Health Informatics Journal最新文献

Background: Insomnia is common among psychiatric outpatients in Taiwan and often coexists with anxiety and depression. Early insomnia changes may predict long-term depression. Although CBT-I is effective, face-to-face therapy requires many resources. This study evaluated the effectiveness of a chatbot to enhance access to sleep training. Methods: This study recruited 80 patients from a psychosomatic outpatient clinic in Taiwan and randomly assigned them 1:1 to the intervention or control group. Due to withdrawals or incomplete assessments, 35 in the intervention group and 31 in the control group completed all procedures. The intervention group used a CBT-I chatbot for 4 weeks, while the control group received basic sleep education via a website. Sleep quality and mental health were assessed using the PSQI, BSRS-5, PHQ-9, BDI, and BAI. Results: The intervention group showed significant PSQI improvement (t (34) = 3.80, p < .001) and reduced BSRS-5, PHQ-9, BDI, and BAI scores (p < .05). The control group showed no significant changes. Conclusions: A CBT-I chatbot significantly enhances sleep and mental health, offering accessible, effective support with broad clinical potential.

Background: Digital health technologies are often subject to regulatory requirements. Regulatory auditing processes are complex but necessary to guarantee quality, efficacy and safety of patients. Evolvements such as digitalized clinical trials, and digital biomarkers require a constant adaption of regulatory frameworks. Objective: This review aims to provide an overview on current regulations and standards for digital therapeutics and digital biomarkers, from technical development to market access. Methods: We conducted an unstructured literature review to identify the relevant guidelines, policies and standards for software based digital therapeutics and digital biomarkers. Results: The principal regulations governing software as a medical device are outlined in Chapter 21 of the Code of Federal Regulations by the US Food and Drug Administration, as well as the European Medical Device Regulation 2017/745. Regulatory pathways, such as the DiGA, are in the process of development, particularly for digital therapeutics, which fall within the purview of software as a medical device. Qualification of (digital) biomarkers is typically voluntary but can play a significant role in the development and approval of digital therapeutics. Conclusions: Fragmented, lacking and diverse regulations around digital biomarkers and digital therapeutics highlight the urge to harmonize and foster regulatory frameworks on an international level.

We develop and validate a clinical guideline-integrated LLM for enhanced sepsis mortality prediction. Using MIMIC-IV data from 24,237 ICU sepsis patients, we fine-tuned a large language model with Low-Rank Adaptation, embedding clinical guidelines into the training process. The model's predictive performance was evaluated using accuracy, F1-score, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Ablation studies assessed the specific contributions of clinical guideline integration. The guideline-enhanced fine-tuned LLM demonstrated moderately higher performance across all evaluation metrics including predictive accuracy (0.819), F1-score (0.815), sensitivity (0.815), specificity (0.822), and AUC (0.852) in predicting mortality risk for septic patients compared to traditional machine learning (highest accuracy: 0.774, AUC: 0.850) and deep learning methods (highest accuracy: 0.762, AUC: 0.841). Ablation experiments demonstrated that explicit integration of clinical guideline knowledge substantially improved performance over both direct prompting (accuracy: 0.709, AUC: 0.706) and fine-tuning without clinical guidelines (accuracy: 0.786, AUC: 0.801). These findings demonstrate that incorporating clinical guidelines into the fine-tuning of large language models outperforms both traditional and deep learning baselines across multiple metrics in sepsis mortality prediction, highlighting the value of explicit domain knowledge integration for clinical AI's robustness.

Introduction: Pediatric restraint orders require frequent renewal to ensure patient safety. Previously, providers depended on nurses paging them upon order expiration, leading to lapses. Methods: In April 2023, we implemented an alerting system in our 38-bed pediatric intensive care unit (PICU) that sent automated text messages to providers upon order expiration. Pediatric wards and adult ICU served as controls. We analyzed 2 years of restraint order data. An unpaired t-test compared pre- and post-intervention. Results: A total of 1394 orders were included (133 PICU, 628 pediatric wards, 633 adult ICU). In the PICU, time without an active order decreased by 39% (2 h 23 min to 1 h 27 min, p = .24) though this result did not reach statistical significance. Conclusion: Despite not reaching statistical significance, this exploratory case study demonstrated that automated EHR alerts may reduce time without an active restraint order. This pilot led the institution's informatics team to system-wide adoption. While promising, such systems must be balanced against risks like provider alarm fatigue.

Objectives: For a population that lacks genetic inheritance knowledge about sickle cell disease/trait, a previously innovative web-based intervention showed significant and sustained knowledge improvement, but current users judged it as "dated." We aimed to modernize the reproductive health intervention, revitalizing its presentation format and providing access to it via all operating systems and browsers. Methods: Young adults (N = 82, mean age 30.3 ± 5.8 years, 76% female, 94% Black, 74% never married) and our interdisciplinary team collaborated in an iterative, user-centered redesign process. We added virtual human narration and interactive interface enhancements to improve accessibility, engagement, and cross-platform compatibility. Functionality testing continued iteratively until all components operated as intended across devices and browsers. Results: After 9 months of redevelopment, the educational program functioned as intended on Windows, Android, and Apple computers and mobile devices. Of the 82 users, 100% enjoyed using it, and 95% indicated it was easy to use. Conclusion: Redevelopment required 6 months longer than expected due to the scope of the updates and integration of advanced features. Designed for an underserved population, the modernized intervention is now undergoing evaluation in a randomized controlled trial. Future directions include the integration of conversational AI and broader application in digital health education.

Objective: COVID-19 has heavily burdened healthcare systems worldwide, underscoring the need for accurate treatment decision-making to optimize patient recovery. This study leverages machine learning (ML) to evaluate how treatments affect the length of stay (LOS) for hospitalized COVID-19 patients in Iran. Method: We analyzed clinical data from 1793 patients with 106 features, identifying key variables through detailed profiles. Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Artificial Neural Network (ANN) models were then used to predict LOS based on personalized COVID-19 treatment regimens. Results: Actemra and Bromhexine exhibited the strongest correlation with LOS. In the first experiment, the models achieved average predictive accuracies of 90.0% (SVM), 89.53% (k-NN), and 86.30% (ANN); in the second experiment, the accuracies were 96.8% (SVM), 89.53% (k-NN), and 94.56% (ANN), demonstrating their effectiveness in forecasting hospital stay durations. Conclusion: Our study showed that medications such as Actemra and Bromhexine were associated with the affected factors for predicting LOS, especially when administered early to patients without major comorbidities. Those with conditions such as cardiovascular disease or diabetes had longer stays. The ML models predicted LOS with high accuracy, demonstrating their potential to assist clinical decisions. Overall, early treatment and predictive modeling can enhance patient outcomes and optimize hospital resource use.

Objectives: This study examined the associations between pesticide exposures, perceived farm stressors, COVID-19-related stressors, and mental health disorders among Thai farmers. Methods: A total of 270 participants were interviewed to assess mental health disorders. Information was also collected on household environments, agricultural activities, and perceived farm- and COVID-19-related stressors. After data preprocessing, 211 samples remained for analysis. Multiple linear regression models were employed as a baseline, and their performance was compared with ensemble tree-based models, which can capture more complex, nonlinear patterns. The Boruta feature selection technique and SHAP scores were used to explain associations between mental health and the independent variables. Results: Lower levels of mental health disorder symptoms were associated with higher levels of personal protective equipment (PPE) use. Certain perceived farm stressors and COVID-19-related stressors were also correlated with mental health outcomes. Conclusions: The findings indicate that greater PPE use and good agricultural practices are associated with reduced symptoms of mental health disorders. This pilot study highlights the potential of machine learning models to explore complex public health issues involving multiple, interrelated factors.

Background: Periodontal disease (PD) is a primary contributor to tooth loss, which negatively affects oral functionality and quality of life. This research aims to investigate the effectiveness of various machine learning (ML) classifiers in identifying PD among U.S. adults. Method: Nineteen features, selected based on prior literature and expert dentist input, were preprocessed using feature engineering techniques. Eleven machine learning classifiers, including basic and ensemble models, were evaluated to identify the best performing model. The interpretability of the model was evaluated using Shapley additive explanations and individual conditional expectation plots to determine key predictors of periodontitis. Results: The predictive efficacy of the ML classifiers is assessed using metrics such as the area under the receiver operating curve (AUC), accuracy, sensitivity, and specificity. The CatBoost classifier performed best in identifying PD. It achieved an AUC of 84.5%, an accuracy of 75.8%, a precision of 75.8%, a sensitivity of 78.8%, and a specificity of 72.5%. Having an annual dentist visit and age emerged as the most influential variables. Conclusions: The ML models utilized in this study exhibited robust predictive performance and can be further improved by incorporating additional clinical parameters. The proposed models effectively identified individuals at high risk for developing PD.

This study aims to combat health misinformation by enhancing the retrieval of credible health information using effective fusion-based techniques. It focuses on clustering-based subset selection to improve data fusion performance. Five clustering methods - two K-means variants, Agglomerative Hierarchical (AH) clustering, BIRCH, and Chameleon - are evaluated for selecting optimal subsets of information retrieval systems. Experiments are conducted on two health-related datasets from the TREC challenge. The selected subsets are used in data fusion to boost retrieval quality and credibility. AH and BIRCH outperform other methods in identifying effective IR subsets. Using AH-based fusion of up to 20 systems results in a 60% gain in MAP and over a 30% increase in NDCG_UCC, a credibility-focused metric, compared to the best single system. Clustering-based fusion strategies significantly enhance the retrieval of trustworthy health content, helping to reduce misinformation. These findings support incorporating advanced data fusion into health information retrieval systems to improve access to reliable information. The source code of this research is publicly available at https://github.com/Gary752752/DataFusion.

Objectives: During the early phase of the COVID-19 outbreak, misinformation spread rapidly, hindering effective health communication and fueling xenophobic violence. The politicization of health issues, along with the manipulation by social bots and astroturfing accounts, posed significant challenges. This study aims to investigate how misinformation spreads through social media, involving malicious actors like trolls and bots, and explores emotional contagion during public health crises. Methods: Using a computational methodology that combines semantic modeling, social network analysis, bot identification, emotion analysis, and time series analysis, the study analyzed over 700,000 tweets from February to July 2020. Results: The findings reveal that inauthentic actors amplified negative emotions, particularly among news and political actors, while positive emotions were less prominent. Astroturfing accounts acted as key nodes, perpetuating negative emotional contagion. Conclusion: This study provides a framework for monitoring emotional responses in public health crises, with findings applicable beyond COVID-19 to other public health emergencies.