The Clinical Decision Support System AMPEL for Laboratory Diagnostics: Implementation and Technical Evaluation

Evidence-based cutoffs for total and adjusted calcium: a major factor in detecting severe hypo- and hypercalcemia

OBJECTIVES

Severe hypo- and hypercalcemia are common and urgent treatment is recommended. Free calcium (fCa) is the gold standard but needs blood gas tests with challenging preanalytics. Total calcium (tCa) and calculated adjusted calcium (aCa) are readily available, but their interpretation is hampered by identical tCa and aCa cutoffs, laborious local aCa calculation and difficult comparability of calcium biomarkers.

METHODS

Laboratory results from University Medicine Leipzig were evaluated over a five-year period (236,274 patients). A local aCa equation was derived by linear least squares regression, the agreement between fCa, tCa and aCa assessed with Cohen's κ and decision thresholds derived by this indirect method.

RESULTS

The local aCa equation was created from data of 9,756 patients, each with one paired measurement of tCa, fCa and albumin. Derived aCa cutoffs (1.95/3.15 mmol/L) differ markedly from derived tCa cutoffs (1.6/2.9 mmol/L) and severe hypo- and hypercalcemia can be more accurately assessed by aCa (κ=0.489, 0.812) than by tCa (κ=0.445, 0.744). Comparing our approach to standard care (tCa, literature cutoff), a total 3,250 of 3,680 (88.3 %) misclassified measurements were correctly classified when using aCa with evidence-based cutoffs.

CONCLUSIONS

Optimized cutoffs for aCa and tCa hold great potential for improved patient care. Locally derived aCa equations differ mostly in the chosen mean normal calcium and provide minimal overall improvement, but entail a close examination of the used cutoffs before application.

Applying Machine Learning to Blood Count Data Predicts Sepsis with ICU Admission

BACKGROUND

Timely diagnosis is crucial for sepsis treatment. Current machine learning (ML) models suffer from high complexity and limited applicability. We therefore created an ML model using only complete blood count (CBC) diagnostics.

METHODS

We collected non-intensive care unit (non-ICU) data from a German tertiary care centre (January 2014 to December 2021). Using patient age, sex, and CBC parameters (haemoglobin, platelets, mean corpuscular volume, white and red blood cells), we trained a boosted random forest, which predicts sepsis with ICU admission. Two external validations were conducted using data from another German tertiary care centre and the Medical Information Mart for Intensive Care IV database (MIMIC-IV). Using the subset of laboratory orders also including procalcitonin (PCT), an analogous model was trained with PCT as an additional feature.

RESULTS

After exclusion, 1 381 358 laboratory requests (2016 from sepsis cases) were available. The CBC model shows an area under the receiver operating characteristic (AUROC) of 0.872 (95% CI, 0.857-0.887). External validations show AUROCs of 0.805 (95% CI, 0.787-0.824) for University Medicine Greifswald and 0.845 (95% CI, 0.837-0.852) for MIMIC-IV. The model including PCT revealed a significantly higher AUROC (0.857; 95% CI, 0.836-0.877) than PCT alone (0.790; 95% CI, 0.759-0.821; P < 0.001).

CONCLUSIONS

Our results demonstrate that routine CBC results could significantly improve diagnosis of sepsis when combined with ML. The CBC model can facilitate early sepsis prediction in non-ICU patients with high robustness in external validations. Its implementation in clinical decision support systems has strong potential to provide an essential time advantage and increase patient safety.

Development, Design and Utilization of a CDSS for Refeeding Syndrome in Real Life Inpatient Care-A Feasibility Study

BACKGROUND

The refeeding syndrome (RFS) is an oftentimes-unrecognized complication of reintroducing nutrition in malnourished patients that can lead to fatal cardiovascular failure. We hypothesized that a clinical decision support system (CDSS) can improve RFS recognition and management.

METHODS

We developed an algorithm from current diagnostic criteria for RFS detection, tested the algorithm on a retrospective dataset and combined the final algorithm with therapy and referral recommendations in a knowledge-based CDSS. The CDSS integration into clinical practice was prospectively investigated for six months.

RESULTS

The utilization of the RFS-CDSS lead to RFS diagnosis in 13 out of 21 detected cases (62%). It improved patient-related care and documentation, e.g., RFS-specific coding (E87.7), increased from once coded in 30 month in the retrospective cohort to four times in six months in the prospective cohort and doubled the rate of nutrition referrals in true positive patients (retrospective referrals in true positive patients 33% vs. prospective referrals in true positive patients 71%).

CONCLUSION

CDSS-facilitated RFS diagnosis is possible and improves RFS recognition. This effect and its impact on patient-related outcomes needs to be further investigated in a large randomized-controlled trial.

Challenge in hyponatremic patients - the potential of a laboratory-based decision support system for hyponatremia to improve patient's safety

OBJECTIVES

Hyponatremia is the most frequent electrolyte disorder in hospitalized patients with increased mortality and morbidity. In this study, we evaluated the follow-up diagnostic, the risk of inadequate fast correction and the outcome of patients with profound hyponatremia (pHN), defined as a blood sodium concentration below 120 mmol/L. The aim was to identify a promising approach for a laboratory-based clinical decision support system (CDSS).

METHODS

This retrospective study included 378,980 blood sodium measurements of 83,315 cases at a German tertiary care hospital. Hospitalized cases with pHN (n=211) were categorized into two groups by the time needed for a follow-up measurement to be performed (time to control, TTC) as either <12 h (group 1: "TTC≤12 h", n=118 cases) or >12 h (group 2: "TTC>12 h", n=93 cases). Length of hospital stay, sodium level at discharge, ward transfers, correction of hyponatremia, and risk of osmotic demyelination syndrome (ODS) due to inadequate fast correction were evaluated with regard to the TTC of sodium blood concentration.

RESULTS

pHN was detected in 1,050 measurements (0.3%) in 211 cases. Cases, in which follow-up diagnostics took longer (TTC>12 h), achieved a significantly lower sodium correction during their hospitalization (11.2 vs. 16.7 mmol/L, p<0.001), were discharged more frequently in hyponatremic states (<135 mmol/L; 58 (62.4%) vs. 43 (36.4%), p<0.001) and at lower sodium blood levels (131.2 vs. 135.0 mmol/L, p<0.001). Furthermore, for these patients there was a trend toward an increased length of hospital stay (13.1 vs. 8.5 days, p=0.089), as well as an increased risk of inadequate fast correction (p<0.001).

CONCLUSIONS

Our study shows that less frequent follow-up sodium measurements in pHN are associated with worse outcomes. Patients with a prolonged TTC are at risk of insufficient correction of hyponatremia, reduced sodium values at discharge, and possible overcorrection. Our results suggest that a CDSS that alerts treating physicians when a control time of >12 h is exceeded could improve patient care in the long term. We are initiating a prospective study to investigate the benefits of our self-invented CDSS (www.ampel.care) for patients with pHN.

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.