|
 
 |
| REVIEW ARTICLE |
|
| Year : 2019 | Volume
: 1
| Issue : 1 | Page : 28-34 |
|
Using Clinical Decision Support Systems for Acute Kidney Injury Pragmatic Trials
Kianoush Kashani1, Nooshin Dalili2, Rickey E Carter3, John A Kellum4, Ravindra L Mehta5
1 Department of Medicine, Division of Pulmonary and Critical Care Medicine, Mayo Clinic; Department of Medicine, Division of Nephrology and Hypertension, Mayo Clinic, Pittsburgh, PA, USA
2 Department of Nephrology, Chronic Kidney Disease Research Center, Labbafinejad Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
3 Department of Health Sciences Research, Division of Biomedical Statistics and Informatics, Clinical Statistics, Mayo Clinic; Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, MN, USA
4 Department of Critical Care Medicine, School of Medicine, University of Pittsburgh; Department of Critical Care Medicine, Center for Critical Care Nephrology, University of Pittsburgh, Pittsburgh, PA, USA
5 Department of Medicine, Division of Nephrology and Hypertension, University of California San Diego, San Diego, CA, USA
| Date of Web Publication | 4-Jan-2019 |
Correspondence Address:
Dr. Kianoush Kashani
Department of Medicine, Division of Nephrology and Hypertension, Mayo Clinic, 200 First Street SW, Rochester, MN 55905
USA
 Source of Support: None, Conflict of Interest: None  | Check |
DOI: 10.4103/jtccm.jtccm_6_18
Following the initial introduction of clinical decision support systems (CDSS) into the clinical practice in the 1970s, the complexity and performance quality of CDSSs have increased. The current literature on the efficacy and effectiveness of such systems shows conflicting results. While some studies show a clear benefit in quality-of-care improvement, others fail to replicate these outcomes. Heterogeneity of studies and the complexity of CDSS characteristics drive these conflicting conclusions. The lower cost and the easier implementation of pragmatic clinical trials provide an excellent platform to prove the effectiveness of CDSS in the real-world scenarios. To achieve better results, a series of explanatory trials are needed to identify the most effective CDSS in controlled settings. Therefore, utilization of both explanatory and pragmatic trial designs is necessary to evaluate the safety and efficacy of CDSS on the care of patients with acute kidney injury (AKI) in the acute setting. In this review, the authors provide an overview of the literature on critical care-related CDSS, its characteristics and dimensions, differences between pragmatic and explanatory trials, and potential proposals for both trial designs for AKI.
Keywords: Clinical decision support systems, electronic health records, pragmatic clinical trial
How to cite this article:
Kashani K, Dalili N, Carter RE, Kellum JA, Mehta RL. Using Clinical Decision Support Systems for Acute Kidney Injury Pragmatic Trials. J Transl Crit Care Med 2019;1:28-34 |
How to cite this URL:
Kashani K, Dalili N, Carter RE, Kellum JA, Mehta RL. Using Clinical Decision Support Systems for Acute Kidney Injury Pragmatic Trials. J Transl Crit Care Med [serial online] 2019 [cited 2023 Mar 29];1:28-34. Available from: http://www.tccmjournal.com/text.asp?2019/1/1/28/249337 |
| Introduction | |  |
The Institute of Medicine published a report, titled “The Learning Healthcare Systems: Workshop Summary” in 2007. Learning health system was defined as, “A…system…designed to generate and apply the best evidence for the collaborative healthcare choices of each patient and provider; to drive the process of discovery as a natural outgrowth of patient care; and to ensure innovation, quality, safety, and value in healthcare.”[1] In this report, using practical or pragmatic clinical trials (PCT) was recommended as an alternative to the pivotal randomized trial in order to evaluate the influence of evidence-based medicine on health-care systems.
Clinical decision support systems (CDSSs) are electronic tools to assist in clinical practice. Within these systems, characteristics of each patient are matched to a computerized clinical knowledge base. Therefore, CDSS can provide patient-specific assessments or recommendations to the clinicians or patients.[2]
One of the very common and consequential syndromes among critically ill patients is acute kidney injury (AKI).[3],[4],[5] AKI is associated with considerable risk of death and morbidities (i.e., chronic and end-stage kidney disease). In addition, hospital and healthcare cost increase substantially following AKI development.[4],[5],[6],[7],[8],[9],[10],[11]
There have been only a limited number of studies to evaluate the impact of CDSS on the care of patients with kidney failure.[12] These studies have had significant heterogeneity in their design and conduct; as a result, the benefits derived from these systems have been very variable. Therefore, there is a critical need to conduct studies to evaluate the impact of CDSS on the care of patients with kidney diseases, particularly in AKI. Due to lower cost and the practicality of PCTs, they seem to be an excellent platform to bridge the knowledge gap in this field.
In this paper, we review the literature regarding the use of PCTs to learn the impact of CDSS on outcomes and process of care for AKI patients.
| Does Clinical Decision Support System Benefit Acute Kidney Injury Patients? | | |
Global clinical decision support system history
The use of computerized CDSSs within the clinical practice was introduced in the 1970s. The Centers for Medicare and Medicare Services (CMS) incentive programs in the United States of America devised a three-stage CDSS implementation schedule to capture electronic data, improve advance clinical processes, and improve patient outcome.[13] The CMS incentive program has encouraged a significant number of institutions to promote their capabilities in electronic health records (EHRs), including implementation of CDSS within their program. Despite the rapid propagation of EHR utilization, the majority of the current institutions only have access to the very basic forms of EHR and CDSS.[14] The use of CDSS in the developed countries is on the upward trajectory. Unlike developed nations that proprietary software is the leading platform for EHR, in the developing countries the use of open source software has been the leading technology for storing and utilization of personal health information.[15] This is mainly due to lower cost and flexibility of the open source software to match the needs of each country. In a systematic review of the literature, the authors showed the open source software as EHR platform is extensively used in the resource-limited countries, especially in Sub-Saharan Africa and South America.[15] Such software, although, has been the primary EHR platform in the developing world, its impact on AKI e-alert has not been reported previously. Indeed the majority of information related to AKI e-alert originates from proprietary software technologies in the resource-sufficient countries.
Clinical decision support system characteristics
Research claims that CDSSs improve patient safety, quality of care, and efficiency in health-care delivery. In a systematic review of seventy randomized clinical trials, Kawamoto et al. showed that several characteristics have undoubted impacts on the performance of health-care providers. These factors included integration of a computerized decision support system within the clinical decision-making process, providing practical alternatives instead of simply stopping rules, implementing e-alerts at the right time and place to the right clinical care providers, and finally, using CDSSs to facilitate clinicians' judgment and actions rather than replacing clinicians with CDSS.[14] The authors concluded that there are the four factors that can impact the benefits of CDSS on the health-care quality: (1) incorporating an automatic decision support into the clinician workflow; (2) providing recommendations rather than just assessments; (3) offering decision support at the time and location of decision-making; and (4) using computer-based decision support with previous proof of favorable impact.[16]
Clinical decision support system and acute kidney injury
The first group that reported the impact of a kidney-related CDSS implementation for potentially nephrotoxic medications was Rind et al.[17] In 1994, they described the use of a computer-based alert system with the ability to detect a stepwise increase in serum creatinine levels among hospitalized patients who were receiving potentially nephrotoxic agents. These investigators found that such CDSS had a significant impact on physician decision-making process which resulted in improved the patients' clinical outcomes.
Obviously, the impact of CDSS on the processes of care for AKI and outcome of patients with AKI are debated in the literature. In the hospital setting, only a few randomized trials have addressed the impact of AKI CDSS which were mainly focused on medication-related nephrotoxicity. In 2009, Field et al. described relative risk reduction of 1.2 (95% confidence interval [CI], 1–1.4) after using EHR system implementation for dose adjustment of nephrotoxic drugs in patients with reduced kidney function.[18] In 2010, Terrell et al. demonstrated an absolute risk reduction of 31% (95% CI, 14–49; P = 0.001) in excessive dosing of drugs prescribed by emergency physicians after implementation of a CDSS order entry.[19] Leehey et al. did not show any statistically significant advantage of using a computerized pharmacist-assisted system in comparison with direct pharmacist drug dosing to prevent AKI after aminoglycoside dosing.[20] In another trial, McCoy et al. could not demonstrate any additional benefit of providing surveillance by pharmacists over an already implemented AKI CDSS, which was initially found to improve the drug dosing adjustment in patients with AKI.[21],[22] It seems that the whole body of the literature even the negative studies signal that the right type of EHR, in a right setting embedded in a workload of patients, can potentially improve the process of care. A very prominent example of such impacts was reported within the Nephrotoxic Injury Negated by Just-in-time Action (NINJA) project where the use of automated nephrotoxin exposure monitoring in pediatric patients led to a significant decline in the risk of AKI.[23]
Despite some encouraging results, the field still suffers from a significant knowledge gap. Although some studies showed benefit, others demonstrated conflicting results. The field suffers from the lack of multiple large-scale multicenter randomized trials to evaluate the efficacy or effectiveness of CDSS utilization in the management of AKI patients. In addition, the information regarding the impact of CDSS characteristics has been scarce.
In acute disease quality initiative (ADQI) XV consensus conference, held in Banff, Canada, the working groups focused on several features of EHR systems which were closely correlated with this systems' ability to improve patients care.[24] [Figure 1] outlines the necessary features of CDSS which could impact its performance. CDSS in the field of AKI can hypothetically provide information in three different aspects: descriptive, predictive, and prescriptive. This means that with using an AKI CDSSs could assist clinical care providers to increase their comprehension related to one of these three questions: (1) What are the risk factors of AKI in a comparable situation? (2) What are the estimated or expected results of a specific approach chosen in this situation? (3) How can the clinicians make individualized decisions regarding the unique situation of each AKI patient? Testing the impact of optimum CDSS features and dimensions is intended to help investigators and clinical care providers to make informed decisions for AKI patients. | Figure 1: Clinical decision support system characteristics that can impact its performance (adapted from acute disease quality initiative XV)[24]
Click here to view |
In 2015, Kolhe et al. evaluated the improvement in processes of care and outcomes in AKI patients using an AKI-related computerized care bundle accompanied by an interruptive alert completed within 24 h in comparison with those who either did not have the care bundle completed or had it completed after 24 h.[25] The authors reported that implementing an interruptive alert would improve compliance with the care bundle from 2.2% to 21.6% which, in turn, result in a significant improvement of 30- and 60-day mortality among those who received early care bundle, that is, within the first 24 h. The remarkable point was that the compliance with the completion of care bundle was about 21% even after implementing interruptive alert. This identified the importance of change management implementation in order to truly impact patient outcomes through culture change using any intervention, including CDSS.[25]
In another study by Park et al., the authors evaluated the impact of implementation of an AKI e-alert in order to automatically engage nephrology teams with the care of AKI patients. They demonstrated that the AKI alert to nephrology teams was able to significantly decrease the overlooked AKI incident cases (odds ratio [OR] 0.40), decline the rate of severe AKI cases (OR 0.75), and promote AKI recovery (hazard ratio 1.70).[26] In another recent study by Al-Jaghbeer et al.,[27] the authors reported a significant improvement in mortality (OR 0.76; 95% CI 0.70–0.83), dialysis (OR 0.66; 95% CI 0.61–0.72), and length of hospital stay (P < 0.001) among AKI patients when AKI CDSS implemented to alert clinical care providers and recommend nephrology or critical care consultations.
In a randomized clinical trial conducted by Wilson et al., the authors compared the standard care management of AKI patients versus using an AKI-related electronic alert system. They not only demonstrated no improvement in the processes of care and patient outcomes but also showed a higher incidence of nephrology consultations, renal replacement therapy, and increased resource utilization among AKI-alert patients in the general surgical floor.[28] The factors that could have led to negative results are the inclusion of patients at lower risk of AKI development and progress (general floor patients), adding care providers workload by sending them multiple alerts (alarm fatigue), not providing further decision-making support, alerting trainees and advanced care practitioners instead of intensive care physicians, and lack of interruptive nature of the e-alerts [Figure 1].[14],[28],[29]
Among several factors that can potentially impact the provider compliance with CDSS, the systems that provide alternatives for unsafe interventions instead of simply recommending stop rules may impact the physician compliance. When these recommendations are provided to the clinicians with higher levels of expertise, the impact of such outcomes is more notable (e.g., AKI e-alerts to intensivists showed improved quality of care[30] while these alerts did not improve processes of care when provided to the trainees or midlevel providers[31]). Another factor that can impact provider compliance is advanced technological capabilities and user-friendliness, this is while most of the EHR systems are at very basic levels and they do not have embedded ability to provide alerts on decision support. The human factors should not be forgotten, as the CDSS have to overcome caregivers unsafe habits.
As the implementation of more advanced EHRs is inevitable, it seems the design and conduct of clinical trials to prove the efficacy and effectiveness of CDSS are mandatory in the field.
| Pragmatic Trials in Assessment of Clinical Decision Support System Impact on Acute Kidney Injury | | |
Pragmatic trial design
The PCTs are designed to test treatments, diagnostic tests, and health-care delivery strategies that are widely utilized in the clinical practice with equipoise.[32] While the PCTs benefit from randomization, unlike the explanatory or pivotal clinical trials, they can be conducted without significant research infrastructure or skilled research staff. Therefore, they could be executed at a lower cost and in settings that may mirror clinical practice. In addition, PCTs mainly address the effectiveness of the intervention at the community and practice level while explanatory trials are focused on showing the efficacy of the intervention in tightly controlled settings. For this reason, PCT studies have very high flexibility and allow clinical hypotheses to be tested in a real-world scenario. By the same token, as the eligibility criteria for patient selection are less stringent, the effect size in PCTs is usually smaller than in explanatory trials; therefore, the sample size used in PCTs should be considerably larger to achieve statistical significance. [Table 1] summarizes the differences between explanatory and PCTs.
Clinical trial in acute kidney injury clinical decision support system
As the number of programs with access to AKI e-alerts and CDSS is growing, learning the impact they may have on the processes of care, patient outcome, and health-care systems would be critical. Pragmatic trials have several characteristics to make them a suitable platform for studying CDSS use and impact in AKI. In many institutions with CDSS available, the data necessary for these trials is extant. The incidence of AKI is very high among Intensive Care Unit patients, and hence enrollment phase could be short despite the need for very large sample size. As in pragmatic trials, adaptive design is acceptable, investigators and providers can change the conduct of the study to account for unknown human and technology-related factors. These trial designs require fewer resources with limited expenses. And finally, as the eligibility criteria for patient accrual in the pragmatic trials are not stringent, the results would more likely be generalizable to the other patient populations.
Recently in ADQI XIX (Wuhan, China, 2016), the participating investigators made recommendations regarding the design of pragmatic trials to study AKI.[33] Inspired by the ADQI expert recommendations, we describe a few possible uses of CDSS in PCTs. CDSS functionalities are vast and depend on its ability to provide different levels of information; it could be incorporated in the clinical trials in variable roles. CDSS not only can detect AKI, but it could also provide risk stratification, prognostication, recommendation for prevention, or treatments. [Figure 2] shows possible scenarios in patient, intervention, control, and outcome format (PICO) that a pragmatic or exploratory trial could be used to assess the impact of CDSS on the processes of care and outcomes of patients with AKI [Figure 2], adapted from ADQI]. | Figure 2: Use of clinical decision support system in the design of pragmatic or exploratory trials (adapted from acute disease quality initiative XIX).[33] (a) In order to conduct a clinical trial, patient screening is considered costly and time-consuming. An acute kidney injury clinical decision support system has the potential ability to identify high- or low-acute kidney injury risk patients. Each one of these two groups could be suitable for enrollment in a trial based on the type intervention. The archetype of a study for high acute kidney injury risk category is when the intervention is thought to be acute kidney injury risk modifier (e.g., mesenchymal stem cells for high-risk patients after cardiovascular surgeries[34]). On the other hand, archetype of a study that needs to enroll low-risk patients is when the pharmacodynamics and pharmacokinetics of a renally cleared chemotherapeutic agent is being assessed. (b) Acute kidney injury clinical decision support system could be used as an intervention, per se In this study type, the standard of care could be compared with care guided by acute kidney injury clinical decision support system. Pragmatic clinical trial by Wilson et al.[31] to compare the standard of care with care provided prompted by acute kidney injury e-alert is an example of this application of acute kidney injury clinical decision support system in clinical trials. (c) Acute kidney injury clinical decision support system could be potentially used to assign each patient to the control versus intervention group. An archetype of this design is when acute kidney injury clinical decision support system directly orders vancomycin or linezolid for patients with risk of acute kidney injury who were enrolled in a randomized clinical trial to compare the impact of the two strategies in the prevention of acute kidney injury among patients with methicillin-resistant Staphylococcus aureus-related sepsis. (d) The use of acute kidney injury clinical decision support system to determine the outcome of interest has significant precedence. In the epidemiology study by Kashani et al.,[3] acute kidney injury e-alert was utilized to identify patients with acute kidney injury among the large population. Another archetype for this design is when acute kidney injury clinical decision support system adjudicates patients who develop chronic kidney disease after an episode of acute kidney injury
Click here to view |
Patient
As CDSS has the capacity to identify high-risk AKI patients or those who have already developed AKI, it could be used as a screening tool. CDSS could be used for studies that requires accrual of patients with AKI or those who have not developed AKI yet. An AKI e-alert can be easily used for this purpose to save screening time and therefore cost of the study. Of course, the result of such study depends on several factors such as the expertise of alert recipients, the hierarchy of alert interruptions, and the type of interventions that are imposed following the alerts. As a result of such differences, some studies show benefit[26],[30] while some show no impact or even harm [Figure 2]a.[31]
Intervention
The next study design to evaluate the impact of CDSS on AKI care is to randomize accrued patients to the standard of care or interventions based on the CDSS recommendation. In the study by Rind et al., CDSS identified patients who had rising creatinine and made recommendations for drug dosing. The investigators were able to show significant improvement in the patient outcomes.[17] A similar improvement in the process of care and clinical outcomes was noted in NINJA project.[23] On the other hand, patients with low-to-moderate risk could be randomized to standard of care or CDSS recommendation for the appropriate prophylactic measure when the intervention or medication is very nephrotoxic [Figure 2]b.
Control
If a study is designed to evaluate the comparative effectiveness of an intervention in AKI development among high-risk patients, then CDSS could be used to identify those who developed AKI as the main arm and those who did not develop AKI as comparators [Figure 2]c.
Outcome
CDSS also could be used to detect outcomes of the study-related interventions, particularly if the intervention is considered to be nephrotoxic or patients being high-risk for AKI. For example, following delivery of mesenchymal stem cells to the renal artery to prevent cardiovascular surgery-associated AKI,[34] CDSS could detect development or progress of AKI in control or intervention groups [Figure 2]d. Another example of this application of AKI CDSS is when it is used for RRT interventions or timing of dialysis.
| Conclusion | | |
Implementation and clinical utilization of CDSS are on the rise.[35] The number of studies with a focus on AKI detection, prevention, and recovery, on the other hand, is also on an upward trajectory. Although utilization of explanatory clinical trials, to assess the impact of CDSS on AKI outcomes, is necessary, utilizing pragmatic trials to learn health systems seem to be inevitable, particularly considering the lower costs of pragmatic trials and their potential impacts on clinical practice.
Acknowledgments
This paper is written as a summary of a similar lecture within the “Pragmatic clinical trials in AKI and RRT: Roundtable” hosted by Drs. Ravindra L Mehta and John A Kellum, held in San Diego, CA, on February 2016. The content of this paper was updated in February 2018.
Financial support and sponsorship
Nil.
Conflicts of interest
There are no conflicts of interest.
| References | | |
| 1. | |
| 2. | Sim I, Gorman P, Greenes RA, Haynes RB, Kaplan B, Lehmann H, et al. Clinical decision support systems for the practice of evidence-based medicine. J Am Med Inform Assoc 2001;8:527-34.  |
| 3. | Kashani K, Shao M, Li G, Williams AW, Rule AD, Kremers WK, et al. No increase in the incidence of acute kidney injury in a population-based annual temporal trends epidemiology study. Kidney Int 2017;92:721-8. |
| 4. | Warren J, Mehran R, Baber U, Xu K, Giacoppo D, Gersh BJ, et al. Incidence and impact of acute kidney injury in patients with acute coronary syndromes treated with coronary artery bypass grafting: Insights from the harmonizing outcomes with revascularization and stents in acute myocardial infarction (HORIZONS-AMI) and acute catheterization and urgent intervention triage strategy (ACUITY) trials. Am Heart J 2016;171:40-7. |
| 5. | Ali T, Khan I, Simpson W, Prescott G, Townend J, Smith W, et al. Incidence and outcomes in acute kidney injury: A comprehensive population-based study. J Am Soc Nephrol 2007;18:1292-8. |
| 6. | An JN, Hwang JH, Kim DK, Lee H, Ahn SY, Kim S, et al. Chronic kidney disease after acute kidney injury requiring continuous renal replacement therapy and its impact on long-term outcomes: A Multicenter retrospective cohort study in Korea. Crit Care Med 2017;45:47-57. |
| 7. | De Corte W, Dhondt A, Vanholder R, De Waele J, Decruyenaere J, Sergoyne V, et al. Long-term outcome in ICU patients with acute kidney injury treated with renal replacement therapy: A prospective cohort study. Crit Care 2016;20:256. |
| 8. | Chawla LS, Eggers PW, Star RA, Kimmel PL. Acute kidney injury and chronic kidney disease as interconnected syndromes. N Engl J Med 2014;371:58-66. |
| 9. | Chawla LS, Kimmel PL. Acute kidney injury and chronic kidney disease: An integrated clinical syndrome. Kidney Int 2012;82:516-24. |
| 10. | Silver SA, Long J, Zheng Y, Chertow GM. Cost of acute kidney injury in hospitalized patients. J Hosp Med 2017;12:70-6. |
| 11. | Collister D, Pannu N, Ye F, James M, Hemmelgarn B, Chui B, et al. Health care costs associated with AKI. Clin J Am Soc Nephrol 2017;12:1733-43. |
| 12. | Tawadrous D, Shariff SZ, Haynes RB, Iansavichus AV, Jain AK, Garg AX, et al. Use of clinical decision support systems for kidney-related drug prescribing: A systematic review. Am J Kidney Dis 2011;58:903-14. |
| 13. | |
| 14. | Kawamoto K, Houlihan CA, Balas EA, Lobach DF. Improving clinical practice using clinical decision support systems: A systematic review of trials to identify features critical to success. BMJ. 2005;330:765. |
| 15. | Aminpour F, Sadoughi F, Ahamdi M. Utilization of open source electronic health record around the world: A systematic review. J Res Med Sci 2014;19:57-64. |
| 16. | Kawamoto K, Houlihan CA, Balas EA, Lobach DF. Improving clinical practice using clinical decision support systems: A systematic review of trials to identify features critical to success. BMJ 2005;330:765. |
| 17. | Rind DM, Safran C, Phillips RS, Wang Q, Calkins DR, Delbanco TL, et al. Effect of computer-based alerts on the treatment and outcomes of hospitalized patients. Arch Intern Med 1994;154:1511-7. |
| 18. | Field TS, Rochon P, Lee M, Gavendo L, Baril JL, Gurwitz JH, et al. Computerized clinical decision support during medication ordering for long-term care residents with renal insufficiency. J Am Med Inform Assoc 2009;16:480-5. |
| 19. | Terrell KM, Perkins AJ, Hui SL, Callahan CM, Dexter PR, Miller DK, et al. Computerized decision support for medication dosing in renal insufficiency: A randomized, controlled trial. Ann Emerg Med 2010;56:623-9. |
| 20. | Leehey DJ, Braun BI, Tholl DA, Chung LS, Gross CA, Roback JA, et al. Can pharmacokinetic dosing decrease nephrotoxicity associated with aminoglycoside therapy. J Am Soc Nephrol 1993;4:81-90. |
| 21. | McCoy AB, Cox ZL, Neal EB, Waitman LR, Peterson NB, Bhave G, et al. Real-time pharmacy surveillance and clinical decision support to reduce adverse drug events in acute kidney injury: A randomized, controlled trial. Appl Clin Inform 2012;3:221-38. |
| 22. | McCoy AB, Waitman LR, Gadd CS, Danciu I, Smith JP, Lewis JB, et al. Acomputerized provider order entry intervention for medication safety during acute kidney injury: A quality improvement report. Am J Kidney Dis 2010;56:832-41. |
| 23. | Goldstein SL, Mottes T, Simpson K, Barclay C, Muething S, Haslam DB, et al. Asustained quality improvement program reduces nephrotoxic medication-associated acute kidney injury. Kidney Int 2016;90:212-21. |
| 24. | Hoste EA, Kashani K, Gibney N, Wilson FP, Ronco C, Goldstein SL, et al. Impact of electronic-alerting of acute kidney injury: Workgroup statements from the 15(th) ADQI consensus conference. Can J Kidney Health Dis 2016;3:10. |
| 25. | Kolhe NV, Staples D, Reilly T, Merrison D, McIntyre CW, Fluck RJ, et al. Impact of Compliance with a Care Bundle on Acute Kidney Injury Outcomes: A Prospective Observational Study. PLoS One 2015;10:e0132279. |
| 26. | Park S, Baek SH, Ahn S, Lee KH, Hwang H, Ryu J, et al. Impact of electronic acute kidney injury (AKI) alerts with automated nephrologist consultation on detection and severity of AKI: A Quality improvement study. Am J Kidney Dis 2018;71:9-19. |
| 27. | Al-Jaghbeer M, Dealmeida D, Bilderback A, Ambrosino R, Kellum JA. Clinical decision support for in-hospital AKI. J Am Soc Nephrol 2018;29:654-60. |
| 28. | Wilson FP, Shashaty M, Testani J, Aqeel I, Borovskiy Y, Ellenberg SS, et al. Automated, electronic alerts for acute kidney injury: a single-blind, parallel-group, randomised controlled trial. Lancet. 2015;385:1966-74. |
| 29. | Kashani K, Herasevich V. Utilities of electronic medical records to improve quality of care for acute kidney injury: Past, present, future. Nephron 2015;131:92-6. |
| 30. | Colpaert K, Hoste EA, Steurbaut K, Benoit D, Van Hoecke S, De Turck F, et al. Impact of real-time electronic alerting of acute kidney injury on therapeutic intervention and progression of RIFLE class. Crit Care Med 2012;40:1164-70. |
| 31. | Wilson FP, Shashaty M, Testani J, Aqeel I, Borovskiy Y, Ellenberg SS, et al. Automated, electronic alerts for acute kidney injury: A single-blind, parallel-group, randomised controlled trial. Lancet 2015;385:1966-74. |
| 32. | Rosenthal GE. The role of pragmatic clinical trials in the evolution of learning health systems. Trans Am Clin Climatol Assoc 2014;125:204-16. |
| 33. | Peng Z, Yu K, Ostermann M, Xi X, Hsu R, Vincent JL, et al. Pragmatic studies for acute kidney injury: Consensus report of the acute disease quality initiative (ADQI) 19 workgroup. J Crit Care 2018;44:337-44. |
| 34. | Swaminathan M, Stafford-Smith M, Chertow GM, Warnock DG, Paragamian V, Brenner RM, et al. Allogeneic mesenchymal stem cells for treatment of AKI after cardiac surgery. J Am Soc Nephrol 2018;29:260-7. |
| 35. | Adler-Milstein J, DesRoches CM, Furukawa MF, Worzala C, Charles D, Kralovec P, et al. More than half of US hospitals have at least a basic EHR, but stage 2 criteria remain challenging for most. Health Aff (Millwood) 2014;33:1664-71. |
[Figure 1], [Figure 2]
[Table 1]
| This article has been cited by | | 1 |
Artificial intelligence to guide management of acute kidney injury in the ICU: a narrative review |
|
| Greet De Vlieger,Kianoush Kashani,Geert Meyfroidt | | Current Opinion in Critical Care. 2020; 26(6): 563 | | [Pubmed] | [DOI] | | | 2 |
Impact of a computerized decision support tool deployed in two intensive care units on acute kidney injury progression and guideline compliance: a prospective observational study |
|
| Christopher Bourdeaux,Erina Ghosh,Louis Atallah,Krishnamoorthy Palanisamy,Payaal Patel,Matthew Thomas,Timothy Gould,John Warburton,Jon Rivers,John Hadfield | | Critical Care. 2020; 24(1) | | [Pubmed] | [DOI] | |
|
 |
|
|
|
Search Pubmed for