Automated prediction of low ferritin concentrations using a machine learning algorithm

Inconsistency in ferritin reference intervals across laboratories: a major concern for clinical decision making

OBJECTIVES

Iron deficiency anemia is a significant global health concern, diagnosed by measuring hemoglobin concentrations in combination with plasma ferritin concentration. This study investigated the variability in ferritin reference intervals among laboratories in the Netherlands and examined how this affects the identification of iron-related disorders.

METHODS

Ferritin reference intervals from 52 Dutch ISO15189-certified medical laboratories were collected. Ferritin, hemoglobin and mean corpuscular volume data of non-anemic apparently healthy primary care patients, measured by four laboratory platforms (Beckman, Abbott, Siemens, and Roche), were collected (n=397,548). Median ferritin levels were determined per platform, stratified by sex and age. The proportion of ferritin measurements outside of the reference interval was calculated using the reference intervals from the 52 laboratories (using a total of n=1,093,442 ferritin measurements). Lastly, ferritin data from 3,699 patients as captured in general practitioner (GP) data from the PHARMO Data Network were used to assess the variation of abnormal ferritin measurements per GP.

RESULTS

Median plasma ferritin concentrations were approximately four times higher in men and twice as high in postmenopausal women compared to premenopausal women. Moreover, there are substantial differences in the median plasma ferritin concentration between the four platforms. However, even among laboratories using the same platform, ferritin reference intervals differ widely. This leads to significant differences in the percentages of measurements classified as abnormal, with the percentage of ferritin measurements below the reference limit in premenopausal women ranging from 11 to 53 %, in postmenopausal women from 3 to 37 %, and in men from 2 to 19 %. The percentage of ferritin measurements above the reference limit in premenopausal women ranged from 0.2 to 11 %, in postmenopausal women from 3 to 36 % and in men from 7 to 32 %.

CONCLUSIONS

The lack of harmonization in ferritin measurement and the disagreement in plasma ferritin reference intervals significantly impact the interpretation of the iron status of patients and thereby the number of iron disorder diagnoses made. Standardization or harmonization of the ferritin assays and establishing uniform reference intervals and medical decision limits are essential to reduce the substantial variability in clinical interpretations of ferritin results.

Machine Learning for Patient-Based Real-Time Quality Control (PBRTQC), Analytical and Preanalytical Error Detection in Clinical Laboratory

The rapidly evolving field of machine learning (ML), along with artificial intelligence in a broad sense, is revolutionising many areas of healthcare, including laboratory medicine. The amalgamation of the fields of ML and patient-based real-time quality control (PBRTQC) processes could improve the traditional PBRTQC and error detection algorithms in the laboratory. This narrative review discusses published studies on using ML for the detection of systematic errors, non-systematic errors, and combinations of different types of errors in clinical laboratories. The studies discussed used ML for detecting bias, the requirement for re-calibration, samples contaminated with intravenous fluid or EDTA, delayed sample analysis, wrong-blood-in-tube errors, interference or a combination of different types of errors, by comparing the performance of ML models with human validators or traditional PBRTQC algorithms. Advantages, limitations, the creation of standardised ML models, ethical and regulatory aspects and potential future developments have also been discussed in brief.

Artificial intelligence in the clinical laboratory

Laboratory medicine has become a highly automated medical discipline. Nowadays, artificial intelligence (AI) applied to laboratory medicine is also gaining more and more attention, which can optimize the entire laboratory workflow and even revolutionize laboratory medicine in the future. However, only a few commercially available AI models are currently approved for use in clinical laboratories and have drawbacks such as high cost, lack of accuracy, and the need for manual review of model results. Furthermore, there are a limited number of literature reviews that comprehensively address the research status, challenges, and future opportunities of AI applications in laboratory medicine. Our article begins with a brief introduction to AI and some of its subsets, then reviews some AI models that are currently being used in clinical laboratories or that have been described in emerging studies, and explains the existing challenges associated with their application and possible solutions, finally provides insights into the future opportunities of the field. We highlight the current status of implementation and potential applications of AI models in different stages of the clinical testing process.

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.

Using artificial intelligence to improve body iron quantification: A scoping review

This scoping review explores the potential of artificial intelligence (AI) in enhancing the screening, diagnosis, and monitoring of disorders related to body iron levels. A systematic search was performed to identify studies that utilize machine learning in iron-related disorders. The search revealed a wide range of machine learning algorithms used by different studies. Notably, most studies used a single data type. The studies varied in terms of sample sizes, participant ages, and geographical locations. AI's role in quantifying iron concentration is still in its early stages, yet its potential is significant. The question is whether AI-based diagnostic biomarkers can offer innovative approaches for screening, diagnosing, and monitoring of iron overload and anemia.

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.

Clinlabomics: leveraging clinical laboratory data by data mining strategies

The recent global focus on big data in medicine has been associated with the rise of artificial intelligence (AI) in diagnosis and decision-making following recent advances in computer technology. Up to now, AI has been applied to various aspects of medicine, including disease diagnosis, surveillance, treatment, predicting future risk, targeted interventions and understanding of the disease. There have been plenty of successful examples in medicine of using big data, such as radiology and pathology, ophthalmology cardiology and surgery. Combining medicine and AI has become a powerful tool to change health care, and even to change the nature of disease screening in clinical diagnosis. As all we know, clinical laboratories produce large amounts of testing data every day and the clinical laboratory data combined with AI may establish a new diagnosis and treatment has attracted wide attention. At present, a new concept of radiomics has been created for imaging data combined with AI, but a new definition of clinical laboratory data combined with AI has lacked so that many studies in this field cannot be accurately classified. Therefore, we propose a new concept of clinical laboratory omics (Clinlabomics) by combining clinical laboratory medicine and AI. Clinlabomics can use high-throughput methods to extract large amounts of feature data from blood, body fluids, secretions, excreta, and cast clinical laboratory test data. Then using the data statistics, machine learning, and other methods to read more undiscovered information. In this review, we have summarized the application of clinical laboratory data combined with AI in medical fields. Undeniable, the application of Clinlabomics is a method that can assist many fields of medicine but still requires further validation in a multi-center environment and laboratory.

A comparison of single- and double-threshold ROC plots for mixture distributions

The receiver operating characteristics (ROC) analysis is commonly used in clinical settings to check the performance of a single threshold for distinguishing population-wise bimodal-distributed test results. However, for population-wise three-modal distributed test results, a single threshold ROC (stROC) analysis showed poor discriminative performance. The purpose of this study is to use a double-threshold ROC analysis for the three-modal distributed test results to provide better discriminative performance than the stROC analysis. A double-threshold receiver operating characteristic plot (dtROC) is constructed by replacing the single threshold with a double threshold. The sensitivity and specificity coordinates are chosen to maximize sensitivity for a given specificity value. Besides a simulation study assuming a mixture of lognormal, Poisson, and Weibull distributions, a clinical application is examined by a secondary data analysis of palpation test results of the C7 spinous process using the modified thorax-rib static technique. For the assumed mixture models, the discrimination performance of dtROC analysis outperforms the stROC analysis (area under ROC (AUROC) increased from 0.436 to 0.983 for lognormal distributed test results, 0.676 to 0.752 for the Poisson distribution, and 0.674 to 0.804 for Weibull distribution).