Informatics in Medicine Unlocked最新文献

Making scribes and prescriptions are the primary activities for a health professional to serve the patients. Although in most of the cases these tasks are pursued manually, a few studies focused on developing digital scribe generation and prescription systems. Moreover, to enhance the effectiveness and adoption of such digital scribe and prescription systems, these systems should be intelligent and useable enough. Therefore, the objective of this research is to understand the user requirements for developing an automated scribes and intelligent prescribing system for health professionals and to develop the automated scribes and intelligent prescribing system based on the revealed users' requirements. And finally, to evaluate the performance of the proposed system. To attain these objectives, a requirement elicitation study was carried out following the semi-structured interviews to reveal the user requirements for an intelligent scribe and prescription system. The study proposed an automated digital scribe that can record medical information adopting the LSTM model; and also be able to generate automated prescriptions based on a doctor's voice command. Finally, the system was evaluated through an empirical study where participants (doctors) were asked to generate scribes and provide prescriptions manually and also by using the proposed system. The study found that the scribes and prescriptions generated using the proposed system are highly similar to the scribes (87.5 %) and prescriptions (96.2 %) generated manually. Analysis of the evaluation results also showed that the system provides a user-friendly, easy-to-use, intuitive, and interactive interface to facilitate the doctors and clinicians.

Background

As the use of technology has increased, a set of problematic psychological behaviors associated with internet use has evolved. This bibliometric research aims to discover and analyze internet addiction (IA) articles trends from 1996 to 2022.

Methods

This research is based on a bibliometric examination of internet addiction papers published between 1996 and 2022. The Scopus database was utilized to extract the needed documents, examine citation patterns and publication growth, and identify prolific authors and institutions.

Results

There were 9692 publications on internet addiction from 1996 to 2022, with an average of 359 documents each year. A total of 21906 authors contributed to the literature, with the majority of publications (86.9%) being multi-authored. The United States (US) ranked first in terms of volume of publications (18.8%, n = 1819), followed by China (12.3%, n = 1194), the United Kingdom (8.3%, n = 808), and Turkey (6.2%, n = 602). However, the majority of the productive institutions were located in East Asia.

Conclusion

There is a substantial body of literature on internet addiction, with numerous worldwide collaborations. As IA will be a lingering problem with the increased digitization of all sectors, future research should focus on emerging topics such as social media and gaming addiction. Internet addiction among adolescents in particular is a key research area.

This paper introduces a novel clustering approach based on Minkowski's mathematical similarity to improve EEG feature selection for classification and have efficient Particle Swarm Optimization (PSO) in the context of machine learning. Given the intricacy of high-dimensional medical datasets, feature selection plays a critical role in preventing disease and promoting public health. By employing Minkowski clustering, the objective is to group dataset records into two clusters exhibiting high feature coherence, thereby improving accuracy by applying optimization techniques like PSO to select the most optimal features. Furthermore, the proposed model can be extended to intelligent datasets, including EEG and others. As fewer features are needed for precise categorization, intelligent feature selection is an advanced step of machine learning. This paper investigates the key factors influencing feature selection in the EEG Bonn University dataset. The proposed system is compared against various optimization and feature selection methods, demonstrating superior performance in analyzing and classifying EEG signals based on accuracy measures. The experimental results have confirmed the effectiveness of the suggested model as a valuable tool for EEG data classification, achieving up to 100% accuracy. The outcomes of this research have the potential to benefit medical experts in related specialties by streamlining the process of identifying and diagnosing brain disorders. Technically, the machine learning algorithms RF, KNN, SVM, NB, and DT are employed to classify the selected features.

Speech impairments, resulting from brain injuries, mental disorders, or vocal abuse, substantially affect an individual’s quality of life and can lead to social isolation. Brain–Computer Interfaces (BCIs), particularly those based on EEG, offer a promising support mechanism by harnessing brain signals. Owing to their clinical efficacy, cost-effective EEG devices, and expanding applications in the medical and social spheres, their usage has surged. This study introduces an ensemble-based feature engineering mechanism to pinpoint the optimal brain rhythm, channel subset, and feature set for accurately predicting imagined words from EEG signals via machine learning models. Leveraging the 2020 International BCI competition dataset, we employed bandpass filtering, channel wrapping, and ranking methods were applied to discern suitable brain rhythms and features associated with imagined speech. Subsequent application of kernel-based principal component analysis enabled us to compress the feature space dimensionality. We then trained various machine learning models, among which the kNN model excelled, achieving an average accuracy of 73% in a 10-fold cross-validation scheme ,surpassing 18% higher than the existing literature. The Gamma rhythm was identified as the most predictive of imagined speech from EEG brain signals. These advancements herald a new era of more precise and effective BCIs, poised to significantly improve the lives of those with speech impairments.

Introduction

There is a need for designing non-invasive methods to predict blood glucose levels to ensure timely diagnosis of Diabetes Mellitus. Needle anxiety and bleeding disorders preclude many from undertaking blood tests.

Objectives

The primary objective of this study was to assess if biomarkers like saliva can be used to estimate blood glucose levels. The second objective was to develop and evaluate Machine Learning (ML) models to predict blood glucose levels based on salivary glucose and associated features. An insight into the patient's features, which was important for predicting blood glucose levels, was also required.

Methods

A cross-sectional study was conducted, and blood and saliva samples, along with patient-related data, were collected from healthy and diabetic patients. ML techniques were applied to the data to develop a tool for predicting blood glucose levels using patient features. The prediction intervals were computed, clinical accuracy was assessed, and important features for the prediction were identified.

Results

The Random Forest Regressor Model, with features identified using the wrapper method, was selected as the best, with an average RMSE of 43.28. The prediction intervals were computed for point estimate, MAE = 23.821, and coverage was 100 percent, the clinical accuracy was compared with that of glucometers and continuous monitoring systems. All predicted values are in Zones A and B of the Clarke error grid, and the bias was 6.41. The most important feature for predicting blood glucose level is salivary glucose level, followed by known risk factors like Family History, BMI, etc. The study found that salivary glucose levels are insufficient to classify blood glucose levels as high or normal.

Conclusion

The study concluded that salivary glucose with associated patient features could be a potential non-invasive biomarker for predicting blood glucose levels in patients. The developed ML model could be deployed in a device that inputs patient features, analyzes salivary glucose, and can monitor blood glucose levels in a non-invasive manner. Further research is needed to validate the findings of this study and develop a proof of concept.

Background:

Data catalogues are used in multiple domains to provide an overview of databases’ characteristics without releasing the actual data. Despite the existence of several web-based catalogues, they do not always meet the needs of certain domains. In the healthcare field, they need to give multiple and iterative views to the data, from high-level metadata up to low-level samples or patient data. This approach is critical to help researchers find relevant datasets for their studies.

Methods:

In this paper, we present MONTRA2, a web platform for profiling distributed databases. The users’ requirements were designed in the context of the EHDEN European project, in close collaboration with medical researchers, data owners, and pharmaceutical companies, leading to a rich set of functionalities to support databases and cohorts discovery. The platform was developed with a modular architecture which simplifies the integration of internal and external services.

Results:

MONTRA2 is successfully being used in several European projects and research initiatives, focused on the dissemination and sharing of biomedical databases. In this paper, we present three health data catalogues that were built upon the core of this framework. MONTRA2 is publicly available under the MIT license at https://github.com/bioinformatics-ua/montra2.

Conclusions:

The execution of federated studies on a large scale and involving multiple centres is only possible if adequate tools for data management and discovery are available. By providing tools for study management, database characterisation and publishing, among others, MONTRA2 simplifies the process of setting up a workspace for a community to expose the characteristics of datasets and provide multiple strategies for data analysis.

Image segmentation, a crucial process of dividing images into distinct parts or objects, has witnessed remarkable advancements with the emergence of deep learning (DL) techniques. The use of layers in deep neural networks, like object form recognition in higher layers and basic edge identification in lower layers, has markedly improved the quality and accuracy of image segmentation. Consequently, DL using picture segmentation has become commonplace, video analysis, facial recognition, etc. Grasping the applications, algorithms, current performance, and challenges are crucial for advancing DL-based medical image segmentation. However, there is a lack of studies delving into the latest state-of-the-art developments in this field. Therefore, this survey aimed to thoroughly explore the most recent applications of DL-based medical image segmentation, encompassing an in-depth analysis of various commonly used datasets, pre-processing techniques and DL algorithms. This study also investigated the state-of-the-art advancement done in DL-based medical image segmentation by analyzing their results and experimental details. Finally, this study discussed the challenges and future research directions of DL-based medical image segmentation. Overall, this survey provides a comprehensive insight into DL-based medical image segmentation by covering its application domains, model exploration, analysis of state-of-the-art results, challenges, and research directions—a valuable resource for multidisciplinary studies.

A deterministic mathematical model for Hepatitis A infection is established and subsequently examined to optimize control strategies. The model incorporates three time-dependent controls: vaccination, health education, and hygiene compliance, focusing on mitigating disease transmission in the community. The derivation of the basic reproduction number was conducted using the Next-Generation Matrix (NGM) technique, which was subsequently utilized to analyze the stability of the equilibria of the model. The optimal control problem is established and analyzed using Pontryagin’s Maximum principle. The numerical simulation of the optimal control problem is achieved via Runge–Kutta fourth-order schemes (forward and backward sweeps). The numerical findings demonstrate a significant reduction in Hepatitis A cases by implementing at least one control measure. Besides that, it has been established that coupling vaccination, health education and hygiene compliance results in the lowest number of cases, making it an optimal option for eradicating Hepatitis A in the community. However, applying this strategy could be more costlier. As such, the cost-effective analysis was carried out via an incremental cost-effectiveness ratio approach to ascertain the most cost-effective strategy. The findings confirmed that the vaccination strategy was the most cost-effective approach among the strategies under consideration because it offers the minimum number of cases at the minimum cost. This approach is particularly applicable in situations with constrained resources, a circumstance prevalent in many developing nations.

Integration of voluminous omics data aids to unravel biological complexities associated with different disease phenotypes. Machine learning (ML) approaches provide insightful techniques for systematic multi-omics data integration. In this study, survival prediction of breast cancer patients was undertaken using omics data of 302 female patients from The Cancer Genome Atlas (TCGA). The data included gene expression, miRNA expression, DNA methylation and copy number variation. Three computational multi-ensemble ML pipelines were tested using Support Vector Machine (SVM), Random Forest (RF) and Partial Least Squares-Discriminant Analysis (PLS-DA) algorithms. To overcome the limitations associated with univariate feature selection criteria, the ML pipelines were built along with latent factors obtained by multivariate dimension reduction method. This facilitated investigation of background genetic networks and identification of potential hub genes. Analysis of the results obtained revealed that SVM with PLS-DA method (integrated with gene expression, DNA methylation, and miRNA expression modalities) was the best-performing model with an Area Under Curve (AUC) of 89% and an accuracy of 83% for survival prediction. This study not only corroborated previously reported breast cancer-specific prognostic biomarkers but also predicted additional potential biomarkers. The work demonstrates the effective use of a multi-ensemble ML model with efficient feature selection methods as a robust protocol for cancer genotype to phenotype correlation.

Background

Method

Results

Conclusion