Figure - available from: BMC Medical Informatics and Decision Making
This content is subject to copyright. Terms and conditions apply.
Acute kidney injury order set. AKI: acute kidney injury, USKUB: kidney, ureter, bladder ultrasound, IV: intravenous, ARB: angiotensin II receptor blockers, ACE: angiotensin converting enzyme, NSAIDs: non-steroidal anti-inflammatory drugs
Source publication
Background
Acute kidney injury (AKI) is common in hospitalized patients and is associated with poor patient outcomes and high costs of care. The implementation of clinical decision support tools within electronic medical record (EMR) could improve AKI care and outcomes. While clinical decision support tools have the potential to enhance recognition...
Similar publications
Background and objectives: The aim of this study is to describe the temporal change in alert override with a minimally interruptive clinical decision support (CDS) on a Next-Generation electronic medical record (EMR) and analyze factors associated with the change. Materials and Methods: The minimally interruptive CDS used in this study was implemen...
Citations
... 46,53,57,60,82,85,88 Among the 61 displays, nurses were target users in 47 displays. 33,35,36,39,40,42,[44][45][46][47][48][49][50]53,54,[56][57][58][59][60][61][62][63]65,66,[68][69][70][71][72][73][74][75]77,80,81,[83][84][85][86][88][89][90][91][92][93][94][95] Information display types Of the 64 included studies, 24 studies included information display screenshots or references to accessible publications that contain screenshots. [39][40][41][42]44,46,48,51,54,56,57,59,66,68,75,[79][80][81]83,86,88,91,92,96 Thirty-six interventions had a single alert modality. ...
... 33,35,36,39,40,42,[44][45][46][47][48][49][50]53,54,[56][57][58][59][60][61][62][63]65,66,[68][69][70][71][72][73][74][75]77,80,81,[83][84][85][86][88][89][90][91][92][93][94][95] Information display types Of the 64 included studies, 24 studies included information display screenshots or references to accessible publications that contain screenshots. [39][40][41][42]44,46,48,51,54,56,57,59,66,68,75,[79][80][81]83,86,88,91,92,96 Thirty-six interventions had a single alert modality. Among them, 24 were simple alerts on the EHR screen, pager, or short message service (SMS) messages to mobile devices, 33,35,38,43,45,47,49,56,58,[64][65][66][69][70][71]76,[80][81][82]84,87,88,90,93 7 were single-patient displays, 41,44,48,68,83,92,95 and 5 were multiple-patient views. ...
... Deep learning algorithms involve multiple layers of parameter evaluation, often with more predictors and cases. Score-based algorithms were used in 48 information displays, 33,34,36,[38][39][40][41][42][43][45][46][47]49,50,[53][54][55][56][57][58][59][60][61][62][63][66][67][68][69][70][71]74,77,78,[80][81][82][83][84][85][86][87][88]90,91,[93][94][95][96] classical ML algorithms in 10,35,37,48,51,52,64,65,72,73,75,76,92 and deep learning algorithms in 3 displays (Table 3). 44,79,89 The algorithms' predictions included vital signs, laboratory results, medication orders, nursing assessments (mental status), and self-reported nursing concerns. ...
Objective:
Surveillance algorithms that predict patient decompensation are increasingly integrated with clinical workflows to help identify patients at risk of in-hospital deterioration. This scoping review aimed to identify the design features of the information displays, the types of algorithm that drive the display, and the effect of these displays on process and patient outcomes.
Materials and methods:
The scoping review followed Arksey and O'Malley's framework. Five databases were searched with dates between January 1, 2009 and January 26, 2022. Inclusion criteria were: participants-clinicians in inpatient settings; concepts-intervention as deterioration information displays that leveraged automated AI algorithms; comparison as usual care or alternative displays; outcomes as clinical, workflow process, and usability outcomes; and context as simulated or real-world in-hospital settings in any country. Screening, full-text review, and data extraction were reviewed independently by 2 researchers in each step. Display categories were identified inductively through consensus.
Results:
Of 14 575 articles, 64 were included in the review, describing 61 unique displays. Forty-one displays were designed for specific deteriorations (eg, sepsis), 24 provided simple alerts (ie, text-based prompts without relevant patient data), 48 leveraged well-accepted score-based algorithms, and 47 included nurses as the target users. Only 1 out of the 10 randomized controlled trials reported a significant effect on the primary outcome.
Conclusions:
Despite significant advancements in surveillance algorithms, most information displays continue to leverage well-understood, well-accepted score-based algorithms. Users' trust, algorithmic transparency, and workflow integration are significant hurdles to adopting new algorithms into effective decision support tools.
... The advancement of arti cial intelligence and the emergence of big data have propelled ML to achieve remarkable milestones in disease diagnosis [33,34] . In contrast to traditional algorithmic models, machine learning demonstrates e cient processing capabilities for large-scale and complex datasets, leading to higher accuracy and improved prediction ability in addressing complex problems [35,36] . ...
Background
Acute Respiratory Distress Syndrome (ARDS) is a prevalent condition in the ICU with a mortality rate of 27% to 45%. Despite the Berlin definition being the current diagnostic standard, it has significant limitations. This study aims to establish and validate a novel machine learning-based prediction model for ARDS in ICU patients.
Methods
The data of suspected ARDS patients was extracted from the Medical Information Mart for Intensive Care (MIMIC)-III and MIMIC-IV databases. Ten-fold cross-validation was employed, utilizing machine learning algorithms such as K-nearest neighbor (KNN), support vector machine (SVM), Decision Tree Classifier (DTC), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting (LightGB), and categorical boosting (CatBoost) and logistic regression (LR) for model construction. Finally, the performance of these models was evaluated based on metrics including area under the ROC curve, calibration curve, and clinical decision curve.
Results
A total of 2,852 patients who met the exclusion criteria were included in the final study, of which 2078 patients developed ARDS.We established scoring models, such as LR, KNN, SVM, DTC, RF, XGBoost, LightGB, and CatBoost. The area under the receiver operating characteristic curve (AUC) values for each model were as follows: LR - 0.664, KNN - 0.692, SVM - 0.567, DTC - 0.709, RF - 0.732, XGBoost - 0.793, LightGB - 0.793, and CatBoost - 0.817. Notably, CatBoost exhibited superior predictive performance in discrimination, calibration, and clinical applicability compared to all other models.
Conclusions
The application of machine learning models has showcased their robustness in predicting ARDS. Notably, the CatBoost algorithm emerges as the most promising in terms of predictive performance.
... Figure 3 is an example of singlepage dashboard. There were six Multipage dashboards [49], [50], [60], [61], [65], [69], enabled by tabs or buttons that opened new dashboard windows when clicked. ...
... This includes drop-down selections or the ability to slice timelines to the appropriate timeframe. Our analysis revealed that many dashboards had filters and included some selections [45]- [47], [50], [52], [54], [56], [59], [62], [64]- [66], [68], [69]. However, it was not very common to find dashboards that were interactive in the sense that data could be filtered by selecting it through the charts, as they usually employed drop downs, slicers, or buttons. ...
... Most dashboards analysed enabled clinicians solely to visualise data and not to add or edit existing data. Exceptions to this were [22], [43], [50], [51], [65], [69], [70], which enabled users to update user data directly on the dashboard. ...
Visualisations in Electronic Health Records (EHRs) are crucial for clinical care. Since clinicians need to quickly diagnose and treat their patients, having appropriate ways to visualise patients’ characteristics and issues documented in the EHR, can be instrumental. However, the existing literature has not yet summarised the characteristics and lessons learned from the studies on patient dashboards for clinical care. Our review analysed patient dashboards, that visualised EHR data to support clinical care, and which were evaluated with end-users. We read papers from Human-Computer Interaction, Information Visualisation, and Medical Informatics, focusing on the user interfaces and the end-user evaluation results. From a set of 3545 articles, we selected 30 studies, which were analysed using Thematic Analysis. Results provide an understanding of the patient dashboard designs, the visualisation techniques employed, the data represented, as well as the lessons learned from this body work; which should contribute to future designs.
... To improve recognition of AKI, electronic alerts were recommended and an e-alert system for AKI was mandated by NHS England in all Laboratory Information Management Systems, across the NHS in 2015 [2,7]. National electronic alerts are based on an algorithm described in the NICE guidelines NG148 [8], which defines AKI using the Kidney Disease: Improving Global Outcomes (KDIGO) classification [9], which was commonly used amongst other studies [10][11][12][13][14]. ...
... Some alerts have unsuccessfully attempted to include urine output [12]. Institutions disseminate this information in a variety of ways-via text messages to a dedicated mobile [12,13]; stand-alone alerts [32], emails [13,15], or in our case, and similar to another study [10], by full integration into the EHR. This may explain the difference between the findings in our study, to those in a meta-analysis [19], where no overall effect was found on outcomes (AKI progression, mortality or dialysis). ...
Background
Electronic alerts (e-alerts) for Acute Kidney Injury (AKI) have been implemented into a variety of different Electronic Health Records (EHR) systems worldwide in order to improve recognition and encourage early appropriate management of AKI. We were interested in the impact on patient safety, specialist referral and clinical management.
Methods
All patients admitted to our institution with AKI were included in the study. We studied AKI progression, dialysis dependency, length of hospital stay, emergency readmission, ICU readmission, and death, before and after the introduction of electronic alerts. The impact on prescription of high risk drugs, fluid administration, and referral to renal services was also analysed.
Results
After the introduction of the e-alert, progression to higher AKI stage, emergency readmission to hospital and death during admission were significantly reduced. More prescriptions were stopped for drugs that adversely affect renal function in AKI and there was a significant increase in the ICU admissions and in the number of patients having dialysis, especially in earlier stages. Longer term mortality, renal referrals, and fluid alteration did not change significantly after the AKI e-alert introduction.
Conclusions
AKI e-alerts can improve clinical outcomes in hospitalised patients.
... We were able to initiate the educational process early in the workflow Utilization of combined order sets is an example of real-time, evidence-based, and context-based tool within the EMR that provides clinicians with clinical decision support capability. 11 When ordering a T ± A surgery, the combined order set named "tonsillectomy with postop sleep study" appeared automatically as a top choice reminding the ordering physician to order the postop PSG when appropriate. ...
Objective
Pediatric patients with severe obstructive sleep apnea (OSA) are at risk for residual OSA following tonsillectomy with/without adenoidectomy (T ± A). We initiated a quality improvement (QI) project to increase the percentage of postoperative (postop) polysomnography (PSG) completion to identify residual OSA.
Methods
This is a prospective QI project carried out at a tertiary pediatric academic hospital. Children ≤18 years of age who underwent T ± A for severe OSA were included. Our Specific, Measurable, Attainable, Relevant, and Time‐based (SMART) aim was to increase the percentage of completed postop PSGs in this cohort from a baseline of 70% to95% by May 31, 2021. We focused on patient education and leveraged both clinical decision support and reporting functionalities of the electronic medical record for project implementation.
Results
During the pre‐intervention period between January 1, 2019 to June 30, 2020, 472 patients met the inclusion criteria with an average age of 8.6 years (SD 4.6). The rate of postop PSG completion was 69.7% (SD 11.4%) with an average time of 99 days (SD 66) between surgery and the postop PSG. A shift was observed starting in September 2020, and the PSG completion rate improved to 94.9% by September 30, 2021. Post‐intervention, there were 178 patients with an average age of 9.3 years (SD 4.9). The average time between surgery and the postop PSG was significantly reduced to 57 days (SD 16; p < .001).
Conclusions
Through a multidisciplinary approach, we successfully completed our SMART aim. With the establishment of QI infrastructure, our goal is to deliver better care in a sustainable fashion using QI methodology.
... This latter construct has been shown as a proof of concept in large health care systems, particularly when AKI risk scoring is integrated into the electronic medical record as a clinical decision tool. [57][58][59] Developing a validated AKI risk scoring system for PAD and TAVR procedures remains an ongoing area of research. 23 Volume management A significant proportion of the cardiac catheterization and AKI literature has focused on intravascular volume management. ...
Patients with chronic kidney disease (CKD) are at an increased risk of developing cardiovascular disease (CVD), whereas those with established CVD are at risk of incident or progressive CKD. Compared with individuals with normal or near normal kidney function, there are fewer data to guide the management of patients with CVD and CKD. As a joint effort between the National Kidney Foundation and the Society for Cardiovascular Angiography and Interventions, a workshop and subsequent review of the published literature was held. The present document summarizes the best practice recommendations of the working group and highlights areas for further investigation.
... Electronic alerts have not been systematically implemented across Canada to the extent they have been through the National Health Service in the United Kingdom. Some provincial and regional health systems have developed their own hospital e-alert systems (6), which largely remain the subject of research due to the lack of evidence that they improve clinical outcomes. ...
This is an Early Access article. Please select the PDF button, above, to view it.
... Clinical decision support systems can provide a systematic and objective way to enhance complex reasoning related to differential diagnostics. They can facilitate the process of diagnosis, contributing to its reliability [28][29][30][31][32][33]. Accumulating health data enables the providers to access relevant information for timely diagnosis, supporting effective management throughout care [10,34]. ...
... Most studies concerning an algorithm to apply AKI or CKD diagnoses and stages consider only one diagnosis, either AKI or CKD [28,29,31]. As our project combines the 2 diagnostic criteria formulated by the KDIGO for both AKI and CKD, it improves the validity of diagnosis and enables the clinicians to easily recognize acute-on-chronic KD. ...
Background:
The criteria for the diagnosis of kidney disease outlined in the Kidney Disease: Improving Global Outcomes guidelines are based on a patient's current, historical, and baseline data. The diagnosis of acute kidney injury, chronic kidney disease, and acute-on-chronic kidney disease requires previous measurements of creatinine, back-calculation, and the interpretation of several laboratory values over a certain period. Diagnoses may be hindered by unclear definitions of the individual creatinine baseline and rough ranges of normal values that are set without adjusting for age, ethnicity, comorbidities, and treatment. The classification of correct diagnoses and sufficient staging improves coding, data quality, reimbursement, the choice of therapeutic approach, and a patient's outcome.
Objective:
In this study, we aim to apply a data-driven approach to assign diagnoses of acute, chronic, and acute-on-chronic kidney diseases with the help of a complex rule engine.
Methods:
Real-time and retrospective data from the hospital's clinical data warehouse of inpatient and outpatient cases treated between 2014 and 2019 were used. Delta serum creatinine, baseline values, and admission and discharge data were analyzed. A Kidney Disease: Improving Global Outcomes-based SQL algorithm applied specific diagnosis-based International Classification of Diseases (ICD) codes to inpatient stays. Text mining on discharge documentation was also conducted to measure the effects on diagnosis.
Results:
We show that this approach yielded an increased number of diagnoses (4491 cases in 2014 vs 11,124 cases of ICD-coded kidney disease and injury in 2019) and higher precision in documentation and coding. The percentage of unspecific ICD N19-coded diagnoses of N19 codes generated dropped from 19.71% (1544/7833) in 2016 to 4.38% (416/9501) in 2019. The percentage of specific ICD N18-coded diagnoses of N19 codes generated increased from 50.1% (3924/7833) in 2016 to 62.04% (5894/9501) in 2019.
Conclusions:
Our data-driven method supports the process and reliability of diagnosis and staging and improves the quality of documentation and data. Measuring patient outcomes will be the next step in this project.
... Predictive modeling (38) Back et al., 2016, Im and Chee, 2011, Moen et al., 2020b, Mohammadi et al., 2020, Topaz et al., 2019b, Yokota et al., 2017, Zachariah et al., 2020 Natural language processing (7) Annapragada et al., 2021Koleck et al., 2021, Topaz et al., 2016, Topaz et al., 2019a Computer vision (6) Aldaz et al., 2015, Shu and Shu, 2021, Sikka et al., 2012 Speech recognition (4) Aldaz et al., 2015 Planning/ scheduling (2) Aldaz et al., 2015 Predictive modeling (13) Howarth et al., 2020, Minvielle and Audiffren, 2019 Natural language processing (4) Chu and Huang, 2020 Computer vision (7) Barrera et al., 2020, Cabri et al., 2020 Predictive modeling (5) Ajay et al., 2016, Ginestra et al., 2019, Oh et al., 2014, Sandhu et al., 2020 Computer vision (1) Rantz et al., 2014 Planning /Scheduling (3) Alshurafa et al., 2017, North et al., 2014, Vedanthan et al., 2015 Predictive modeling (1) Jauk et al., 2021 Predictive modeling ( n = 57, 61.3%) Natural language processing ( n = 11, 11.8%) Computer vision ( n = 14, 15.1%) Speech recognition ( n = 7, 7.5%) Planning/ scheduling ( n = 9, 9.7%) ...
Background
Research on technologies based on artificial intelligence in healthcare has increased during the last decade, with applications showing great potential in assisting and improving care. However, introducing these technologies into nursing can raise concerns related to data bias in the context of training algorithms and potential implications for certain populations. Little evidence exists in the extant literature regarding the efficacious application of many artificial intelligence -based health technologies used in healthcare.
Objectives
To synthesize currently available state-of the-art research in artificial intelligence -based technologies applied in nursing practice.
Design
Scoping review
Methods
PubMed, CINAHL, Web of Science and IEEE Xplore were searched for relevant articles with queries that combine names and terms related to nursing, artificial intelligence and machine learning methods. Included studies focused on developing or validating artificial intelligence -based technologies with a clear description of their impacts on nursing. We excluded non-experimental studies and research targeted at robotics, nursing management and technologies used in nursing research and education.
Results
A total of 7610 articles published between January 2010 and March 2021 were revealed, with 93 articles included in this review. Most studies explored the technology development (n=55, 59.1%) and formation (testing) (n=28, 30.1%) phases, followed by implementation (n=9, 9.7%) and operational (n=1, 1.1%) phases. The vast majority (73.1%) of studies provided evidence with a descriptive design (level VI) while only a small portion (4.3 %) were randomised controlled trials (level II). The study aims, settings and methods were poorly described in the articles, and discussion of ethical considerations were lacking in 36.6% of studies. Additionally, one-third of papers (33.3%) were reported without the involvement of nurses.
Conclusions
Contemporary research on applications of artificial intelligence -based technologies in nursing mainly cover the earlier stages of technology development, leaving scarce evidence of the impact of these technologies and implementation aspects into practice. The content of research reported is varied. Therefore, guidelines on research reporting and implementing artificial intelligence -based technologies in nursing are needed. Furthermore, integrating basic knowledge of artificial intelligence -related technologies and their applications in nursing education is imperative, and interventions to increase the inclusion of nurses throughout the technology research and development process is needed.
... Clinical decision support systems can provide a systematic and objective way to enhance complex reasoning related to differential diagnostics. They can facilitate the process of diagnosis, contributing to its reliability [28][29][30][31][32][33]. Accumulating health data enables the providers to access relevant information for timely diagnosis, supporting effective management throughout care [10,34]. ...
... Most studies concerning an algorithm to apply AKI or CKD diagnoses and stages consider only one diagnosis, either AKI or CKD [28,29,31]. As our project combines the 2 diagnostic criteria formulated by the KDIGO for both AKI and CKD, it improves the validity of diagnosis and enables the clinicians to easily recognize acute-on-chronic KD. ...
