-
Medical Image Analysis Jun 2024In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require...
In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. However, catastrophic forgetting occurs, decreasing the performance of earlier classes when adapting the model to new data. Prior proposed methodologies to overcome this require perpetual storage of previous samples, posing potential practical concerns regarding privacy and storage regulations in healthcare. To this end, we propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes. Our key contributions include acquiring synthetic data known as Continual Class-Specific Impression (CCSI) for previously inaccessible trained classes and presenting a methodology to effectively utilize this data for updating networks when introducing new classes. We obtain CCSI by employing data inversion over gradients of the trained classification model on previous classes starting from the mean image of each class inspired by common landmarks shared among medical images and utilizing continual normalization layers statistics as a regularizer in this pixel-wise optimization process. Subsequently, we update the network by combining the synthesized data with new class data and incorporate several losses, including an intra-domain contrastive loss to generalize the deep network trained on the synthesized data to real data, a margin loss to increase separation among previous classes and new ones, and a cosine-normalized cross-entropy loss to alleviate the adverse effects of imbalanced distributions in training data. Extensive experiments show that the proposed framework achieves state-of-the-art performance on four of the public MedMNIST datasets and in-house echocardiography cine series, with an improvement in classification accuracy of up to 51% compared to baseline data-free methods. Our code is available at https://github.com/ubc-tea/Continual-Impression-CCSI.
PubMed: 38936223
DOI: 10.1016/j.media.2024.103239 -
Journal of Medical Internet Research Jun 2024The US health care delivery system does not systematically engage or support family or friend care partners. Meanwhile, the uptake and familiarity of portals to personal...
The US health care delivery system does not systematically engage or support family or friend care partners. Meanwhile, the uptake and familiarity of portals to personal health information are increasing among patients. Technology innovations, such as shared access to the portal, use separate identity credentials to differentiate between patients and care partners. Although not well-known, or commonly used, shared access allows patients to identify who they do and do not want to be involved in their care. However, the processes for patients to grant shared access to portals are often limited or so onerous that interested patients and care partners often circumvent the process entirely. As a result, the vast majority of care partners resort to accessing portals using a patient's identity credentials-a "do-it-yourself" solution in conflict with a health systems' legal responsibility to protect patient privacy and autonomy. The personal narratives in this viewpoint (shared by permission) elaborate on quantitative studies and provide first-person snapshots of challenges faced by patients and families as they attempt to gain or grant shared access during crucial moments in their lives. As digital modalities increase patient roles in health care interactions, so does the importance of making shared access work for all stakeholders involved-patients, clinicians, and care partners. Electronic health record vendors must recognize that both patients and care partners are important users of their products, and health care organizations must acknowledge and support the critical contributions of care partners as distinct from patients.
Topics: Humans; Patient Portals; Electronic Health Records; Caregivers; Patient Participation
PubMed: 38935963
DOI: 10.2196/49394 -
JMIR Bioinformatics and Biotechnology May 2024Genetic data are widely considered inherently identifiable. However, genetic data sets come in many shapes and sizes, and the feasibility of privacy attacks depends on... (Review)
Review
BACKGROUND
Genetic data are widely considered inherently identifiable. However, genetic data sets come in many shapes and sizes, and the feasibility of privacy attacks depends on their specific content. Assessing the reidentification risk of genetic data is complex, yet there is a lack of guidelines or recommendations that support data processors in performing such an evaluation.
OBJECTIVE
This study aims to gain a comprehensive understanding of the privacy vulnerabilities of genetic data and create a summary that can guide data processors in assessing the privacy risk of genetic data sets.
METHODS
We conducted a 2-step search, in which we first identified 21 reviews published between 2017 and 2023 on the topic of genomic privacy and then analyzed all references cited in the reviews (n=1645) to identify 42 unique original research studies that demonstrate a privacy attack on genetic data. We then evaluated the type and components of genetic data exploited for these attacks as well as the effort and resources needed for their implementation and their probability of success.
RESULTS
From our literature review, we derived 9 nonmutually exclusive features of genetic data that are both inherent to any genetic data set and informative about privacy risk: biological modality, experimental assay, data format or level of processing, germline versus somatic variation content, content of single nucleotide polymorphisms, short tandem repeats, aggregated sample measures, structural variants, and rare single nucleotide variants.
CONCLUSIONS
On the basis of our literature review, the evaluation of these 9 features covers the great majority of privacy-critical aspects of genetic data and thus provides a foundation and guidance for assessing genetic data risk.
PubMed: 38935957
DOI: 10.2196/54332 -
JMIR Bioinformatics and Biotechnology Jul 2023While genomic variations can provide valuable information for health care and ancestry, the privacy of individual genomic data must be protected. Thus, a secure...
BACKGROUND
While genomic variations can provide valuable information for health care and ancestry, the privacy of individual genomic data must be protected. Thus, a secure environment is desirable for a human DNA database such that the total data are queryable but not directly accessible to involved parties (eg, data hosts and hospitals) and that the query results are learned only by the user or authorized party.
OBJECTIVE
In this study, we provide efficient and secure computations on panels of single nucleotide polymorphisms (SNPs) from genomic sequences as computed under the following set operations: union, intersection, set difference, and symmetric difference.
METHODS
Using these operations, we can compute similarity metrics, such as the Jaccard similarity, which could allow querying a DNA database to find the same person and genetic relatives securely. We analyzed various security paradigms and show metrics for the protocols under several security assumptions, such as semihonest, malicious with honest majority, and malicious with a malicious majority.
RESULTS
We show that our methods can be used practically on realistically sized data. Specifically, we can compute the Jaccard similarity of two genomes when considering sets of SNPs, each with 400,000 SNPs, in 2.16 seconds with the assumption of a malicious adversary in an honest majority and 0.36 seconds under a semihonest model.
CONCLUSIONS
Our methods may help adopt trusted environments for hosting individual genomic data with end-to-end data security.
PubMed: 38935952
DOI: 10.2196/44700 -
JCO Global Oncology Jun 2024Quality improvement (QI) programs have rapidly grown in health care over recent years. Despite increasing evidence of successful QI initiatives resulting in improved... (Review)
Review
Quality improvement (QI) programs have rapidly grown in health care over recent years. Despite increasing evidence of successful QI initiatives resulting in improved outcomes, the adoption and implementation of QI programs remain a challenge worldwide. This paper briefly describes political and administrative barriers that impede the implementation of QI programs, including political and ideological factors, socioeconomic and educational barriers, and barriers related to data collection, privacy, and security. Key political and administrative barriers identified include resource limitations due to inadequate public funding, stringent laws, and change resistance. Potential solutions include support and commitment from regional and national authorities, consultation of all involved parties during QI program development, and financial incentives. The barrier of limited resources is starker among low- and middle-income countries (LMICs) compared with high-income countries (HICs) due to the absence of adequate infrastructure, personnel equipped with QI-oriented skills, and analytical technology. Solutions that have facilitated QI programs in some LMICs include outreach and collaboration with other health centers and established QI programs in HICs. The lack of QI-specific training and education in medical curricula challenges QI implementation but can be mitigated through the provision of QI promotion webinars, QI-specific project opportunities, and formalized QI training modules. Finally, barriers related to data collection, privacy, and security include laws hindering the availability of quality data, inefficient data collection and processes, and outdated clinical information systems. Access to high-quality data, organized record-keeping, and alignment of data collection processes will help alleviate these barriers to QI program implementation. The multidimensional nature of these barriers means that proposed solutions will require coordination from multiple stakeholders, government support, and leaders across multiple fields.
Topics: Humans; Quality Improvement; Politics; Delivery of Health Care; Developing Countries
PubMed: 38935883
DOI: 10.1200/GO.23.00455 -
PloS One 2024The elderly is commonly susceptible to depression, the symptoms for which may overlap with natural aging or other illnesses, and therefore miss being captured by routine...
BACKGROUND
The elderly is commonly susceptible to depression, the symptoms for which may overlap with natural aging or other illnesses, and therefore miss being captured by routine screening questionnaires. Passive sensing data have been promoted as a tool for depressive symptoms detection though there is still limited evidence on its usage in the elderly. Therefore, this study aims to review current knowledge on the use of passive sensing data via smartphones and smartwatches in depressive symptom screening for the elderly.
METHOD
The search of literature was performed in PubMed, IEEE Xplore digital library, and PsycINFO. Literature investigating the use of passive sensing data to screen, monitor, and/or predict depressive symptoms in the elderly (aged 60 and above) via smartphones and/or wrist-worn wearables was included for initial screening. Studies in English from international journals published between January 2012 to September 2022 were included. The reviewed studies were further analyzed by a narrative analysis.
RESULTS
The majority of 21 included studies were conducted in Western countries with a few in Asia and Australia. Most studies adopted a cohort study design (n = 12), followed by cross-sectional design (n = 7) and a case-control design (n = 2). The most popular passive sensing data was related to sleep and physical activity using an actigraphy. Sleep characteristics, such as prolonged wakefulness after sleep onset, along with lower levels of physical activity, exhibited a significant association with depression. However, cohort studies expressed concerns regarding data quality stemming from incomplete follow-up and potential confounding effects.
CONCLUSION
Passive sensing data, such as sleep, and physical activity parameters should be promoted for depressive symptoms detection. However, the validity, reliability, feasibility, and privacy concerns still need further exploration.
Topics: Humans; Smartphone; Depression; Aged; Mass Screening; Wearable Electronic Devices; Sleep; Middle Aged; Exercise; Female
PubMed: 38935797
DOI: 10.1371/journal.pone.0304845 -
PloS One 2024Monitoring and improving the quality of sleep are crucial from a public health perspective. In this study, we propose a change-point detection method using diffusion...
Monitoring and improving the quality of sleep are crucial from a public health perspective. In this study, we propose a change-point detection method using diffusion maps for a more accurate detection of respiratory arrest points. Conventional change-point detection methods are limited when dealing with complex nonlinear data structures, and the proposed method overcomes these limitations. The proposed method embeds subsequence data in a low-dimensional space while considering the global and local structures of the data and uses the distance between the data as the score of the change point. Experiments using synthetic and real-world contact-free sensor data confirmed the superiority of the proposed method when dealing with noise, and it detected apnea events with greater accuracy than conventional methods. In addition to improving sleep monitoring, the proposed method can be applied in other fields, such as healthcare, manufacturing, and finance. This study will contribute to the development of advanced monitoring systems that adapt to diverse conditions while protecting privacy.
Topics: Humans; Sleep Apnea Syndromes; Polysomnography; Algorithms; Monitoring, Physiologic
PubMed: 38935677
DOI: 10.1371/journal.pone.0306139 -
Environmental Monitoring and Assessment Jun 2024Although machine learning methods have enabled considerable progress in air quality assessment, challenges persist regarding data privacy, cross-regional data...
Although machine learning methods have enabled considerable progress in air quality assessment, challenges persist regarding data privacy, cross-regional data processing, and model generalization. To address these issues, we introduce an advanced federated Bayesian network (FBN) approach. By integrating federated learning, adaptive optimization algorithms, and homomorphic encryption technologies, we substantially enhanced the efficiency and security of cross-regional air quality data processing. The novelty of this research lies in the improvements implemented in federated learning for air quality data analysis, particularly in distributed model training optimization and data consistency. Through the integration of adaptive structural modification strategies and simulated annealing immune optimization algorithms, we markedly enhanced the structural learning accuracy of the Bayesian network, resulting in a 20% improvement in prediction accuracy. Moreover, employing homomorphic encryption ensured data transmission security and confidentiality. In our Beijing-Tianjin-Hebei case study, our method demonstrated a 15% improvement in air quality classification accuracy compared to conventional methods and exhibited superior interpretability in analyzing environmental factor interactions. We quantified complex air pollution patterns across regions and found that a 30% fluctuation in the air quality index correlated with NO concentrations. We also observed a moderate positive correlation between specific pollutant indicators in Hebei Province and Tianjin and changes in air quality. Additionally, the FBN exhibited better operational efficiency and data confidentiality than other machine learning models in handling large-scale and multisource environmental data. Our FBN approach presents a novel perspective for environmental monitoring and assessment, vital for understanding complex air pollution patterns and formulating future ecological protection policies.
Topics: Bayes Theorem; Air Pollution; Environmental Monitoring; Air Pollutants; China; Machine Learning; Beijing; Algorithms
PubMed: 38935164
DOI: 10.1007/s10661-024-12809-6 -
Journal of Pediatric Health Care :... Jun 2024The aim of this study is to test the feasibility of a smartphone serious game-based intervention to promote resilience for adolescents with type 1 diabetes mellitus...
INTRODUCTION
The aim of this study is to test the feasibility of a smartphone serious game-based intervention to promote resilience for adolescents with type 1 diabetes mellitus (T1DM).
METHOD
A two-arm feasibility study was employed. Adolescents with T1DM were recruited. Adolescents in intervention group completed the serious game (named "WeCan") in one month. We evaluated feasibility and acceptability using criteria such as the recruitment response rate, the follow-up response rate, and satisfaction.
RESULTS
Sixty-one adolescents with T1DM were included in this study. The study had a recruitment response rate of 62.89% (61/97) and an intervention completion rate of 64.52% (20/31). Eighty-two percent of the adolescents were satisfied with WeCan, which they perceived to have the advantages of being a lively format, attractive, and privacy, easy to operate, and improved attitude towards diabetes.
CONCLUSIONS
These findings suggest that WeCan demonstrated good feasibility among the target population. However, the efficacy of health-related outcomes needs to be clarified in future studies.
PubMed: 38935014
DOI: 10.1016/j.pedhc.2024.05.009 -
Indian Journal of Public Health Oct 2023A major group of the population, especially antenatal checkup (ANC) mothers and their spouses, people admitted for surgery, and people attending STI clinics, are...
BACKGROUND
A major group of the population, especially antenatal checkup (ANC) mothers and their spouses, people admitted for surgery, and people attending STI clinics, are reluctant to pretest counseling.
OBJECTIVES
This study has been taken up to explore the barriers and possible solutions to improve the utilization of Facility based integrated counseling and testing center (F-ICTC) counseling services.
MATERIALS AND METHODS
Phase 1: In-depth interview and ranking with stakeholders from the F-ICTC center (n = 13) were conducted to identify the barriers to utilization of F-ICTC and solution for the same. Phase 2.
A
Delphi panel with experts (n = 17) was invited through mail to find out the potential solution to improve the utilization of F-ICTC counseling services.
RESULTS
Possible barriers from the stakeholders' perspectives were fear of the disease, violate the privacy, unacceptance, gender bias, fear of social stigma and discrimination, and neglect attached to the disease. At third round of Delphi experts had arrived at a consensus regarding of following possible potential solutions: 1. Those who refuse pretest counseling they should be asked to answer a set of questions(which are usually told during counseling), only those questions not answered correctly by them can be corrected, 2.conducive hospital environment, 3.zero discrimination policy, 4. group counseling for ANC mothers and patients in waiting area of the hospital,5. phone counseling for unwilling patients and relocation of testing center and health education camping.
CONCLUSION
Context-specific proactive evidence-based intervention will help in improving the proper utilization of the F-ICTC center.
Topics: Humans; Delphi Technique; Female; Counseling; Prenatal Care; Male; Pregnancy; Adult; India; Social Stigma; Interviews as Topic; Patient Acceptance of Health Care
PubMed: 38934833
DOI: 10.4103/ijph.ijph_1529_22