Refine
Language
- English (7)
Has Fulltext
- yes (7)
Is part of the Bibliography
- no (7)
Keywords
- ARDS (1)
- COVID-19 (1)
- COVID‐19 (1)
- CVID (1)
- Comparative analysis (1)
- Critical care (1)
- Deep neural network (1)
- European Society for Immunodeficiencies (ESID) (1)
- German PID-NET registry (1)
- Glioblastoma (1)
Institute
- Medizin (7) (remove)
Background: Intensive Care Resources are heavily utilized during the COVID-19 pandemic. However, risk stratification and prediction of SARS-CoV-2 patient clinical outcomes upon ICU admission remain inadequate. This study aimed to develop a machine learning model, based on retrospective & prospective clinical data, to stratify patient risk and predict ICU survival and outcomes. Methods: A Germany-wide electronic registry was established to pseudonymously collect admission, therapeutic and discharge information of SARS-CoV-2 ICU patients retrospectively and prospectively. Machine learning approaches were evaluated for the accuracy and interpretability of predictions. The Explainable Boosting Machine approach was selected as the most suitable method. Individual, non-linear shape functions for predictive parameters and parameter interactions are reported. Results: 1039 patients were included in the Explainable Boosting Machine model, 596 patients retrospectively collected, and 443 patients prospectively collected. The model for prediction of general ICU outcome was shown to be more reliable to predict “survival”. Age, inflammatory and thrombotic activity, and severity of ARDS at ICU admission were shown to be predictive of ICU survival. Patients’ age, pulmonary dysfunction and transfer from an external institution were predictors for ECMO therapy. The interaction of patient age with D-dimer levels on admission and creatinine levels with SOFA score without GCS were predictors for renal replacement therapy. Conclusions: Using Explainable Boosting Machine analysis, we confirmed and weighed previously reported and identified novel predictors for outcome in critically ill COVID-19 patients. Using this strategy, predictive modeling of COVID-19 ICU patient outcomes can be performed overcoming the limitations of linear regression models. Trial registration “ClinicalTrials” (clinicaltrials.gov) under NCT04455451.
Importance: The entry of artificial intelligence into medicine is pending. Several methods have been used for the predictions of structured neuroimaging data, yet nobody compared them in this context.
Objective: Multi-class prediction is key for building computational aid systems for differential diagnosis. We compared support vector machine, random forest, gradient boosting, and deep feed-forward neural networks for the classification of different neurodegenerative syndromes based on structural magnetic resonance imaging.
Design, setting, and participants: Atlas-based volumetry was performed on multi-centric T1-weighted MRI data from 940 subjects, i.e., 124 healthy controls and 816 patients with ten different neurodegenerative diseases, leading to a multi-diagnostic multi-class classification task with eleven different classes.
Interventions: N.A.
Main outcomes and measures: Cohen’s kappa, accuracy, and F1-score to assess model performance.
Results: Overall, the neural network produced both the best performance measures and the most robust results. The smaller classes however were better classified by either the ensemble learning methods or the support vector machine, while performance measures for small classes were comparatively low, as expected. Diseases with regionally specific and pronounced atrophy patterns were generally better classified than diseases with widespread and rather weak atrophy.
Conclusions and relevance: Our study furthermore underlines the necessity of larger data sets but also calls for a careful consideration of different machine learning methods that can handle the type of data and the classification task best.
Introduction: The German PID-NET registry was founded in 2009, serving as the first national registry of patients with primary immunodeficiencies (PID) in Germany. It is part of the European Society for Immunodeficiencies (ESID) registry. The primary purpose of the registry is to gather data on the epidemiology, diagnostic delay, diagnosis, and treatment of PIDs.
Methods: Clinical and laboratory data was collected from 2,453 patients from 36 German PID centres in an online registry. Data was analysed with the software Stata® and Excel.
Results: The minimum prevalence of PID in Germany is 2.72 per 100,000 inhabitants. Among patients aged 1–25, there was a clear predominance of males. The median age of living patients ranged between 7 and 40 years, depending on the respective PID. Predominantly antibody disorders were the most prevalent group with 57% of all 2,453 PID patients (including 728 CVID patients). A gene defect was identified in 36% of patients. Familial cases were observed in 21% of patients. The age of onset for presenting symptoms ranged from birth to late adulthood (range 0–88 years). Presenting symptoms comprised infections (74%) and immune dysregulation (22%). Ninety-three patients were diagnosed without prior clinical symptoms. Regarding the general and clinical diagnostic delay, no PID had undergone a slight decrease within the last decade. However, both, SCID and hyper IgE- syndrome showed a substantial improvement in shortening the time between onset of symptoms and genetic diagnosis. Regarding treatment, 49% of all patients received immunoglobulin G (IgG) substitution (70%—subcutaneous; 29%—intravenous; 1%—unknown). Three-hundred patients underwent at least one hematopoietic stem cell transplantation (HSCT). Five patients had gene therapy.
Conclusion: The German PID-NET registry is a precious tool for physicians, researchers, the pharmaceutical industry, politicians, and ultimately the patients, for whom the outcomes will eventually lead to a more timely diagnosis and better treatment.
Antisynthetase syndrome (ASSD) is a rare clinical condition that is characterized by the occurrence of a classic clinical triad, encompassing myositis, arthritis, and interstitial lung disease (ILD), along with specific autoantibodies that are addressed to different aminoacyl tRNA synthetases (ARS). Until now, it has been unknown whether the presence of a different ARS might affect the clinical presentation, evolution, and outcome of ASSD. In this study, we retrospectively recorded the time of onset, characteristics, clustering of triad findings, and survival of 828 ASSD patients (593 anti-Jo1, 95 anti-PL7, 84 anti-PL12, 38 anti-EJ, and 18 anti-OJ), referring to AENEAS (American and European NEtwork of Antisynthetase Syndrome) collaborative group’s cohort. Comparisons were performed first between all ARS cases and then, in the case of significance, while using anti-Jo1 positive patients as the reference group. The characteristics of triad findings were similar and the onset mainly began with a single triad finding in all groups despite some differences in overall prevalence. The “ex-novo” occurrence of triad findings was only reduced in the anti-PL12-positive cohort, however, it occurred in a clinically relevant percentage of patients (30%). Moreover, survival was not influenced by the underlying anti-aminoacyl tRNA synthetase antibodies’ positivity, which confirmed that antisynthetase syndrome is a heterogeneous condition and that antibody specificity only partially influences the clinical presentation and evolution of this condition.
Scores to identify patients at high risk of progression of coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), may become instrumental for clinical decision-making and patient management. We used patient data from the multicentre Lean European Open Survey on SARS-CoV-2-Infected Patients (LEOSS) and applied variable selection to develop a simplified scoring system to identify patients at increased risk of critical illness or death. A total of 1946 patients who tested positive for SARS-CoV-2 were included in the initial analysis and assigned to derivation and validation cohorts (n = 1297 and n = 649, respectively). Stability selection from over 100 baseline predictors for the combined endpoint of progression to the critical phase or COVID-19-related death enabled the development of a simplified score consisting of five predictors: C-reactive protein (CRP), age, clinical disease phase (uncomplicated vs. complicated), serum urea, and D-dimer (abbreviated as CAPS-D score). This score yielded an area under the curve (AUC) of 0.81 (95% confidence interval [CI]: 0.77–0.85) in the validation cohort for predicting the combined endpoint within 7 days of diagnosis and 0.81 (95% CI: 0.77–0.85) during full follow-up. We used an additional prospective cohort of 682 patients, diagnosed largely after the “first wave” of the pandemic to validate the predictive accuracy of the score and observed similar results (AUC for the event within 7 days: 0.83 [95% CI: 0.78–0.87]; for full follow-up: 0.82 [95% CI: 0.78–0.86]). An easily applicable score to calculate the risk of COVID-19 progression to critical illness or death was thus established and validated.
Bipolar disorder (BD) is a genetically complex mental illness characterized by severe oscillations of mood and behavior. Genome-wide association studies (GWAS) have identified several risk loci that together account for a small portion of the heritability. To identify additional risk loci, we performed a two-stage meta-analysis of >9 million genetic variants in 9,784 bipolar disorder patients and 30,471 controls, the largest GWAS of BD to date. In this study, to increase power we used ~2,000 lithium-treated cases with a long-term diagnosis of BD from the Consortium on Lithium Genetics, excess controls, and analytic methods optimized for markers on the Xchromosome. In addition to four known loci, results revealed genome-wide significant associations at two novel loci: an intergenic region on 9p21.3 (rs12553324, p = 5.87×10-9; odds ratio = 1.12) and markers within ERBB2 (rs2517959, p = 4.53×10-9; odds ratio = 1.13). No significant X-chromosome associations were detected and X-linked markers explained very little BD heritability. The results add to a growing list of common autosomal variants involved in BD and illustrate the power of comparing well-characterized cases to an excess of controls in GWAS.
Purpose: The role of obesity in glioblastoma remains unclear, as previous analyses have reported contradicting results. Here, we evaluate the prognostic impact of obesity in two trial populations; CeTeG/NOA-09 (n = 129) for MGMT methylated glioblastoma patients comparing temozolomide (TMZ) to lomustine/TMZ, and GLARIUS (n = 170) for MGMT unmethylated glioblastoma patients comparing TMZ to bevacizumab/irinotecan, both in addition to surgery and radiotherapy.
Methods: The impact of obesity (BMI ≥ 30 kg/m2) on overall survival (OS) and progression-free survival (PFS) was investigated with Kaplan–Meier analysis and log-rank tests. A multivariable Cox regression analysis was performed including known prognostic factors as covariables.
Results: Overall, 22.6% of patients (67 of 297) were obese. Obesity was associated with shorter survival in patients with MGMT methylated glioblastoma (median OS 22.9 (95% CI 17.7–30.8) vs. 43.2 (32.5–54.4) months for obese and non-obese patients respectively, p = 0.001), but not in MGMT unmethylated glioblastoma (median OS 17.1 (15.8–18.9) vs 17.6 (14.7–20.8) months, p = 0.26). The prognostic impact of obesity in MGMT methylated glioblastoma was confirmed in a multivariable Cox regression (adjusted odds ratio: 2.57 (95% CI 1.53–4.31), p < 0.001) adjusted for age, sex, extent of resection, baseline steroids, Karnofsky performance score, and treatment arm.
Conclusion: Obesity was associated with shorter survival in MGMT methylated, but not in MGMT unmethylated glioblastoma patients.