| 1. |
- Jacobson, Petra, et al.
(author)
-
Unleashing the Power of Very Small Data to Predict Acute Exacerbations of Chronic Obstructive Pulmonary Disease
- 2023
-
In: The International Journal of Chronic Obstructive Pulmonary Disease. - : Dove Medical Press Ltd. - 1176-9106 .- 1178-2005. ; 18, s. 1457-1473
-
Journal article (peer-reviewed)abstract
- Introduction: In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD). Methods: We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed. Results: We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data. Discussion: To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is “maintenance medication changes by HBHC”. This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs. Conclusion: The experiments return useful insights about the use of small data for ML. © 2023 Jacobson et al.
|
|
| 2. |
- Kuna, Vijay Kumar, 1987, et al.
(author)
-
Successful tissue engineering of competent allogeneic venous valves
- 2015
-
In: Journal of Vascular Surgery. - : Elsevier Inc.. - 0741-5214. ; 3:4, s. 421-430
-
Journal article (peer-reviewed)abstract
- Objective The purpose of this study was to evaluate whether tissue-engineered human allogeneic vein valves have a normal closure time (competency) and tolerate reflux pressure in vitro. Methods Fifteen human allogeneic femoral vein segments containing valves were harvested from cadavers. Valve closure time and resistance to reflux pressure (100 mm Hg) were assessed in an in vitro model to verify competency of the vein valves. The segments were tissue engineered using the technology of decellularization (DC) and recellularization (RC). The decellularized and recellularized vein segments were characterized biochemically, immunohistochemically, and biomechanically. Results Four of 15 veins with valves were found to be incompetent immediately after harvest. In total, 2 of 4 segments with incompetent valves and 10 of 11 segments with competent valves were further decellularized using detergents and DNAse. DC resulted in significant decrease in host DNA compared with controls. DC scaffolds, however, retained major extracellular matrix proteins and mechanical integrity. RC resulted in successful repopulation of the lumen and valves of the scaffold with endothelial and smooth muscle cells. Valve mechanical parameters were similar to the native tissue even after DC. Eight of 10 veins with competent valves remained competent even after DC and RC, whereas the two incompetent valves remained incompetent even after DC and RC. The valve closure time to reflux pressure of the tissue-engineered veins was <0.5 second. Conclusions Tissue-engineered veins with valves provide a valid template for future preclinical studies and eventual clinical applications. This technique may enable replacement of diseased incompetent or damaged deep veins to treat axial reflux and thus reduce ambulatory venous hypertension. Copyright © 2015 by the Society for Vascular Surgery. Published by Elsevier Inc.
|
|
| 3. |
- Patel, Harshida, 1958, et al.
(author)
-
Home care as an option in worsening chronic heart failure -- a pilot study to evaluate feasibility, quality adjusted life years and cost-effectiveness
- 2008
-
In: European Journal of Heart Failure. - : Wiley. - 1388-9842 .- 1879-0844. ; 10:7, s. 675-81
-
Journal article (peer-reviewed)abstract
- BACKGROUND: Worsening chronic heart failure (CHF) is largely characterized by frequent hospital admissions and the need for specialist care. AIM: To evaluate the feasibility of home care (HC) versus conventional care (CC) in relation to health-related quality of life (HRQL) and cost-utility in patients with worsening CHF. METHODS: Thirty-one patients seeking medical attention at hospital for worsening CHF were randomised to HC or CC. Following discharge within 48 hours from the hospital, patients in the HC group were followed-up in their homes by a specialist nurse. Follow-ups were conducted for both groups, 1, 4, 8 and 12 months after inclusion in the study. RESULTS: There was no significant difference in clinical events, adverse events or in HRQL. The total cost related to CHF was lower in the HC group after 12 months (p=0.05). CONCLUSION: Reduction in cost of care for selected patients with CHF eligible for hospital care might be achieved by early discharge from hospital followed by home visits. Due to the small number of patients, these results must be interpreted with caution.
|
|
| 4. |
- Strid, Anna, et al.
(author)
-
Diets benefiting health and climate relate to longevity in northern Sweden
- 2021
-
In: American Journal of Clinical Nutrition. - : Elsevier BV. - 0002-9165 .- 1938-3207. ; 114:2, s. 515-529
-
Journal article (peer-reviewed)abstract
- Background: Diets combining adequate nutritional quality and low climate impact are highly needed for human and planet health. Objectives; We aimed to 1) evaluate nutrient density indexes' ability to predict mortality, and 2) assess the effects of diets varying in nutrient density and climate impact on total mortality. Methods: Dietary data from 49,124 women and 47,651 men aged 35-65 y in the population-based prospective study Vasterbotten Intervention Programme (Sweden) were used. Greenhouse gas emissions (GHGEs) were estimated using data from life cycle assessments. Fifteen variants of nutrient density indexes were evaluated and the index that best predicted mortality was used to estimate participants' nutrient density. GHGEs and nutrient density were adjusted for energy intakes. Total mortality risk was estimated by Cox proportional hazards models for 4 groups of women and men, respectively, i.e., higher nutrient density, lower climate impact (HNutr/LClim); higher nutrient density, higher climate impact (HNutr/HClim); lower nutrient density, lower climate impact (LNutr/LClim); and lower nutrient density, higher climate impact (LNutr/HClim-reference group). Results: NRF11.3, a Sweden-adapted variant of the Nutrient Rich Foods index, was identified to have the best ability to predict mortality in the study population. Median follow-up times for women and men were 16.0 and 14.7 y, respectively. For women a significantly lower mortality risk was found for HNutr/LClim (HR: 0.87; 95% CI: 0.79, 0.96; P = 0.008) and HNutr/HClim (HR: 0.87; 95% CI: 0.78, 0.97; P = 0.011) than for LNutr/HClim. Among men LNutr/LClim had a significantly higher mortality risk (HR: 1.10; 95% CI: 1.01, 1.21; P = 0.033) than LNutr/HClim. Conclusions: Diets beneficial for both health and climate are feasible and associated with lower mortality risk in women. Further studies are needed to understand how men may transition into diets that are more sustainable from a combined health and climate perspective.
|
|
