| 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. |
- Elias, Kevin M., et al.
(författare)
-
The Reporting on ERAS Compliance, Outcomes, and Elements Research (RECOvER) Checklist : A Joint Statement by the ERAS® and ERAS® USA Societies
- 2019
-
Ingår i: World Journal of Surgery. - : Springer. - 0364-2313 .- 1432-2323. ; 43:1, s. 1-8
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Enhanced recovery after surgery (ERAS) programs are multimodal care pathways designed to minimize the physiological and psychological impact of surgery for patients. Increased compliance with ERAS guidelines is associated with improved patient outcomes across surgical types. As ERAS programs have proliferated, an unintentional effect has been significant variation in how ERAS-related studies are reported in the literature.METHODS: Society launched an effort to create an instrument to assist authors in manuscript preparation. Criteria to include were selected by a combination of literature review and expert opinion. The final checklist was refined by group consensus.RESULTS: The Societies present the Reporting on ERAS Compliance, Outcomes, and Elements Research (RECOvER) Checklist. The tool contains 20 items including best practices for reporting clinical pathways, compliance auditing, and formatting guidelines.CONCLUSIONS: The RECOvER Checklist is intended to provide a standardized framework for the reporting of ERAS-related studies. The checklist can also assist reviewers in evaluating the quality of ERAS-related manuscripts. Authors are encouraged to include the RECOvER Checklist when submitting ERAS-related studies to peer-reviewed journals.
|
|
| 3. |
- Malm, Eva, et al.
(författare)
-
Alteration of rod and cone function in children with Usher syndrome
- 2011
-
Ingår i: European Journal of Ophthalmology. - Milan, Italy : Wichtig Editore Srl. - 1120-6721 .- 1724-6016. ; 21:1, s. 30-38
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: To evaluate the retinal function, with emphasis on phenotype and rate of progression, in infants and children with different genotypes of Usher syndrome.Methods: Fourteen children (2-10 years of age) with retinitis pigmentosa and hearing impairment were examined with full-field electroretinography (ERG) during general anesthesia, ophthalmologic examination, and genetic analysis. Five children were repeatedly examined (follow-up 5-10 years) with full-field ERG under local anesthesia and in 2 children multifocal ERG and optical coherence tomography (OCT) were performed. These results were compared to full-field ERG data from 58 children without retinal eye disorder.Results: Six children were genotyped as Usher 1B, 2A, and 3A. Full-field ERG demonstrated early alterations corresponding to a rod-cone dystrophy in all children. A remaining rod function could be verified in the majority of the children up to 4 years of age. After 4 years of age, there was a further deterioration of the rod function; the progress was severe in Usher types 1 and 2 and moderate in Usher type 3. In all children, the cone function was moderately reduced, in a few cases almost normal. The results from the 58 children without retinal disorder confirm that full-field ERG during general anesthesia is reliable. Multifocal ERG confirmed a preserved central cone function and in OCT there were discrete structural alterations.Conclusions: Full-field ERG during general anesthesia in children with Usher syndrome demonstrates variable phenotypes and different degrees in rate of progression during childhood.
|
|
| 4. |
- Sharma, T., et al.
(författare)
-
Biomarkers associated with vulnerable plaques
- 2022
-
Ingår i: European Heart Journal. - : Oxford University Press. - 0195-668X .- 1522-9645. ; 43:Suppl. 2, s. 1292-1292
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Background: Cardiovascular heart disease is the leading cause of mortality worldwide, with the rupture or thrombosis of an atherosclerotic plaque being the main reason behind an acute coronary syndrome. It has already been established that the morphology of atherosclerotic plaques determine their stability. A lipid rich lesion with a thin fibrous cap is more prone to rupture compared to solid fibrous lesions. In the PROSPECTII study we used Near infrared spectroscopy (NIRS) and Intravascular ultrasound (IVUS) to identify atherosclerotic plaques in the coronary arteries; NIRS-derived lipid core burden index (LCBI) and IVUS-derived plaque burden (PB) identified plaques that caused adverse cardiovascular events.Purpose: Our aim is to find biomarkers associated with LCBI or PB, to understand the development of vulnerable plaques.Methods: 902 patients were enrolled in this study after successful percutaneous coronary intervention (PCI). A combined NIRS-IVUS catheter was then used to analyze approximately 200m of coronary arteries. Blood samples for biomarker analysis were taken before the PCI procedure and plasma levels of 182 proteins associated with cardiovascular disease were assessed using a novel method for measuring proximity extension assay. Adjusted linear regression models were calculated between the biomarkers and the outcomes of interest, followed by a false discovery rate (FDR) correction.Results: We found 24 proteins associated with plaque burden and 28 proteins associated with LCBI after using a cut off of two tailed P value <0.05. An overlap of 8 biomarkers could be seen between the two groups. After adjusting the P values with FDR, Angiopoeitin like 3 (ANGPTL3) retain edits association to LCBI, and Interleukin 18 receptor 1 (IL18R1) and colony stimulating factor 1 (CSF-1) to plaque burden.Conclusion: We were able to identify different biomarker patterns associated with plaque burden compared to lipid rich vulnerable plaques. ANGPTL3 was shown to only have an association with lipid rich plaques and not with solid fibrous lesions which further supports its role in vulnerable plaques.
|
|
