International Journal of Telemedicine and Applications最新文献

Behçet's disease (BD) is one of the most difficult diseases to diagnose in the field of rheumatic immune diseases because it is rare, has many different symptoms, and we do not know much about how it works. Instead of trying to make a direct clinical diagnosis, this study was set up as an exploratory investigation to find out more about BD and figure out which clinical and laboratory features are most important. To accomplish this, clinical data were gathered from 148 patients (76 with bipolar disorder and 72 with rheumatoid arthritis) at the Rheumatology Clinic of King Abdulaziz University. We used several machine learning (ML) algorithms, such as decision tree, bagging, random forest (RF), XGBoost, and support vector machines (SVMs), to see if they could learn patterns that set BD apart from other rheumatic diseases. We used three different methods to find out how important each feature was: built-in model importance, permutation-based analysis, and Shapley additive explanation (SHAP) values. The ML models worked well, with the RF getting the best accuracy (96.7%) and an area under the curve (AUC) of 1.0. XGBoost came in second with an AUC of 0.9985. The feature analysis showed that the results were partially in line with established diagnostic criteria (Japan, ISG, and ICBD), with oral ulcers being the most important feature. Overall, this study serves as an exploratory framework to deepen understanding of BD's distinctive characteristics and underlying feature interactions, offering insights that can inform future diagnostic support systems rather than serving as a diagnostic tool itself.

Background: The UAE's rapid economic growth and adoption of advanced healthcare technologies necessitate understanding pharmacists' perspectives on large language models (LLMs) to address implementation challenges and align with the nation's digital health initiatives.

Aim: This study explored UAE pharmacists' perceived benefits, concerns, and barriers to LLM adoption, as well as factors contributing to heightened concerns in community pharmacies.

Methods: A survey-based cross-sectional study was conducted among 528 community pharmacists (51.3% female) in the UAE between October and November 2024. Pharmacists completed a validated questionnaire assessing socio-demographic information, perceived benefits, concerns, and barriers related to LLM use. Binary logistic regression was applied to identify factors associated with concerns about LLMs.

Results: The least-perceived benefits of LLMs included providing around-the-clock support (37.3%), designing personalized care plans (74.4%), and improving patient outcomes (77.0%). Barriers included the need for human supervision (54.7%), insufficient training (32.4%), lack of pharmacy-focused LLM programs (28.4%), and inadequate resources (28.4%). Key concerns were technical failures or downtime (97.5%), hacking vulnerabilities (97.2%) and limited capacity for empathy, cultural understanding, or ethical considerations in healthcare (95.6%). Increased age was significantly associated with greater concerns (OR = 1.124, p < 0.001). Conversely, pharmacists with master's or doctoral degrees (OR = 0.483, p = 0.008) and those likely to use LLMs in the future (OR = 0.357, p < 0.001) expressed fewer concerns.

Conclusion: The integration of LLMs into community pharmacy practice faces challenges, including hacking risks, security vulnerabilities, insufficient empathy, and technical failures. Targeted interventions such as enhanced training, robust security measures, and tailored LLM solutions are essential to address these barriers and support safe adoption in pharmacy settings.

Background: Informed consent (IC) is essential in medical decision-making, ensuring that patients and their families fully understand the consequences of treatment options. In pediatric surgery, however, the process is often inadequate due to limited consultation time, high parental anxiety, and widespread misinformation. This study evaluates the effectiveness of the "ChPedBo" smartphone application in improving parental understanding and reducing preoperative anxiety.

Methods: A prospective observational study was conducted at the Department of Pediatric Surgery, IRCCS Sant'Orsola-Malpighi University Hospital of Bologna. A total of 150 questionnaires were distributed to parents of children scheduled for elective surgery; 100 completed questionnaires were included in the final analysis. Parents completed a structured 9-item questionnaire assessing knowledge, anxiety, usefulness, and satisfaction before and after using the "ChPedBo" app. Statistical analysis included the Wilcoxon signed-rank test, with a significance threshold set at p < 0.05.

Results: Parental knowledge of their child's condition significantly improved after using the app, with mean scores increasing from 2.39 to 3.14 (p = 3.88 × 10^-6). Similarly, comprehension of the surgical procedure improved from 2.27 to 3.20 (p = 1.71 × 10^-6). Preoperative anxiety levels decreased from 1.64 to 1.36 (p = 0.0073). The app was rated highly useful (mean score 2.64) and received a high overall satisfaction rating (mean score 2.70).

Conclusions: The "ChPedBo" app significantly enhanced parental understanding and reduced preoperative anxiety, demonstrating its potential as a valuable digital tool in the IC process for pediatric surgery. Future studies should explore its application in emergency settings and its long-term impact.

Introduction: Pressure injuries are injuries caused by reduced blood circulation over regular and repetitive periods when applying pressure to a specific area of the body. This incident requires daily prevention and health promotion to prevent its occurrence.

Objective: To develop and evaluate a virtual board game with guidelines for pressure injury prevention for nurses specializing in stoma therapy.

Methodology: This is an applied, exploratory, and descriptive technological development study. The game was developed in stages consisting of: conceptual review, definition of the game dynamics, initial design of the board and cards, creation of the cards, and definition of the components. The study stages include development with a specialist team, testing and validation of the platform with specialist nurses, and subsequently, release of the final product.

Results: The results showed high acceptance of the game among the 17 participants, with emphasis on high levels of engagement and learning (≥ 94% reported acquiring new knowledge), ease of use (≥ 82% strongly agreed with the intuitiveness of the interface), and intention to continue using it (94% expressed a desire to continue using and recommend the tool). The main limitations identified were related to technical difficulties during installation and the lack of interactive features for multiple users.

Conclusion: The results of this study reinforce the potential of gamification as a complementary and innovative strategy for teaching stomatherapy. The prototype proved to be an effective and well-accepted tool for educating nurses on pressure injury prevention, with significant potential for improving knowledge and clinical practice. It is believed that gamification, combined with theoretical teaching and practical learning, can mobilize and engage participants, significantly contributing to the development of highly qualified professionals and, consequently, improving the quality of patient care.

Objective: The widespread use of telepsychiatry requires a better understanding of its integration into routine practice. Using the normalisation process theory (NPT), we aimed to measure and explore Australian psychiatrists' normalisation of telepsychiatry into private practice.

Methods: This convergent parallel-mixed methods study consists of an online survey of private psychiatrists using the Normalisation Measures Development (NoMAD) instrument and semistructured in-depth interviews of private psychiatrists. We measured normalisation levels by the NPT constructs. We used logistic regression analyses to examine individual (psychiatrist) and practice factors for higher telepsychiatry patient load. We also thematically analysed the interviews according to the NPT. Finally, we integrated the quantitative and qualitative findings and drew inferences on factors for greater telepsychiatry integration.

Results: We surveyed 110 respondents. Higher cognitive participation and collective action were associated with greater telepsychiatry use (> 50% patient load). The high-load group was less likely to view telepsychiatry as different from usual work practice. Solo practices, and practices covering nonmetropolitan areas, were associated with a higher telepsychiatry load. Thirteen interviews were conducted. Telepsychiatry was largely regarded as equivalent, accessible, flexible and efficient. A conducive environment (resources, policy frameworks and general acceptance) promoted adoption. Telepsychiatry's adverse effects on work quality and well-being and its limitations and potential misuse were noted. In implementing telepsychiatry, perceived similarity to conventional consultations, bottom-up initiatives tailored to individual needs, confidence and skills and personal appreciation of its benefits were important.

Conclusions: Telepsychiatry is a useful tool that can be successfully integrated into routine private practice with adequate support.

Background: Long COVID still challenges healthcare systems worldwide. Tailored treatments are scarce. In the ErgoLoCo study, we have developed and tested a telehealth-delivered occupational therapy intervention for people affected by long COVID. Acceptability from both recipients and providers is a prerequisite for implementing such new interventions.

Aim: This study is aimed at exploring the perceptions of people with long COVID and occupational therapists regarding the intervention's acceptability and telehealth delivery approaches.

Methods: Semistructured interviews were conducted with 13 participants who experience long COVID and received the ErgoLoCo intervention delivered as teletherapy sessions or prerecorded videos. Eight occupational therapists who guided the teletherapy sessions participated in a focus group. Materials were analyzed following qualitative descriptive methods and interpreted using the theoretical framework of acceptability (TFA).

Results: Occupational therapists and long COVID clients considered the occupational therapy approach a positive experience. While all participants in the teletherapy group found the occupational therapy approach helpful in coping with long COVID symptoms and regaining participation in meaningful occupations, perceptions varied in the group supplied with prerecorded videos. Some saw the intervention as helpful, but all emphasized the need for professional support from occupational therapists to use the program more effectively. The occupational therapists emphasized the need to tailor the therapy content to clients' needs to ensure effective and successful management of occupational challenges.

Discussion: The study highlights telehealth-delivered occupational therapy's potential benefits and challenges for individuals with long COVID. It contributes to understanding the challenges and potential of telehealth-delivered occupational therapy for long COVID rehabilitation. This study's key finding is the importance of personalized and professionally guided telehealth interventions. Trial Registration: German Clinical Trial Registry identifier DRKS00029990.

Background: A variety of patient populations receive allergen immunotherapy (AIT), but clinicians still lack an effective electronic platform to manage them.

Methods: We designed a platform based on the framework of value set extraction standardization, integration, and structurization. Average medication scoring (AMS) and other electronic medical records were developed and stored on a MySQL database. Data storage is hosted on cloud servers, linked to a mobile application, Bluetooth lung function monitoring, and a dedicated website that acts as a front-end.

Results: Since 2015, 23,847 patients in 48 hospitals with AIT prescriptions were included. Of these patients, the median age was 15 (interquartile range, 10-27) years. Allergic rhinitis was the most common disorder and accounted for 9753 (40.9%) of the cases. Five hundred and thirty-three basic data elements and six independent modules were constructed for the platform to facilitate the physicians in establishing SCIT projects, symptom scores, AMS, lung function tests, and follow-up appointments. One hundred and twelve drugs including 10 dosage forms were identified from an internal list of the dataset. The unit score was calculated based on the action mechanism of the medicine. The AMS formula has six parameters: total dose, frequency, period, unit score, unit dose, and follow-up days. A lower AMS suggests a better treatment efficacy.

Conclusion: The program presented our experience in developing, pilot testing, and evaluating an electronic AIT platform, and future research would indicate whether the template could be made more time efficient in clinical practice.

Objective: Anemia remains a major public health concern among pregnant women, significantly contributing to maternal and infant morbidity and mortality. With advances in digital technology, particularly machine learning (ML), there is potential to enhance early detection and prevention strategies. This scoping review is aimed at synthesizing the existing literature on the application of ML-based digital tools for predicting and preventing anemia in pregnant women.

Methods: Following the PRISMA-ScR guidelines, this review included articles from PubMed, Scopus, and Google Scholar published between 2015 and 2024. Eligibility criteria included studies using ML methods for anemia prediction in pregnant women. Extracted data included study population, ML algorithms used, and performance metrics. Due to the scoping nature of this review, risk of bias assessment was not conducted.

Results: A total of 11 studies met the inclusion criteria, utilizing various ML algorithms such as decision trees, random forest, support vector machines, naive Bayes, K-nearest neighbors, PART, fuzzy Tsukamoto, and boosting algorithms. Comparative analysis based on performance metrics (accuracy, precision, recall, F1-score, and AUC) identified boosting and random forest as the most effective models in resource-limited settings. However, heterogeneity in data sources, evaluation metrics, and populations limits generalizability.

Conclusions: ML-based models demonstrate considerable promise in predicting anemia among pregnant women. However, further validation across diverse datasets, clearer articulation of methodological strengths and limitations, and attention to implementation feasibility in low-resource settings are needed.

Teledermatology is increasingly recognized as a valuable tool for expanding access to dermatologic care, particularly in underserved and remote settings. This randomized prospective cohort study, the first of its kind in the region, examined the diagnostic and treatment concordance of teledermatologists compared to in-clinic dermatologists, with a focus on the impact of image acquisition methods. A total of 360 adult patients presenting for dermatologic evaluation at the American University of Beirut Medical Center were enrolled. Each patient contributed three sets of skin lesion photographs: unassisted patient-taken, assisted patient-taken after brief standardized training, and resident-taken under clinical conditions. Using a store-and-forward model, teledermatologists reviewed one randomized image set per patient. Their diagnoses and treatment decisions were compared to in-person assessments, which served as the reference standard. Diagnostic concordance improved with image quality: 79% for unassisted patient images, 84% for assisted images, and 87% for resident-taken images. Treatment concordance similarly increased from 38% to 44% to 45%, while the need to request additional history declined from 64% to 47%. Acne showed the highest diagnostic match across all image types. These findings support the clinical validity of store-and-forward teledermatology and highlight the value of patient education in improving image quality and diagnostic outcomes. As the first regional study to systematically evaluate real-world image acquisition methods, it offers a practical roadmap for integrating teledermatology into routine dermatologic care.

The growing advancements in science, technology, innovation, and research are paralleled by a concerning rise in stress levels worldwide. Stress, an inevitable psychosocial factor, significantly affects human life, mental status, and overall physiosocial health. This research focuses on developing an accurate galvanic skin response (GSR) system to effectively identify and analyze stress levels. The core concept of GSR involves measuring the conductivity between skin contacts, where increased conductivity corresponds to heightened stress levels. Advanced algorithms are employed to efficiently convert these readings into digital formats for precise analysis. The system leverages the Kalman filter algorithm to reduce noise, ensuring smooth and reliable signals from raw GSR readings. A dynamic range normalization technique transforms filtered readings into a consistent scale (0-500) tailored to individual baseline values. This approach ensures that stable measurements are unaffected by noise using the Kalman filter, consistency across users despite physiological differences, and accurate, personalized stress-level detection through adaptive categorization. Tested on over 5000 samples, the system accurately identifies stress levels across defined ranges, established in collaboration with psychologist practitioners. This research culminates in developing an accurate and personalized stress detection and analysis system, providing actionable insights into stress management.