A Machine Learning Model for the Routine Detection of "Wrong Blood in Complete Blood Count Tube" Errors.

BACKGROUND: Current laboratory procedures may fail to detect wrong blood in tube (WBIT) errors. Machine learning models have the potential to improve WBIT error detection, as demonstrated by proof-of-concept studies. The models developed so far, however, are not appropriate for routine use because they are unable to handle missing values and have low positive predictive value (PPV). In this study, a machine learning model suitable for routine use was developed. METHODS: A model was trained and a preliminary evaluation performed on a retrospective data set of 135 128 current and previous patient complete blood count (CBC) results. The model was then applied prospectively to routine samples tested in a public hospital laboratory over a period of 22 weeks. Each week, the 5 samples identified by the model as most likely to be WBIT errors underwent further investigation by testing blood group and red cell phenotype. The study assessed the number of WBIT errors that were missed by current procedures but detected by the model, as well as the PPV of the model. RESULTS: The model was applied prospectively to 38 187 CBC results that had passed routine laboratory checks. One hundred and ten samples were identified for further testing and 12 WBIT errors were detected. The PPV of the model was 10.9%. CONCLUSION: A machine learning model suitable for routine use was able to identify WBIT errors missed by the laboratory's current procedures. Machine learning models are valuable for the identification of WBIT errors, and their validation and deployment in clinical laboratories would improve patient safety.

Machine learning models outperform manual result review for the identification of wrong blood in tube errors in complete blood count results.

INTRODUCTION: Wrong blood in tube (WBIT) errors are a significant patient-safety issue encountered by clinical laboratories. This study assessed the performance of machine learning models for the identification of WBIT errors affecting complete blood count (CBC) results against the benchmark of manual review of results by laboratory staff. METHODS: De-identified current and previous (within seven days) CBC results were used in the computer simulation of WBIT errors. 101 015 sets of samples were used to develop machine learning models using artificial neural network, extreme gradient boosting, support vector machine, random forest, logistic regression, decision trees (one complex and one simple) and k-nearest neighbours algorithms. The performance of these models, and of manual review by laboratory staff, was assessed on a separate data set of 1940 samples. RESULTS: Volunteers manually reviewing results identified WBIT errors with an accuracy of 85.7%, sensitivity of 80.1% and specificity of 92.1%. All machine learning models exceeded human-level performance (p-values for all metrics were <.001). The artificial neural network model was the most accurate (99.1%), and the simple decision tree was the least accurate (96.8%). Sensitivity for the machine learning models varied from 95.7% to 99.3%, and specificity varied from 96.3% to 98.9%. CONCLUSION: This study provides preliminary evidence supporting the value of machine learning for detecting WBIT errors affecting CBC results. Although further work addressing practical issues is required, substantial patient-safety benefits await the successful deployment of machine learning models for WBIT error detection.

Evaluation of point-of-care testing in critically unwell patients: comparison with clinical laboratory analysers and applicability to patients with Ebolavirus infection.

Data on the performance of point-of-care (POC) or near-patient devices in the management of critically unwell patients are limited, meaning that there are demands for confirming POC test results in the routine clinical laboratory and so potentially leading to delay in treatment provision. We evaluated the performance of the i-STAT CHEM 8+ and CG4+, Hemochron Signature Elite, HemoCue Hb 201+ and WBC Diff Systems on whole blood collected from medical and surgical patients admitted to the intensive care unit at an Australian tertiary care hospital. Measurements obtained for haematology, coagulation, biochemistry and arterial blood gas parameters using POC devices were compared against clinical laboratory analysers (XE-5000, STA-R Evolution, Dimension Vista 1500 and ABL800 FLEX). Bland-Altman and Passing-Bablok regression plots were constructed to assess agreement. Good correlation was defined as a bias of <10% between the POC device and the reference method. Forty arterial blood samples were collected from 28 patients. There was good correlation demonstrated for sodium, potassium, chloride, ionised calcium, glucose, urea, haemoglobin and haematocrit values (i-STAT Chem 8+); pH, pCO(2), bicarbonate and oxygen saturation (i-STAT CG4+); haemoglobin, white cell, neutrophil count and lymphocyte counts (Hemocue); and internationalised normal ratio (INR; Hemochron Signature Elite), but not creatinine, anion gap, pO(2), base excess, lactate, eosinophil count, prothrombin and activated partial thromboplastin time. POC devices were comparable to clinical laboratory analysers in measuring the majority of haematology, biochemistry and coagulation parameters in critically unwell patients, including those with infections. These devices may be deployed at the bedside to allow 'real-time' testing to improve patient care.