Electronic Health Record-Oriented Knowledge Graph System for Collaborative Clinical Decision Support Using Multicenter Fragmented Medical Data: Design and Application Study.

BACKGROUND: The medical knowledge graph provides explainable decision support, helping clinicians with prompt diagnosis and treatment suggestions. However, in real-world clinical practice, patients visit different hospitals seeking various medical services, resulting in fragmented patient data across hospitals. With data security issues, data fragmentation limits the application of knowledge graphs because single-hospital data cannot provide complete evidence for generating precise decision support and comprehensive explanations. It is important to study new methods for knowledge graph systems to integrate into multicenter, information-sensitive medical environments, using fragmented patient records for decision support while maintaining data privacy and security. OBJECTIVE: This study aims to propose an electronic health record (EHR)-oriented knowledge graph system for collaborative reasoning with multicenter fragmented patient medical data, all the while preserving data privacy. METHODS: The study introduced an EHR knowledge graph framework and a novel collaborative reasoning process for utilizing multicenter fragmented information. The system was deployed in each hospital and used a unified semantic structure and Observational Medical Outcomes Partnership (OMOP) vocabulary to standardize the local EHR data set. The system transforms local EHR data into semantic formats and performs semantic reasoning to generate intermediate reasoning findings. The generated intermediate findings used hypernym concepts to isolate original medical data. The intermediate findings and hash-encrypted patient identities were synchronized through a blockchain network. The multicenter intermediate findings were collaborated for final reasoning and clinical decision support without gathering original EHR data. RESULTS: The system underwent evaluation through an application study involving the utilization of multicenter fragmented EHR data to alert non-nephrology clinicians about overlooked patients with chronic kidney disease (CKD). The study covered 1185 patients in nonnephrology departments from 3 hospitals. The patients visited at least two of the hospitals. Of these, 124 patients were identified as meeting CKD diagnosis criteria through collaborative reasoning using multicenter EHR data, whereas the data from individual hospitals alone could not facilitate the identification of CKD in these patients. The assessment by clinicians indicated that 78/91 (86%) patients were CKD positive. CONCLUSIONS: The proposed system was able to effectively utilize multicenter fragmented EHR data for clinical application. The application study showed the clinical benefits of the system with prompt and comprehensive decision support.

Multicenter privacy-preserving model training for deep learning brain metastases autosegmentation.

OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.

Current strategies to address data scarcity in artificial intelligence-based drug discovery: A comprehensive review.

Artificial intelligence (AI) has played a vital role in computer-aided drug design (CADD). This development has been further accelerated with the increasing use of machine learning (ML), mainly deep learning (DL), and computing hardware and software advancements. As a result, initial doubts about the application of AI in drug discovery have been dispelled, leading to significant benefits in medicinal chemistry. At the same time, it is crucial to recognize that AI is still in its infancy and faces a few limitations that need to be addressed to harness its full potential in drug discovery. Some notable limitations are insufficient, unlabeled, and non-uniform data, the resemblance of some AI-generated molecules with existing molecules, unavailability of inadequate benchmarks, intellectual property rights (IPRs) related hurdles in data sharing, poor understanding of biology, focus on proxy data and ligands, lack of holistic methods to represent input (molecular structures) to prevent pre-processing of input molecules (feature engineering), etc. The major component in AI infrastructure is input data, as most of the successes of AI-driven efforts to improve drug discovery depend on the quality and quantity of data, used to train and test AI algorithms, besides a few other factors. Additionally, data-gulping DL approaches, without sufficient data, may collapse to live up to their promise. Current literature suggests a few methods, to certain extent, effectively handle low data for better output from the AI models in the context of drug discovery. These are transferring learning (TL), active learning (AL), single or one-shot learning (OSL), multi-task learning (MTL), data augmentation (DA), data synthesis (DS), etc. One different method, which enables sharing of proprietary data on a common platform (without compromising data privacy) to train ML model, is federated learning (FL). In this review, we compare and discuss these methods, their recent applications, and limitations while modeling small molecule data to get the improved output of AI methods in drug discovery. Article also sums up some other novel methods to handle inadequate data.

European survey: citizens' attitudes on personalized medicine, genetic testing and health data sharing - design and delivery.

In the transformative landscape of healthcare, personalized medicine emerges as a pivotal shift, harnessing genetic, environmental and lifestyle data to tailor medical treatments for enhanced outcomes and cost efficiency. Central to its success is public engagement and consent to share health data amidst rising data privacy concerns. To investigate European public opinion on this paradigm, we executed a comprehensive cross-sectional survey to capture the general public's views on personalized medicine and data-sharing modalities, including digital tools and electronic records. The survey was distributed in eight major European Union countries and the results aim at guiding future policymaking and trust-building measures for secure health data exchange. This article delineates our methodological approach, whereby survey findings will be expounded in subsequent publications.

[Box: see text].

Artificial intelligence and its implications for data privacy.

Contemporary, multidisciplinary research sheds light on data privacy implications of artificial intelligence (AI). This review adopts an AI ecosystem perspective and proposes a process-outcome continuum to classify AI technologies; this perspective helps to understand the nuances of AI relative to psychological aspects of privacy decision-making. Specifically, different types of AI affect traditionally studied privacy decision-making frameworks including the privacy calculus, psychological ownership, and social influence in varied ways. By understanding how the process- or outcome-orientation of an AI technology affects privacy decision-making, we explain how AI creates privacy benefits but also poses challenges. Future research is needed across privacy decision-making, but also more generally at the intersection of privacy and AI, to help foster an ethical, sustainable society.

'I just LOVE data': perceptions and practices of data sharing and privacy among users of the Lioness.

High profile data breaches and the proliferation of self-tracking technologies generating bio-feedback data have raised concerns about data privacy and data sharing practices among users of these devices. However, our understanding of how self-trackers in sexual health populations, where the data may be sensitive, personal, and stigmatising, perceive data privacy and sharing is limited. This study combined industry consultation with a survey of users of the world's first biofeedback smart vibrator, the Lioness, that enables users to monitor and analyse their sexual response intensity and orgasm duration over time. We found users of the Lioness are motivated to self-track by both individual and altruistic goals: to learn more about their bodies, and to contribute to research that leads to better sexual health outcomes. Perceptions of data privacy and data sharing were shaped by an eagerness to collaborate with sexual health researchers to challenge traditional male-centric perspectives in biomedical research on women's sexual health, where gender plays a crucial role in defining healthcare systems and outcomes. This study extends our understanding of the non-digital aspects of self-tracking by emphasising the role of gender and inclusive healthcare advocacy in shaping perceptions of data privacy and sharing within sexual health populations.

Efficient differential privacy enabled federated learning model for detecting COVID-19 disease using chest X-ray images.

The rapid spread of COVID-19 pandemic across the world has not only disturbed the global economy but also raised the demand for accurate disease detection models. Although many studies have proposed effective solutions for the early detection and prediction of COVID-19 with Machine Learning (ML) and Deep learning (DL) based techniques, but these models remain vulnerable to data privacy and security breaches. To overcome the challenges of existing systems, we introduced Adaptive Differential Privacy-based Federated Learning (DPFL) model for predicting COVID-19 disease from chest X-ray images which introduces an innovative adaptive mechanism that dynamically adjusts privacy levels based on real-time data sensitivity analysis, improving the practical applicability of Federated Learning (FL) in diverse healthcare environments. We compared and analyzed the performance of this distributed learning model with a traditional centralized model. Moreover, we enhance the model by integrating a FL approach with an early stopping mechanism to achieve efficient COVID-19 prediction with minimal communication overhead. To ensure privacy without compromising model utility and accuracy, we evaluated the proposed model under various noise scales. Finally, we discussed strategies for increasing the model's accuracy while maintaining robustness as well as privacy.

Continuously monitoring the human machine? - A cross-sectional study to assess the acceptance of wearables in Germany.

Background: Wearables have the potential to transform healthcare by enabling early detection and monitoring of chronic diseases. This study aimed to assess wearables' acceptance, usage, and reasons for non-use. Methods: Anonymous questionnaires were used to collect data in Germany on wearable ownership, usage behaviour, acceptance of health monitoring, and willingness to share data. Results: Out of 643 respondents, 550 participants provided wearable acceptance data. The average age was 36.6 years, with 51.3% female and 39.6% residing in rural areas. Overall, 33.8% reported wearing a wearable, primarily smartwatches or fitness wristbands. Men (63.3%) and women (57.8%) expressed willingness to wear a sensor for health monitoring, and 61.5% were open to sharing data with healthcare providers. Concerns included data security, privacy, and perceived lack of need. Conclusion: The study highlights the acceptance and potential of wearables, particularly for health monitoring and data sharing with healthcare providers. Addressing data security and privacy concerns could enhance the adoption of innovative wearables, such as implants, for early detection and monitoring of chronic diseases.

[Large language models from OpenAI, Google, Meta, X and Co. : The role of "closed" and "open" models in radiology]. / Große Sprachmodelle von OpenAI, Google, Meta, X und Co. : Die Rolle von "closed" und "open" Modellen in der Radiologie.

BACKGROUND: In 2023, the release of ChatGPT triggered an artificial intelligence (AI) boom. The underlying large language models (LLM) of the nonprofit organization "OpenAI" are not freely available under open-source licenses, which does not allow on-site implementation inside secure clinic networks. However, efforts are being made by open-source communities, start-ups and large tech companies to democratize the use of LLMs. This opens up the possibility of using LLMs in a data protection-compliant manner and even adapting them to our own data. OBJECTIVES: This paper aims to explain the potential of privacy-compliant local LLMs for radiology and to provide insights into the "open" versus "closed" dynamics of the currently rapidly developing field of AI. MATERIALS AND METHODS: PubMed search for radiology articles with LLMs and subjective selection of references in the sense of a narrative key topic article. RESULTS: Various stakeholders, including large tech companies such as Meta, Google and X, but also European start-ups such as Mistral AI, contribute to the democratization of LLMs by publishing the models (open weights) or by publishing the model and source code (open source). Their performance is lower than current "closed" LLMs, such as GPT­4 from OpenAI. CONCLUSION: Despite differences in performance, open and thus locally implementable LLMs show great promise for improving the efficiency and quality of diagnostic reporting as well as interaction with patients and enable retrospective extraction of diagnostic information for secondary use of clinical free-text databases for research, teaching or clinical application.

Future-proofing genomic data and consent management: a comprehensive review of technology innovations.

Genomic information is increasingly used to inform medical treatments and manage future disease risks. However, any personal and societal gains must be carefully balanced against the risk to individuals contributing their genomic data. Expanding our understanding of actionable genomic insights requires researchers to access large global datasets to capture the complexity of genomic contribution to diseases. Similarly, clinicians need efficient access to a patient's genome as well as population-representative historical records for evidence-based decisions. Both researchers and clinicians hence rely on participants to consent to the use of their genomic data, which in turn requires trust in the professional and ethical handling of this information. Here, we review existing and emerging solutions for secure and effective genomic information management, including storage, encryption, consent, and authorization that are needed to build participant trust. We discuss recent innovations in cloud computing, quantum-computing-proof encryption, and self-sovereign identity. These innovations can augment key developments from within the genomics community, notably GA4GH Passports and the Crypt4GH file container standard. We also explore how decentralized storage as well as the digital consenting process can offer culturally acceptable processes to encourage data contributions from ethnic minorities. We conclude that the individual and their right for self-determination needs to be put at the center of any genomics framework, because only on an individual level can the received benefits be accurately balanced against the risk of exposing private information.

Improved Intrusion Detection Based on Hybrid Deep Learning Models and Federated Learning.

The security of the Industrial Internet of Things (IIoT) is of vital importance, and the Network Intrusion Detection System (NIDS) plays an indispensable role in this. Although there is an increasing number of studies on the use of deep learning technology to achieve network intrusion detection, the limited local data of the device may lead to poor model performance because deep learning requires large-scale datasets for training. Some solutions propose to centralize the local datasets of devices for deep learning training, but this may involve user privacy issues. To address these challenges, this study proposes a novel federated learning (FL)-based approach aimed at improving the accuracy of network intrusion detection while ensuring data privacy protection. This research combines convolutional neural networks with attention mechanisms to develop a new deep learning intrusion detection model specifically designed for the IIoT. Additionally, variational autoencoders are incorporated to enhance data privacy protection. Furthermore, an FL framework enables multiple IIoT clients to jointly train a shared intrusion detection model without sharing their raw data. This strategy significantly improves the model's detection capability while effectively addressing data privacy and security issues. To validate the effectiveness of the proposed method, a series of experiments were conducted on a real-world Internet of Things (IoT) network intrusion dataset. The experimental results demonstrate that our model and FL approach significantly improve key performance metrics such as detection accuracy, precision, and false-positive rate (FPR) compared to traditional local training methods and existing models.

Combating Fraudulent Participation in Urban American Indian and Alaska Native Virtual Health Research: Protocol for Increasing Data Integrity in Online Research (PRIOR).

BACKGROUND: While the advantages of using the internet and social media for research recruitment are well documented, the evolving online environment also enhances motivations for misrepresentation to receive incentives or to "troll" research studies. Such fraudulent assaults can compromise data integrity, with substantial losses in project time; money; and especially for vulnerable populations, research trust. With the rapid advent of new technology and ever-evolving social media platforms, it has become easier for misrepresentation to occur within online data collection. This perpetuation can occur by bots or individuals with malintent, but careful planning can help aid in filtering out fraudulent data. OBJECTIVE: Using an example with urban American Indian and Alaska Native young women, this paper aims to describe PRIOR (Protocol for Increasing Data Integrity in Online Research), which is a 2-step integration protocol for combating fraudulent participation in online survey research. METHODS: From February 2019 to August 2020, we recruited participants for formative research preparatory to an online randomized control trial of a preconceptual health program. First, we described our initial protocol for preventing fraudulent participation, which proved to be unsuccessful. Then, we described modifications we made in May 2020 to improve the protocol performance and the creation of PRIOR. Changes included transferring data collection platforms, collecting embedded geospatial variables, enabling timing features within the screening survey, creating URL links for each method or platform of data collection, and manually confirming potentially eligible participants' identifying information. RESULTS: Before the implementation of PRIOR, the project experienced substantial fraudulent attempts at study enrollment, with less than 1% (n=6) of 1300 screened participants being identified as truly eligible. With the modified protocol, of the 461 individuals who completed a screening survey, 381 did not meet the eligibility criteria assessed on the survey. Of the 80 that did, 25 (31%) were identified as ineligible via PRIOR. A total of 55 (69%) were identified as eligible and verified in the protocol and were enrolled in the formative study. CONCLUSIONS: Fraudulent surveys compromise study integrity, validity of the data, and trust among participant populations. They also deplete scarce research resources including respondent compensation and personnel time. Our approach of PRIOR to prevent online misrepresentation in data was successful. This paper reviews key elements regarding fraudulent data participation in online research and demonstrates why enhanced protocols to prevent fraudulent data collection are crucial for building trust with vulnerable populations. TRIAL REGISTRATION: ClinicalTrials.gov NCT04376346; https://www.clinicaltrials.gov/study/NCT04376346. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/52281.

Biobanks in chronic disease management: A comprehensive review of strategies, challenges, and future directions.

Biobanks, through the collection and storage of patient blood, tissue, genomic, and other biological samples, provide unique and rich resources for the research and management of chronic diseases such as cardiovascular diseases, diabetes, and cancer. These samples contain valuable cellular and molecular level information that can be utilized to decipher the pathogenesis of diseases, guide the development of novel diagnostic technologies, treatment methods, and personalized medical strategies. This article first outlines the historical evolution of biobanks, their classification, and the impact of technological advancements. Subsequently, it elaborates on the significant role of biobanks in revealing molecular biomarkers of chronic diseases, promoting the translation of basic research to clinical applications, and achieving individualized treatment and management. Additionally, challenges such as standardization of sample processing, information privacy, and security are discussed. Finally, from the perspectives of policy support, regulatory improvement, and public participation, this article provides a forecast on the future development directions of biobanks and strategies to address challenges, aiming to safeguard and enhance their unique advantages in supporting chronic disease prevention and treatment.

Harnessing the potential of shared data in a secure, inclusive, and resilient manner via multi-key homomorphic encryption.

In this manuscript, we develop a multi-party framework tailored for multiple data contributors seeking machine learning insights from combined data sources. Grounded in statistical learning principles, we introduce the Multi-Key Homomorphic Encryption Logistic Regression (MK-HELR) algorithm, designed to execute logistic regression on encrypted multi-party data. Given that models built on aggregated datasets often demonstrate superior generalization capabilities, our approach offers data contributors the collective strength of shared data while ensuring their original data remains private due to encryption. Apart from facilitating logistic regression on combined encrypted data from diverse sources, this algorithm creates a collaborative learning environment with dynamic membership. Notably, it can seamlessly incorporate new participants during the learning process, addressing the key limitation of prior methods that demanded a predetermined number of contributors to be set before the learning process begins. This flexibility is crucial in real-world scenarios, accommodating varying data contribution timelines and unanticipated fluctuations in participant numbers, due to additions and departures. Using the AI4I public predictive maintenance dataset, we demonstrate the MK-HELR algorithm, setting the stage for further research in secure, dynamic, and collaborative multi-party learning scenarios.

A guide to understanding big data for the nurse scientist: A discursive paper.

Big data refers to extremely large data generated at high volume, velocity, variety, and veracity. The nurse scientist is uniquely positioned to leverage big data to suggest novel hypotheses on patient care and the healthcare system. The purpose of this paper is to provide an introductory guide to understanding the use and capability of big data for nurse scientists. Herein, we discuss the practical, ethical, social, and educational implications of using big data in nursing research. Some practical challenges with the use of big data include data accessibility, data quality, missing data, variable data standards, fragmentation of health data, and software considerations. Opposing ethical positions arise with the use of big data, and arguments for and against the use of big data are underpinned by concerns about confidentiality, anonymity, and autonomy. The use of big data has health equity dimensions and addressing equity in data is an ethical imperative. There is a need to incorporate competencies needed to leverage big data for nursing research into advanced nursing educational curricula. Nursing science has a great opportunity to evolve and embrace the potential of big data. Nurse scientists should not be spectators but collaborators and drivers of policy change to better leverage and harness the potential of big data.

Home nursing in clinical trials: Result from semi-structured qualitative interviews.

There is a need to transition from conventional (on-site) clinical trials (CTs) to trials conducted within the comfort of a patient's home or community (decentralized CT) through e-consent, remote data monitoring, and telemedicine consults. This shift in trial procedures will positively impact recruitment rates, compliance and participant retention, protocol deviations, and delays or missed visits. Home nursing in CTs (HNCTs) will be an important component of this decentralization effort. A few limitations may impact the implementation of HNCT in India. In this regard, the workstream conducted semi-structured qualitative interviews with experts from diverse domains of CT conduct (researchers from academia and industry, clinicians, investigators, nursing staff, patient research advocates, institutional ethics committee, or institutional review board members, legal experts, and trial participants) to collect their understanding, perspectives, and the ground realities about HNCTs in India. The current review puts forth the key areas that would facilitate the establishment of HNCTs in India and provides recommendations for the same.

Orbital learning: a novel, actively orchestrated decentralised learning for healthcare.

A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority of them face shortcomings that affect their performance and accuracy. These shortcomings include a non-uniform rate of data accumulation, non-uniform patient demographics, biased human labelling, and erroneous or malicious training data. A novel method to reduce such shortcomings is proposed in the present work through selective grouping and displacing of actors in a network of many entities for intra-group sharing of learning with inter-group accessibility. The proposed system, known as Orbital Learning, incorporates various features from split learning and ensemble learning for a robust and secure performance of supervised models. A digital embodiment of the information quality and flow within a decentralised network, this platform also acts as a digital twin of healthcare network. An example of ECG classification for arrhythmia with 6 clients is used to analyse its performance and is compared against federated learning. In this example, four separate experiments are conducted with varied configurations, such as varied age demographics and clients with data tampering. The results obtained show an average area under receiver operating characteristic curve (AUROC) of 0.819 (95% CI 0.784-0.853) for orbital learning whereas 0.714 (95% CI 0.692-0.736) for federated learning. This result shows an increase in overall performance and establishes that the proposed system can address the majority of the issues faced by existing decentralised learning methodologies. Further, a scalability demo conducted establishes the versatility and scalability of this platform in handling state-of-the-art large language models.

"Incorporating large language models into academic neurosurgery: embracing the new era".

This correspondence examines how LLMs, such as ChatGPT, have an effect on academic neurosurgery. It emphasises the potential of LLMs in enhancing clinical decision-making, medical education, and surgical practice by providing real-time access to extensive medical literature and data analysis. Although this correspondence acknowledges the opportunities that come with the incorporation of LLMs, it also discusses challenges, such as data privacy, ethical considerations, and regulatory compliance. Additionally, recent studies have assessed the effectiveness of LLMs in perioperative patient communication and medical education, and stressed the need for cooperation between neurosurgeons, data scientists, and AI experts to address these challenges and fully exploit the potential of LLMs in improving patient care and outcomes in neurosurgery.

Human-Unrecognizable Differential Private Noised Image Generation Method.

Differential privacy has emerged as a practical technique for privacy-preserving deep learning. However, recent studies on privacy attacks have demonstrated vulnerabilities in the existing differential privacy implementations for deep models. While encryption-based methods offer robust security, their computational overheads are often prohibitive. To address these challenges, we propose a novel differential privacy-based image generation method. Our approach employs two distinct noise types: one makes the image unrecognizable to humans, preserving privacy during transmission, while the other maintains features essential for machine learning analysis. This allows the deep learning service to provide accurate results, without compromising data privacy. We demonstrate the feasibility of our method on the CIFAR100 dataset, which offers a realistic complexity for evaluation.

PrivShieldROS: An Extended Robot Operating System Integrating Ethereum and Interplanetary File System for Enhanced Sensor Data Privacy.

With the application of robotics in security monitoring, medical care, image analysis, and other high-privacy fields, vision sensor data in robotic operating systems (ROS) faces the challenge of enhancing secure storage and transmission. Recently, it has been proposed that the distributed advantages of blockchain be taken advantage of to improve the security of data in ROS. Still, it has limitations such as high latency and large resource consumption. To address these issues, this paper introduces PrivShieldROS, an extended robotic operating system developed by InterPlanetary File System (IPFS), blockchain, and HybridABEnc to enhance the confidentiality and security of vision sensor data in ROS. The system takes advantage of the decentralized nature of IPFS to enhance data availability and robustness while combining HybridABEnc for fine-grained access control. In addition, it ensures the security and confidentiality of the data distribution mechanism by using blockchain technology to store data content identifiers (CID) persistently. Finally, the effectiveness of this system is verified by three experiments. Compared with the state-of-the-art blockchain-extended ROS, PrivShieldROS shows improvements in key metrics. This paper has been partly submitted to IROS 2024.