| 1. |
|
|
| 2. |
- Romagnoni, A, et al.
(författare)
-
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
- 2019
-
Ingår i: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 9:1, s. 10351-
-
Tidskriftsartikel (refereegranskat)abstract
- Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.
|
|
| 3. |
|
|
| 4. |
- Bayley, PJ, et al.
(författare)
-
2013 SYR Accepted Poster Abstracts
- 2013
-
Ingår i: International journal of yoga therapy. - 1531-2054. ; 23:1, s. 32-53
-
Tidskriftsartikel (refereegranskat)
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Charidimou, A, et al.
(författare)
-
Clinical significance of cerebral microbleeds on MRI: A comprehensive meta-analysis of risk of intracerebral hemorrhage, ischemic stroke, mortality, and dementia in cohort studies (v1)
- 2018
-
Ingår i: International journal of stroke : official journal of the International Stroke Society. - : SAGE Publications. - 1747-4949. ; 13:5, s. 454-468
-
Tidskriftsartikel (refereegranskat)abstract
- Cerebral microbleeds can confer a high risk of intracerebral hemorrhage, ischemic stroke, death and dementia, but estimated risks remain imprecise and often conflicting. We investigated the association between cerebral microbleeds presence and these outcomes in a large meta-analysis of all published cohorts including: ischemic stroke/TIA, memory clinic, “high risk” elderly populations, and healthy individuals in population-based studies. Methods Cohorts (with > 100 participants) that assessed cerebral microbleeds presence on MRI, with subsequent follow-up (≥3 months) were identified. The association between cerebral microbleeds and each of the outcomes (ischemic stroke, intracerebral hemorrhage, death, and dementia) was quantified using random effects models of (a) unadjusted crude odds ratios and (b) covariate-adjusted hazard rations. Results We identified 31 cohorts ( n = 20,368): 19 ischemic stroke/TIA ( n = 7672), 4 memory clinic ( n = 1957), 3 high risk elderly ( n = 1458) and 5 population-based cohorts ( n = 11,722). Cerebral microbleeds were associated with an increased risk of ischemic stroke (OR: 2.14; 95% CI: 1.58–2.89 and adj-HR: 2.09; 95% CI: 1.71–2.57), but the relative increase in future intracerebral hemorrhage risk was greater (OR: 4.65; 95% CI: 2.68–8.08 and adj-HR: 3.93; 95% CI: 2.71–5.69). Cerebral microbleeds were an independent predictor of all-cause mortality (adj-HR: 1.36; 95% CI: 1.24–1.48). In three population-based studies, cerebral microbleeds were independently associated with incident dementia (adj-HR: 1.35; 95% CI: 1.00–1.82). Results were overall consistent in analyses stratified by different populations, but with different degrees of heterogeneity. Conclusions Our meta-analysis shows that cerebral microbleeds predict an increased risk of stroke, death, and dementia and provides up-to-date effect sizes across different clinical settings. These pooled estimates can inform clinical decisions and trials, further supporting cerebral microbleeds role as biomarkers of underlying subclinical brain pathology in research and clinical settings.
|
|
