| 1. |
|
|
| 2. |
- Kabir, Misha, et al.
(författare)
-
DECIDE: Delphi Expert Consensus Statement on Inflammatory Bowel Disease Dysplasia Shared Management Decision-Making
- 2023
-
Ingår i: Journal of Crohn's & Colitis. - : OXFORD UNIV PRESS. - 1873-9946 .- 1876-4479. ; 17:10, s. 1652-1671
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Aims Inflammatory bowel disease colitis-associated dysplasia is managed with either enhanced surveillance and endoscopic resection or prophylactic surgery. The rate of progression to cancer after a dysplasia diagnosis remains uncertain in many cases and patients have high thresholds for accepting proctocolectomy. Individualised discussion of management options is encouraged to take place between patients and their multidisciplinary teams for best outcomes. We aimed to develop a toolkit to support a structured, multidisciplinary and shared decision-making approach to discussions about dysplasia management options between clinicians and their patients. Methods Evidence from systematic literature reviews, mixed-methods studies conducted with key stakeholders, and decision-making expert recommendations were consolidated to draft consensus statements by the DECIDE steering group. These were then subjected to an international, multidisciplinary modified electronic Delphi process until an a priori threshold of 80% agreement was achieved to establish consensus for each statement. Results In all, 31 members [15 gastroenterologists, 14 colorectal surgeons and two nurse specialists] from nine countries formed the Delphi panel. We present the 18 consensus statements generated after two iterative rounds of anonymous voting. Conclusions By consolidating evidence for best practice using literature review and key stakeholder and decision-making expert consultation, we have developed international consensus recommendations to support health care professionals counselling patients on the management of high cancer risk colitis-associated dysplasia. The final toolkit includes clinician and patient decision aids to facilitate shared decision-making.
|
|
| 3. |
- Mcteer, Matthew, et al.
(författare)
-
Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information
- 2024
-
Ingår i: PLOS ONE. - : PUBLIC LIBRARY SCIENCE. - 1932-6203. ; 19:2
-
Tidskriftsartikel (refereegranskat)abstract
- Aims Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints.Methods Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable.Results Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance.Conclusions This study developed a series of ML models of accuracy ranging from 71.9-99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.
|
|
| 4. |
- Szaló, Gábor, 1982, et al.
(författare)
-
Impaired artery elasticity predicts cardiovascular morbidity and mortality- A longitudinal study in the Vara-Skövde Cohort.
- 2023
-
Ingår i: Journal of human hypertension. - : Springer Nature. - 1476-5527 .- 0950-9240. ; 38, s. 140-5
-
Tidskriftsartikel (refereegranskat)abstract
- It is still debated whether arterial elasticity provides prognostic information for cardiovascular risk beyond blood pressure measurements in a healthy population. To investigate the association between arterial elasticity obtained by radial artery pulse wave analysis and risk for cardiovascular diseases (CVD) in men and women. In 2002-2005, 2362 individuals (men=1186, 50.2%) not taking antihypertensive medication were included. C2 (small artery elasticity) was measured using the HDI/Pulse Wave CR2000. Data on acute myocardial infarction or stroke, fatal or non-fatal, was obtained between 2002-2019. Cox- regression was used to investigate associations between C2 and future CVD, adjusting for confounding factors such as age, sex, systolic blood pressure, heart rate, HOMA-IR (Homeostatic Model Assessment for Insulin Resistance), LDL- cholesterol, CRP (C-Reactive Protein), alcohol consumption, smoking and physical activity. At baseline, the mean age of 46±10.6 years and over the follow-up period, we observed 108 events 70 events in men [event rate: 5.9%], 38 in women [event rate: 3.2%]. In the fully adjusted model, and for each quartile decrease in C2, there was a significant increase in the risk for incident CVD by 36%. (HR=1.36, 95% CI: 1.01-1.82, p=0.041). The results were accentuated for all men (HR=1.74, 95% CI: 1.21-2.50, p=0.003) and women over the age of 50 years (HR=1.70, 95% CI: 0.69-4.20). We showed a strong and independent association between C2 and CVD in men. In women after menopause, similar tendencies and effect sizes were observed.
|
|
