Health Informatics Journal最新文献

Objective: This study presents a structured evaluation of large language models (LLMs) in predicting suicide methods based exclusively on indirect forensic psychiatric indicators. Methods: Ninety-two forensic psychiatric cases (2019-2024), involving survivors of suicide attempts formally examined in medico-legal contexts, were retrospectively analyzed. Variables included age, sex, psychiatric diagnosis, previous suicide attempts, psychiatric medication use, impulsivity, and consciousness at emergency admission. Six LLMs were tested: ChatGPT-4o, ChatGPT-4o Mini, ChatGPT-O3 (OpenAI), Gemini 2.0 Flash, Gemini 2.5 Pro, and Gemini 2.5 Flash (Google DeepMind). Each case was converted into a standardized anonymized prompt. Model predictions were categorized by blinded forensic physicians and evaluated using accuracy, precision, recall, F1-score, and Cohen's Kappa for 1-month reproducibility. Results: Gemini 2.5 Flash achieved the highest performance with 76.09% accuracy, 46.9% F1-score, and 45.2% recall. It accurately predicted the dominant method, medication overdose, but underperformed for rare categories. Temporal reproducibility was moderate (κ = 0.582), while other models exhibited lower and less stable performance. Conclusion: LLMs can infer suicide methods from indirect psychiatric data with encouraging accuracy. However, limitations in detecting rare methods and maintaining temporal consistency suggest the need for further methodological refinement and external validation prior to forensic application.

Background: The rapid expansion of digital health services (DHS) highlights the need to assess their accessibility and effectiveness, particularly among older adults. Despite increasing digitalization, many older individuals still face barriers, including limitations in digital competence and access. Objective: This study examines the use, barriers, and perceived benefits of DHS among individuals aged 75 and older in Finland. Methods: A nationwide survey was conducted in March 2023 using both electronic and paper questionnaires. In addition to descriptive analysis, regression analysis was performed to identify variables associated with perceived benefits of digital health services. Results: Of the 1124 responses (1011 electronic, 113 paper), 1100 were fully completed. Overall, 84% of respondents had used DHS, with usage being higher among those under 85 years (87%) than those over 85 (57%). The majority of respondents (82%) reported using the national Omakanta service, which grants access to personal health information. Digital competence and the number of services used were the strongest predictors of perceived benefits, alongside higher satisfaction, service frequency, and female gender. Conclusions: DHS adoption among older adults, especially in Finland, may be higher than previously reported. However, digital social services remain underdeveloped. Addressing the digital divide is essential to ensuring equitable access.

Background: The introduction of the RTS, S (Mosquirix®) malaria vaccine in Cameroon represents a significant public health milestone. This study analyzed social media sentiment surrounding the vaccine rollout using natural language processing and machine learning. Methods: Data from Twitter (X) and Facebook (Meta) regarding the RTS, S vaccine in Cameroon was analyzed using the Hugging Face Transformer library for sentiment evaluation. The data was pre-processed, cleaned, and visualized with Matplotlib. Results: The sentiment analysis revealed that 42.0% of reactions were negative, 40.0% were positive, and 18.0% were neutral, indicating a nearly even split between skeptical and supportive viewpoints among Cameroonian users regarding the vaccine rollout. Conclusion: The research highlights the necessity for targeted communication strategies to address public concerns and foster vaccine confidence. Sentiment analysis can act as a real-time tool, offering policymakers valuable insights into public reactions and attitudes toward immunization and other health initiatives. These findings reveal significant public skepticism that must be addressed through evidence-based communication strategies focused on vaccine safety, efficacy data from pilot programs, and engagement with community leaders to counter misinformation.

Introduction: Patients increasingly use chatbots to obtain medical information, a trend that has provoked both optimism and pessimism. Numerous studies have evaluated the quality and readability of these outputs. This study synthesizes these findings through a cross-sectional meta-synthesis. Methods: We identified studies that evaluated responses using the DISCERN instrument, designed to assess the quality of written material. Additionally, we only included studies that also evaluated readability. We recorded the chatbot used, DISCERN scores, the number of words in each question, the number of questions asked, the number of DISCERN evaluators, the readability of responses, and the year the study was conducted. We also assessed the influence of each publication's journal ranking using the Journal Citation Indicator. Results: We identified 42 studies that conducted 86 tests. Chatbot response readability decreased as response quality increased. Forty-nine tests produced responses ranked "good" or better, and only 10 scored below college-level readability. We significantly increased readability by adding the phrase "write responses at sixth-grade reading level" to prompts that previously produced post-graduate reading level responses in published studies. Discussion: Variable quality and poor readability of chatbot responses reinforce pessimism about their utility. Nevertheless, appropriate "prompt engineering" provides scope to enhance response quality and readability.

Objectives: Digital patient-reported outcome (PRO) tools, though beneficial for managing inflammatory bowel disease (IBD), remain underutilized in Australia. This study aimed to investigate a group of Australian patients' readiness to engage with digital PRO tools and identify potential barriers to their implementation. Methods: We assessed 58 patients from a tertiary IBD clinic in Melbourne, Australia, using the Readiness and Enablement Index for Health Technology (ReadHy) tool, and compared the results to those from a Danish study. Results: Compared to the Danish cohort, our patients were younger with more frequent users of electronic devices, showed higher readiness across most ReadHy dimensions, except in the "heiQ8 Emotional Distress" dimension. Conclusion: These findings suggest a generally favourable environment for implementing digital PRO tools at an Australian tertiary IBD clinic, though attention should be paid to emotional well-being to improve adoption. This study also provides a framework for other centres to evaluate their patients' readiness for digital PRO engagement.

Objective: This study evaluates the feasibility and performance of a cloud-based healthcare blockchain framework that integrates Fully Homomorphic Encryption (FHE), Extended Secure Searchable Encryption (ESSE), and Attribute-Based Signature (ABS) for managing encrypted Personal Health Records (PHRs). Methods: A synthetic dataset of 1,000 anonymized health records, modeled after the publicly available Cell-Phone Brain Tumour dataset (Kaggle), was generated in MATLAB. The dataset emulated attributes typically collected by IoT-enabled or mobile health devices (e.g., usage duration, radiation exposure), although no physical IoT integration was implemented. The cryptographic modules-FHE, ESSE, and ABS-were implemented and simulated in a MATLAB-based cloud environment. System evaluation focused on encryption latency, query throughput, access control accuracy, and overall operational efficiency. Results: The FHE module achieved an average encryption time of 2.5 s and a computation time of 4.8 s per 1 KB record. ESSE sustained 20 encrypted queries per second with an 85% success rate. ABS enforced decentralized access with 97% accuracy and a false positive rate of 0.002%. When integrated, the system reached 94% operational efficiency across simulated healthcare workloads. Conclusion: The proposed FHE-ESSE-ABS framework advances existing healthcare blockchain solutions by enabling encrypted computation, privacy-preserving search, and fine-grained access control. These findings confirm its feasibility for secure cloud-based healthcare data management and establish a foundation for future real-world deployment in health informatics.

To achieve useful interoperability between electronic health record (EHR) systems, many approaches have been proposed. To date, none has prevailed as a clear solution. This scoping review studies 24 publications from 2014 to 2023. The aim is to streamline the understanding of current EHR interoperability expectations, practices, and problems, highlight learnings from the Levels of Conceptual Interoperability Model (LCIM), and suggest means for expediting EHR interoperability. Four interoperability levels are visible in EHR compared to seven in the LCIM: technical/foundational, syntactic/structural, semantic, and process/organization. Semantic interoperability-preserving meaning of exchanged data-is the main focus and the problem to solve. Its many expectations cause implementation difficulty. Standardization of data structures, transfer protocols, terminologies, vocabularies, and ontologies are the most common approach, but there is a lack of consensus on standards. Emerging approaches include fuzzy ontologies, natural language processing, and bidirectional transformation. Standardized data structure is not a prerequisite to useful EHR interoperability. Focusing on the state of health records rather than full system integration can expedite interoperability. Different use cases can benefit from various approaches. Artificial intelligence shows promise for handling semi-structured or unstructured data. Stronger regulations may be necessary to guide ongoing integrations.

Objectives: This study aimed to explore healthcare professionals' views on the use of technology in adult transitional care, identifying challenges, critical procedures, and enabling factors for adoption. Methods: This was a prospective, multisite qualitative study. Data were collected through semi-structured co-creation sessions that explored two main themes, clinical decision-making and technology use in transitional care, through the lenses of current practices, challenges, and future directions. Data were analysed using constant comparison analysis by three independent researchers through iterative open, axial, and selective coding, followed by an impact relationship analysis to explore interconnections between themes. Results: Eleven co-creation sessions were held involving 115 participants. Findings highlight five key transitional care processes, beginning with patient assessment and evaluation, continuing through discharge planning and adherence to protocols, and extending to post-discharge support and follow-up care. The results show how technology can enhance each of these steps by improving digital literacy, user-friendliness, interoperability, and the flow of information. Cross-cutting barriers such as limited resources, privacy concerns, and lack of trust in technology were also identified. Conclusions: Technological tools can support various aspects and processes of transitional care, but their effective adoption requires a distinct set of strategies to address the multiple and complex factors involved.

Objective: To develop and compare the predictive accuracy of machine learning (ML) models for coronary artery calcium (CAC) prediction among firefighters and to evaluate their cross-validated performance against traditional binary logistic regression (BLR). Methods: This study utilized health records from 416 firefighters who underwent comprehensive health screenings at Ascension Public Safety Medical. CAC was assessed using cardiac computed tomography scans. The degree of CAC was measured using the Agatston scores. 17 clinical and lifestyle related risk variables were collected. Machine learning models, including XGBoost, Random Forest (RF), Support Vector Machine (SVM), Naïve Bayes (NB), and K Nearest Neighbor (KNN), were developed and compared. Additionally, the performance of these ML models was evaluated against traditional binary logistic regression (BLR). Results: Among the 416 firefighters, age (r = 0.28, p < 0.0001), glucose levels (r = 0.13, p = 0.001), monocyte percentages (r = 0.13, p = 0.001), and resting systolic blood pressure (r = 0.13, p = 0.009) were positively associated with CAC. While sodium levels (r = -0.11, p = 0.038), GFR (r = -0.17, p = 0.021), and maximum oxygen volumes (r = -0.19, p = 0.0002) were inversely associated with CAC. XGBoost achieved the highest cross-validated area under the curve (AUC) of 0.770, outperforming NB (0.768), SVM (0.765), RF (0.749), KNN (0.671), and BLR (0.658). Conclusion: Our research demonstrates the efficacy of ML algorithms, particularly XGBoost, in enhancing early detection and preventive strategies for CAC among firefighters. These advancements are crucial for proactive health management in this high-risk group, potentially mitigating risks associated with their demanding profession.

Objective: The study aimed to assess the predictors and the reasons for refusal to participate in a digitally supported remote maintenance pulmonary rehabilitation programme (M-PRP). Methods: Patients contacted to integrate a 12-month M-PRP were assessed for clinical and sociodemographic characteristics and completed a series of 11 questionnaires including digital literacy (MDPQ-16), personality traits (BFI-10) and reasons for refusal. Results: Of the 136 patients included, 78 accepted the M-PRP and 58 refused (43%). The likelihood of refusal was associated with low forced expiratory volume in 1s (FEV₁), body mass index, neuroticism (BFI-10) and MDPQ-16. Main reasons for refusal were programme constraints (47%), intention to continue physical activity alone (45%), and lack of information technologies (IT) equipment (29%). Conclusion: Digital M-PRP rejection is a common problem. Disease severity and technology issues are main barriers. Particular attention should be paid to patients who state they intend to continue on their own, given conflicting literature data.