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

Diabetic retinopathy (DR) involves retina damage due to diabetes, often leading to blindness. It is diagnosed via color fundus injections, but the manual analysis is cumbersome and error-prone. While computer vision techniques can predict DR stages, they are computationally intensive and struggle with complex data extraction. In this research, our prime objective was to automate the process of DR classification into its various stages using convolutional neural network (CNN) models. We employed the performance of fifteen pre-trained models with our novel proposed diabetic retinopathy network (DRNet13) model. We aimed to discern the most efficient model for accurate diabetic retinopathy (DR) staging based on fundus images from five DR classes. We preprocessed the image using a median filter for noise reduction and Gamma correction for image enhancement. We expanded our dataset from 3662 to 7500 images to create a more generalized training model through various augmentation techniques. We also evaluated multiple evaluation metrics, including accuracy, precision, F1-score, Sensitivity, Specificity, Area under the curve (AUC), Mean Squared Error (MSE), False Positive Rate (FPR), False Negative Rate (FNR), in addition to confusion matrices for an in-depth comparison of the performance of these models. Feature maps were employed to illuminate decision making areas in the DRNet13 model, which achieved a 97 % accuracy rate for DR detection, surpassing other CNN architectures in speed and efficiency. Despite a few misclassifications, the model's capability to identify critical features demonstrates its potential as an impactful diagnostic tool for timely and accurate identification of diabetic retinopathy.

This study introduces a novel fractional-order stochastic epidemic model to analyze the spread of conjunctivitis, a prevalent ocular infection, while accounting for the influence of media awareness on disease transmission. The model incorporates fractional derivatives to capture memory effects and non-local interactions inherent in epidemic processes, allowing for a more accurate representation of disease dynamics. The stability analysis of equilibrium points is carried out based on the basic reproduction number ${ℛ}_0$ and fractional-order $\alpha$. Further, the Hopf bifurcation phenomenon is discussed in this paper. Stochasticity accounts for the randomness in transmission events. The findings of this study provide insights into the complex interrelationship between disease dynamics and media influence, shedding light on the role of public awareness in mitigating or exacerbating conjunctivitis outbreaks. The implications of this work extend to public health policy formulation, highlighting the importance of targeted communication strategies in controlling and preventing the spread of conjunctivitis and similar infectious diseases.

This study introduces the first-ever self-explanatory interface for diagnosing diabetes patients using machine learning. We propose four classification models (Decision Tree (DT), K-nearest Neighbor (KNN), Support Vector Classification (SVC), and Extreme Gradient Boosting (XGB)) based on the publicly available diabetes dataset. To elucidate the inner workings of these models, we employed the machine learning interpretation method known as Shapley Additive Explanations (SHAP). All the models exhibited commendable accuracy in diagnosing patients with diabetes, with the XGB model showing a slight edge over the others. Utilising SHAP, we delved into the XGB model, providing in-depth insights into the reasoning behind its predictions at a granular level. Subsequently, we integrated the XGB model and SHAP’s local explanations into an interface to predict diabetes in patients. This interface serves a critical role as it diagnoses patients and offers transparent explanations for the decisions made, providing users with a heightened awareness of their current health conditions. Given the high-stakes nature of the medical field, this developed interface can be further enhanced by including more extensive clinical data, ultimately aiding medical professionals in their decision-making processes.

The coronavirus pandemic is a global health crisis creating an unprecedented socio-economic catastrophe. This pandemic is the biggest challenge the world has faced since World War II and is the main turning point in the history of humanity. Media coverage can change citizens’ attention to emerging infectious diseases and consequently change individual behaviors and attitudes. This study proposes and analyzes a seven-compartmental mathematical model to investigate the impact of media coverage on the spread and control of COVID-19. The threshold condition Ro for the initial transmission of infection is achieved by the next-generation approach. Stability analysis of the proposed model on disease-free and endemic equilibria is investigated in terms of basic reproduction numbers locally and globally. The sensitivity analysis of the reproduction number is visualized to distinguish the most sensitive parameters that can be regulated to control the transmission dynamics of coronavirus disease. Moreover, the theoretical results of the deterministic model are compared using numerical simulations. The outcomes of the analysis suggest that the disease prevalence can be terminated by suitable management of quarantine/medical care. We further extend the model to the optimal control framework. It is analyzed using Pontryagin’s maximum principle to characterize preventive control, testing facility, and treatment measures for managing COVID-19 transmission.

Autistic Spectrum Disorder (ASD) is a neurological disease characterized by difficulties with social interaction, communication, and repetitive activities. While its primary origin lies in genetics, early detection is crucial, and leveraging machine learning offers a promising avenue for a faster and more cost-effective diagnosis. This study employs diverse machine learning methods to identify crucial ASD traits, aiming to enhance and automate the diagnostic process. We study eight state-of-the-art classification models to determine their effectiveness in ASD detection. We evaluate the models using accuracy, precision, recall, specificity, F1-score, area under the curve (AUC), kappa, and log loss metrics to find the best classifier for these binary datasets. Among all the classification models, for the children dataset, the SVM and LR models achieve the highest accuracy of 100% and for the adult dataset, the LR model produces the highest accuracy of 97.14%. Our proposed ANN model provides the highest accuracy of 94.24% for the new combined dataset when hyperparameters are precisely tuned for each model. As almost all classification models achieve high accuracy which utilize true labels, we become interested in delving into five popular clustering algorithms to understand model behavior in scenarios without true labels. We calculate Normalized Mutual Information (NMI), Adjusted Rand Index (ARI), and Silhouette Coefficient (SC) metrics to select the best clustering models. Our evaluation finds that spectral clustering outperforms all other benchmarking clustering models in terms of NMI and ARI metrics while demonstrating comparability to the optimal SC achieved by k-means. The implemented code is available at GitHub.

Diabetes is a prevalent chronic condition that poses significant challenges to early diagnosis and identifying at-risk individuals. Machine learning plays a crucial role in diabetes detection by leveraging its ability to process large volumes of data and identify complex patterns. However, imbalanced data, where the number of diabetic cases is substantially smaller than non-diabetic cases, complicates the identification of individuals with diabetes using machine learning algorithms. This study focuses on predicting whether a person is at risk of diabetes, considering the individual’s health and socio-economic conditions while mitigating the challenges posed by imbalanced data. We employ several data augmentation techniques, such as oversampling (Synthetic Minority Over Sampling for Nominal Data, i.e.SMOTE-N), undersampling (Edited Nearest Neighbor, i.e. ENN), and hybrid sampling techniques (SMOTE-Tomek and SMOTE-ENN) on training data before applying machine learning algorithms to minimize the impact of imbalanced data. Our study sheds light on the significance of carefully utilizing data augmentation techniques without any data leakage to enhance the effectiveness of machine learning algorithms. Moreover, it offers a complete machine learning structure for healthcare practitioners, from data obtaining to machine learning prediction, enabling them to make informed decisions.

Breast cancer is the second-leading cause of cancer death in women. Breast cells develop into malignant, cancerous lumps, the first signs of breast cancer. Breast cancer can be discovered by the automated diagnostic system when it is still too little to be found by conventional medical methods. Early breast cancers identified with automated screening and diagnosis technologies are generally treatable. This study proposes an enhanced multi-scale deep Convolutional Capsule Neural Network (CapsNet) optimized with Orchard Optimization Algorithm for breast cancer detection. The proposed system consists of preprocessing, feature extraction, segmentation, and classification process. Two input images are taken initially: the Breast Cancer Histopathology Images dataset and the Infrared Thermal Images dataset. The quality of the collected data is improved, and unwanted noises are removed. The features are extracted to segment the image to derive a Region of Interest for effectively segmenting the affected region. Finally, the images are classified as benign/malignant for histopathology images and healthy/cancer for thermal images. The proposed CapsNet is implemented in Python, run for 200 epochs, and compared with existing methods in terms of evaluation metrics. The result shows that the proposed CapsNet attained 99.74 % accuracy, 0.0482 binary entropy loss on the Breast Cancer Histopathology Image dataset and 97 % accuracy, 0.2081 binary entropy loss on the Infrared Thermal Images dataset while incrementing the epochs at each level.

Electromyogram (EMG) signal monitoring is an effective method for controlling the movements of a prosthetic limb. The classification of the EMG pattern of various finger motions in upper-arm amputees has drawn much attention in recent years to develop algorithms that provide adequate accuracy. However, due to the complexity of EMG data, movement detection is a challenging task. Therefore, an effective model is needed that can accurately process, analyze, and classify various hand and finger movements. This paper proposes a novel algorithm for processing and classifying 15 finger movements from surface EMG signals based on Welch power estimation from frequency analysis. Five time-domain features are extracted and trained with a machine learning classifier to classify 15 single fingers and combined finger gestures from eight healthy subjects. The experimental results show 92.30 % classification accuracy considering data from eight channels which was improved to 94.15 % after selecting two channels as dominating. For performance evaluation, 10-fold cross-validation is used during classification. We demonstrate an average accuracy of 92.35 % with 25 % test data.

Care providers in intellectual disability care use various health information systems (HIS) to document the care they provide. This generates a substantial amount of structured and unstructured data with significant potential for reuse, which is currently underexploited. To enhance data reuse, it is important to understand the architecture of health information systems in intellectual disability care, including their commonalities and variabilities (differences), as well as to identify related privacy and security issues. Our study adopts a multiple-case study approach, examining the architectures of four health information systems in the Netherlands. We conducted interviews with seven stakeholders from four HISs and reviewed multiple documents concerning system infrastructure. We identified commonalities and differences between these systems and outlined the primary challenges regarding privacy and security for data reuse. For each HIS, four architectural views were developed: a context diagram, decomposition view, layered view, and deployment view. The study discusses crucial security and privacy aspects for data reuse in intellectual disability care and highlights several challenges that must be addressed to unlock the full potential of this data. This research provides initial guidelines for overcoming these challenges.

Intuitionistic fuzzy sets cannot consider the degree of indeterminacy (i.e., the degree of hesitation). This study presents an intuitionistic fuzzy differential equation approach for the lake water and sediment phosphorus model. We examine the proposed model by assuming generalized trapezoidal intuitionistic fuzzy numbers for the initial condition. Feasible equilibrium points, along with their stability criteria, are evaluated. We describe the characteristics of intuitionistic fuzzy solutions and clarify the difference between strong and weak intuitionistic fuzzy solutions. Numerical simulations are performed in MATLAB to validate the model results.