Study Objective: We explored the feasibility of a Clinical Decision Support System (CDSS) to guide evidence-based perioperative anticoagulation.
Design: Prospective randomised clinical management simulation multicentre study.
Setting: Five University and 11 general hospitals in Germany.
Participants: We enrolled physicians (anaesthesiologist (n = 73), trauma surgeons (n = 2), unknown (n = 1)) with different professional experience.
Interventions: A CDSS based on a multiple-choice test was developed and validated at the University Hospital of Frankfurt (phase-I). The CDSS comprised European guidelines for the management of anticoagulation in cardiology, cardio-thoracic, non-cardio-thoracic surgery and anaesthesiology. Phase-II compared the efficiency of physicians in identifying evidence-based approach of managing perioperative anticoagulation. In total 168 physicians were randomised to CDSS (PERI-KOAG) or CONTROL.
Measurements: Overall mean score and association of processing time and professional experience were analysed. The multiple-choice test consists of 11 cases and two correct answers per question were required to gain 100% success rate (=22 points).
Main Results: In total 76 physicians completed the questionnaire (n = 42 PERI-KOAG; n = 34 CONTROL; attrition rate 54%). Overall mean score (max. 100% = 22 points) was significantly higher in PERI-KOAG compared to CONTROL (82 ± 15% vs. 70 ± 10%; 18 ± 3 vs. 15 ± 2 points; P = 0.0003). A longer processing time is associated with significantly increased overall mean scores in PERI-KOAG (≥33 min. 89 ± 10% (20 ± 2 points) vs. <33 min. 73 ± 15% (16 ± 3 points), P = 0.0005) but not in CONTROL (≥33 min. 74 ± 13% (16 ± 3 points) vs. <33 min. 69 ± 9% (15 ± 2 points), P = 0.11). Within PERI-KOAG, there is a tendency towards higher results within the more experienced group (>5 years), but no significant difference to less (≤5 years) experienced colleagues (87 ± 10% (19 ± 2 points) vs. 78 ± 17% (17 ± 4 points), P = 0.08). However, an association between professional experience and success rate in CONTROL has not been shown (71 ± 8% vs. 70 ± 13%, 16 ± 2 vs. 15 ± 3 points; P = 0.66).
Conclusions: CDSS significantly improved the identification of evidence-based treatment approaches. A precise usage of CDSS is mandatory to maximise efficiency.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jclinane.2022.110877 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Population encoding of observed and actual somatosensations in the human posterior parietal cortex.
Proc Natl Acad Sci U S A
January 2025
Department of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA 91125.
Cognition relies on transforming sensory inputs into a generalizable understanding of the world. Mirror neurons have been proposed to underlie this process, mapping visual representations of others' actions and sensations onto neurons that mediate our own, providing a conduit for understanding. However, this theory has limitations.
View Article and Find Full Text PDFClinical outcomes and cost-utility analysis of GKRS plus TKIs versus TKIs in patients with EGFR-mutant lung adenocarcinoma and brain metastases: a Markov decision model.
J Neurosurg
January 2025
8Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung.
Objective: This study focuses on epidermal growth factor receptor-mutated lung adenocarcinoma, known for frequent brain metastasis. It aimed to compare the clinical outcomes and cost-effectiveness of combining Gamma Knife radiosurgery (GKRS) with tyrosine kinase inhibitors (TKIs) (GKRS+TKI group) versus TKIs alone (TKI group) for the treatment of patients with newly diagnosed brain metastasis in this condition.
Methods: Study characteristics of the two groups were matched using inverse probability of treatment weighting (IPTW).
The Paradigm Shift From Patient to Health Consumer: 20 Years of Value Assessment in Health.
J Med Internet Res
January 2025
Virginia Commonwealth University, Richmond, VA, United States.
Health care is undergoing a "revolution," where patients are becoming consumers and armed with apps, consumer review scores, and, in some countries, high out-of-pocket costs. Although economic analyses and health technology assessment (HTA) have come a long way in their evaluation of the clinical, economic, ethical, legal, and societal perspectives that may be impacted by new technologies and procedures, these approaches do not reflect underlying patient preferences that may be important in the assessment of "value" in the current value-based health care transition. The major challenges that come with the transformation to a value-based health care system lead to questions such as "How are economic analyses, often the basis for policy and reimbursement decisions, going to switch from a societal to an individual perspective?" and "How do we then assess (economic) value, considering individual preference heterogeneity, as well as varying heuristics and decision rules?" These challenges, related to including the individual perspective in cost-effectiveness analysis (CEA), have been widely debated.
View Article and Find Full Text PDFQwen-2.5 Outperforms Other Large Language Models in the Chinese National Nursing Licensing Examination: Retrospective Cross-Sectional Comparative Study.
JMIR Med Inform
January 2025
Department of Science and Education, Shenzhen Baoan Women's and Children's Hospital, Shenzhen, China.
Background: Large language models (LLMs) have been proposed as valuable tools in medical education and practice. The Chinese National Nursing Licensing Examination (CNNLE) presents unique challenges for LLMs due to its requirement for both deep domain-specific nursing knowledge and the ability to make complex clinical decisions, which differentiates it from more general medical examinations. However, their potential application in the CNNLE remains unexplored.
View Article and Find Full Text PDFSmart Imitator: Learning from Imperfect Clinical Decisions.
J Am Med Inform Assoc
January 2025
Institute of Data Science, National University of Singapore, 117602, Singapore.
Objectives: This study introduces Smart Imitator (SI), a 2-phase reinforcement learning (RL) solution enhancing personalized treatment policies in healthcare, addressing challenges from imperfect clinician data and complex environments.
Materials And Methods: Smart Imitator's first phase uses adversarial cooperative imitation learning with a novel sample selection schema to categorize clinician policies from optimal to nonoptimal. The second phase creates a parameterized reward function to guide the learning of superior treatment policies through RL.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!