| 1. |
|
|
| 2. |
- Nunes, A, et al.
(författare)
-
Using structural MRI to identify bipolar disorders - 13 site machine learning study in 3020 individuals from the ENIGMA Bipolar Disorders Working Group
- 2020
-
Ingår i: Molecular psychiatry. - : Springer Science and Business Media LLC. - 1476-5578 .- 1359-4184. ; 25:9, s. 2130-2143
-
Tidskriftsartikel (refereegranskat)abstract
- Bipolar disorders (BDs) are among the leading causes of morbidity and disability. Objective biological markers, such as those based on brain imaging, could aid in clinical management of BD. Machine learning (ML) brings neuroimaging analyses to individual subject level and may potentially allow for their diagnostic use. However, fair and optimal application of ML requires large, multi-site datasets. We applied ML (support vector machines) to MRI data (regional cortical thickness, surface area, subcortical volumes) from 853 BD and 2167 control participants from 13 cohorts in the ENIGMA consortium. We attempted to differentiate BD from control participants, investigated different data handling strategies and studied the neuroimaging/clinical features most important for classification. Individual site accuracies ranged from 45.23% to 81.07%. Aggregate subject-level analyses yielded the highest accuracy (65.23%, 95% CI = 63.47–67.00, ROC-AUC = 71.49%, 95% CI = 69.39–73.59), followed by leave-one-site-out cross-validation (accuracy = 58.67%, 95% CI = 56.70–60.63). Meta-analysis of individual site accuracies did not provide above chance results. There was substantial agreement between the regions that contributed to identification of BD participants in the best performing site and in the aggregate dataset (Cohen’s Kappa = 0.83, 95% CI = 0.829–0.831). Treatment with anticonvulsants and age were associated with greater odds of correct classification. Although short of the 80% clinically relevant accuracy threshold, the results are promising and provide a fair and realistic estimate of classification performance, which can be achieved in a large, ecologically valid, multi-site sample of BD participants based on regional neurostructural measures. Furthermore, the significant classification in different samples was based on plausible and similar neuroanatomical features. Future multi-site studies should move towards sharing of raw/voxelwise neuroimaging data.
|
|
| 3. |
- White, Harvey D., et al.
(författare)
-
In patients with stable coronary heart disease, low-density lipoprotein-cholesterol levels < 70 mg/dL and glycosylated hemoglobin A1c < 7% are associated with lower major cardiovascular events
- 2020
-
Ingår i: American Heart Journal. - : Elsevier BV. - 0002-8703 .- 1097-6744. ; 225, s. 97-107
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundIn patients with stable coronary heart disease, it is not known whether achievement of standard of care (SOC) targets in addition to evidence-based medicine (EBM) is associated with lower major adverse cardiovascular events (MACE): cardiovascular death, myocardial infarction, and stroke.MethodsEBM use was recommended in the STabilisation of Atherosclerotic plaque By Initiation of darapLadIb TherapY trial. SOC targets were blood pressure (BP) <140/90 mm Hg and low-density lipoprotein-cholesterol (LDL-C) <100 mg/dL and <70 mg/dL. In patients with diabetes, glycosylated hemoglobin A1c (HbA1c) < 7% and BP of <130/80 mm Hg were recommended. Feedback to investigators about rates of EBM and SOC was provided regularly.ResultsIn 13,623 patients, 1-year landmark analysis assessed the association between EBM, SOC targets, and MACE during follow-up of 2.7 years (median) after adjustment in a Cox proportional hazards model.At 1 year, aspirin was prescribed in 92.5% of patients, statins in 97.2%, β-blockers in 79.0%, and angiotensin-converting enzyme inhibitors/angiotensin-II receptor blockers in 76.9%. MACE was lower with LDL-C < 100 mg/dL (70-99 mg/dL) compared with LDL-C ≥ 100 mg/dL (hazard ratio [HR] 0.694, 95% CI 0.594-0.811) and lower with LDL-C < 70 mg/dL compared with LDL-C < 100 mg/dL (70-99 mg/dL) (HR 0.834, 95% CI 0.708-0.983). MACE was lower with HbA1c < 7% compared with HbA1c ≥ 7% (HR 0.705, 95% CI 0.573-0.866). There was no effect of BP targets on MACE.ConclusionsMACE was lower with LDL-C < 100 mg/dL (70-99 mg/dL) and even lower with LDL-C < 70 mg/dL. MACE in patients with diabetes was lower with HbA1c < 7%. Achievement of targets is associated with improved patient outcomes.
|
|
| 4. |
|
|
