Background: 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. Objective: 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. Methods: 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. Results: 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. Conclusions: 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.

Systematic reviews (SR) synthesize evidence-based medical literature, but they involve labor-intensive manual article screening. Large language models (LLMs) can select relevant literature, but their quality and efficacy are still being determined compared to humans. We evaluated the overlap between title- and abstract-based selected articles of 18 different LLMs and human-selected articles for three SR. In the three SRs, 185/4,662, 122/1,741, and 45/66 articles have been selected and considered for full-text screening by two independent reviewers. Due to technical variations and the inability of the LLMs to classify all records, the LLM’s considered sample sizes were smaller. However, on average, the 18 LLMs classified 4,294 (min 4,130; max 4,329), 1,539 (min 1,449; max 1,574), and 27 (min 22; max 37) of the titles and abstracts correctly as either included or excluded for the three SRs, respectively. Additional analysis revealed that the definitions of the inclusion criteria and conceptual designs significantly influenced the LLM performances. In conclusion, LLMs can reduce one reviewer´s workload between 33% and 93% during title and abstract screening. However, the exact formulation of the inclusion and exclusion criteria should be refined beforehand for ideal support of the LLMs.

Background: Satisfaction with care is an important indicator of health care quality. However, if this process measure is associated with patients’ outcomes in real-world data is largely unknown. We, therefore, aimed to evaluate if satisfaction with physician- and nurse-related care is associated with quality of life and self-rated health among inpatients at the University Hospital Hamburg-Eppendorf in Germany. Method: We used standard hospital quality survey data of 4925 patients treated at various departments. We used multiple linear regressions to examine an association between satisfaction with staff-related care and quality of life as well as self-rated health, adjusted for age, gender, mother tongue, and treating ward. Patients rated their satisfaction with physician- and nurse-related care from 0 “not at all” to 9 “very much”. The outcomes regarding quality of life and self-rated health were evaluated on five-point Likert scales ranking from 1 “bad” to 5 “excellent”. Results: We found that satisfaction with physician-related care was positively associated with quality of life (ß = 0.16; p < 0.001) as well as with self-rated health (ß = 0.16; p < 0.001). Similar findings were observed for satisfaction with nurse-related care and the two outcomes (ß = 0.13; p < 0.001 and ß = 0.14; p < 0.001, respectively). Conclusion: We show that patients who are more satisfied with staff-related care report better quality of life and self-rated health than patients less satisfied with care. Thus, patient satisfaction with care, is not only a process measure indicating the quality of care but is also positively associated with patient-reported outcomes.

To investigate the association between having osteoarthritis (OA), hypertension, or diabetes, either alone or in combination, and receiving guideline-recommended exercise or weight-reduction advice. Cross-sectional study. We applied logistic regression to analyse self-reported data from the 2017 Danish National Health survey (DNHS). We calculated the proportions and odds ratios of receiving exercise advice and weight-reduction advice (if BMI>30) from the general practitioner (GP) in seven patient groups: those with OA or hypertension or diabetes or any combination of these diseases. From the 183,372 DNHS responders, we included 71,717 patients (≥45 years) who reported consulting a GP during the previous year. Among patients with only one disease, those with OA were least likely to receive exercise advice (13%, 1441/11,024) and weight-reduction advice (27%, 504/1877), while those with diabetes were most likely to receive these advice (32%, 387/1200 and 55%, 160/289, respectively). For OA-only patients, the adjusted odds ratios of receiving exercise advice and weight-reduction advice were 1.4 (95% CI 1.3 to 1.5) and 1.6 (95% CI 1.4 to 1.8), respectively, compared with patients with none of the three diseases. For diabetes-only patients, the adjusted odds ratios were 4.2 (95% CI 3.7 to 4.7) and 5.4 (95% CI 4.2 to 7.0), respectively. Few patients with OA self-reported having received guideline-recommended exercise advice, or weight-reduction advice if obese, from their GP. Furthermore, patients with OA were less likely to report having received these advice compared with patients with other chronic diseases.