Article
Refine
Year of publication
- 2019 (2) (remove)
Document Type
- Article (2) (remove)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2)
Keywords
- Patients (2) (remove)
Institute
- Medizin (2)
A machine-learned analysis suggests non-redundant diagnostic information in olfactory subtests
(2019)
Background: The functional performance of the human sense of smell can be approached via assessment of the olfactory threshold, the ability to discriminate odors or the ability to identify odors. Contemporary clinical test batteries include all or a selection of these components, with some dissent about the required number and choice.
Methods: Olfactory thresholds, odor discrimination and odor identification scores were available from 10,714 subjects (3662 with anomia, 4299 with hyposmia, and 2752 with normal olfactory function). To assess, whether the olfactory subtests confer the same information or each subtest confers at least partly non-redundant information relevant to the olfactory diagnosis, we compared the diagnostic accuracy of supervised machine learning algorithms trained with the complete information from all three subtests with that obtained when performing the training with the information of only two or one subtests.
Results: The training of machine-learned algorithms with the full information about olfactory thresholds, odor discrimination and odor identification from 2/3 of the cases, resulted in a balanced olfactory diagnostic accuracy of 98% or better in the 1/3 remaining cases. The most pronounced decrease in the balanced accuracy, to approximately 85%, was observed when omitting olfactory thresholds from the training, whereas omitting odor discrimination or identification was associated with smaller decreases (balanced accuracies approximately 90%).
Conclusions: Results support partly non-redundant contributions of each olfactory subtest to the clinical olfactory diagnosis. Olfactory thresholds provided the largest amount of non-redundant information to the olfactory diagnosis.
Purpose: To examine whether applying case management in general practices reduces thromboembolic events requiring hospitalization and major bleeding events (combined primary outcome). Secondary endpoints were mortality, frequency and duration of hospitalization, severe treatment interactions, adverse events, quality of anticoagulation, health-related quality of life and intervention costs, patients’ assessment of chronic illness care, self-reported adherence to medication, GP and HCA knowledge, patient knowledge and satisfaction with shared decision-making.
Methods: Cluster-randomized controlled trial undertaken at 52 general practices in Germany with adult patients with a long-term indication for oral anticoagulation. The complex intervention included training for healthcare assistants, information and quality circles for general practitioners and 24 months of case management for patients. Assessment was after 12 and 24 months. The intention-to-treat population included all randomized practices and patients, while the per-protocol analysis included only those that received treatment without major protocol violations.
Results: The mean (SD) age of the 736 patients was 73.5 (9.4) years and 597 (81.1%) had atrial fibrillation. After 24 months, the primary endpoint had occurred in 40 (11.0%) intervention and 48 (12.9%) control patients (hazard ratio 0.83, 95% CI 0.55 to 1.25; P = .37). Patients’ perceived quality of care, their knowledge, and HCAs’ knowledge, had improved significantly at 24 months. The other secondary endpoints did not differ between groups. In the intervention group, hospital admissions were significantly reduced in patients that received treatment without major protocol deviations.
Conclusions: Even though the main outcomes did not differ significantly, the intervention appears to have positively influenced several process parameters under "real-world conditions".