| 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. |
- Middeldorp, Christel M., et al.
(författare)
-
The Early Growth Genetics (EGG) and EArly Genetics and Lifecourse Epidemiology (EAGLE) consortia : design, results and future prospects
- 2019
-
Ingår i: European Journal of Epidemiology. - : Springer Science and Business Media LLC. - 0393-2990 .- 1573-7284. ; 34:3, s. 279-300
-
Tidskriftsartikel (refereegranskat)abstract
- The impact of many unfavorable childhood traits or diseases, such as low birth weight and mental disorders, is not limited to childhood and adolescence, as they are also associated with poor outcomes in adulthood, such as cardiovascular disease. Insight into the genetic etiology of childhood and adolescent traits and disorders may therefore provide new perspectives, not only on how to improve wellbeing during childhood, but also how to prevent later adverse outcomes. To achieve the sample sizes required for genetic research, the Early Growth Genetics (EGG) and EArly Genetics and Lifecourse Epidemiology (EAGLE) consortia were established. The majority of the participating cohorts are longitudinal population-based samples, but other cohorts with data on early childhood phenotypes are also involved. Cohorts often have a broad focus and collect(ed) data on various somatic and psychiatric traits as well as environmental factors. Genetic variants have been successfully identified for multiple traits, for example, birth weight, atopic dermatitis, childhood BMI, allergic sensitization, and pubertal growth. Furthermore, the results have shown that genetic factors also partly underlie the association with adult traits. As sample sizes are still increasing, it is expected that future analyses will identify additional variants. This, in combination with the development of innovative statistical methods, will provide detailed insight on the mechanisms underlying the transition from childhood to adult disorders. Both consortia welcome new collaborations. Policies and contact details are available from the corresponding authors of this manuscript and/or the consortium websites.
|
|
| 3. |
- Carlsson, K. Steen, et al.
(författare)
-
Costs of diabetes complications : hospital based care and production loss for 392,200 people with type 2 diabetes and matched controls in Sweden
- 2020
-
Ingår i: Diabetologia. - : Springer. - 0012-186X .- 1432-0428. ; 63:Suppl. 1, s. S121-S121
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- Background and aims: The prevalence of diabetes has increased rapidly over the last decades worldwide. The risk of complications and medical consequences is well known and identified as key driver of costs. Less evidence on the impact of individual diabetic complications on the societal burden is available. The objective was to analyse costs of hospital-based health care and work absence related to individual macrovascular and microvascular complications of type 2 diabetes in Sweden in 2016.Materials and methods: The study used data from a Swedish retrospective observational database cross-linking 20 years of individual-level data (1997-2016) from national population-based health, social insurance and socio-economic registers for 392,200 people with type 2 diabetes and matched controls (5:1). Diabetes status and presence of 19 types of complications were derived from years 1997-2016 while the costs of hospital-based care and of production loss due to diabetes complications were estimated for 2016. Regression analysis was used for comparison to controls, to attribute production loss to individual complications, and to account for joint presence of complications.Results: Complications are prevalent and patterns complex in type 2 diabetes (Fig. 1). Use of hospital care for complications was higher compared to controls: 86,104 vs 24,608 outpatient visits per 100,000 persons and 9,894 vs 2,546 inpatient admissions per 100,000 persons (p<0.001) in 2016. 26% vs 12% had ≥1 hospital contact. The corresponding total costs of hospital-based care fo rcomplications were EUR 91,875 vs EUR 23,222 per 100 persons (p<0.001) and 75% were directly attributed to diabetes (EUR 689/person). Regression analyses distributed the costs of days absent from work across diabetes complications, basic type 2 diabetes effect and unattributed causes: diabetes complications amounted to EUR 2,165/person in 2016. Key drivers of costs of production loss were macrovascular complications angina pectoris, heart failure and stroke, and microvascular complications eye disease including retinopathy, kidney disease and neuropathy. Early mortality in working ages cost additional EUR 579/person and medications used in risk-factor treatment amounted to EUR 418/person.Conclusion: The economic burden of complications in type 2 diabetes is substantial. Costs of productivity loss in this study were found to be greater than those of hospital-based care highlighting the need for considering treatment consequences in a societal perspective in research and policy.
|
|
| 4. |
- Djekic, Demir, et al.
(författare)
-
Body Mass Index in Adolescence and Long-Term Risk of Early Incident Atrial Fibrillation and Subsequent Mortality, Heart Failure, and Ischemic Stroke
- 2022
-
Ingår i: Journal of the American Heart Association. - : John Wiley & Sons. - 2047-9980. ; 11:21
-
Tidskriftsartikel (refereegranskat)abstract
- Background: We sought to determine the role of obesity in adolescent men on development of atrial fibrillation (AF) and subsequent associated clinical outcomes in subjects diagnosed with AF.Methods and Results: We conducted a nationwide, register-based, cohort study of 1 704 467 men (mean age, 18.3±0.75 years) enrolled in compulsory military service in Sweden from 1969 through 2005. Height and weight, blood pressure, fitness, muscle strength, intelligence quotient, and medical disorders were recorded at baseline. Records obtained from the National Inpatient Registry and the Cause of Death Register were used to determine incidence and clinical outcomes of AF. During a median follow-up of 32 years (interquartile range, 24-41 years), 36 693 cases (mean age at diagnosis, 52.4±10.6 years) of AF were recorded. The multivariable-adjusted hazard ratio (HR) for AF increased from 1.06 (95% CI, 1.03-1.10) in individuals with body mass index (BMI) of 20.0 to <22.5 kg/m2 to 3.72 (95% CI, 2.44-5.66) among men with BMI of 40.0 to 50.0 kg/m2, compared with those with BMI of 18.5 to <20.0 kg/m2. During a median follow-up of ≈6 years in patients diagnosed with AF, we identified 3767 deaths, 3251 cases of incident heart failure, and 921 cases of ischemic stroke. The multivariable-adjusted HRs for all-cause mortality, incident heart failure, and ischemic stroke in AF-diagnosed men with baseline BMI >30 kg/m2 compared with those with BMI <20 kg/m2 were 2.86 (95% CI, 2.30-3.56), 3.42 (95% CI, 2.50-4.68), and 2.34 (95% CI, 1.52-3.61), respectively.Conclusions: Increasing BMI in adolescent men is strongly associated with early AF, and with subsequent worse clinical outcomes in those diagnosed with AF with respect to all-cause mortality, incident heart failure, and ischemic stroke.
|
|
