Automation, decision support, and expert systems in nephrology

Novelle QLL 2020 – welche Auswirkungen haben die neu empfohlenen Hämoglobin-Transfusionstrigger auf die klinische Versorgung?

In der Gesamtnovelle der Querschnittsleitlinie (QLL) Hämotherapie der Bundesärztekammer (BÄK) 2020 wurde der Hämoglobin-Transfusionstrigger (Hb-Transfusionstrigger) bei akutem Blutverlust ohne zusätzliche Risikofaktoren aufgrund einer Neubewertung der internationalen Evidenz von 3,7 mmol/l (6 g/dl) auf 4,3 mmol/l (7 g/dl) angepasst. Ziel der vorliegenden Studie ist die retrospektive Analyse des Transfusionsverhaltens von EK bezüglich der Maßgaben der QLL. Zu diesem Zweck analysierten wir individuelle Prä- und Posttransfusions-Hb-Werte von Erythrozytenkonzentraten (EK), die im 4. Quartal 2019 (4946 EKs, 129 560 Hb-Werte) und 2020 (5502 EKs, 134 404 Hb-Werte) am Universitätsklinikum Leipzig (UKL) transfundiert wurden. Der mediane Hb-Wert vor der Transfusion betrug 4,3 mmol/l (7 g/dl) (680 medizinische Fälle, die 2724 EK in 1801 Transfusionen im Jahr 2019 erhielten). Von allen Transfusionen im Jahr 2019 zeigten 899 (49,9%) Transfusionen Hb-Werte < 4,3 mmol/l (7 g/dl) vor der Transfusion, während 152 (8,4%) Hb-Werte < 3,7 mmol/l (6 g/dl) aufwiesen. 2020 wurden jeweils vergleichbare Ergebnisse ermittelt. Wir zeigen, dass der mediane Hb-Anstieg nach der Transfusion eines EK 0,6 mmol/l (1 g/dl) betrug. 34,7% aller Transfusionen erreichten den erwarteten Anstieg von 0,6 mmol/l (1 g/dl) pro EK. Der absolute Anstieg nahm bei Transfusionen mit mehreren EK im Vergleich zu Transfusionen mit einem EK nicht linear zu. Der Grad der Hb-Erhöhung korrelierte invers mit dem Hb-Wert vor Transfusion. Der Hb-Wert nach der Transfusion wurde bei 96,3% der Fälle innerhalb von 24 Stunden nach Hämotherapie kontrolliert. Zusammenfassend spiegelt das Transfusionsverhalten generell die Empfehlungen der Leitlinie. Um ein optimiertes, individualisiertes und dennoch restriktives Transfusionsverhalten bei EK zu erreichen, schlagen wir die Implementierung eines klinischen Entscheidungsunterstützungssystems (CDSS) bei Verschreibung jeder einzelnen EK-Transfusion vor, welches Ärzte bei der Einhaltung der Transfusionsleitlinie unterstützt und über Abweichungen informiert.

Automation in nursing decision support systems: A systematic review of effects on decision making, care delivery, and patient outcomes

OBJECTIVE

The study sought to summarize research literature on nursing decision support systems (DSSs ); understand which steps of the nursing care process (NCP) are supported by DSSs, and analyze effects of automated information processing on decision making, care delivery, and patient outcomes.

MATERIALS AND METHODS

We conducted a systematic review in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement. PubMed, CINAHL, Cochrane, Embase, Scopus, and Web of Science were searched from January 2014 to April 2020 for studies focusing on DSSs used exclusively by nurses and their effects. Information about the stages of automation (information acquisition, information analysis, decision and action selection, and action implementation), NCP, and effects was assessed.

RESULTS

Of 1019 articles retrieved, 28 met the inclusion criteria, each studying a unique DSS. Most DSSs were concerned with two NCP steps: assessment (82%) and intervention (86%). In terms of automation, all included DSSs automated information analysis and decision selection. Five DSSs automated information acquisition and only one automated action implementation. Effects on decision making, care delivery, and patient outcome were mixed. DSSs improved compliance with recommendations and reduced decision time, but impacts were not always sustainable. There were improvements in evidence-based practice, but impact on patient outcomes was mixed.

CONCLUSIONS

Current nursing DSSs do not adequately support the NCP and have limited automation. There remain many opportunities to enhance automation, especially at the stage of information acquisition. Further research is needed to understand how automation within the NCP can improve nurses' decision making, care delivery, and patient outcomes.

The development of an automated ward independent delirium risk prediction model

Background A delirium is common in hospital settings resulting in increased mortality and costs. Prevention of a delirium is clearly preferred over treatment. A delirium risk prediction model can be helpful to identify patients at risk of a delirium, allowing the start of preventive treatment. Current risk prediction models rely on manual calculation of the individual patient risk. Objective The aim of this study was to develop an automated ward independent delirium riskprediction model. To show that such a model can be constructed exclusively from electronically available risk factors and thereby implemented into a clinical decision support system (CDSS) to optimally support the physician to initiate preventive treatment. Setting A Dutch teaching hospital. Methods A retrospective cohort study in which patients, 60 years or older, were selected when admitted to the hospital, with no delirium diagnosis when presenting, or during the first day of admission. We used logistic regression analysis to develop a delirium predictive model out of the electronically available predictive variables. Main outcome measure A delirium risk prediction model. Results A delirium risk prediction model was developed using predictive variables that were significant in the univariable regression analyses. The area under the receiver operating characteristics curve of the "medication model" model was 0.76 after internal validation. Conclusions CDSSs can be used to automatically predict the risk of a delirium in individual hospitalised patients' by exclusively using electronically available predictive variables. To increase the use and improve the quality of predictive models, clinical risk factors should be documented ready for automated use.

Automated clinical reminders for primary care providers in the care of CKD: a small cluster-randomized controlled trial

BACKGROUND

Primary care physicians (PCPs) care for most non-dialysis-dependent patients with chronic kidney disease (CKD). Studies suggest that PCPs may deliver suboptimal CKD care. One means to improve PCP treatment of CKD is clinical decision support systems (CDSSs).

STUDY DESIGN

Cluster-randomized controlled trial.

SETTING & PARTICIPANTS

30 PCPs in a university-based outpatient general internal medicine practice and their 248 patients with moderate to advanced CKD who had not been referred to a nephrologist.

INTERVENTION

2 CKD educational sessions were held for PCPs in both arms. The 15 intervention-arm PCPs also received real-time automated electronic medical record alerts for patients with estimated glomerular filtration rates <45 mL/min/1.73 m(2) recommending renal referral and urine albumin quantification if not done within the prior year.

OUTCOMES

Primary outcome was referral to a nephrologist; secondary outcomes were albuminuria/proteinuria assessment, CKD documentation, optimal blood pressure (ie, <130/80 mm Hg), and use of renoprotective medications.

RESULTS

The intervention and control arms did not differ in renal referrals (9.7% vs 16.5%, respectively; between-group difference, -6.8%; 95% CI, -15.5% to 1.8%; P = 0.1) or proteinuria assessments (39.3% vs 30.1%, respectively; between-group difference, 9.2%; 95% CI, -2.7% to 21.1%; P = 0.1). For intervention and control patients without a baseline proteinuria assessment, 27.7% versus 16.3%, respectively, had one at follow-up (P = 0.06). After controlling for clustering, these findings were largely unchanged and no significant differences were apparent between groups.

LIMITATIONS

Small single-center university-based practice, use of a passive CDSS that required PCPs to trigger the electronic order set.

CONCLUSIONS

PCPs were willing to partake in a randomized trial of a CDSS to improve outpatient CKD care. Although CDSSs may have potential, larger studies are needed to further explore how best to deploy them to enhance CKD care.

Under-documentation of chronic kidney disease in the electronic health record in outpatients

OBJECTIVE

To ascertain if outpatients with moderate chronic kidney disease (CKD) had their condition documented in their notes in the electronic health record (EHR).

DESIGN

Outpatients with CKD were selected based on a reduced estimated glomerular filtration rate and their notes extracted from the Columbia University data warehouse. Two lexical-based classification tools (classifier and word-counter) were developed to identify documentation of CKD in electronic notes.

MEASUREMENTS

The tools categorized patients' individual notes on the basis of the presence of CKD-related terms. Patients were categorized as appropriately documented if their notes contained reference to CKD when CKD was present.

RESULTS

The sensitivities of the classifier and word-count methods were 95.4% and 99.8%, respectively. The specificity of both was 99.8%. Categorization of individual patients as appropriately documented was 96.9% accurate. Of 107 patients with manually verified moderate CKD, 32 (22%) lacked appropriate documentation. Patients whose CKD had not been appropriately documented were significantly less likely to be on renin-angiotensin system inhibitors or have urine protein quantified, and had the illness for half as long (15.1 vs 30.7 months; p<0.01) compared to patients with documentation.

CONCLUSION

Our studies show that lexical-based classification tools can accurately ascertain if appropriate documentation of CKD is present in a EHR. Using this method, we demonstrated under-documentation of patients with moderate CKD. Under-documented patients were less likely to receive CKD guideline recommended care. A tool that prompts providers to document CKD might shorten the time to implementing guideline-based recommendations.