Explore the vast range of titles available.

Prognostic models in medicine have garnered significant attention, with established guidelines governing their development. However, there remains a lack of clarity regarding the appropriate circumstances for (1) creating and (2) implementing tools based on models with limited performance. This commentary addresses this gap by analyzing the pros and cons of tool development and providing a structured outline that includes critical questions to consider in the decision-making process, based on an example of patients with osteoarthritis. We propose three general justifications for the implementation of survey-based models: (1) mitigation of expectation bias among patients and clinicians, (2) advancement of personalized medicine, and (3) enhancement of existing predictive information sources. Nevertheless, it is crucial to acknowledge that implementing such models is always context-dependent and may harm certain patients, necessitating careful consideration of the withdrawal of tool development and implementation in specific cases. To facilitate the identification of these scenarios, we delineate 16 possibilities following the implementation of a personalized prognostic model and compare the consequences to a current one-size-fits-all treatment recommendation at a population level. Our analysis encompasses the possible patient benefits and harms resulting from implementing or not implementing personalized prognostic models and summarizes them. These findings, together with context-related factors, are important to consider when deciding if, how, and for whom a personalized prognostic tool should be created and implemented. We present a checklist of questions and an Excel sheet calculation table, allowing researchers to weigh the benefits and harms of creating and implementing a personalized prognostic model at a population level against one-size-fits-all standard care in a structured and standardized manner. We condense this into a single value using a uniform Benefit-Risk Score formula. Together with context-related factors, the calculation table and formula are designed to aid researchers in their decision-making process on providing a personalized prognostic tool and deciding for or against its complete or partial implementation. This work serves as a foundation for further discourse and refinement of tool development decisions for prognostic models in health care.

The collection, storage, and analysis of large data sets are relevant in many sectors. Especially in the medical field, the processing of patient data promises great progress in personalized health care. However, it is strictly regulated, such as by the General Data Protection Regulation (GDPR). These regulations mandate strict data security and data protection and, thus, create major challenges for collecting and using large data sets. Technologies such as federated learning (FL), especially paired with differential privacy (DP) and secure multiparty computation (SMPC), aim to solve these challenges. This scoping review aimed to summarize the current discussion on the legal questions and concerns related to FL systems in medical research. We were particularly interested in whether and to what extent FL applications and training processes are compliant with the GDPR data protection law and whether the use of the aforementioned privacy-enhancing technologies (DP and SMPC) affects this legal compliance. We placed special emphasis on the consequences for medical research and development. We performed a scoping review according to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews). We reviewed articles on Beck-Online, SSRN, ScienceDirect, arXiv, and Google Scholar published in German or English between 2016 and 2022. We examined 4 questions: whether local and global models are \"personal data\" as per the GDPR; what the \"roles\" as defined by the GDPR of various parties in FL are; who controls the data at various stages of the training process; and how, if at all, the use of privacy-enhancing technologies affects these findings. We identified and summarized the findings of 56 relevant publications on FL. Local and likely also global models constitute personal data according to the GDPR. FL strengthens data protection but is still vulnerable to a number of attacks and the possibility of data leakage. These concerns can be successfully addressed through the privacy-enhancing technologies SMPC and DP. Combining FL with SMPC and DP is necessary to fulfill the legal data protection requirements (GDPR) in medical research dealing with personal data. Even though some technical and legal challenges remain, for example, the possibility of successful attacks on the system, combining FL with SMPC and DP creates enough security to satisfy the legal requirements of the GDPR. This combination thereby provides an attractive technical solution for health institutions willing to collaborate without exposing their data to risk. From a legal perspective, the combination provides enough built-in security measures to satisfy data protection requirements, and from a technical perspective, the combination provides secure systems with comparable performance with centralized machine learning applications.

Genomic data holds huge potential for medical progress but requires strict safety measures due to its sensitive nature to comply with data protection laws. This conflict is especially pronounced in genome-wide association studies (GWAS) which rely on vast amounts of genomic data to improve medical diagnoses. To ensure both their benefits and sufficient data security, we propose a federated approach in combination with privacy-enhancing technologies utilising the findings from a systematic review on federated learning and legal regulations in general and applying these to GWAS.

Background Previous research showed negative associations between physical activity and loneliness in older adults. However, information on associations among middle-aged adults is scarce. In this prognostic factor study, we investigated if starting or stopping to follow the WHO physical activity recommendations was associated with changes in perceived social exclusion and loneliness in this age bracket. Methods We used longitudinal representative data of participants aged 40 to 64 years from the German Ageing Survey waves in 2014 and 2017 (analytical sample = 4,264 observations, 54% women). Perceived social exclusion was investigated with the scale from Bude and Lantermann. Loneliness was quantified with the 6-items loneliness scale from De Jong Gierveld. Information from the International Physical Activity Survey items on the time spend in moderate and vigorous physical activity per week was dichotomized. Participants were coded as either following or not following the WHO´s physical activity recommendations of spending at least 150 min of moderate, 75 min of vigorous or an appropriated combination of physical activity per week. We investigated the within (individual) association between starting and stopping to follow WHO´s physical activity recommendations and perceived social exclusion as well as loneliness in asymmetric fixed effects regressions. Analyses were adjusted for age, marital status, employment status, social-network size, general self-efficacy, depressive symptoms, self-rated health, BMI, comorbidities, and physical functioning (SF-36). Results Stopping to follow the physical activity recommendations from the WHO was associated with perceived social exclusion (ß= 0.09 p = 0.04) but not with loneliness (ß=-0.01, p = 0.71). Starting to follow the WHO physical activity recommendations was neither associated with social exclusion (ß=-0.02, p = 0.54) nor with loneliness (ß=-0.01, p = 0.74) in adjusted asymmetric fixed effects regressions. Conclusion In middle-aged adults, longitudinal associations were found for physical activity and perceived social exclusion. Perceived social exclusion may be prevented by maintaining at least 150 min of moderate physical activities per week, which is the WHO physical activity recommendation. Future research should investigate moderators and mediators in the association between physical activity and social exclusion as well as loneliness.

Machine learning and artificial intelligence have shown promising results in many areas and are driven by the increasing amount of available data. However, these data are often distributed across different institutions and cannot be easily shared owing to strict privacy regulations. Federated learning (FL) allows the training of distributed machine learning models without sharing sensitive data. In addition, the implementation is time-consuming and requires advanced programming skills and complex technical infrastructures. Various tools and frameworks have been developed to simplify the development of FL algorithms and provide the necessary technical infrastructure. Although there are many high-quality frameworks, most focus only on a single application case or method. To our knowledge, there are no generic frameworks, meaning that the existing solutions are restricted to a particular type of algorithm or application field. Furthermore, most of these frameworks provide an application programming interface that needs programming knowledge. There is no collection of ready-to-use FL algorithms that are extendable and allow users (eg, researchers) without programming knowledge to apply FL. A central FL platform for both FL algorithm developers and users does not exist. This study aimed to address this gap and make FL available to everyone by developing FeatureCloud, an all-in-one platform for FL in biomedicine and beyond. The FeatureCloud platform consists of 3 main components: a global frontend, a global backend, and a local controller. Our platform uses a Docker to separate the local acting components of the platform from the sensitive data systems. We evaluated our platform using 4 different algorithms on 5 data sets for both accuracy and runtime. FeatureCloud removes the complexity of distributed systems for developers and end users by providing a comprehensive platform for executing multi-institutional FL analyses and implementing FL algorithms. Through its integrated artificial intelligence store, federated algorithms can easily be published and reused by the community. To secure sensitive raw data, FeatureCloud supports privacy-enhancing technologies to secure the shared local models and assures high standards in data privacy to comply with the strict General Data Protection Regulation. Our evaluation shows that applications developed in FeatureCloud can produce highly similar results compared with centralized approaches and scale well for an increasing number of participating sites. FeatureCloud provides a ready-to-use platform that integrates the development and execution of FL algorithms while reducing the complexity to a minimum and removing the hurdles of federated infrastructure. Thus, we believe that it has the potential to greatly increase the accessibility of privacy-preserving and distributed data analyses in biomedicine and beyond.

Background Patient-reported survey data are used to train prognostic models aimed at improving healthcare. However, such data are typically available multi-centric and, for privacy reasons, cannot easily be centralized in one data repository. Models trained locally are less accurate, robust, and generalizable. We aim to investigate the applicability of privacy-preserving federated machine learning techniques for prognostic model building on health survey data, where local data never leaves the legally safe harbors of the medical centers. Methods We used centralized, local, and federated learning techniques on two healthcare datasets ( GLA: D ® data from the five health regions of Denmark and international SHARE data of 27 countries) to predict two different health outcomes. We compared linear regression, random forest regression, and random forest classification models trained on local data with those trained on the entire data in a centralized and in a federated fashion. Results In GLA: D ® data, federated linear regression (R 2 0.34, RMSE 18.2) and federated random forest regression (R 2 0.34, RMSE 18.3) models outperform their local counterparts (i.e., R 2 0.32, RMSE 18.6, R 2 0.30, RMSE 18.8) with statistical significance. We also found that centralized models (R 2 0.34, RMSE 18.2, R 2 0.32, RMSE 18.5, respectively) did not perform significantly better than the federated models. In SHARE, the federated model (AC 0.78, AUROC: 0.71) and centralized model (AC 0.84, AUROC: 0.66) perform significantly better than the local models (AC: 0.74, AUROC: 0.69). Conclusion Federated learning enables the training of prognostic models from multi-center surveys without compromising privacy and with only minimal or no compromise regarding model performance.

Background Physical activity (PA) contributes to healthy aging. Several studies have investigated factors influencing PA. However, population-based studies evaluating associations between volunteering and changes in PA are lacking. Our aim was to clarify whether starting and stopping to volunteer is associated with changes in physical activity in older adults. Method We used data from the German Ageing Survey (wave 5 and 6 in the years 2014 and 2017), which is a representative survey of community-dwelling middle-aged and older adults. We included individuals ≥ 65 years (analytical sample: n  = 5,682). PA was investigated using questions from the international physical activity questionnaire (IPAQ) and converted into metabolic equivalent of tasks (METs) per week. Changes in volunteering status in groups or organizations (yes/no) and their association with changes in PA were investigated in adjusted asymmetric fixed effects models stratified by sex. Results We found an association, between starting to volunteer and increased physical activity in older adults in the total sample (ß = 1,078.93, p  = 0.052). This change reached significance for men (ß = 1,751.54, p  = 0.016), but not for women (ß = 187.25, p  = 0.832) in the stratified analyses. In the total sample, there was no association between stopping volunteering and decreases in PA (ß = -285.61, p  = 0.543). This also held true in the stratified analyses for men (ß = -320.76, p  = 0.583) and women (ß = -158.96, p  = 0.845). Conclusion Our study identified an association between beginning to volunteer and increased physical activity among older men. Thus, beginning to volunteer may assist older men in increasing their physical activity levels.

To fully leverage big data, they need to be shared across institutions in a manner compliant with privacy considerations and the EU General Data Protection Regulation (GDPR). Federated machine learning is a promising option.

IntroductionSeveral economic evaluations of musculoskeletal physiotherapy have been published in the literature. We aim to provide an overview of these existing economic evaluations. This overview will be useful for healthcare funders in identifying studies matching their context. In addition, research gaps as well as literature extensive enough to be combined in a meta-analysis will be identified. This will support researchers in planning relevant research projects.Methods and analysesWe will search in PubMed, EconLit and NHS-EED for relevant literature. Full economic evaluations of musculoskeletal physiotherapy interventions will be included, regardless of type, and economic evaluation perspective. Initial searches were performed on 7th October 2021. Study selection, data extraction and the quality evaluation will be conducted initially by two independent researchers. If their agreement is sufficient, one reviewer will proceed with the respected process. From the included studies, we will extract information on the publication year, the country of origin, the type of economical evaluation analyses and the specific musculoskeletal condition. An overview will be provided, concerning the distributions of the included studies regarding the extracted information. Furthermore, an evaluation of the individual study quality will be offered.Ethics and disseminationNo ethical approval will be required for this systematic review, since no human participants are involved. We aim to distribute the findings of this review in a peer-reviewed journal, on national and international conferences, as well as via social media.