| 1. |
- Arora, Anmol, et al.
(författare)
-
The value of standards for health datasets in artificial intelligence-based applications
- 2023
-
Ingår i: Nature Medicine. - : NATURE PORTFOLIO. - 1078-8956 .- 1546-170X. ; 29, s. 2929-2938
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial intelligence as a medical device is increasingly being applied to healthcare for diagnosis, risk stratification and resource allocation. However, a growing body of evidence has highlighted the risk of algorithmic bias, which may perpetuate existing health inequity. This problem arises in part because of systemic inequalities in dataset curation, unequal opportunity to participate in research and inequalities of access. This study aims to explore existing standards, frameworks and best practices for ensuring adequate data diversity in health datasets. Exploring the body of existing literature and expert views is an important step towards the development of consensus-based guidelines. The study comprises two parts: a systematic review of existing standards, frameworks and best practices for healthcare datasets; and a survey and thematic analysis of stakeholder views of bias, health equity and best practices for artificial intelligence as a medical device. We found that the need for dataset diversity was well described in literature, and experts generally favored the development of a robust set of guidelines, but there were mixed views about how these could be implemented practically. The outputs of this study will be used to inform the development of standards for transparency of data diversity in health datasets (the STANDING Together initiative). A systematic review, combined with a stakeholder survey, presents an overview of current practices and recommendations for dataset curation in health, with specific focuses on data diversity and artificial intelligence-based applications.
|
|
| 2. |
- Becher, Nina, et al.
(författare)
-
Anticoagulation with edoxaban in patients with long atrial high-rate episodes ≥24 h
- 2024
-
Ingår i: European Heart Journal. - : Oxford University Press. - 0195-668X .- 1522-9645. ; 45:10, s. 837-849
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND AND AIMS: Patients with long atrial high-rate episodes (AHRE) ≥ 24 hours and stroke risk factors are often treated with anticoagulation for stroke prevention. Anticoagulation has never been compared to no anticoagulation in these patients.METHODS: This secondary prespecified analysis of NOAH-AFNET 6 examined interactions between AHRE duration at baseline and anticoagulation with edoxaban compared to placebo in patients with AHRE and stroke risk factors. The primary efficacy outcome was a composite of stroke, systemic embolism, or cardiovascular death. The safety outcome was a composite of major bleeding and death. Key secondary outcomes were components of these outcomes and ECG-diagnosed atrial fibrillation.RESULTS: AHRE ≥24 hours were present at baseline in 259/2389 patients enrolled in NOAH-AFNET 6 (11%, 78 ± 7 years old, 28% women, CHA2DS2-VASc score 4). Clinical characteristics were not different from patients with shorter AHRE. During a median follow-up of 1.8 years, the primary outcome occurred in 9/132 patients with AHRE ≥24 hours (4.3%/patient-year, 2 strokes) treated with anticoagulation and in 14/127 patients treated with placebo (6.9%/patient-year, 2 strokes). AHRE duration did not interact with the efficacy (p-interaction = 0.65) or safety (p-interaction = 0.98) of anticoagulation. Analyses including AHRE as a continuous parameter confirmed this. Patients with AHRE ≥24 hours developed more ECG-diagnosed atrial fibrillation (17.0%/patient-year) than patients with shorter AHRE (8.2%/patient-year; p < 0.001).CONCLUSIONS: This hypothesis-generating analysis does not find an interaction between AHRE duration and anticoagulation therapy in patients with device-detected AHRE and stroke risk factors. Further research is needed to identify patients with long AHRE at high stroke risk.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Kirchhof, Paulus, et al.
(författare)
-
A roadmap to improve the quality of atrial fibrillation management : proceedings from the fifth Atrial Fibrillation Network/European Heart Rhythm Association consensus conference
- 2016
-
Ingår i: Europace. - : Oxford University Press (OUP). - 1099-5129 .- 1532-2092. ; 18:1, s. 37-50
-
Tidskriftsartikel (refereegranskat)abstract
- At least 30 million people worldwide carry a diagnosis of atrial fibrillation (AF), and many more suffer from undiagnosed, subclinical, or 'silent' AF. Atrial fibrillation-related cardiovascular mortality and morbidity, including cardiovascular deaths, heart failure, stroke, and hospitalizations, remain unacceptably high, even when evidence-based therapies such as anticoagulation and rate control are used. Furthermore, it is still necessary to define how best to prevent AF, largely due to a lack of clinical measures that would allow identification of treatable causes of AF in any given patient. Hence, there are important unmet clinical and research needs in the evaluation and management of AF patients. The ensuing needs and opportunities for improving the quality of AF care were discussed during the fifth Atrial Fibrillation Network/European Heart Rhythm Association consensus conference in Nice, France, on 22 and 23 January 2015. Here, we report the outcome of this conference, with a focus on (i) learning from our 'neighbours' to improve AF care, (ii) patient-centred approaches to AF management, (iii) structured care of AF patients, (iv) improving the quality of AF treatment, and (v) personalization of AF management. This report ends with a list of priorities for research in AF patients.
|
|
| 6. |
- Rich, Rebecca L., et al.
(författare)
-
A global benchmark study using affinity-based biosensors
- 2009
-
Ingår i: Analytical Biochemistry. - : Elsevier BV. - 0003-2697 .- 1096-0309. ; 386:2, s. 194-216
-
Tidskriftsartikel (refereegranskat)abstract
- To explore the variability in biosensor studies, 150 participants from 20 countries were given the same protein samples and asked to determine kinetic rate constants for the interaction. We chose a protein system that was amenable to analysis using different biosensor platforms as well as by users of different expertise levels. The two proteins (a 50-kDa Fab and a 60-kDa glutathione S-transferase [GST] antigen) form a relatively high-affinity complex, so participants needed to optimize several experimental parameters, including ligand immobilization and regeneration conditions as well as analyte concentrations and injection/dissociation times. Although most participants collected binding responses that could be fit to yield kinetic parameters, the quality of a few data sets could have been improved by optimizing the assay design. Once these outliers were removed, the average reported affinity across the remaining panel of participants was 620 pM with a standard deviation of 980 pM. These results demonstrate that when this biosensor assay was designed and executed appropriately, the reported rate constants were consistent, and independent of which protein was immobilized and which biosensor was used.
|
|
