Search Results (103)

In recent years, Electronic Medical Record (EMR) sharing has played an indispensable role in optimizing clinical treatment plans, advancing medical research in biomedical science. However, existing EMR management schemes often face security risks and suffer from inefficient search performance. To address these issues, this paper proposes a secure EMR sharing scheme based on blockchain and searchable encryption. This scheme implements a decentralized management system with enhanced security and operational efficiency. Considering the scenario of EMRs requiring confirmation of multiple doctors to improve safety, the proposed solution leverages Shamir’s Secret Sharing to enable multi-party authorization, thereby enhancing privacy protection. Meanwhile, the scheme utilizes Bloom filter and vector operation to achieve efficient data search. The proposed method maintains rigorous EMR protection while improving the search efficiency of EMRs. Experimental results demonstrate that, compared to existing methodologies, the proposed scheme enhances security during EMR sharing processes. It achieves higher efficiency in index generation and trapdoor generation while reducing keyword search time. This scheme provides reliable technical support for the development of intelligent healthcare systems. Full article

Background: Sharing substance use disorder (SUD) data is essential for advancing equitable healthcare and improving outcomes for marginalized populations. However, concerns about privacy, stigma, and adherence to data privacy regulations often hinder effective data sharing. This study explores patient preferences and considerations related to sharing SUD-related medical records, with a focus on the sociocultural and systemic factors that shape their willingness to share. Methods: A total of 357 adult patients from four community-based clinics in Arizona participated in a cross-sectional electronic survey. The survey assessed sociodemographic factors, experiences of stigma (self-directed, anticipated, and provider-based), trust in healthcare providers, satisfaction with care, and willingness to share SUD data across various scenarios. Data were analyzed using descriptive statistics, Pearson correlations, and one-way ANOVA to uncover key associations. Results: Patients identified SUD history, diagnoses, and treatment information as particularly sensitive. Stigma was significantly correlated with increased sensitivity and reduced willingness to share data, especially with providers outside their primary facility (p < 0.001). In contrast, trust in providers and higher satisfaction with care were linked to greater willingness to share data with all providers (p < 0.01). Patients were more inclined to share SUD data during emergencies or for direct treatment purposes than for administrative or research applications (p < 0.001). Discussion: These findings underscore the ethical imperative to address stigma and foster trust to promote equitable SUD data sharing. Policies must empower patients with control over sensitive health information while ensuring cultural competence and fairness in care delivery. Ensuring that patients feel confident in how their data are used may encourage greater participation in health information exchange, ultimately supporting more effective and individualized SUD care. Full article

Secure and privacy-preserving health status representation learning has become a critical challenge in clinical prediction systems. While deep learning models require substantial high-quality data for training, electronic health records are often restricted by strict privacy regulations and institutional policies, particularly during emerging health crises. Traditional approaches to data integration across medical institutions face significant privacy and security challenges, as healthcare providers cannot directly share patient data. This work presents MultiProg, a secure federated learning framework for clinical representation learning. Our approach enables multiple medical institutions to collaborate without exchanging raw patient data, maintaining data locality while improving model performance. The framework employs a multi-channel architecture where institutions share only the low-level feature extraction layers, protecting sensitive patient information. We introduce a feature calibration mechanism that ensures robust performance even with heterogeneous feature sets across different institutions. Through extensive experiments, we demonstrate that the framework successfully enables secure knowledge sharing across institutions without compromising sensitive patient data, achieving enhanced predictive capabilities compared to isolated institutional models. Compared to state-of-the-art methods, our approach achieves the best performance across multiple datasets with statistically significant improvements. Full article

This study proposes DtMin, a novel protocol for implementing data minimization principles in medical information sharing between healthcare providers (HCPs) and electronic health record providers (EHRPs). DtMin utilizes a multi-type encryption approach, combining attribute-based encryption (ABE) and hybrid encryption techniques. The protocol classifies patient data attributes into six categories based on sensitivity, consent status, and sharing requests. It then applies differential encryption methods to ensure only the intersection of patient-consented and EHRP-requested attributes is shared in decipherable form. DtMin’s security is formally analyzed and proven under the ICR-DB and ICR-IS security games. Performance analysis demonstrates efficiency across various data volumes and patient numbers. This study explores the integration of DtMin with advanced cryptographic techniques such as lattice-based ABE and lightweight ABE variants, which can potentially enhance its performance and security in complex healthcare environments. Furthermore, it proposes strategies for integrating DtMin with existing healthcare information systems and adapting it to future big data environments processing over 100,000 records. These enhancements and integration strategies position DtMin as a scalable and practical solution for implementing data minimization in diverse healthcare settings, from small clinics to large-scale health information exchanges. Full article

Background/Objectives: Artificial intelligence-based software as a medical device (AI-SaMD) refers to AI-powered software used for medical purposes without being embedded in physical devices. Despite increasing approvals over the past decade, research in this domain—spanning technology, healthcare, and national security—remains limited. This research aims to bridge the existing research gap in AI-SaMD by systematically reviewing the literature from the past decade, with the aim of classifying key findings, identifying critical challenges, and synthesizing insights related to technological, clinical, and regulatory aspects of AI-SaMD. Methods: A systematic literature review based on the PRISMA framework was performed to select the relevant AI-SaMD studies published between 2015 and 2024 in order to uncover key themes such as publication venues, geographical trends, key challenges, and research gaps. Results: Most studies focus on specialized clinical settings like radiology and ophthalmology rather than general clinical practice. Key challenges to implement AI-SaMD include regulatory issues (e.g., regulatory frameworks), AI malpractice (e.g., explainability and expert oversight), and data governance (e.g., privacy and data sharing). Existing research emphasizes the importance of (1) addressing the regulatory problems through the specific duties of regulatory authorities, (2) interdisciplinary collaboration, (3) clinician training, (4) the seamless integration of AI-SaMD with healthcare software systems (e.g., electronic health records), and (5) the rigorous validation of AI-SaMD models to ensure effective implementation. Conclusions: This study offers valuable insights for diverse stakeholders, emphasizing the need to move beyond theoretical analyses and prioritize practical, experimental research to advance the real-world application of AI-SaMDs. This study concludes by outlining future research directions and emphasizing the limitations of the predominantly theoretical approaches currently available. Full article

Background: Children with medical complexity (CMC), a subset of children with special healthcare needs, have chronic conditions affecting multiple organ systems, require medical technology, and account for a significant share of pediatric healthcare spending despite comprising only 1% of the population. Their families experience unique stressors, including financial strain and high rates of workforce attrition, suggesting medical inequity is an independent risk factor for health inequity. The role of universal caregiver stress screening using a validated tool within the outpatient primary care medical home for CMC youth has not been explored in the literature. Methods: Caregivers of all patients in the Complex Care Program (CCP) within a large academic pediatric primary care Medical Home-certified practice at the Children’s National Hospital were screened for caregiver stress during routine primary care appointments using the University of Washington Caregiver Stress Scale 8-Item Short Form V. 2.0 (UW-CSS). Elevated scores prompted referrals to the CCP psychosocial team, and composite scores were recorded in the electronic medical record. Demographics, medical diagnoses, and technology support status were extracted from the medical chart. The childhood opportunity index (COI) was calculated as a proxy for socioeconomic position. Results: Screening for caregiver stress in our medical home for CMC was feasible and yielded unexpected results. We found no difference in levels of stress among caregivers based on the COI. This finding highlights the importance of universal rather than targeted screening. Future directions include measuring the impact of targeted interventions for families who initially screen positive via longitudinal follow-up. Conclusions: Screening for caregiver stress in a primary care medical home for CMC is feasible. As no single variable alone was a predictor of high caregiver stress, universal screening seems to be the most appropriate strategy to capture all families at the highest risk. Full article

As the medical information systems continue to develop, the sharing of electronic medical records (EMRs) is becoming a vital tool for improving the quality and efficiency of medical services. However, during the process of sharing EMRs, establishing mutual-trust relationships and increasing users’ participation are urgent problems to be solved. Current solutions mainly focus on incentive mechanisms for users’ honest and active participation, but often ignore the potential impact of research institutions’ behavior on users’ trust and participation. To address this, this paper proposes an incentive mechanism based on evolutionary game theory. It combines the unchangeable nature of blockchain and the dynamic adjustment characteristics of evolutionary games to build a secure and trustworthy incentive system. This system considers the potential malicious behaviors of both users and research institutions, encouraging research institutions to protect users’ privacy, reduce users’ concerns, and guide users to actively contribute data. At the same time, it ensures data security and system trust through clear rewards and punishments. Based on this, we have carried out a comprehensive simulation using game theory. The results confirm that our designed incentive mechanism can effectively achieve its expected goals. Full article

We sought to incorporate a community-based solution with a family health history (FHH) clinical support program (MeTree) integrated into well-patient appointments with the novel partnership of a public health state-level health information exchange (HIE). The Arkansas—Making History pilot project tested informatics compatibility among these systems and the patients’ electronic medical record (EPIC) in a rural clinic in the north central region of the state, having the state HIE as a means for patients to store and share their FHHs across multiple healthcare providers with updates in real time. We monitored for unexpected issues during the pilot and asked for the perspectives of patients and healthcare providers throughout the project to have a clear understanding of how to implement this project on a larger scale. The greatest barrier to project implementation was the inability of the state HIE to host or share the FHH data. We compensated for the lack of systems compatibility and documented valuable information about patient acceptability and usability of the MeTree platform, as well as gleaning important clinical outcome data from those who completed MeTree FHH accounts in an underserved area. Rural patients need additional technological support in the larger scaling of this project, both in available linkages to community clinics with patient-controlled options for how their data is stored and shared and in Internet connectivity and software options available for ease of use. Full article

Approximately 50% of Alzheimer’s disease (AD) patients develop psychotic symptoms, leading to a subtype known as psychosis in AD (AD + P), which is associated with accelerated cognitive decline compared to AD without psychosis. Currently, no FDA-approved medication specifically addresses AD + P. This study aims to improve psychosis predictions and identify potential therapeutic agents using the DeepBiomarker deep learning model by incorporating drug–target interactions. Electronic health records from the University of Pittsburgh Medical Center were analyzed to predict psychosis within three months of AD diagnosis. AD + P patients were classified as those with either a formal psychosis diagnosis or antipsychotic prescriptions post-AD diagnosis. Two approaches were employed as follows: (1) a drug-focused method using individual medications and (2) a target-focused method pooling medications by shared targets. The updated DeepBiomarker model achieved an area under the receiver operating curve (AUROC) above 0.90 for psychosis prediction. A drug-focused analysis identified gabapentin, amlodipine, levothyroxine, and others as potentially beneficial. A target-focused analysis highlighted significant proteins, including integrins, calcium channels, and tyrosine hydroxylase, confirming several medications linked to these targets. Integrating drug–target information into predictive models improves the identification of medications for AD + P risk reduction, offering a promising strategy for therapeutic development. Full article

The COVID-19 pandemic exposed critical vulnerabilities in global healthcare systems, particularly in data security and interoperability. This paper introduces the blockHealthSecure Framework, which integrates blockchain technology with advanced cybersecurity measures to address these weaknesses and build resilient post-pandemic healthcare systems. Blockchain’s decentralized and immutable architecture enhances the accuracy, transparency, and protection of electronic medical records (EMRs) and sensitive healthcare data. Additionally, it facilitates seamless and secure data sharing among healthcare providers, addressing long-standing interoperability challenges. This study explores the challenges and benefits of blockchain integration in healthcare, with a focus on regulatory and ethical considerations such as HIPAA and GDPR compliance. Key contributions include detailed case studies and examples that demonstrate blockchain’s ability to mitigate risks like ransomware, insider threats, and data breaches. This framework’s design leverages smart contracts, cryptographic hashing, and zero-trust architecture to ensure secure data management and proactive threat mitigation. The findings emphasize the framework’s potential to enhance data security, improve system adaptability, and support regulatory compliance in the face of evolving healthcare challenges. By bridging existing gaps in healthcare cybersecurity, the blockHealthSecure Framework offers a scalable, future-proof solution for safeguarding health outcomes and preparing for global health crises. Full article

Introduction: The ongoing care of transgender patients in United Kingdom (UK) general practice (GP) is hampered by a lack of UK primary care guidelines regarding the monitoring of treatments, despite the key role that general practice has in holistic lifelong care. This quality improvement project aimed to audit the monitoring of treatments and health screening in a GP practice population, across two large practices in southwest England, in order to drive local improvement and to identify gaps in wider healthcare support for this population. Methods: This project updated a previously published audit instrument, incorporating a novel, pragmatic standard, based on up-to-date UK gender clinic guidelines and the UK population screening programmes. National Health Service (NHS) Health Research Authority and Medical Research Council processes were used to confirm that this quality improvement project did not require formal ethics committee approval. An audit against this standard was performed for 176 transgender and gender-minority patients, to provide data on the consistency of the monitoring of gender hormonal treatments and reminders for appropriate population health screening programmes. Results: A total of 16% of those undergoing hormonal treatments had received optimal monitoring; 20% were missing the most basic hormone level monitoring. Reminders regarding appropriate health screening were rare in patients who had changed the gender markers on their electronic record. Long waiting lists, the use of private clinics, confusion around responsibilities shared between primary and secondary care and growing complex co-morbidity were demonstrated. Conclusions: This project supports previous calls for consistent evidence-based guidelines, improved data systems and adequately resourced primary and secondary care services to support the safe and effective lifelong care of transgender patients. Full article

Electronic health record (EHR) de-identification is crucial for publishing or sharing medical data without violating the patient’s privacy. Protected health information (PHI) is abundant in EHRs, and privacy regulations worldwide mandate de-identification before downstream tasks are performed. The ever-growing data generation in healthcare and the advent of generative artificial intelligence have increased the demand for de-identified EHRs and highlighted privacy issues with large language models (LLMs), especially data transmission to cloud-based LLMs. In this study, we benchmark ten LLMs for de-identifying EHRs in English and German. We then compare de-identification performance for in-context learning and full model fine-tuning and analyze the limitations of LLMs for this task. Our experimental evaluation shows that LLMs effectively de-identify EHRs in both languages. Moreover, in-context learning with a one-shot setting boosts de-identification performance without the costly full fine-tuning of the LLMs. Full article

Electronic health records (EHRs) are widely used in healthcare institutions worldwide, containing vast amounts of unstructured textual data. However, the sensitive nature of Protected Health Information (PHI) embedded within these records presents significant privacy challenges, necessitating robust de-identification techniques. This paper introduces a novel approach, leveraging a Bi-LSTM-CRF model to achieve accurate and reliable PHI de-identification, using the i2b2 dataset sourced from Harvard University. Unlike prior studies that often unify Bi-LSTM and CRF layers, our approach focuses on the individual design, optimization, and hyperparameter tuning of both the Bi-LSTM and CRF components, allowing for precise model performance improvements. This rigorous approach to architectural design and hyperparameter tuning, often underexplored in the existing literature, significantly enhances the model’s capacity for accurate PHI tag detection while preserving the essential clinical context. Comprehensive evaluations are conducted across 23 PHI categories, as defined by HIPAA, ensuring thorough security across critical domains. The optimized model achieves exceptional performance metrics, with a precision of 99%, recall of 98%, and F1-score of 98%, underscoring its effectiveness in balancing recall and precision. By enabling the de-identification of medical records, this research strengthens patient confidentiality, promotes compliance with privacy regulations, and facilitates safe data sharing for research and analysis. Full article

Background/Objectives: Earlier detection of severe immune-related hematological adverse events (irHAEs) in cancer patients treated with a PD-1 or PD-L1 inhibitor is critical to improving treatment outcomes. The study aimed to develop a simple machine learning (ML) model for predicting irHAEs associated with PD-1/PD-L1 inhibitors. Methods: We utilized the Observational Medical Outcomes Partnership–Common Data Model based on electronic medical records from a tertiary (KHMC) and a secondary (KHNMC) hospital in South Korea. Severe irHAEs were defined as Grades 3–5 by the Common Terminology Criteria for Adverse Events (version 5.0). The predictive model was developed using the KHMC dataset, and then cross-validated against an independent cohort (KHNMC). The full ML models were then simplified by selecting critical features based on the feature importance values (FIVs). Results: Overall, 397 and 255 patients were included in the primary (KHMC) and cross-validation (KHNMC) cohort, respectively. Among the tested ML algorithms, random forest achieved the highest accuracy (area under the receiver operating characteristic curve [AUROC] 0.88 for both cohorts). Parsimonious models reduced to 50% FIVs of the full models showed comparable performance to the full models (AUROC 0.83–0.86, p > 0.05). The KHMC and KHNMC parsimonious models shared common predictive features including furosemide, oxygen gas, piperacillin/tazobactam, and acetylcysteine. Conclusions: Considering the simplicity and adequate predictive performance, our simplified ML models might be easily implemented in clinical practice with broad applicability. Our model might enhance early diagnostic screening of irHAEs induced by PD-1/PD-L1 inhibitors, contributing to minimizing the risk of severe irHAEs and improving the effectiveness of cancer immunotherapy. Full article

(1) Background: With the increasing digitalization of healthcare systems, data security and privacy have become crucial issues. In parallel, blockchain technology has gradually proven to be an innovative solution to address this challenge, as its ability to provide an immutable and secure record of transactions offers significant promise for healthcare information management. This systematic review aims to explore the applications of blockchain in health information systems, highlighting its advantages and challenges. (2) Methods: The publications chosen to compose this review were collected from six databases, resulting in the initial identification of 4864 studies. Of these, 73 were selected for in-depth analysis. (3) Results: The main results show that blockchain has been used mainly in electronic health records (63%). Furthermore, it was used in the Internet of Medical Things (8.2%) and for data sharing during the COVID-19 pandemic (6.8%). As advantages, greater security, privacy, and data integrity were identified, while the challenges point to the need for standardization and regulatory issues. (4) Conclusions: Despite the difficulties encountered, blockchain has significant potential to improve healthcare data management. However, more research and continued collaboration between those involved are needed to maximize its benefits. Full article