This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on http://www.jmir.org/, as well as this copyright and license information must be included.
The development of acute kidney injury (AKI) in hospitalized patients is associated with adverse outcomes and increased health care costs. Simple
We sought to test this hypothesis by evaluating the impact of a digitally enabled intervention on clinical outcomes and health care costs associated with AKI in hospitalized patients.
We developed a care pathway comprising automated AKI detection, mobile clinician notification, in-app triage, and a protocolized specialist clinical response. We evaluated its impact by comparing data from pre- and postimplementation phases (May 2016 to January 2017 and May to September 2017, respectively) at the intervention site and another site not receiving the intervention. Clinical outcomes were analyzed using segmented regression analysis. The primary outcome was recovery of renal function to ≤120% of baseline by hospital discharge. Secondary clinical outcomes were mortality within 30 days of alert, progression of AKI stage, transfer to renal/intensive care units, hospital re-admission within 30 days of discharge, dependence on renal replacement therapy 30 days after discharge, and hospital-wide cardiac arrest rate. Time taken for specialist review of AKI alerts was measured. Impact on health care costs as defined by Patient-Level Information and Costing System data was evaluated using difference-in-differences (DID) analysis.
The median time to AKI alert review by a specialist was 14.0 min (interquartile range 1.0-60.0 min). There was no impact on the primary outcome (estimated odds ratio [OR] 1.00, 95% CI 0.58-1.71;
The digitally enabled clinical intervention to detect and treat AKI in hospitalized patients reduced health care costs and possibly reduced cardiac arrest rates. Its impact on other clinical outcomes and identification of the
Acute kidney injury (AKI)—a sudden decline in kidney function—can be caused by hypovolemia, infection (including severe sepsis), nephrotoxicity, primary renal diseases, and urinary tract obstruction [
AKI management involves the identification and treatment of life-threatening complications and medical or surgical treatment of underlying cause, supportive care (including RRT, where necessary), and interventions to reduce risk of recurrence [
To address these issues, we developed a digitally enabled care pathway for AKI patients [
We have reported the clinical impact of this digitally enabled care pathway on patients with AKI at the point of presentation to the emergency department (ED) [
The digital pathway was implemented at the Royal Free Hospital (RFH), a large (839 beds including a 34-bed intensive treatment unit [ITU]) hospital in north London, United Kingdom. It provides acute and emergency care as well as a range of specialist, regional inpatient services (eg, hepatology, HIV and infectious disease, amyloidosis, and vascular surgery) and has a large inpatient nephrology and renal transplant service.
For the purposes of our evaluation, we used a comparator site managed by the same health care provider organization (Royal Free London NHS Foundation Trust, RFLFT) in which the intervention was not implemented. Barnet General Hospital (BGH) is an acute general hospital with 459 beds. It has a 21-bed ITU that can provide acute RRT and a liaison nephrology service. Tertiary, specialist services are not provided on this site. A number of parallel improvement initiatives were ongoing at the comparator site during the study period, including a sepsis improvement project and an active deteriorating patients improvement program.
Blood tests, including serum creatinine, are routinely undertaken on hospitalized inpatients across all wards as directed by the treating clinicians. Historically, at both sites, blood tests would be reviewed in batches by the clinicians who ordered them. Results suggesting AKI would be telephoned to relevant wards by laboratory staff. Referral for nephrology assessment would be undertaken at the discretion of the clinical teams and using hospital pagers and phones. Cases would be prioritized and treated by the nephrology teams through assessment of referral information and results on desktop computers and through bedside review. The Patient at Risk and Resuscitation Team (PARRT) provides support to ward teams for patients deemed at risk of deterioration or who trigger existing, physiology-based early warning systems.
The digitally enabled AKI care pathway and the technical architecture of the Streams app have been described in detail previously [
At both sites, data from RFLFT hospital databases and those supporting Streams app relating to the intervention period (May to September 2017) were compared with those from a predeployment phase (May 2016 to January 2017). Data relating to patients in whom an AKI alert was generated on presentation to the hospital ED are reported elsewhere [
Data collected and their sources are detailed in
For the economic analysis, we used Payment Level Information and Costing System (PLICS) data supplied by the RFLFT. PLICS is a clinical costing system where costs are derived for each patient spell (ie, admission) by tracing resources used by an individual patient in diagnosis and treatment and calculating the expenditure on those resources using the actual costs incurred by the provider. PLICS has the advantage of including staffing costs and infrastructure absorbed costs. In our study, the PLICS data for hospitalized patients with AKI included the following components: total length of stay (including the length of stay in intensive care unit), pathology and radiology examinations, total theater time, theater cutting time, inpatient dialysis, and overhead costs. These data were analyzed at the spell level. We also obtained data on the costs associated with selected individual components of a spell, which we analyzed separately (ie, length of stay, pathology and radiology examinations, theater total time, and theater cutting time). However, individual cost components were based on tariffs and not fully absorbed costs. Furthermore, we could not obtain individual costs of inpatient dialysis. The final dataset used in the economic analysis comprised total and component-specific spell-level costs at the RFH and BGH, before and after the digitally enabled care pathway was introduced at the RFH.
The primary outcome was recovery of renal function (return to a serum creatinine concentration within 120% of the baseline, as defined by the NHSEDA) before hospital discharge.
Definitions of each outcome and sources of data collected.
Data category and measure | Definition | Source of data | |||
Age | Age in years at the time of alert | HL7a data aggregated within the Streams data processor | |||
Gender | Gender codes used in the NHSb Data Dictionary [ |
HL7 data aggregated within the Streams data processor | |||
Ethnicity | Ethnicity category codes used in the NHS Data Dictionary [ |
HL7 data aggregated within the Streams data processor | |||
Comorbid disease | Presence of individual Charlson index comorbidities and overall Charlson score | HL7 data aggregated within the Streams data processor | |||
Deprivation | Index of Multiple Deprivation | Ministry of Housing, Communities and Local Government database | |||
Recovery of renal function | Return to <120% index creatinine (as defined by NHSEDAc) by the time of hospital discharge | HL7 data aggregated within the Streams data processor | |||
Time to recovery of renal function | The time from AKId alert to recovery of renal function (<120% index creatinine) | HL7 data aggregated within the Streams data processor | |||
Mortality | Death in 30 days following AKI alert | HL7 data aggregated within the Streams data processor | |||
Progression of AKI stage | Movement between AKI severity classes following AKI alert and before hospital discharge | HL7 data aggregated within the Streams data processor | |||
Admission to high acuity or specialist renal inpatient bed | Admission to acute kidney unit/high dependency unit/intensive treatment unit during index admission | HL7 data aggregated within the Streams data processor | |||
Requirement long-term renal replacement therapy | Use of hemofiltration/hemodiafiltration/hemodialysis/peritoneal dialysis in 30 days following hospital discharge date | RFHe Nephrology Clinical Information Management System | |||
Length of stay | Time from AKI alert to hospital discharge | HL7 data aggregated within the Streams data processor | |||
Re-admission to hospital | Re-admission to hospital in 30 days following index admission discharge date | HL7 data aggregated within the Streams data processor | |||
Cardiac arrest rate | Number of cardiac arrests per 1000 bed days | Trust critical care nursing team logs | |||
Costs per patient | Cost per patient per hospital spell | Payment Level Information and Costing System data and Payment by Results/local tariffs at the trust | |||
Time to alert review | Time from alert generation to alert viewing by a clinician | Data aggregated within the Streams data processor |
aHealth Level 7 (HL7) messages are used to transfer information between different health care information technology systems.
bNHS: National Health Service.
cNHSEDA: NHS Early Detection Algorithm.
dAKI: acute kidney injury.
eRFH: Royal Free Hospital.
Defining the final evaluation sample. AKI: acute kidney injury; ITU: intensive treatment unit.
All data were pseudonymized before transfer to the University College London (UCL) for analysis. Analyses were performed using R, version 3.4.3 (R core team) [
where the proportion of interest is denoted by
For all models, we inspected the autocorrelation function (up to lag 15). No significant autocorrelation was detected in any model. At the point of protocol publication, it was not anticipated that we would be able to collect patient-level data relating to sociodemographic characteristics and comorbid disease.
To examine the robustness of our primary outcome analysis, we used binary logistic regression to perform a sensitivity analysis: the same model mentioned previously was used, except that (1) the outcome was defined at the patient level and (2) patient-level characteristics (age, sex, ethnicity category, index of multiple deprivation, AKI alert level, the presence of complications at the time of alert, and the presence of individual Charlson score comorbidities) were included as covariates to adjust for any differences in casemix between sites and within sites over time.
The Wilcoxon rank-sum test was used to analyze the time to creatinine recovery (where this occurred by hospital discharge). To allow for the effects of in-hospital death on this outcome, the effect of the intervention on the length of hospital stay was estimated by competing risk analysis [
A total of 500 alerts were selected randomly from all periods, and all sites were reviewed a second time to assess the reliability of case validation. Intra- and interrater reliability was determined using Cohen’s kappa coefficient (
The number of cardiac arrests was recorded monthly at both hospital sites. Data relating to those which occurred in the hospitals’ ED, cardiac catheterization laboratory, intensive care unit, coronary care unit or in patients who had a formal
Economic analyses used generalized linear models (GLMs) to estimate DID, where costs were defined at the spell level, and patient-level characteristics (age, sex, ethnicity category, IMD, the presence of complications at the time of alert, and the presence of individual Charlson score comorbidities, such as diabetes mellitus or congestive cardiac failure) were included as covariates so as to allow adjustment for any differences in casemix between sites and within sites over time. A GLM was specified using a gamma family and log link to account for data skewness. The model used was:
where
The digitally enabled care pathway constituted a new standard service at the RFH. The UCL Joint Research Office reviewed the study protocol and judged that the project fell under the remit of service evaluation as per guidance from the NHS Health Research Authority [
Alerts produced for hospitalized patients during the intervention period were reviewed by a member of the specialist response team in a median time of 14.0 min (interquartile range [IQR] 1.0-60.0 min). At the intervention site, clinical validation of the 4392 and 2254 AKI alerts during predeployment (May 2016 to January 2017) and postdeployment (May to September 2017) phases, respectively, yielded 1760 and 919 inpatient AKI episodes in each phase. Of these, 56.5% (994/1960) and 52.2% (480/919), respectively, were located outside the ED. In the predeployment and postdeployment phases at the nonintervention site, clinical validation of the 2866 and 1364 alerts, respectively, yielded 1669 and 772 inpatient AKI episodes, with 39.2% (654/1669) and 45.3% (350/772) being located outside the ED.
Sociodemographic and clinical characteristics of patients producing acute kidney injury alerts.
Variable | Hospital site/period | |||||||
RFHa | BGHb | RFH pre vs RFH post | BGH pre vs BGH post | All RFH vs all BGH | ||||
Prec | Postd | Pre | Post | |||||
AKIe alerts, n | 994 | 480 | 654 | 350 | —f | — | — | |
.102 | .01 | .32 | ||||||
AKI1 | 809 (81.4) | 411 (85.6) | 571 (87.3) | 281 (80.3) | ||||
AKI2 | 127 (12.8) | 44 (9.2) | 60 (9.2) | 47 (13.4) | ||||
AKI3 | 58 (5.8) | 25 (5.2) | 23 (3.5) | 22 (6.3) | ||||
Male, n (%) | 541 (54.4) | 257 (53.5) | 331 (50.6) | 186 (53.1) | .74 | .48 | .30 | |
Age (years), median (interquartile range) | 73.00 (58.00-84.00) | 7.00 (57.00-83.00) | 82.00 (73.00-88.00) | 82.00 (73.25-88.75) | .14 | .81 | <.001 | |
.09 | .32 | <.001 | ||||||
White | 625 (62.9) | 281 (58.5) | 512 (78.3) | 274 (78.3) | ||||
Black or Black British | 76 (7.7) | 34 (7.1) | 29 (4.4) | 12 (3.4) | ||||
Asian or Asian British | 110 (11.1) | 52 (10.8) | 60 (9.2) | 25 (7.1) | ||||
Mixed | 10 (1.0) | 2 (0.42) | 3 (0.5) | 4 (1.1) | ||||
Other ethnic groups | 173 (17.4) | 111 (23.1) | 50 (7.7) | 35 (10.0) | ||||
.87 | .83 | <.001 | ||||||
Quintile 1 (least deprived) | 184 (18.5) | 84 (17.5) | 42 (6.42) | 25 (7.1) | ||||
Quintile 2 | 216 (21.7) | 130 (27.1) | 132 (20.2) | 60 (17.1) | ||||
Quintile 3 | 233 (23.4) | 89 (18.5) | 183 (28.0) | 111 (31.7) | ||||
Quintile 4 | 224 (22.5) | 111 (23.1) | 186 (28.4) | 99 (28.3) | ||||
Quintile 5 (most deprived) | 97 (9.8) | 46 (9.6) | 108 (16.5) | 53 (15.1) | ||||
Unknown | 40 (4.0) | 20 (4.2) | 3 (0.5) | 2 (0.6) | ||||
.49 | <.001 | <.001 | ||||||
0 | 114 (11.5) | 49 (10.2) | 10 (1.5) | 7 (2.0) | ||||
1 | 51 (5.13) | 11 (2.3) | 25 (3.8) | 9 (2.6) | ||||
2 | 63 (6.3) | 54 (11.2) | 29 (4.4) | 13 (3.7) | ||||
3 | 107 (1.8) | 43 (9.0) | 78 (11.9) | 21 (6.0) | ||||
4 | 169 (17.0) | 63 (13.1) | 150 (22.9) | 59 (16.9) | ||||
≥5 | 490 (49.3) | 260 (54.2) | 362 (55.4) | 241 (68.9) | ||||
Pre-existing renal disease present, n (%) | 303 (30.5) | 162 (33.8) | 215 (32.9) | 158 (45.1) | .23 | <.001 | <.001 |
aRFH: Royal Free Hospital.
bBGH: Barnet General Hospital.
cPre: May 2016 to January 2017.
dPost: May 2017 to September 2017.
eAKI: acute kidney injury.
fNot applicable.
Descriptive statistics of total cost per spell producing acute kidney injury alerts.
Statistics | Royal Free Hospital (£) | Barnet General Hospital (£) | ||
Prea | Postb | Pre | Post | |
Mean (SD) | 12,015.24 (22,732.78) | 10,154.92 (19,582.30) | 7391.16 (14,346.27) | 7108.88 (11,512.95) |
Median | 5640.50 | 4954.00 | 3712.50 | 3774.00 |
1st centile | 166.00 | 207.00 | 160.00 | 199.00 |
25th centile | 2391.50 | 2079.00 | 1424.00 | 1153.50 |
75th centile | 13,208.50 | 10,567.00 | 8466.00 | 8897.00 |
99th centile | 111,245.00 | 90,138.00 | 51,991.00 | 45,614.00 |
aPre: May 2016 to January 2017.
bPost: May 2017 to September 2017.
Estimates from the models predicting clinical outcomes are reported in
Results of segmented regression analyses for renal recovery and mortality.
Variable/interaction term | Renal recovery | Mortality | ||||
Beta | ORa (95% CI) | Beta | OR (95% CI) | |||
Interventionb | .00 | .99 | 1.00 (0.58-1.71) | .17 | .67 | 1.18 (0.55-2.52) |
Site×interventionc | .22 | .62 | 1.24 (0.53-2.92) | .06 | .91 | 1.07 (0.36-3.15) |
Time×interventiond | −.01 | .61 | 0.99 (0.96-1.03) | .00 | .89 | 1.00 (0.96-1.05) |
Time×site×interventione | −.03 | .29 | 0.97 (0.92-1.03) | −.03 | .44 | 0.97 (0.91-1.04) |
aOR: odds ratio.
bThe coefficient
cThe 2-way interaction
dThe 2-way interaction
eThe 3-way interaction
Results of segmented regression analyses for progression of acute kidney injury stage and admission to intensive treatment unit/renal unit.
Variable/interaction term | Progression of acute kidney injury stage | Admission to intensive treatment unit/renal unit | |||||
Beta | ORa (95% CI) | Beta | OR (95% CI) | ||||
Interventionb | .67 | .11 | 1.96 (0.86-4.47) | .40 | .42 | 1.50 (0.57-4.00) | |
Site×interventionc | −.71 | .27 | 0.49 (0.14-1.71) | −1.18 | .18 | 0.31 (0.05-1.68) | |
Time×interventiond | −.01 | .60 | 0.99 (0.93-1.04) | .02 | .55 | 1.02 (0.96-1.08) | |
Time×site×interventione | .04 | .32 | 1.04 (0.96-1.13) | .07 | .19 | 1.08 (0.97-1.20) |
aOR: odds ratio.
bThe coefficient
cThe 2-way interaction
dThe 2-way interaction
eThe 3-way interaction
Results of segmented regression analyses for hospital re-admission and renal replacement therapy use.
Variable/interaction term | Re-admission at 30 days | Renal replacement therapy use at 30 days | ||||
Beta | ORa (95% CI) | Beta | OR (95% CI) | |||
Interventionb | .20 | .54 | 1.22 (0.65-2.29) | −3.32 | .03 | 0.04 (0.00-0.62) |
Site×interventionc | −.16 | .77 | 0.86 (0.31-2.39) | −1.04 | .99 | 0.35 (0-infinity) |
Time×interventiond | −.03 | .23 | 0.97 (0.93-1.02) | .00 | .98 | 1.00 (0.83-1.23) |
Time×site×interventione | .01 | .84 | 1.01 (0.94-1.08) | −17.62 | .99 | 0.00 (0-infinity) |
aOR: odds ratio.
bThe coefficient
cThe 2-way interaction
dThe 2-way interaction
eThe 3-way interaction
Results of segmented regression analysis for hospital cardiac arrest rate
Variable/interaction term | Cardiac arrests | ||
Beta | OR (95% CI) | ||
Interventiona | −.60 | <.001 | 0.55 (0.38-0.76) |
Site×interventionb | .12 | .69 | 1.13 (0.63-1.99) |
aThe coefficient
bThe 2-way interaction
We found no evidence for a step change in renal recovery rate (return to a serum creatinine concentration within 120% of the baseline) following the intervention at the RFH. The estimated odds ratio (OR) for the intervention step change was 1.00 (95% CI 0.58-1.71). There was also no evidence for a significant difference in step change of recovery rate between RFH and BGH (estimated OR 1.24, 95% CI 0.53-2.92;
The model did not estimate a statistically significant change in the trend of renal recovery rates at RFH (estimated OR 0.99, 95% CI 0.96-1.03;
Weekly recovery rate at Royal Free Hospital (RFH) and Barnet General Hospital (BGH) before and after implementation of the care pathway. Individual data points reflect the rate of each outcome for a single week. Solid lines indicate fitted values from the modeling functions.
We found evidence for a reduction (step change) in the rate of cardiac arrest following the intervention at RFH (estimated OR 0.55, 95% CI 0.38-0.76;
We also found evidence for a reduction (step change) in the rates of RRT use at 30 days at the intervention site (estimated OR 0.04, 95% CI 0.00-0.62,
We found no evidence for an effect of the intervention on time to renal recovery. At RFH, the median (IQR) time to renal recovery was 3.00 days (1.00-15.00 days) before and 4.00 days (1.00-12.00 days) after the introduction of the intervention (
Cardiac arrests at Royal Free Hospital (RFH) and Barnet General Hospital (BGH). Individual data points reflect the rate of cardiac arrest per thousand admissions for a single month. Solid lines indicate fitted values from the modeling functions.
There was a significant reduction in adjusted mean costs per spell over time at the RFH but not at the BGH (
Results of economic analysis: Royal Free Hospital.
Time period | Preintervention (£) | Postintervention (£) | Difference (£) | ||||
Mean | 95% CI | Mean | 95% CI | Mean | 95% CI | ||
Periods t1a and t3b only | 12,176.52 | 10,996.53 to 13,356.50 | 9853.37 | 8840.91 to 10,865.82 | −2323.15 | −3843.90 to −802.41 | .003 |
All periods | 11,772.63 | 10,936.03 to 12,609.23 | 9761.59 | 8755.45 to 10,767.72 | −2011.05 | −3283.53 to −738.56 | .002 |
at1: May to September 2016.
bt3: May to September 2017.
Results of economic analysis: Barnet General Hospital.
Time period | Preintervention (£) | Postintervention (£) | Difference (£) | ||||
Mean | 95% CI | Mean | 95% CI | Mean | 95% CI | ||
Periods t1a and t3b only | 7507.88 | 6589.77 to 8425.99 | 7307.27 | 6461.82 to 8152.71 | −200.62 | −1370.27 to 969.04 | .74 |
All periods | 7623.76 | 7007.67 to 8239.86 | 7243.58 | 6413.81 to 8073.35 | −380.19 | −1358.56 to 598.19 | .45 |
at1: May to September 2016.
bt3: May to September 2017.
Results of economic analysis: difference-in-difference analysis of Royal Free Hospital and Barnet General Hospital.
Time period | Mean | 95% CI | |
Periods t1a and t3b only (£) | −2122.54 | −4023.37 to −221.70 | .03 |
All periods (£) | −1630.86 | −3217.50 to −44.22 | .04 |
at1: May to September 2016.
bt3: May to September 2017.
The digitally enabled care pathway for the management of AKI in a large, acute hospital with a complex casemix resulted in no significant impact on the primary outcome of renal recovery or any of the other secondary clinical outcomes measured but was associated with a significant reduction in adjusted mean costs per patient admission. We did not include the costs of providing the technology, and therefore, it is not possible to judge whether or not it would be cost saving overall. Our results suggest that the digitally enabled care pathway would be cost saving, provided provision of the technology costs less than around £1600 per patient spell. The causes of the cost savings are unclear but are likely to be multifactorial, and further research to investigate these would be useful. The most important cost components contributing to this reduction (detailed in
There are several possible explanations for the lack of impact on renal recovery. First, this may reflect existing high standards of AKI care before implementation: 30-day mortality for preintervention patients at RFH was 14.9% compared with 18.1% nationally [
An explanation for the possible effect of the intervention on rates of cardiac arrest emerged from qualitative data provided in our parallel paper [
Our data are consistent with recent reports of the benefits of e-alerting systems for AKI for patients and the wider health system. We have reported on the impact of the digitally enabled care pathway on processes of care and clinical outcomes for patients with AKI at the point of presentation to the ED. Implementation of the digitally enabled care pathway for these patients was associated with significant improvement in the reliability of AKI recognition, a reduction in time to recognize and adjust potentially nephrotoxic medications [
Our evaluation had a number of strengths. First, this is, to our knowledge, the first study to define the economic impact of implementing a digital innovation for AKI on health systems. Second, we clinically validated all NHSEDA AKI alerts before analysis and validated this process. Third, our inclusion of a comparator site follows best practice [
Our evaluation also had several limitations. First, longer time frames and the inclusion of multiple intervention and comparator sites would have helped overcome the effect of differences in casemix in the pre- and postintervention period (identified in our single comparator site) and may have helped to clarify any added value of the integration of our digital innovation into the care pathway. This would also have allowed us to investigate the impact on specific patient subgroups and better understand if outcomes differed between different AKI stages. It is possible, for instance, that established severe AKI is far less responsive to intervention than the early disease. It is important that such issues are prospectively addressed in future studies. Longer time frames would also have allowed us to control for any seasonal changes in outcome, which are known to occur [
The digitally enabled AKI care pathway reduced inpatient health care costs and may also help reduce hospital-wide cardiac arrest rates: this result requires reanalysis in larger, multisite studies. Growing support for greater digitalization of health systems offers the opportunity to improve the quality and safety of care and to reduce its cost. However, prospective evaluation of the clinical and cost impacts of digital innovations within the context in which they are delivered will be key in delivering maximum utility for patients and health systems.
The National Health Service Early Detection Algorithm; acute kidney injury (AKI) care pathway; AKI care protocol; nursing advisory sticker; inter- and intra-operator variability analyses; Royal Free Hospital Data Monitoring Committee; distribution of costs per spell; results of segmented regression analyses; results from binary logistic regression analysis; graphs of secondary outcome data; cost component analyses.
acute kidney injury
Barnet General Hospital
difference-in-differences
emergency department
generalized linear model
Index of Multiple Deprivation
interquartile range
intensive treatment unit
National Health Service
NHS Early Detection Algorithm
National Institute for Health Research
odds ratio
Patient at Risk and Resuscitation Team
Payment Level Information and Costing System
Royal Free Hospital
Royal Free London NHS Foundation Trust
renal replacement therapy
University College London
ECB and RR are supported by the National Institute for Health Research (NIHR) Collaboration for Leadership in Applied Health Research and Care North Thames at Barts Health NHS Trust. RR is an NIHR Senior Investigator. GR and HM are funded in part by the NIHR University College London Hospitals Biomedical Research Centre. OSA is partially supported by an NIHR academic clinical fellowship. The authors wish to express their gratitude to the staff and patients of RFLFT. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health.
HM, CL, RR, CH, AK, TB, KA, DK, and MS initiated the project and collaboration. CL conceived the care pathway. AC, CL, CM, JC, GJ, SS, and ME supported implementation. AC, CL, GR, RR, HM, PM, and CN were responsible for the design of the evaluation. AC and CL triaged alerts necessary for the evaluation. AC collected all necessary data. Clinical outcomes were analyzed by AC with assistance and oversight from PM and CN. Economic outcomes were analyzed by ECB with assistance from SM. AC, HM, RR, PM, CL, ECB, SM, and GR wrote the paper. All authors read and agreed the final submission.
CL, HM, GR, and RR are paid clinical advisors to DeepMind. AC’s clinical research fellowship was part-funded by DeepMind, where he has been a full-time employee since May 2018. DeepMind remained independent from the collection and analysis of all data. CL was a member of the NICE clinical guideline 169 development group referenced in the article. HM coholds a patent on a fluid delivery device, which might ultimately help in preventing some (dehydration-related) cases of AKI occurring.
DeepMind was acquired by Google in 2014 and is now part of the Alphabet group. The deployment of Streams app at RFH was the subject of an investigation by the Information Commissioner’s Office in 2017. RFH has since published an audit completed to comply with undertakings following this investigation [