Alpha-1-antitrypsin-deficiency is associated with lower cardiovascular risk: an approach based on federated learning.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is an inflammatory multisystemic disease caused by environmental exposures and/or genetic factors. Inherited alpha-1-antitrypsin deficiency (AATD) is one of the best recognized genetic factors increasing the risk for an early onset COPD with emphysema. The aim of this study was to gain a better understanding of the associations between comorbidities and specific biomarkers in COPD patients with and without AATD to enable future investigations aimed, for example, at identifying risk factors or improving care. METHODS: We focused on cardiovascular comorbidities, blood high sensitivity troponin (hs-troponin) and lipid profiles in COPD patients with and without AATD. We used clinical data from six German University Medical Centres of the MIRACUM (Medical Informatics Initiative in Research and Medicine) consortium. The codes for the international classification of diseases (ICD) were used for COPD as a main diagnosis and for comorbidities and blood laboratory data were obtained. Data analyses were based on the DataSHIELD framework. RESULTS: Out of 112,852 visits complete information was available for 43,057 COPD patients. According to our findings, 746 patients with AATD (1.73%) showed significantly lower total blood cholesterol levels and less cardiovascular comorbidities than non-AATD COPD patients. Moreover, after adjusting for the confounder factors, such as age, gender, and nicotine abuse, we confirmed that hs-troponin is a suitable predictor of overall mortality in COPD patients. The comorbidities associated with AATD in the current study differ from other studies, which may reflect geographic and population-based differences as well as the heterogeneous characteristics of AATD. CONCLUSION: The concept of MIRACUM is suitable for the analysis of a large healthcare database. This study provided evidence that COPD patients with AATD have a lower cardiovascular risk and revealed that hs-troponin is a predictor for hospital mortality in individuals with COPD.

App-Controlled Treatment Monitoring and Support for Patients With Head and Neck Cancer Undergoing Radiotherapy: Results From a Prospective Randomized Controlled Trial.

BACKGROUND: Head and neck cancers (HNCs) are very common malignancies, and treatment often requires multimodal approaches, including radiotherapy and chemotherapy. Patients with HNC often display a high symptom burden, both due to the disease itself and the adverse effects of the multimodal therapy. Close telemonitoring of symptoms and quality of life during the course of treatment may help to identify those patients requiring early medical support. OBJECTIVE: The App-Controlled Treatment Monitoring and Support for Patients With Head and Neck Cancer (APCOT) trial aimed to investigate the feasibility of integrating electronic patient-reported outcomes (ePROs) in the treatment surveillance pathway of patients with HNC during the course of their radiotherapy. Additionally, the influence of app-based ePRO monitoring on global and disease-specific quality of life and patient satisfaction with treatment was assessed. METHODS: Patients undergoing radiotherapy for histologically proven HNCs at the Department of Radiation Oncology, University Medical Center Freiburg, Germany, were enrolled in this trial and monitored by weekly physician appointments. Patients were randomized between additional ePRO monitoring on each treatment day or standard-of-care monitoring. Feasibility of ePRO monitoring was defined as ≥80% of enrolled patients answering ≥80% of their daily app-based questions. Quality of life and patient satisfaction were assessed by the European Organisation for Research and Treatment of Cancer Core Quality of Life Questionnaire (QLQ-C30), the head and neck cancer module (H&N35), and the validated Patient Satisfaction Questionnaire Short Form (PSQ-18) at the completion of treatment and compared between trial arms. RESULTS: A total of 100 patients were enrolled in this trial, and 93 patients were evaluable. All patients (100%) in the experimental arm answered ≥80% of the ePRO questions during treatment, reaching the predefined threshold for the feasibility of ePRO monitoring (P<.001 in the binomial test). No clinical or patient-specific factor was found to influence feasibility. Global health and most domains of the general quality of life were comparable between trial arms, but an increased HNC-specific symptom burden was reported by patients undergoing ePRO surveillance. ePRO monitoring resulted in improved patient satisfaction regarding interpersonal manners (P=.01), financial aspects (P=.01), and time spent with a doctor (P=.01). CONCLUSIONS: This trial demonstrated the feasibility of incorporating daily app-based ePRO surveillance for patients with HNC undergoing radiotherapy. Our data, for the first time, demonstrate that telemonitoring in this setting led to increased reporting of HNC-specific symptom burden and significantly improved several domains of patient satisfaction. Further analyses are needed to assess whether our findings hold true outside the context of a clinical trial. TRIAL REGISTRATION: German Clinical Trials Register DRKS00020491; https://drks.de/search/en/trial/DRKS00020491.

Deep dynamic modeling with just two time points: Can we still allow for individual trajectories?

Longitudinal biomedical data are often characterized by a sparse time grid and individual-specific development patterns. Specifically, in epidemiological cohort studies and clinical registries we are facing the question of what can be learned from the data in an early phase of the study, when only a baseline characterization and one follow-up measurement are available. Inspired by recent advances that allow to combine deep learning with dynamic modeling, we investigate whether such approaches can be useful for uncovering complex structure, in particular for an extreme small data setting with only two observations time points for each individual. Irregular spacing in time could then be used to gain more information on individual dynamics by leveraging similarity of individuals. We provide a brief overview of how variational autoencoders (VAEs), as a deep learning approach, can be linked to ordinary differential equations (ODEs) for dynamic modeling, and then specifically investigate the feasibility of such an approach that infers individual-specific latent trajectories by including regularity assumptions and individuals' similarity. We also provide a description of this deep learning approach as a filtering task to give a statistical perspective. Using simulated data, we show to what extent the approach can recover individual trajectories from ODE systems with two and four unknown parameters and infer groups of individuals with similar trajectories, and where it breaks down. The results show that such dynamic deep learning approaches can be useful even in extreme small data settings, but need to be carefully adapted.

Clinical Effectiveness of Newborn Screening for Spinal Muscular Atrophy: A Nonrandomized Controlled Trial.

Importance: There is increasing evidence that early diagnosis and treatment are key for outcomes in infants with spinal muscular atrophy (SMA), and newborn screening programs have been implemented to detect the disease before onset of symptoms. However, data from controlled studies that reliably confirm the benefits of newborn screening are lacking. Objective: To compare data obtained on patients with SMA diagnosed through newborn screening and those diagnosed after clinical symptom onset. Design, Setting, and Participants: This nonrandomized controlled trial used data from the SMARTCARE registry to evaluate all children born between January 2018 and September 2021 with genetically confirmed SMA and up to 3 SMN2 copies. The registry includes data from 70 participating centers in Germany, Austria, and Switzerland. Data analysis was performed in February 2023 so that all patients had a minimal follow-up of 18 months. Exposure: Patients born in 2 federal states in Germany underwent screening in a newborn screening pilot project. All other patients were diagnosed after clinical symptom onset. All patients received standard care within the same health care system. Main Outcomes: The primary end point was the achievement of motor milestones. Results: A total of 234 children (123 [52.6%] female) were identified who met inclusion criteria and were included in the analysis: 44 (18.8%) in the newborn screening cohort and 190 children (81.2%) in the clinical symptom onset cohort. The mean (SD) age at start of treatment with 1 of the approved disease-modifying drugs was 1.3 (2.2) months in the newborn screening cohort and 10.7 (9.1) months in the clinical symptom onset cohort. In the newborn screening cohort, 40 of 44 children (90.9%) gained the ability to sit independently vs 141 of 190 (74.2%) in the clinical symptom onset cohort. For independent ambulation, the ratio was 28 of 40 (63.6%) vs 28 of 190 (14.7%). Conclusions and Relevance: This nonrandomized controlled trial demonstrated effectiveness of newborn screening for infants with SMA in the real-world setting. Functional outcomes and thus the response to treatment were significantly better in the newborn screening cohort compared to the unscreened clinical symptom onset group. Trial Registration: German Clinical Trials Register: DRKS00012699.