Detection of Falsely Elevated Point-of-Care Potassium Results Due to Hemolysis Using Predictive Analytics

The influence of undetected hemolysis on POCT potassium results in the emergency department

OBJECTIVES

This study aimed to evaluate discrepancies in potassium measurements between point-of-care testing (POCT) and central laboratory (CL) methods, focusing on the impact of hemolysis on these measurements and its impact in the clinical practice in the emergency department (ED).

METHODS

A retrospective analysis was conducted using data from three European university hospitals: Technische Universitat Munchen (Germany), Hospital Universitario La Paz (Spain), and Erasmus University Medical Center (The Netherlands). The study compared POCT potassium measurements in EDs with CL measurements. Data normalization was performed in categories for potassium levels (kalemia) and hemolysis. The severity of discrepancies between POCT and CL potassium measurements was assessed using the reference change value (RCV).

RESULTS

The study identified significant discrepancies in potassium between POCT and CL methods. In comparing POCT normo- and mild hypokalemia against CL results, differences of -4.20 % and +4.88 % were noted respectively. The largest variance in the CL was a +4.14 % difference in the mild hyperkalemia category. Additionally, the RCV was calculated to quantify the severity of discrepancies between paired potassium measurements from POCT and CL methods. The overall hemolysis characteristics, as defined by the hemolysis gradient, showed considerable variation between the testing sites, significantly affecting the reliability of potassium measurements in POCT.

CONCLUSIONS

The study highlighted the challenges in achieving consistent potassium measurement results between POCT and CL methods, particularly in the presence of hemolysis. It emphasised the need for integrated hemolysis detection systems in future blood gas analysis devices to minimise discrepancies and ensure accurate POCT results.

Machine learning-based clinical decision support using laboratory data

Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.

Artificial Intelligence Applications in Clinical Chemistry

Artificial intelligence (AI) applications are an area of active investigation in clinical chemistry. Numerous publications have demonstrated the promise of AI across all phases of testing including preanalytic, analytic, and postanalytic phases; this includes novel methods for detecting common specimen collection errors, predicting laboratory results and diagnoses, and enhancing autoverification workflows. Although AI applications pose several ethical and operational challenges, these technologies are expected to transform the practice of the clinical chemistry laboratory in the near future.

Data-Driven Anomaly Detection in Laboratory Medicine: Past, Present, and Future

BACKGROUND

Anomaly detection is an integral component of operating a clinical laboratory. It covers both the recognition of laboratory errors and the rapid reporting of clinically impactful results. Procedures for identifying laboratory errors and highlighting critical results can be improved by applying modern data-driven approaches.

CONTENT

This review will prepare the reader to appraise anomaly detection literature, identify common sources of anomalous results in the clinical laboratory, and offer potential solutions for common shortcomings in current laboratory practices.

SUMMARY

Laboratories should implement data-driven approaches to detect technical anomalies and keep them from entering the medical record, while also using the full array of clinical metadata available in the laboratory information system for context-dependent, patient-centered result interpretations.

POCT errors can lead to false potassium results

Point-of-care-testing (POCT) facilitates rapid availability of results that allows prompt clinical decision making. These results must be reliable and the whole process must not compromise its quality. Blood gas analyzers are one of the most used methods for POCT tests in Emergency Departments (ED) and in critical patients. Whole blood is the preferred sample, and we must be aware that hemolysis can occur. These devices cannot detect the presence of hemolysis in the sample, and because of the characteristics of the sample, we cannot visually detect it either. Hemolysis can alter the result of different parameters, including potassium with abnormal high results or masking low levels (hypokalemia) when reporting normal concentrations. Severe hyperkalemia is associated with the risk of potentially fatal cardiac arrhythmia and demands emergency clinical intervention. Hemolysis can be considered the most frequent cause of pseudohyperkalemia (spurious hyperkalemia) or pseudonormokalemia and can be accompanied by a wrong diagnosis and an ensuing inappropriate clinical decision making. A complete review of the potential causes of falsely elevated potassium concentrations in blood is presented in this article. POCT programs properly led and organized by the clinical laboratory can help to prevent errors and their impact on patient care.

Diagnostic Modalities in Critical Care: Point-of-Care Approach

The concept of intensive care units (ICU) has existed for almost 70 years, with outstanding development progress in the last decades. Multidisciplinary care of critically ill patients has become an integral part of every modern health care system, ensuing improved care and reduced mortality. Early recognition of severe medical and surgical illnesses, advanced prehospital care and organized immediate care in trauma centres led to a rise of ICU patients. Due to the underlying disease and its need for complex mechanical support for monitoring and treatment, it is often necessary to facilitate bed-side diagnostics. Immediate diagnostics are essential for a successful treatment of life threatening conditions, early recognition of complications and good quality of care. Management of ICU patients is incomprehensible without continuous and sophisticated monitoring, bedside ultrasonography, diverse radiologic diagnostics, blood gas analysis, coagulation and blood management, laboratory and other point-of-care (POC) diagnostic modalities. Moreover, in the time of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, particular attention is given to the POC diagnostic techniques due to additional concerns related to the risk of infection transmission, patient and healthcare workers safety and potential adverse events due to patient relocation. This review summarizes the most actual information on possible diagnostic modalities in critical care, with a special focus on the importance of point-of-care approach in the laboratory monitoring and imaging procedures.

Applications of machine learning in the chemical pathology laboratory

Machine learning (ML) is an area of artificial intelligence that provides computer programmes with the capacity to autodidact and learn new skills from experience, without continued human programming. ML algorithms can analyse large data sets quickly and accurately, by supervised and unsupervised learning techniques, to provide classification and prediction value outputs. The application of ML to chemical pathology can potentially enhance efficiency at all phases of the laboratory's total testing process. Our review will broadly discuss the theoretical foundation of ML in laboratory medicine. Furthermore, we will explore the current applications of ML to diverse chemical pathology laboratory processes, for example, clinical decision support, error detection in the preanalytical phase, and ML applications in gel-based image analysis and biomarker discovery. ML currently demonstrates exploratory applications in chemical pathology with promising advancements, which have the potential to improve all phases of the chemical pathology total testing pathway.