Search

Background: Digitalization and big health system data open new avenues for targeted prevention and treatment strategies. We aimed to develop and validate prediction models for stroke and myocardial infarction (MI) in patients with type 2 diabetes based on routinely collected high-dimensional health insurance claims and compared predictive performance of traditional regression with state-of-the-art machine learning including deep learning methods. Methods: We used German health insurance claims from 2014 to 2019 with 287 potentially relevant literature-derived variables to predict 3-year risk of MI and stroke. Following a train-test split approach, we compared the performance of logistic methods with and without forward selection, LASSO-regularization, random forests (RF), gradient boosting (GB), multi-layer-perceptrons (MLP) and feature-tokenizer transformers (FTT). We assessed discrimination (Areas Under the Precision-Recall and Receiver-Operator Curves, AUPRC and AUROC) and calibration. Results: Among n = 371,006 patients with type 2 diabetes (mean age: 67.2 years), 3.5% (n = 13,030) had MIs and 3.4% (n = 12,701) strokes. AUPRCs were 0.035 (MI) and 0.034 (stroke) for a null model, between 0.082 (MLP) and 0.092 (GB) for MI, and between 0.061 (MLP) and 0.073 (GB) for stoke. AUROCs were 0.5 for null models, between 0.70 (RF, MLP, FTT) and 0.71 (all other models) for MI, and between 0.66 (MLP) and 0.69 (GB) for stroke. All models were well calibrated. Conclusions: Discrimination performance of claims-based models reached a ceiling at around 0.09 AUPRC and 0.7 AUROC. While for AUROC this performance was comparable to existing epidemiological models incorporating clinical information, comparison of other, potentially more relevant metrics, such as AUPRC, sensitivity and Positive Predictive Value was hampered by lack of reporting in the literature. The fact that machine learning including deep learning methods did not outperform more traditional approaches may suggest that feature richness and complexity were exploited before the choice of algorithm could become critical to maximize performance. Future research might focus on the impact of different feature derivation approaches on performance ceilings. In the absence of other more powerful screening alternatives, applying transparent regression-based models in routine claims, though certainly imperfect, remains a promising scalable low-cost approach for population-based cardiovascular risk prediction and stratification. [ABSTRACT FROM AUTHOR]

Author(s): Sara Pedron 1,2,3,*, Michael Hanselmann 1, Jacob Burns 1,4,5, Alexander Rich 2,4,5, Annette Peters 6, Margit Heier 6,7, Lars Schwettmann 2,8, Jacob H. Bor 9,10, Till Bärnighausen 11,12,13, Michael [...], Background Hypertension represents one of the major risk factors for cardiovascular morbidity and mortality globally. Early detection and treatment of this condition is vital to prevent complications. However, hypertension often goes undetected, and even if detected, not every patient receives adequate treatment. Identifying simple and effective interventions is therefore crucial to fight this problem and allow more patients to receive the treatment they need. Therefore, we aim at investigating the impact of a population-based blood pressure (BP) screening and the subsequent "low-threshold" information treatment on long-term cardiovascular disease (CVD) morbidity and mortality. Methods and findings We examined the impact of a BP screening embedded in a population-based cohort study in Germany and subsequent personalized "light touch" information treatment, including a hypertension diagnosis and a recommendation to seek medical attention. We pooled four waves of the KORA study, carried out between 1984 and 1996 (N = 14,592). Using a sharp multivariate regression discontinuity (RD) design, we estimated the impact of the information treatment on CVD mortality and morbidity over 16.9 years. Additionally, we investigated potential intermediate outcomes, such as hypertension awareness, BP, and behavior after 7 years. No evidence of effect of BP screening was observed on CVD mortality (hazard ratio (HR) = 1.172 [95% confidence interval (CI): 0.725, 1.896]) or on any (fatal or nonfatal) long-term CVD event (HR = 1.022 [0.636, 1.641]) for individuals just above (versus below) the threshold for hypertension. Stratification for previous self-reported diagnosis of hypertension at baseline did not reveal any differential effect. The intermediate outcomes, including awareness of hypertension, were also unaffected by the information treatment. However, these results should be interpreted with caution since the analysis might not be sufficiently powered to detect a potential intervention effect. Conclusions The study does not provide evidence of an effect of the assessed BP screening and subsequent information treatment on BP, health behavior, or long-term CVD mortality and morbidity. Future studies should consider larger datasets to detect possible effects and a shorter follow-up for the intermediate outcomes (i.e., BP and behavior) to detect short-, medium-, and long-term effects of the intervention along the causal pathway.

Introduction: Almost 25% of German adults have obesity and numbers are rising, making it an important health issue. Bariatric-metabolic surgery reduces body weight and complications for persons with obesity, but therapeutic success requires long-term postoperative care. Since no German standards for follow-up by family physicians exist, follow-up is provided by surgical obesity centers, but they are reaching their limits. The ACHT study, funded by the German Innovation Fund, is designed to establish and evaluate the follow-up program, with local physicians following patients supported remotely by obesity centers. Methods: ACHT is a multicenter, prospective, non-randomized control group study. The 18-month ACHT follow-up program is a digitally supported, structured, cross-sectoral, and close-to-home program to improve success after bariatric-metabolic surgery. Four groups are compared: intervention group 1 starts the program immediately (3 weeks) after Roux-en-Y gastric bypass or sleeve gastrectomy (months 1–18 postoperatively), intervention group 2 begins the program 18 months after surgery (months 19–36 postoperatively). Intervention groups are compared to respective control groups that had surgery 18 and 36 months previously. In total, 250 patients, enrolled in the intervention groups, are compared with 360 patients in the control groups, who only receive standard care. Results: The primary endpoint to compare intervention and control groups is the adapted King's score, a composite tool evaluating physical, psychological, socioeconomic, and functional health status. Secondary endpoints include changes in care structures and care processes for the intervention groups. Multivariate regression analyses adjusting for confounders (including the type of surgery) are used to compare intervention and control groups and evaluate determinants in longitudinal analyses. The effect of the intervention on healthcare costs will be evaluated based on health insurance billing data of patients who had bariatric-metabolic surgery in the 3 years prior to the start of the study and of patients who undergo bariatric-metabolic surgery during the study period. Conclusions: ACHT will be the one of the first evaluated structured, close-to-home follow-up programs for bariatric surgery in Germany. It will evaluate the effectiveness of the implemented program regarding improvements in health status, mental health, quality of life, and the feasibility of such a program outside of specialized obesity centers. [ABSTRACT FROM AUTHOR]

Imaging mass spectrometry (IMS) is a promising technology which allows for detailed analysis of spatial distributions of (bio)molecules in organic samples. In many current applications, IMS relies heavily on (semi)automated exploratory data analysis procedures to decompose the data into characteristic component spectra and corresponding abundance maps, visualizing spectral and spatial structure. The most commonly used techniques are principal component analysis (PCA) and independent component analysis (ICA). Both methods operate in an unsupervised manner. However, their decomposition estimates usually feature negative counts and are not amenable to direct physical interpretation. We propose probabilistic latent semantic analysis (pLSA) for nonnegative decomposition and the elucidation of interpretable component spectra and abundance maps. We compare this algorithm to PCA, ICA, and non-negative PARAFAC (parallel factors analysis) and show on simulated and real-world data that pLSA and non-negative PARAFAC are superior to PCA or ICA in terms of complementarity of the resulting components and reconstruction accuracy. We further combine pLSA decomposition with a statistical complexity estimation scheme based on the Akaike information criterion (AIC) to automatically estimate the number of components present in a tissue sample data set and show that this results in sensible complexity estimates.

Background: Large-scale, polymerase chain reaction (PCR)-based SARS-CoV-2 testing is expensive, resource intensive, and time consuming. A self-collection approach is a probable alternative; however, its feasibility, cost, and ability to prevent infections need to be evaluated. Objective: This study aims to compare an innovative self-collection approach with a regular SARS-CoV-2 testing strategy in a large European industrial manufacturing site. Methods: The feasibility of a telemedicine-guided PCR-based self-collection approach was assessed for 150 employees (intervention group) and compared with a regular SARS-CoV-2 testing approach used for 143 employees (control group). Acceptance, ergonomics, and efficacy were evaluated using a software application. A simulation model was implemented to evaluate the effectiveness. An interactive R shiny app was created to enable customized simulations. Results: The test results were successfully communicated to and interpreted without uncertainty by 76% (114/150) and 76.9% (110/143) of the participants in the intervention and control groups, respectively (P=.96). The ratings for acceptability, ergonomics, and efficacy among intervention group participants were noninferior when compared to those among control group participants (acceptability: 71.6% vs 37.6%; ergonomics: 88.1% vs 74.5%; efficacy: 86.4% vs 77.5%). The self-collection approach was found to be less time consuming (23 min vs 38 min; P<.001). The simulation model indicated that both testing approaches reduce the risk of infection, and the self-collection approach tends to be slightly less effective owing to its lower sensitivity. Conclusions: The self-collection approach for SARS-CoV-2 diagnosis was found to be technically feasible and well rated in terms of acceptance, ergonomics, and efficacy. The simulation model facilitates the evaluation of test effectiveness; nonetheless, considering context specificity, appropriate adaptation by companies is required. [ABSTRACT FROM AUTHOR]

Digital staining for the automated annotation of mass spectrometry imaging (MSI) data has previously been achieved using state-of-the-art classifiers such as random forests or support vector machines (SVMs). However, the training of such classifiers requires an expert to label exemplary data in advance. This process is time-consuming and hence costly, especially if the tissue is heterogeneous. In theory, it may be sufficient to only label a few highly representative pixels of an MS image, but it is not known a priori which pixels to select. This motivates active learning strategies in which the algorithm itself queries the expert by automatically suggesting promising candidate pixels of an MS image for labeling. Given a suitable querying strategy, the number of required training labels can be significantly reduced while maintaining classification accuracy. In this work, we propose active learning for convenient annotation of MSI data. We generalize a recently proposed active learning method to the multiclass case and combine it with the random forest classifier. Its superior performance over random sampling is demonstrated on secondary ion mass spectrometry data, making it an interesting approach for the classification of MS images. [ABSTRACT FROM AUTHOR]

Background: The universal availability of smartphones has created new opportunities for innovative telemedicine applications in health care. The COVID-19 pandemic has heightened the demand for contactless health care services, making SARS-CoV-2 polymerase chain reaction (PCR) testing a crucial component of pandemic containment., Objective: This feasibility study aimed to examine a comprehensive telemedicine approach for SARS-CoV-2 testing, focusing on the practicality, user satisfaction, and economic implications of self-sampling guided by a telemedicine platform., Methods: The study process involved shipping self-sampling kits, providing instructions for at-home sample collection, processing biomaterials (swabs and capillary blood), communicating test results, and providing interoperable data for clinical routine and research through a medical mobile app. A total of 100 individuals were randomly assigned to either the conventional health care professional (HCP)-performed SARS-CoV-2 testing group (conventional testing group, CG) or the telemedicine-guided SARS-CoV-2 self-sampling approach (telemedicine group, TG). Feasibility of the TG approach, user satisfaction, user-centered outcomes, and economic aspects were assessed and compared between the groups., Results: In the TG group, 47 out of 49 (95%) individuals received a self-sampling kit via mail, and 37out of 49 (76%) individuals successfully returned at least one sample for diagnostics. SARS-CoV-2 PCR tests were conducted in 95% (35/37) of TG cases compared with 88% (44/50) in the CG. Users in the TG reported high satisfaction levels with ease of use (5.2/7), interface satisfaction (5.2/7), and usefulness (4.3/7). A microcosting model indicated a slightly higher cost for the TG approach than the CG approach. The TG demonstrated the potential to facilitate interoperable data transmission by providing anonymized, standardized datasets for extraction using Health Level 7-Fast Healthcare Interoperability Resources. This supports the national COVID-19 Data Exchange Platform and facilitates epidemiological evaluation based on the German COVID Consensus dataset., Conclusions: These preliminary findings suggest that a telemedicine-based approach to SARS-CoV-2 testing is feasible and could be integrated into existing hospital data infrastructures. This model has the potential for broader application in medical care, offering a scalable solution that could improve user satisfaction and treatment quality in the future., (© Florian Voit, Johanna Erber, Silvia Egert-Schwender, Michael Hanselmann, Michael Laxy, Victoria Kehl, Dieter Hoffmann, Samuel D Jeske, Thomas Michler, Ulrike Protzer, Florian Kohlmayer, Roland M Schmid, Christoph D Spinner, Simon Weidlich. Originally published in JMIR Formative Research (https://formative.jmir.org).)