority Over-Sampling Technique to improve dataset balance and overall performance. The ultimate result is achieved by merging the results of both subsystems together. An assessment of our approach was carried out on the MIT-BIH dataset, which acts as a recognized ECG signal classification benchmark. Our technique attained an impressive accuracy rate of 99.26%, ranking it as one of the most superior methods in the current literature. Our findings demonstrate the effectiveness and efficiency of our approach in accurately classifying ECG signals for arrhythmia detection.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100366"},"PeriodicalIF":0.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An inter-hospital performance assessment model for evaluating hospitals performing hip arthroplasty","authors":"Fabian Dehanne ,&nbsp;Magali Pirson ,&nbsp;Etienne Cuvelier ,&nbsp;Frédéric Bielen ,&nbsp;Pol Leclercq ,&nbsp;Benoît Libert ,&nbsp;Maximilien Gourdin","doi":"10.1016/j.health.2024.100365","DOIUrl":"10.1016/j.health.2024.100365","url":null,"abstract":"<div><div>The value of hospital care to patients is expressed as a combination of reduced healthcare costs, fewer medical complications, and improved patient satisfaction. Few studies highlight the value hospitals provide to their patients through hip replacement surgery.</div><div>This study aims to define a methodology for inter-hospital comparison purposes that can assess the value of hip replacement management to patients by using indicators of costs, medical complications, and patient outcomes.</div><div>We identified medical complications and costs from medico-administrative data collected by three hospitals. We associated a Disability Adjusted Life Years (DALYs) impact with medical complications, readmissions (within 30 days), and hospital mortality. Costs were analysed from a social security perspective. Patient outcomes were collected through a questionnaire-based survey after hip surgery. To compare the three hospitals, we created a composite indicator by standardizing each dependent variable and combining a weighting of importance provided by patients.</div><div>This study analysed 342 hospital stays. The mean (standard deviation) number of DALYs per stay was estimated to be more than 0.0028 (0.016) for a mean (standard deviation) cost of €4,834 (€3,665). The composite indicator allowed hospitals to be ranked and areas for improvement to be identified. In our case mix, Hospital 3 is the lowest-ranked hospital, with excessively high costs and a relatively low level of satisfaction compared to the others.</div><div>The simultaneous evaluation of medical complications, patient outcomes, and costs is a prerequisite for quality improvement efforts by managers and practitioners. In our opinion, this experiment, which sought to estimate the value hospitals bring to patients, may be viewed as the first step towards value-based purchasing in Belgium.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100365"},"PeriodicalIF":0.0,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A data envelopment analysis model for optimizing transfer time of ischemic stroke patients under endovascular thrombectomy","authors":"Mirpouya Mirmozaffari,&nbsp;Noreen Kamal","doi":"10.1016/j.health.2024.100364","DOIUrl":"10.1016/j.health.2024.100364","url":null,"abstract":"<div><div>This study applies Data Envelopment Analysis (DEA) to optimize transfer times and futile transfers of eligible ischemic stroke patients receiving Endovascular Thrombosis (EVT) in Primary Stroke Centers (PSC) in Nova Scotia. The study aims to assess healthcare delivery in Nova Scotia over two periods. It seeks to improve stroke care for rural populations by examining nine inputs, including age and distance between PSCs and the Comprehensive Stroke Centre (CSC) that provided EVT treatment, concerning a single output variable: whether EVT is performed or not. In the first phase, 115 patients were treated as Decision-Making Units (DMUs) for ten PSCs by applying an input-oriented Variable Returns to Scale (VRS) assisted by super-efficiency analysis using the Python-based PyDEA tool. This tool is known for its unrestricted capacity to handle DMUs, inputs, and outputs. In the second phase, eight PSCs with low patient numbers were merged into four DMUs, each consisting of two PSCs. These two merged PSCs have limited patients, and the selected PSCs are also geographically close. Two PSCs have been kept separate because they had sufficient patient volume. In the first phase, VRS generated more reasonable efficiency scores for evaluation, while in the second phase, Constant Returns to Scale (CRS) outperformed VRS, yielding better results. In the initial stage of the second phase, ten PSCs were considered as six DMUs using the input-oriented CRS and VRS for 115 patients. Super-efficiency measures were applied in this stage to improve the evaluation process further. In the second part of the second phase, a comparison between the first period (2018–2019) and the second period (2020–2021) was conducted using the Malmquist Productivity Index (MPI), considering CRS and VRS to evaluate the relative efficiency and productivity change of six DMUs over time.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100364"},"PeriodicalIF":0.0,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142319289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An investigation of Susceptible–Exposed–Infectious–Recovered (SEIR) tuberculosis model dynamics with pseudo-recovery and psychological effect","authors":"Yudi Ari Adi ,&nbsp;Suparman","doi":"10.1016/j.health.2024.100361","DOIUrl":"10.1016/j.health.2024.100361","url":null,"abstract":"<div><div>Tuberculosis is one of the most pressing issues of the modern era, posing a severe health risk to humans in recent decades. This study proposes a Susceptible–Exposed–Infectious–Recovered (SEIR) tuberculosis epidemic transmission model with psychological effects and pseudo-recovery. We consider a compartmental mathematical model in which the entire population is divided into four compartments based on their natural features. The model is validated, and parameter values are estimated using Indonesian data from 2002 to 2022. To investigate their epidemiological significance, we proved the positivity and boundedness of solutions, as well as the local and global stability of equilibria. Sensitivity analysis is used to find the most influential parameters with the most significant influence on the basic reproduction number, <span><math><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub></math></span>. The bifurcation procedure tools of the center manifold theory are used to conduct a bifurcation study. Mathematical conditions ensure the inferred event of forward bifurcation. We performed numerical simulations that support our theoretical findings.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100361"},"PeriodicalIF":0.0,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142323345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel integrated logistic regression model enhanced with recursive feature elimination and explainable artificial intelligence for dementia prediction","authors":"Rasel Ahmed ,&nbsp;Nafiz Fahad ,&nbsp;Md Saef Ullah Miah ,&nbsp;Md. Jakir Hossen ,&nbsp;Md. Kishor Morol ,&nbsp;Mufti Mahmud ,&nbsp;M. Mostafizur Rahman","doi":"10.1016/j.health.2024.100362","DOIUrl":"10.1016/j.health.2024.100362","url":null,"abstract":"<div><p>Dementia is a major global health issue that significantly impacts millions of individuals, families, and societies worldwide, creating a substantial burden on healthcare systems. This study introduces a novel approach for predicting dementia by employing the Logistic Regression (LR) model, enhanced with Recursive Feature Elimination (RFE), applied to a unique dataset comprising 1000 patients, with 49.60% male and 50.40% female. The LR model, recognized for its simplicity and effectiveness in binary classification tasks, is optimized through RFE, a technique that iteratively eliminates less significant features to improve model performance. The model’s effectiveness was assessed using comprehensive metrics, including accuracy, precision, recall, F1-score, Matthews Correlation Coefficient (MCC), and Kappa score. Furthermore, SHapley Additive exPlanations (SHAP) values were employed to increase the interpretability of the model, providing insights into the most influential features for dementia prediction. To address the issue of overfitting, a standardization technique was implemented, which enhanced the model’s predictive performance. The findings of this study hold potential implications for early dementia detection, informing intervention strategies, and optimizing healthcare resource allocation.</p></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100362"},"PeriodicalIF":0.0,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772442524000649/pdfft?md5=1b759d8a985cabb4b185f0a36f88797f&pid=1-s2.0-S2772442524000649-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Markov cohort model for Endoscopic surveillance and management of Barrett’s esophagus","authors":"Ravi Vissapragada ,&nbsp;Norma B. Bulamu ,&nbsp;Roger Yazbeck ,&nbsp;Jonathan Karnon ,&nbsp;David I. Watson","doi":"10.1016/j.health.2024.100360","DOIUrl":"10.1016/j.health.2024.100360","url":null,"abstract":"<div><p>Barrett's esophagus is an asymptomatic precursor to esophageal adenocarcinoma. Its rising incidence due to lifestyle factors, coupled with healthcare costs, requires cost-effective alternatives for surveillance. We propose a decision-analytic Markov cohort model to simulate Barrett's esophagus's natural progression to esophageal adenocarcinoma using TreeAge Pro. Health states include metaplasia (non-dysplastic Barrett's esophagus), low-grade dysplasia, high-grade dysplasia, and esophageal adenocarcinoma. Triplicates of these health states represent one non-stratified and two risk-stratified cohorts for devising risk-based strategies. A cycle length of six months and a time horizon of 35 years, totaling 70 cycles, is considered. Model inputs are derived from literature and, when unavailable from an extensive local database of 1087 patients (5081 person-years) from March 2003–2021, cleaned and analyzed with Rstudio (R version 3.6.3). Specific tests included descriptive statistics, Cox-proportional hazard models, and graphing. A seven-step calibration process is performed for risk-stratified and non-stratified groups simultaneously to match the progression to high-grade dysplasia and esophageal adenocarcinoma. This allows comparison between risk- and non-risk-based strategies. The calibration process included input parameterization, optimization, goodness of fit calculation, selection of sets meeting convergence criteria, and integration into probabilistic sensitivity analysis. This process generated 10,187 sets of transition probabilities, with 4358 meeting convergence criteria, ensuring equal model outputs in all groups. Mortality was 10.7% for cancer-related deaths, matching literature values. This process provides a robust framework for evaluating Barrett's esophagus progression and management strategies, supporting informed decision-making in healthcare.</p></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"6 ","pages":"Article 100360"},"PeriodicalIF":0.0,"publicationDate":"2024-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2772442524000625/pdfft?md5=39571667386e7018b829933792fd6ca7&pid=1-s2.0-S2772442524000625-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142147835","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}