Frontiers in digital health最新文献

Background: Digital therapeutics (DTx) in the form of mobile health (mHealth) self-management programs have demonstrated effectiveness in reducing disease activity across various diseases, including fibromyalgia and arthritis. However, the content of online self-management programs varies widely, making them difficult to compare.

Aim: This study aims to employ generative artificial intelligence (AI)-based knowledge graphs and network analysis to categorize and structure mHealth content at the example of a fibromyalgia self-management program.

Methods: A multimodal mHealth online self-management program targeting fibromyalgia and post-viral fibromyalgia-like syndromes was developed. In addition to general content, the program was customized to address specific features and digital personas identified through hierarchical agglomerative clustering applied to a cohort of 202 patients with chronic musculoskeletal pain syndromes undergoing multimodal assessment. Text files consisting of 22,150 words divided into 24 modules were used as the input data. Two generative AI web applications, ChatGPT-4 (OpenAI) and Infranodus (Nodus Labs), were used to create knowledge graphs and perform text network analysis, including 3D visualization. A sentiment analysis of 129 patient feedback entries was performed.

Results: The ChatGPT-generated knowledge graph model provided a simple visual overview with five primary edges: "Mental health challenges", "Stress and its impact", "Immune system function", "Long COVID and fibromyalgia" and "Pain management and therapeutic approaches". The 3D visualization provided a more complex knowledge graph, with the term "pain" appearing as the central edge, closely connecting with "sleep", "body", and "stress". Topical cluster analysis identified categories such as "chronic pain management", "sleep hygiene", "immune system function", "cognitive therapy", "healthy eating", "emotional development", "fibromyalgia causes", and "deep relaxation". Gap analysis highlighted missing links, such as between "negative behavior" and "systemic inflammation". Retro-engineering of the self-management program showed significant conceptual similarities between the knowledge graph and the original text analysis. Sentiment analysis of free text patient comments revealed that most relevant topics were addressed by the online program, with the exception of social contacts.

Conclusion: Generative AI tools for text network analysis can effectively structure and illustrate DTx content. Knowledge graphs are valuable for increasing the transparency of self-management programs, developing new conceptual frameworks, and incorporating feedback loops.

In clinical nutrition research, the medical industry chain generates a wealth of multidimensional spatial data across various formats, including text, images, and semi-structured tables. This data's inherent heterogeneity and diversity present significant challenges for processing and mining, which are further compounded by the data's diverse features, which are difficult to extract. To address these challenges, we propose an innovative integration of artificial intelligence (AI) with the medical industry chain data, focusing on constructing semantic knowledge graphs and extracting core features. These knowledge graphs are pivotal for efficiently acquiring insights from the vast and granular big data within the medical industry chain. Our study introduces the Clinical Feature Extraction Knowledge Mapping ( $CFEKM$ ) model, designed to augment the attributes of medical industry chain knowledge graphs through an entity extraction method grounded in syntactic dependency rules. The $CFEKM$ model is applied to real and large-scale datasets within the medical industry chain, demonstrating robust performance in relation extraction, data complementation, and feature extraction. It achieves superior results to several competitive baseline methods, highlighting its effectiveness in handling medical industry chain data complexities. By representing compact semantic knowledge in a structured knowledge graph, our model identifies knowledge gaps and enhances the decision-making process in clinical nutrition research.

Introduction: Operating room (OR) efficiency is a key factor in determining surgical healthcare costs. To enable targeted changes for improving OR efficiency, a comprehensive quantification of the underlying sources of variability contributing to OR efficiency is needed. Previous literature has focused on select stages of the OR process or on aggregate process times influencing efficiency. This study proposes to analyze the OR process in more fine-grained stages to better localize and quantify the impact of important factors.

Methods: Data spanning from 2019-2023 were obtained from a surgery center at a large academic hospital. Linear mixed models were developed to quantify the sources of variability in the OR process. The primary factors analyzed in this study included the primary surgeon, responsible anesthesia provider, primary circulating nurse, and procedure type. The OR process was segmented into eight stages that quantify eight process times, e.g., procedure duration and procedure start time delay. Model selection was performed to identify the key factors in each stage and to quantify variability.

Results: Procedure type accounted for the most variability in three process times and for 44.2% and 45.5% of variability, respectively, in procedure duration and OR time (defined as the total time the patient spent in the OR). Primary surgeon, however, accounted for the most variability in five of the eight process times and accounted for as much as 21.1% of variability. The primary circulating nurse was also found to be significant for all eight process times.

Discussion: The key findings of this study include the following. (1) It is crucial to segment the OR process into smaller, more homogeneous stages to more accurately assess the underlying sources of variability. (2) Variability in the aggregate quantity of OR time appears to mostly reflect the variability in procedure duration, which is a subinterval of OR time. (3) Primary surgeon has a larger effect on OR efficiency than previously reported in the literature and is an important factor throughout the entire OR process. (4) Primary circulating nurse is significant for all stages of the OR process, albeit their effect is small.

The Internet of Medical Things (IoMT) has revolutionized healthcare with remote patient monitoring and real-time diagnosis, but securing patient data remains a critical challenge due to sophisticated cyber threats and the sensitivity of medical information. Traditional machine learning methods struggle to capture the complex patterns in IoMT data, and conventional intrusion detection systems often fail to identify unknown attacks, leading to high false positive rates and compromised patient data security. To address these issues, we propose RCLNet, an effective Anomaly-based Intrusion Detection System (A-IDS) for IoMT. RCLNet employs a multi-faceted approach, including Random Forest (RF) for feature selection, the integration of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models to enhance pattern recognition, and a Self-Adaptive Attention Layer Mechanism (SAALM) designed specifically for the unique challenges of IoMT. Additionally, RCLNet utilizes focal loss (FL) to manage imbalanced data distributions, a common challenge in IoMT datasets. Evaluation using the WUSTL-EHMS-2020 healthcare dataset demonstrates that RCLNet outperforms recent state-of-the-art methods, achieving a remarkable accuracy of 99.78%, highlighting its potential to significantly improve the security and confidentiality of patient data in IoMT healthcare systems.

Introduction: Clinical research increasingly recognizes the role and value of patient-centric data incorporation in trial design, aiming for more relevant, feasible, and engaging studies for participating patients. Despite recognition, research on analytical models regarding qualitative patient data analysis has been insufficient.

Aim: This pilot study aims to explore and demonstrate the analytical framework of the "patient feasibility" concept-a novel approach for integrating patient-centric data into clinical trial design using psychometric latent class analysis (LCA) and interval response theory (IRT) models.

Methods: A qualitative survey was designed to capture the diverse experiences and attitudes of patients in an oncological indication. Results were subjected to content analysis and categorization as a preparatory phase of the study. The analytical phase further employed LCA and hybrid IRT models to discern distinct patient subgroups and characteristics related to patient feasibility.

Results: LCA identified three latent classes each with distinct characteristics pertaining to a latent trait defined as patient feasibility. Covariate analyses further highlighted subgroup behaviors. In addition, IRT analyses using the two-parameter logistic model, generalized partial credit model, and nominal response model highlighted further distinct characteristics of the studied group. The results provided insights into perceived treatment challenges, logistic challenges, and limiting factors regarding the standard of care therapy and clinical trial attitudes.

Introduction: An immobile patient cannot be weighed on a stand-on weighing machine, i.e., a bathroom scale. They have to get weighed while lying, which is not easy. The main objective of this research is to design a medical apparatus that measures the patient's weight in a lying condition. To achieve this the apparatus is designed as a stretcher to carry the patient in and around the hospital.

Methods: The stretcher has four load cells to measure the patient's weight; it can bear a weight of 500 kg and has a self-weight of 20 kg. A Microcontroller unit (MCU) is embedded into the apparatus to weigh the patient lying on it. The stretcher comprises the top frame, middle frame, and base frame. The top frame can be detached and mounted back to the middle frame; this will help the medical personnel shift the patients from a medical bed. The middle frame is a plate structure where the four load cells are mounted at the corners of the lower plate. The upper plate functions as a pressure plate on the load cell. The base plate has four heavy-duty wheels that can bear the load. The middle frame and base frame, together, form a single structure, giving mobility to the structure. A control panel is employed with reset, tare, and on-off buttons to control the embedded platform. The LCD panel on the side of the apparatus shows the weight when the patient is placed on top of the apparatus.

Results and discussion: A prototype trolley equipped with a wireless data logging system was tested on 10 healthy participants. The device accurately measured weight within ±50 g across a scale range of 2-140 kg, with data captured every 30 s over a 5-min testing period. Wireless communication was successfully demonstrated over a 100-m range. The important add-on feature of this work is the apparatus is connected to the internet, transforming it into an IoT-based medical device.

Background: Discharge date prediction plays a crucial role in healthcare management, enabling efficient resource allocation and patient care planning. Accurate estimation of the discharge date can optimize hospital operations and facilitate better patient outcomes.

Materials and methods: In this study, we employed a systematic approach to develop a discharge date prediction model. We collaborated closely with clinical experts to identify relevant data elements that contribute to the prediction accuracy. Feature engineering was used to extract predictive features from both structured and unstructured data sources. XGBoost, a powerful machine learning algorithm, was employed for the prediction task. Furthermore, the developed model was seamlessly integrated into a widely used Electronic Medical Record (EMR) system, ensuring practical usability.

Results: The model achieved a performance surpassing baseline estimates by up to 35.68% in the F1-score. Post-deployment, the model demonstrated operational value by aligning with MS GMLOS and contributing to an 18.96% reduction in excess hospital days.

Conclusions: Our findings highlight the effectiveness and potential value of the developed discharge date prediction model in clinical practice. By improving the accuracy of discharge date estimations, the model has the potential to enhance healthcare resource management and patient care planning. Additional research endeavors should prioritize the evaluation of the model's long-term applicability across diverse scenarios and the comprehensive analysis of its influence on patient outcomes.

Introduction: The incorporation of health-related sensors in wearable devices has increased their use as essential monitoring tools for a wide range of clinical applications. However, the signals obtained from these devices often present challenges such as artifacts, spikes, high-frequency noise, and data gaps, which impede their direct exploitation. Additionally, clinically relevant features are not always readily available. This problem is particularly critical within the H2020 BRAINTEASER project, funded by the European Community, which aims at developing models for the progression of Multiple Sclerosis (MS) and Amyotrophic Lateral Sclerosis (ALS) using data from wearable devices.

Methods: The objective of this study is to present the automated pipeline developed to process signals and extract features from the Garmin Vivoactive 4 smartwatch, which has been chosen as the primary wearable device in the BRAINTEASER project. The proposed pipeline includes a signal processing step, which applies retiming, gap-filling, and denoising algorithms to enhance the quality of the data. The feature extraction step, on the other hand, utilizes clinical partners' knowledge and feedback to select the most relevant variables for analysis.

Results: The performance and effectiveness of the proposed automated pipeline have been evaluated through pivotal beta testing sessions, which demonstrated the ability of the pipeline to improve the data quality and extract features from the data. Further clinical validation of the extracted features will be performed in the upcoming steps of the BRAINTEASER project.

Discussion: Developed in Python, this pipeline can be used by researchers for automated signal processing and feature extraction from wearable devices. It can also be easily adapted or modified to suit the specific requirements of different scenarios.

Digital mental health interventions (DMHIs) have surged in popularity over the last few years. However, adherence to self-guided interventions remains a major hurdle to overcome. The current study utilized a phased implementation design, incorporating diverse samples and contexts to delve into the engagement challenges faced by a recently launched online mental health platform in Brazil with self-evaluation forms. Employing an iterative mixed-methods approach, including focus groups, online surveys, and think-aloud protocols, the research aims to evaluate user satisfaction, identify barriers to adherence, and explore potential hybrid solutions. Engagement in the platform was evaluated by descriptive statistics of the number of instruments completed, and qualitative interviews that were interpreted thematically. In the fully self-guided mode, 2,145 individuals registered, but a substantial majority (88.9%) engaged with the platform for only 1 day, and merely 3.3% completed all activities. In another sample of 50 participants were given a choice between online-only or a hybrid experience with face-to-face meetings. 40% of individuals from the hybrid group completed all activities, compared to 8% in the online-only format. Time constraints emerged as a significant barrier to engagement, with suggested improvements including app development, periodic reminders, and meetings with healthcare professionals. While the study identified weaknesses in the number and length of instruments, personalized results stood out as a major strength. Overall, the findings indicate high satisfaction with the mental health platform but underscore the need for improvements, emphasizing the promise of personalized mental health information and acknowledging persistent barriers in a digital-only setting.

Background: Hospital readmissions pose a challenge for modern healthcare systems. Our aim was to assess the efficacy of telemedicine incorporating telemonitoring of patients' vital signs in decreasing readmissions with a focus on a specific patient population particularly prone to rehospitalization: patients with heart failure (HF) and/or chronic obstructive pulmonary disease (COPD) through a comparative effectiveness systematic review.

Methods: Three major electronic databases, including PubMed, Scopus, and ProQuest's ABI/INFORM, were searched for English-language articles published between 2012 and 2023. The studies included in the review employed telemedicine incorporating telemonitoring technologies and quantified the effect on hospital readmissions in the HF and/or COPD populations.

Results: Thirty scientific articles referencing twenty-nine clinical studies were identified (total of 4,326 patients) and were assessed for risk of bias using the RoB2 (nine moderate risk, six serious risk) and ROBINS-I tools (two moderate risk, two serious risk), and the Newcastle-Ottawa Scale (three good-quality, four fair-quality, two poor-quality). Regarding the primary outcome of our study which was readmissions: the readmission-related outcome most studied was all-cause readmissions followed by HF and acute exacerbation of COPD readmissions. Fourteen studies suggested that telemedicine using telemonitoring decreases the readmission-related burden, while most of the remaining studies suggested that it had a neutral effect on hospital readmissions. Examination of prospective studies focusing on all-cause readmission resulted in the observation of a clearer association in the reduction of all-cause readmissions in patients with COPD compared to patients with HF (100% vs. 8%).

Conclusions: This systematic review suggests that current telemedicine interventions employing telemonitoring instruments can decrease the readmission rates of patients with COPD, but most likely do not impact the readmission-related burden of the HF population. Implementation of novel telemonitoring technologies and conduct of more high-quality studies as well as studies of populations with ≥2 chronic disease are necessary to draw definitive conclusions.

Systematic review registration: This study is registered at the International Platform of Registered Systematic Review and Meta-analysis Protocols (INPLASY), identifier (INPLASY202460097).