Recent evolutions of machine learning applications in clinical laboratory medicine

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.

Applications of Artificial Intelligence in Urinalysis: Is the Future Already Here?

BACKGROUND

Artificial intelligence (AI) has emerged as a promising and transformative tool in the field of urinalysis, offering substantial potential for advancements in disease diagnosis and the development of predictive models for monitoring medical treatment responses.

CONTENT

Through an extensive examination of relevant literature, this narrative review illustrates the significance and applicability of AI models across the diverse application area of urinalysis. It encompasses automated urine test strip and sediment analysis, urinary tract infection screening, and the interpretation of complex biochemical signatures in urine, including the utilization of cutting-edge techniques such as mass spectrometry and molecular-based profiles.

SUMMARY

Retrospective studies consistently demonstrate good performance of AI models in urinalysis, showcasing their potential to revolutionize clinical practice. However, to comprehensively evaluate the real clinical value and efficacy of AI models, large-scale prospective studies are essential. Such studies hold the potential to enhance diagnostic accuracy, improve patient outcomes, and optimize medical treatment strategies. By bridging the gap between research and clinical implementation, AI can reshape the landscape of urinalysis, paving the way for more personalized and effective patient care.

Key considerations, target product profiles, and research gaps in the application of infrared spectroscopy and artificial intelligence for malaria surveillance and diagnosis

Studies on the applications of infrared (IR) spectroscopy and machine learning (ML) in public health have increased greatly in recent years. These technologies show enormous potential for measuring key parameters of malaria, a disease that still causes about 250 million cases and 620,000 deaths, annually. Multiple studies have demonstrated that the combination of IR spectroscopy and machine learning (ML) can yield accurate predictions of epidemiologically relevant parameters of malaria in both laboratory and field surveys. Proven applications now include determining the age, species, and blood-feeding histories of mosquito vectors as well as detecting malaria parasite infections in both humans and mosquitoes. As the World Health Organization encourages malaria-endemic countries to improve their surveillance-response strategies, it is crucial to consider whether IR and ML techniques are likely to meet the relevant feasibility and cost-effectiveness requirements-and how best they can be deployed. This paper reviews current applications of IR spectroscopy and ML approaches for investigating malaria indicators in both field surveys and laboratory settings, and identifies key research gaps relevant to these applications. Additionally, the article suggests initial target product profiles (TPPs) that should be considered when developing or testing these technologies for use in low-income settings.

Developing machine learning systems worthy of trust for infection science: a requirement for future implementation into clinical practice

Infection science is a discipline of healthcare which includes clinical microbiology, public health microbiology, mechanisms of microbial disease, and antimicrobial countermeasures. The importance of infection science has become more apparent in recent years during the SARS-CoV-2 (COVID-19) pandemic and subsequent highlighting of critical operational domains within infection science including the hospital, clinical laboratory, and public health environments to prevent, manage, and treat infectious diseases. However, as the global community transitions beyond the pandemic, the importance of infection science remains, with emerging infectious diseases, bloodstream infections, sepsis, and antimicrobial resistance becoming increasingly significant contributions to the burden of global disease. Machine learning (ML) is frequently applied in healthcare and medical domains, with growing interest in the application of ML techniques to problems in infection science. This has the potential to address several key aspects including improving patient outcomes, optimising workflows in the clinical laboratory, and supporting the management of public health. However, despite promising results, the implementation of ML into clinical practice and workflows is limited. Enabling the migration of ML models from the research to real world environment requires the development of trustworthy ML systems that support the requirements of users, stakeholders, and regulatory agencies. This paper will provide readers with a brief introduction to infection science, outline the principles of trustworthy ML systems, provide examples of the application of these principles in infection science, and propose future directions for moving towards the development of trustworthy ML systems in infection science.

Automated Urine Cell Image Classification Model Using Chaotic Mixer Deep Feature Extraction

Microscopic examination of urinary sediments is a common laboratory procedure. Automated image-based classification of urinary sediments can reduce analysis time and costs. Inspired by cryptographic mixing protocols and computer vision, we developed an image classification model that combines a novel Arnold Cat Map (ACM)- and fixed-size patch-based mixer algorithm with transfer learning for deep feature extraction. Our study dataset comprised 6,687 urinary sediment images belonging to seven classes: Cast, Crystal, Epithelia, Epithelial nuclei, Erythrocyte, Leukocyte, and Mycete. The developed model consists of four layers: (1) an ACM-based mixer to generate mixed images from resized 224 × 224 input images using fixed-size 16 × 16 patches; (2) DenseNet201 pre-trained on ImageNet1K to extract 1,920 features from each raw input image, and its six corresponding mixed images were concatenated to form a final feature vector of length 13,440; (3) iterative neighborhood component analysis to select the most discriminative feature vector of optimal length 342, determined using a k-nearest neighbor (kNN)-based loss function calculator; and (4) shallow kNN-based classification with ten-fold cross-validation. Our model achieved 98.52% overall accuracy for seven-class classification, outperforming published models for urinary cell and sediment analysis. We demonstrated the feasibility and accuracy of deep feature engineering using an ACM-based mixer algorithm for image preprocessing combined with pre-trained DenseNet201 for feature extraction. The classification model was both demonstrably accurate and computationally lightweight, making it ready for implementation in real-world image-based urine sediment analysis applications.

State of affairs and future challenges in laboratory medicine in Spain: an analysis of the Spanish Society of Laboratory Medicine (SEQCML)

Objectives

Laboratory Medicine is a crucial discipline that contributes to the diagnosis, management and monitoring of patients. This branch of medicine faces two major challenges: New technologies and increased demand. There is limited information available of the state of affairs in Laboratory Medicine in Spain. This study provides a picture of clinical laboratories and clinical laboratory professionals.

Methods

The Spanish Society of Laboratory Medicine distributed a questionnaire among the 250 most representative centers (the ones with the largest volume of determinations and training programs), of which 174 (69.6%) returned the questionnaire providing data for 2019.

Results

Laboratories were classified according to the number of determinations. In total, 37% identified themselves as small (<1 million determinations per year); 40% considered themselves medium-sized (1-5 million determinations per year) and 23% considered they were large laboratories (>5 million determinations). The level of specialization of laboratory physicians and laboratory performance were higher in large laboratories. Most requests (87%) and determinations (93%) corresponded to biochemistry and hematology. As many as 63% of physicians had an indefinite contract, and 23% were older than 60 years.

Conclusions

Laboratory medicine is a consolidated discipline that is gaining relevance in Spain. It adds value to the diagnosis, prognosis and follow-up of diseases, and to treatment response monitoring. The results of this study will help us address challenges such as the need for specialized training for laboratory professionals; the emergence of technological innovations; exploitation of Big Data; optimization of quality management systems and patient safety.

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.

Artificial intelligence in the immunodiagnostics of chronic periodontitis

Artificial intelligence is used to diagnose various diseases of the oral cavity. In the field of clinical laboratory diagnostics, machine learning algorithms are used in the interpretation of complex biochemical data. The purpose of this study was to search for significant infectious-immunological clinical and laboratory data based on a machine learning algorithm for chronic periodontitis. To do this, 124 patients aged 40 to 70 years diagnosed with chronic periodontitis were examined by real-time PCR to detect the periodontal pocket DNA of human herpes viruses and bacterial periodontopathogenic microflora Fusobacterium nucleatum, Treponema denticola, Porphyromonas endodontalis etc., and Porphyromonas gingivalis. Matrix RNAs of proinflammatory cytokines and other markers of chronic inflammatory process were also studied: IL-1, IL-10, IL-18, TNFa, TLR4, GATA3, CD68. TNFa, IFNg, IL-1, IL-4, IL-6, IL-10, IL-18; VEGF were determined in a dentoalveolar fluid. Immune cells of the oral cavity were evaluated by analyzing level of CD3+, CD4+, CD8+, CD3+HLA-DR+, CD64+16+14, CD4+25+127+low, CD3+CD16+CD56+, CD3CD16+CD56+, CD14+, CD14+HLA-DR+, CD19+HLA-DR+, CD19+CD5+B27, CD19+CD5B27, CD19+CD5B27+ cells. Random forest machine learning was used to evaluate the data. A relationship between pathogenic microflora and modality of immune response was revealed. The proinflammatory component reflected in the expression of IL-1, TNFa, and IFNg mRNA, prevailed in the immune response against aggressive periodontal pathogens: T. denticola, F. nucleatum, etc. The random forest machine learning algorithm selected correlation ratios r 0.5 (both positive and negative) from a set of data for further analysis by the operator. The random forest machine learning model showed the following significant combinations of data by 10% with a teacher: VEGF, CD3+, CD14+HLA-DR, CD19+CD5CD27+, as well as TLR4, IL-1b, IL-10, TNFa, and IL-18 mRNA. The development of the applied random forest machine learning model with a teacher has already shown a 25% difference: P. endodontalis, GATA3, CD3+, CD14+, CD19+CD5CD27+, as well as TLR4, TNFa, IL-1b, IL-10, and IL-18 mRNA. The search for significant infectious-immunological clinical and laboratory data based on a machine learning algorithm for chronic periodontitis has shown the importance of proinflammatory cytokines, monocytes, T-lymphocytes and memory B-cells in the development of osteodestructive inflammatory process of mRNA to reveal non-evident causality factors.

Evaluation of a machine learning tool to screen for hypoadrenocorticism in dogs presenting to a teaching hospital

BACKGROUND

Dogs with hypoadrenocorticism (HA) have clinical signs and clinicopathologic abnormalities that can be mistaken as other diseases. In dogs with a differential diagnosis of HA, a machine learning model (MLM) has been validated to discriminate between HA and other diseases. This MLM has not been evaluated as a screening tool for a broader group of dogs.

HYPOTHESIS

An MLM can accurately screen dogs for HA.

ANIMALS

Dogs (n = 1025) examined at a veterinary hospital.

METHODS

Dogs that presented to a tertiary referral hospital that had a CBC and serum chemistry panel were enrolled. A trained MLM was applied to clinicopathologic data and in dogs that were MLM positive for HA, diagnosis was confirmed by measurement of serum cortisol.

RESULTS

Twelve dogs were MLM positive for HA and had further cortisol testing. Five had HA confirmed (true positive), 4 of which were treated for mineralocorticoid and glucocorticoid deficiency, and 1 was treated for glucocorticoid deficiency alone. Three MLM positive dogs had baseline cortisol ≤2 μg/dL but were euthanized or administered glucocorticoid treatment without confirming the diagnosis with an ACTH-stimulation test (classified as "undetermined"), and in 4, HA was ruled out (false positives). The positive likelihood ratio of the MLM was 145 to 254. All dogs diagnosed with HA by attending clinicians tested positive by the MLM.

CONCLUSIONS AND CLINICAL IMPORTANCE

This MLM can robustly predict HA status when indiscriminately screening all dogs with blood work. In this group of dogs with a low prevalence of HA, the false positive rates were clinically acceptable.

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 Novel Ensemble-Based Technique for the Preemptive Diagnosis of Rheumatoid Arthritis Disease in the Eastern Province of Saudi Arabia Using Clinical Data

Rheumatoid arthritis (RA) is a chronic inflammatory disease caused by numerous genetic and environmental factors leading to musculoskeletal system pain. RA may damage other tissues and organs, causing complications that severely reduce patients' quality of life. According to the World Health Organization (WHO), over 1.71 billion individuals worldwide had musculoskeletal problems in 2021. Rheumatologists face challenges in the early detection of RA since its symptoms are similar to other illnesses, and there is no definitive test to diagnose the disease. Accordingly, it is preferable to profit from the power of computational intelligence techniques that can identify hidden patterns to diagnose RA early. Although multiple studies were conducted to diagnose RA early, they showed unsatisfactory performance, with the highest accuracy of 87.5% using imaging data. Yet, imaging data requires diagnostic tools that are challenging to collect and examine and are more costly. Recent studies indicated that neither a blood test nor a physical finding could early confirm the diagnosis. Therefore, this study proposes a novel ensemble technique for the preemptive prediction of RA and investigates the possibility of diagnosing the disease using clinical data before the symptoms appear. Two datasets were obtained from King Fahad University Hospital (KFUH), Dammam, Saudi Arabia, including 446 patients, with 251 positive cases of RA and 195 negative cases of RA. Two experiments were conducted where the former was developed without upsampling the dataset, and the latter was carried out using an upsampled dataset. Multiple machine learning (ML) algorithms were utilized to assemble the novel voting ensemble, including support vector machine (SVM), logistic regression (LR), and adaptive boosting (Adaboost). The results indicated that clinical laboratory tests fed to the proposed voting ensemble technique could accurately diagnose RA preemptively with an accuracy, recall, and precision of 94.03%, 96.00%, and 93.51%, respectively, with 30 clinical features when utilizing the original data and sequential forward feature selection (SFFS) technique. It is concluded that deploying the proposed model in local hospitals can contribute to introducing a method that aids medical specialists in preemptively diagnosing RA and stopping or delaying the course using clinical laboratory tests.

Erroneous data: The Achilles' heel of AI and personalized medicine

This paper reviews dilemmas and implications of erroneous data for clinical implementation of AI. It is well-known that if erroneous and biased data are used to train AI, there is a risk of systematic error. However, even perfectly trained AI applications can produce faulty outputs if fed with erroneous inputs. To counter such problems, we suggest 3 steps: (1) AI should focus on data of the highest quality, in essence paraclinical data and digital images, (2) patients should be granted simple access to the input data that feed the AI, and granted a right to request changes to erroneous data, and (3) automated high-throughput methods for error-correction should be implemented in domains with faulty data when possible. Also, we conclude that erroneous data is a reality even for highly reputable Danish data sources, and thus, legal framework for the correction of errors is universally needed.

Artificial intelligence and thyroid disease management

Artificial intelligence (AI) is transforming healthcare and offers new tools in clinical research, personalized medicine, and medical diagnostics. Thyroid function tests represent an important asset for physicians in the diagnosis and monitoring of pathologies. Artificial intelligence tools can clearly assist physicians and specialists in laboratory medicine to optimize test prescription, tests interpretation, decision making, process optimization, and assay design. Our article is reviewing several of these aspects. As thyroid AI models rely on large data sets, which often requires distributed learning from multi-center contributions, this article also briefly discusses this issue.

Interferences in immunoassays: review and practical algorithm

Immunoassays are currently the methods of choice for the measurement of a large panel of complex and heterogenous molecules owing to full automation, short turnaround time, high specificity and sensitivity. Despite remarkable performances, immunoassays are prone to several types of interferences that may lead to harmful consequences for the patient (e.g., prescription of an inadequate treatment, delayed diagnosis, unnecessary invasive investigations). A systematic search is only performed for some interferences because of its impracticality in clinical laboratories as it would notably impact budget, turnaround time, and human resources. Therefore, a case-by-case approach is generally preferred when facing an aberrant result. Hereby, we review the current knowledge on immunoassay interferences and present an algorithm for interference workup in clinical laboratories, from suspecting their presence to using the appropriate tests to identify them. We propose an approach to rationalize the attitude of laboratory specialists when faced with a potential interference and emphasize the importance of their collaboration with clinicians and manufacturers to ensure future improvements.

Predicting Blood Parasite Load and Influence of Expression of iNOS on the Effect Size of Clinical Laboratory Parameters in Acute Trypanosoma cruzi Infection With Different Inoculum Concentrations in C57BL/6 Mice

In Chagas disease, the initial responses of phagocyte-mediated innate immunity are strongly associated with the control of Trypanosoma cruzi and are mediated by various signaling pathways, including the inducible nitric oxide synthetase (iNOS) pathway. The clinical and laboratory manifestations of Chagas disease depend on the parasite–host relationship, i.e., the responsive capacity of the host immune system and the immunogenicity of the parasite. Here, we evaluated effect sizes in clinical and laboratory parameters mediated by acute infection with different concentrations of T. cruzi inoculum in mice immunosuppressed via iNOS pathway inactivation. Infection was induced in C57BL/6 wild-type and iNOS^-/- mice with the “Y” strain of T. cruzi at three inoculum concentrations (3 × 10², 3 × 10³, and 3 × 10⁴). Parasitemia and mortality in both mouse strains were monitored. Immunohistochemistry was performed to quantify amastigotes in cardiac tissues and cardiac musculature cells. Biochemical parameters, such as blood urea nitrogen, sodium, albumin, and globulin concentrations, among others, were measured, and cytokine concentrations were also measured. Effect sizes were determined by the eta squared formula. Compared with that in wild-type animals, mice with an absence of iNOS expression demonstrated a greater parasite load, with earlier infection and a delayed parasitemia peak. Inoculum concentration was positively related to death in the immunosuppressed subgroup. Nineteen parameters (hematological, biochemical, cytokine-related, and histopathological) in the immunocompetent subgroup and four in the immunosuppressed subgroup were associated with parasitemia. Parasitemia, biochemical parameters, and hematological parameters were found to be predictors in the knockout group. The impact of effect sizes on the markers evaluated based on T. cruzi inoculum concentration was notably high in the immunocompetent group (Cohen’s d = 88.50%; p <.001). These findings contribute to the understanding of physiopathogenic mechanisms underlying T. cruzi infection and also indicate the influence of the concentration of T. cruzi during infection and the immunosuppression through the iNOS pathway in clinical laboratory heterogeneity reported in acute Chagas disease.

Artificial Intelligence and Mapping a New Direction in Laboratory Medicine: A Review

BACKGROUND

Modern artificial intelligence (AI) and machine learning (ML) methods are now capable of completing tasks with performance characteristics that are comparable to those of expert human operators. As a result, many areas throughout healthcare are incorporating these technologies, including in vitro diagnostics and, more broadly, laboratory medicine. However, there are limited literature reviews of the landscape, likely future, and challenges of the application of AI/ML in laboratory medicine.

CONTENT

In this review, we begin with a brief introduction to AI and its subfield of ML. The ensuing sections describe ML systems that are currently in clinical laboratory practice or are being proposed for such use in recent literature, ML systems that use laboratory data outside the clinical laboratory, challenges to the adoption of ML, and future opportunities for ML in laboratory medicine.

SUMMARY

AI and ML have and will continue to influence the practice and scope of laboratory medicine dramatically. This has been made possible by advancements in modern computing and the widespread digitization of health information. These technologies are being rapidly developed and described, but in comparison, their implementation thus far has been modest. To spur the implementation of reliable and sophisticated ML-based technologies, we need to establish best practices further and improve our information system and communication infrastructure. The participation of the clinical laboratory community is essential to ensure that laboratory data are sufficiently available and incorporated conscientiously into robust, safe, and clinically effective ML-supported clinical diagnostics.

So Many Diagnostic Tests, So Little Time: Review and Preview of Candida auris Testing in Clinical and Public Health Laboratories

The recognition of a new yeast, Candida auris, in 2009 in East Asia, and its rapid global spread, was a reminder of the threats posed by multidrug-resistant fungal pathogens. C. auris had likely remained unrecognized for a long time as accurate tests were not available. The laboratory community responded to the C. auris challenge by publishing 35 new or revised diagnostic methods between 2014 and early 2021. The commercial sector also modified existing diagnostic devices. These C. auris diagnostic tests run the gamut from traditional culture-based differential and selective media, biochemical assimilations, and rapid protein profiles, as well as culture-independent DNA-based diagnostics. We provide an overview of these developments, especially the tests with validation data that were subsequently adopted for common use. We share a workflow developed in our laboratory to process over 37,000 C. auris surveillance samples and 5,000 C. auris isolates from the outbreak in the New York metropolitan area. Our preview covers new devices and diagnostic approaches on the horizon based on microfluidics, optics, and nanotechnology. Frontline laboratories need rapid, cheap, stable, and easy-to-implement tests to improve C. auris diagnosis, surveillance, patient isolation, admission screening, and environmental control. Among the urgent needs is a lateral flow assay or similar device for presumptive C. auris identification. All laboratories will benefit from devices that allow rapid antifungal susceptibility testing, including detection of mutations conferring drug resistance. Hopefully, multiplex test panels are on the horizon for synergy of C. auris testing with ongoing surveillance of other healthcare-associated infections. C. auris genome analysis has a proven role for outbreak investigations, and diagnostic laboratories need quick access to regional and national genome analysis networks.