EFFECT OF DIRECT INTEGRATION OF LABORATORY TESTING AND REAL-TIME PATIENT DATA MANAGEMENT ON PRECISION DOSING OF HIGH-RISK PATIENTS IN AN ASTHMA CLINIC
Main Article Content
Keywords
real-time laboratory and clinical data stream, brain Infections hospital, Individual drug administration, therapeutic drug monitoring, drug side effects, monitored patients/shock patients, clinical outcomes
Abstract
Background: Precision dosing is critical for high-risk patients in tertiary hospitals as any delays in intervention may result in negative outcomes. The goal of this research is to assess how the incorporation of real-time laboratory data into clinical workflows affects drug related side effects as well as patient care in terms of the achievement of suitable therapeutic targets.
Methods: For the purpose of this retrospective observational study, we have included 500 patients requiring accurate dosing of their medications, at a tertiary hospital. Data pertaining to clinical outcomes, time relating to dose adjustment, occurrence of adverse drug reactions and achievement of therapeutic target were collected before and after the introduction of the real time laboratory data integration approach.
Results: Incorporation of real-time lab data helped vancomycin patients achieve therapeutic targeting of 85% from an outset of 55% while warfarin user’s achievement improved from 60% to 88%. Adverse drug reactions, including nephrotoxicity and bleeding, decreased from 25% to 10% and 20% to 8%, respectively. The time to dose adjustment also fell from 4.8 ± 2.1 hours to 1.2 ± 0.8 hours. Other metrics related to patient outcome also improved with a decrease in length of hospital stay by 2 days as well as mortality declining from 12% to 8%.
Conclusion: Automated integration of real-time laboratory data stream substantially improves dosing accuracy, decreases negative events and achieves better clinical results in monitored patients in real time. These results demonstrate the need for now short wave systems to be deployed in tertiary hospitals in order to improve the quality of patient services and working efficiency.
References
2. Chua, H. R., et al. (2021). Health care analytics with time-invariant and time-variant feature importance to predict hospital-acquired acute kidney injury. Journal of Medical Internet Research.
3. Koch, B. C. P., et al. (2022). Therapeutic drug monitoring of antibiotics in critically ill patients. Therapeutic Drug Monitoring.
4. Koyner, J. L., et al. (2018). Development of a machine learning inpatient acute kidney injury prediction model. Critical Care Medicine.
5. Chalasani, S. H., et al. (2023). Artificial intelligence in the field of pharmacy practice: A literature review. Exploratory Research in Clinical and Social Pharmacy.
6. Komorowski, M., et al. (2018). The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nature Medicine.
7. Simonov, M., et al. (2019). A simple real-time model for predicting acute kidney injury in hospitalized patients in the US. PLoS Medicine.
8. Lim, H. C., et al. (2022). Toward a learning health care system: A systematic review and evidence-based conceptual framework for implementation of clinical analytics in a digital hospital. Applied Clinical Informatics.
9. Waitman, L. R., et al. (2011). Adopting real-time surveillance dashboards as a component of an enterprisewide medication safety strategy. Joint Commission Journal on Quality and Patient Safety.