| 1. |
- 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.
|
|
| 2. |
- Manzano-Nunez, Ramiro, et al.
(författare)
-
Outcomes and management approaches of resuscitative endovascular balloon occlusion of the aorta based on the income of countries
- 2020
-
Ingår i: World Journal of Emergency Surgery. - : Springer Science and Business Media LLC. - 1749-7922. ; 15:57
-
Tidskriftsartikel (refereegranskat)abstract
- © 2020 The Author(s). Background: Resuscitative endovascular balloon occlusion of the aorta (REBOA) could provide a survival benefit to severely injured patients as it may improve their initial ability to survive the hemorrhagic shock. Although the evidence supporting the use of REBOA is not conclusive, its use has expanded worldwide. We aim to compare the management approaches and clinical outcomes of trauma patients treated with REBOA according to the countries' income based on the World Bank Country and Lending Groups. Methods: We used data from the AORTA (USA) and the ABOTrauma (multinational) registries. Patients were stratified into two groups: (1) high-income countries (HICs) and (2) low-to-middle income countries (LMICs). Propensity score matching extracted 1:1 matched pairs of subjects who were from an LMIC or a HIC based on age, gender, the presence of pupillary response on admission, impeding hypotension (SBP ≤ 80), trauma mechanism, ISS, the necessity of CPR on arrival, the location of REBOA insertion (emergency room or operating room) and the amount of PRBCs transfused in the first 24 h. Logistic regression (LR) was used to examine the association of LMICs and mortality. Results: A total of 817 trauma patients from 14 countries were included. Blind percutaneous approach and surgical cutdown were the preferred means of femoral cannulation in HICs and LIMCs, respectively. Patients from LMICs had a significantly higher occurrence of MODS and respiratory failure. LR showed no differences in mortality for LMICs when compared to HICs; neither in the non-matched cohort (OR = 0.63; 95% CI: 0.36-1.09; p = 0.1) nor in the matched cohort (OR = 1.45; 95% CI: 0.63-3,33; p = 0.3). Conclusion: There is considerable variation in the management practices of REBOA and the outcomes associated with this intervention between HICs and LMICs. Although we found significant differences in multiorgan and respiratory failure rates, there were no differences in the risk-adjusted odds of mortality between the groups analyzed. Trauma surgeons practicing REBOA around the world should joint efforts to standardize the practice of this endovascular technology worldwide.
|
|
