| 1. |
- Gunnarsson, Jenny, et al.
(författare)
-
Efficient diagnosis of suspected functional bowel disorders.
- 2008
-
Ingår i: Nature clinical practice. Gastroenterology & hepatology. - : Springer Science and Business Media LLC. - 1743-4386 .- 1743-4378. ; 5:9, s. 498-507
-
Forskningsöversikt (refereegranskat)abstract
- Functional bowel disorders (FBDs) are common disorders that are characterized by various combinations of abdominal pain and/or discomfort, bloating and changes in bowel habits. At present, diagnosing FBDs often incurs considerable health-care costs, partly because unnecessary investigations are performed. Patients are currently diagnosed as having an FBD on the basis of a combination of typical symptoms, normal physical examination and the absence of alarm features indicative of an organic gastrointestinal disease. Basic laboratory investigations, such as a complete blood count, measurement of the erythrocyte sedimentation rate and serological tests for celiac disease, are useful in the initial evaluation. No further investigations are needed for most patients who have typical symptoms and no alarm symptoms. The most important alarm symptoms include signs of gastrointestinal bleeding, symptom onset above 50 years of age, a family history of colorectal cancer, documented weight loss and nocturnal symptoms. The presence of alarm symptoms obviously does not exclude an FBD, but further investigation is needed before confirmation of the diagnosis. For patients with predominant and severe diarrhea, a more thorough diagnostic work-up should normally be considered, including colonoscopy with colonic biopsies and a test for bile-acid malabsorption.
|
|
| 2. |
|
|
| 3. |
- Nakchbandi, IA, et al.
(författare)
-
Coagulation, anticoagulation and pancreatic carcinoma
- 2008
-
Ingår i: Nature clinical practice. Gastroenterology & hepatology. - : Springer Science and Business Media LLC. - 1743-4386 .- 1743-4378. ; 5:8, s. 445-455
-
Tidskriftsartikel (refereegranskat)
|
|
| 4. |
|
|
| 5. |
- Johansson, Simon, 1994, et al.
(författare)
-
Using Active Learning to Develop Machine Learning Models for Reaction Yield Prediction
- 2022
-
Ingår i: Molecular Informatics. - : Wiley. - 1868-1743 .- 1868-1751. ; 41:12
-
Tidskriftsartikel (refereegranskat)abstract
- Computer aided synthesis planning, suggesting synthetic routes for molecules of interest, is a rapidly growing field. The machine learning methods used are often dependent on access to large datasets for training, but finite experimental budgets limit how much data can be obtained from experiments. This suggests the use of schemes for data collection such as active learning, which identifies the data points of highest impact for model accuracy, and which has been used in recent studies with success. However, little has been done to explore the robustness of the methods predicting reaction yield when used together with active learning to reduce the amount of experimental data needed for training. This study aims to investigate the influence of machine learning algorithms and the number of initial data points on reaction yield prediction for two public high-throughput experimentation datasets. Our results show that active learning based on output margin reached a pre-defined AUROC faster than random sampling on both datasets. Analysis of feature importance of the trained machine learning models suggests active learning had a larger influence on the model accuracy when only a few features were important for the model prediction.
|
|
