Digital health technologies include big data analytics, electronic health records (EHRs)/clinical information systems (CISs), mobile-health applications, connected devices, wearables, and computer modeling. Acute kidney injury (AKI) is a common clinical syndrome in which several digital health innovations are increasingly encountered and continue to emerge.
Many jurisdictions have leveraged hospital EHRs and laboratory information management systems to implement AKI detection algorithms that deliver AKI e-alerts to promote patient safety in clinical care and for use in AKI surveillance systems (1) (Figure 1). With increasing volume, veracity, and storage of health data, there has been a proliferation of prediction models developed for AKI (2) and its downstream clinical outcomes (3). As access to high-performance computing resources increases, these predictive models are increasingly being developed using machine learning algorithms that leverage the wealth of structured and unstructured data available from modern clinical data systems (4, 5). EHRs/CISs are ubiquitous in modern health systems and have been leveraged to deliver point-of-care, computerized, clinical decision support to care providers for AKI prevention and early intervention (6, 7). Recent examples also illustrate how electronic clinical data can be used to deliver audit and feedback reports and dashboards that process information on recent clinical performance to providers to encourage practice improvement for AKI prevention (8, 9).
Mobile health applications, connected devices, and wearables are also growing in use and entering clinical use to collect measurements directly from patients, thereby en-abling real-time monitoring and intervention strategies for AKI (10, 11). These data can be rapidly processed via artificial intelligence systems with the potential to provide continuous monitoring linked to recommendations for clinical actions. The extension of digital monitoring systems beyond the hospital and into the home holds promise to extend this paradigm into community-onset AKI and through transition from hospital to home to facilitate recovery and rehabilitation after AKI.
Although we expect these exciting digital health tools will rapidly progress in the clinical arenas in which AKI is encountered, innovators cannot simply “flip the on switch” and expect they will be effortlessly taken up into practice, accepted by end-users, and improve health system performance and health outcomes. Effective implementation will require evidence-based, scientific approaches to integrate digital tools within patient self-management strategies and clinical care, based on principles of behavior change and implementation science frameworks that support their uptake by the users of these tools. Incorporation of rigorous evaluation alongside deployment will also be required to demonstrate value for patients and providers and to ensure return on investment for health systems.
National Health Services. Acute kidney injury (AKI) algorithm. Accessed March 20, 2023. https://www.england.nhs.uk/akiprogramme/aki-algorithm/
Van Acker P, et al. Risk prediction models for acute kidney injury in adults: An overview of systematic reviews. PLoS One 2021; 16:e0248899. doi: 10.1371/journal.pone.0248899
Sawhney S, et al. Validation of risk prediction models to inform clinical decisions after acute kidney injury. Am J Kidney Dis 2021; 78:28–37. doi: 10.1053/j.ajkd.2020.12.008
Tomašev N, et al. A clinically applicable approach to continuous prediction of future acute kidney injury. Nature 2019; 572:116–119. doi: 10.1038/s41586-019-1390-1
Zhang Z, et al. Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care. Crit Care 2019; 23:112. doi: 10.1186/s13054-019-2411-z
McCoy AB, et al. A computerized provider order entry intervention for medication safety during acute kidney injury: A quality improvement report. Am J Kidney Dis 2010; 56:832–841. doi: 10.1053/j.ajkd.2010.05.024
Goldstein SL, et al. A sustained quality improvement program reduces nephrotoxic medication-associated acute kidney injury. Kidney Int 2016; 90:212–221. doi: 10.1016/j.kint.2016.03.031
James MT, et al. Effect of clinical decision support with audit and feedback on prevention of acute kidney injury in patients undergoing coronary angiography: A randomized clinical trial. JAMA 2022; 328:839–849. doi: 10.1001/jama.2022.13382
Brown JR, et al. Team-based coaching intervention to improve contrast-associated acute kidney injury: A cluster-randomized trial. Clin J Am Soc Nephrol 2023; 18:315–326. doi: 10.2215/CJN.0000000000000067
Panagiotou A, et al. Continuous real-time urine output monitoring for early detection of acute kidney injury. Contrib Nephrol 2011; 171:194–200. doi: 10.1159/000327323
Bergholz A, et al. Effect of personalized perioperative blood pressure management on postoperative complications and mortality in high-risk patients having major abdominal surgery: Protocol for a multicenter randomized trial (IMPROVE-multi). Trials 2022; 23:946. doi: 10.1186/s13063-022-06854-0.
- Search Google Scholar
- Export Citation
, Bergholz A Effect of personalized perioperative blood pressure management on postoperative complications and mortality in high-risk patients having major abdominal surgery: Protocol for a multicenter randomized trial (IMPROVE-multi). Trials 2022; 23: 946. doi: 10.1186/s13063-022-06854-0.