Detection of COVID-19 by Machine Learning Using Routine Laboratory Tests

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.

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.

Concordance and generalization of an AI algorithm with real-world clinical data in the pre-omicron and omicron era

All viruses, including SARS-CoV-2, the virus responsible for COVID-19, continue to evolve, which can lead to new variants. The objective of this study is to assess the agreement between real-world clinical data and an algorithm that utilizes laboratory markers and age to predict the progression of disease severity in COVID-19 patients during the pre-Omicron and Omicron variant periods. The study evaluated the performance of a deep learning (DL) algorithm in predicting disease severity scores for COVID-19 patients using data from the USA, Spain, and Turkey (Ankara City Hospital (ACH) data set). The algorithm was developed and validated using pre-Omicron era data and was tested on both pre-Omicron and Omicron-era data. The predictions were compared to the actual clinical outcomes using a multidisciplinary approach. The concordance index values for all datasets ranged from 0.71 to 0.81. In the ACH cohort, a negative predictive value (NPV) of 0.78 or higher was observed for severe patients in both the pre-Omicron and Omicron eras, which is consistent with the algorithm's performance in the development cohort.

Clinical decision support systems (CDSS) in assistance to COVID-19 diagnosis: A scoping review on types and evaluation methods

Background and Aims

Due to the COVID-19 pandemic, a precise and reliable diagnosis of this disease is critical. The use of clinical decision support systems (CDSS) can help facilitate the diagnosis of COVID-19. This scoping review aimed to investigate the role of CDSS in diagnosing COVID-19.

Methods

We searched four databases (Web of Science, PubMed, Scopus, and Embase) using three groups of keywords related to CDSS, COVID-19, and diagnosis. To collect data from studies, we utilized a data extraction form that consisted of eight fields. Three researchers selected relevant articles and extracted data using a data collection form. To resolve any disagreements, we consulted with a fourth researcher.

Results

A search of the databases retrieved 2199 articles, of which 68 were included in this review after removing duplicates and irrelevant articles. The studies used nonknowledge-based CDSS (n = 52) and knowledge-based CDSS (n = 16). Convolutional Neural Networks (CNN) (n = 33) and Support Vector Machine (SVM) (n = 8) were employed to design the CDSS in most of the studies. Accuracy (n = 43) and sensitivity (n = 35) were the most common metrics for evaluating CDSS.

Conclusion

CDSS for COVID-19 diagnosis have been developed mainly through machine learning (ML) methods. The greater use of these techniques can be due to their availability of public data sets about chest imaging. Although these studies indicate high accuracy for CDSS based on ML, their novelty and data set biases raise questions about replacing these systems as clinician assistants in decision-making. Further studies are needed to improve and compare the robustness and reliability of nonknowledge-based and knowledge-based CDSS in COVID-19 diagnosis.

TubIAgnosis: A machine learning-based web application for active tuberculosis diagnosis using complete blood count data

Objective

Tuberculosis remains a major global health challenge, with delayed diagnosis contributing to increased transmission and disease burden. While microbiological tests are the gold standard for confirming active tuberculosis, many cases lack microbiological evidence, necessitating additional clinical and laboratory data for diagnosis. The complete blood count (CBC), an inexpensive and widely available test, could provide a valuable tool for tuberculosis diagnosis by analyzing disturbances in blood parameters. This study aimed to develop and evaluate a machine learning (ML)-based web application, TubIAgnosis, for diagnosing active tuberculosis using CBC data.

Methods

We conducted a retrospective case-control study using data from 449 tuberculosis patients and 1200 healthy controls in Oran, Algeria, from January 2016 to April 2023. Eight ML algorithms were trained on 18 CBC parameters and demographic data. Model performance was evaluated using balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC).

Results

The best-performing model, Extreme Gradient Boosting (XGB), achieved a balanced accuracy of 83.3%, AUC of 89.4%, sensitivity of 83.3%, and specificity of 83.3% on the testing dataset. Platelet-to-lymphocyte ratio was the most influential parameter in this ML predictive model. The best performing model (XGB) was made available online as a web application called TubIAgnosis, which is available free of charge at https://yh5f0z-ghermi-mohamed.shinyapps.io/TubIAgnosis/.

Conclusions

TubIAgnosis, a ML-based web application utilizing CBC data, demonstrated promising performance for diagnosing active tuberculosis. This accessible and cost-effective tool could complement existing diagnostic methods, particularly in resource-limited settings. Prospective studies are warranted to further validate and refine this approach.

Rapid Triage of Children with Suspected COVID-19 Using Laboratory-Based Machine-Learning Algorithms

In order to limit the spread of the novel betacoronavirus (SARS-CoV-2), it is necessary to detect positive cases as soon as possible and isolate them. For this purpose, machine-learning algorithms, as a field of artificial intelligence, have been recognized as a promising tool. The aim of this study was to assess the utility of the most common machine-learning algorithms in the rapid triage of children with suspected COVID-19 using easily accessible and inexpensive laboratory parameters. A cross-sectional study was conducted on 566 children treated for respiratory diseases: 280 children with PCR-confirmed SARS-CoV-2 infection and 286 children with respiratory symptoms who were SARS-CoV-2 PCR-negative (control group). Six machine-learning algorithms, based on the blood laboratory data, were tested: random forest, support vector machine, linear discriminant analysis, artificial neural network, k-nearest neighbors, and decision tree. The training set was validated through stratified cross-validation, while the performance of each algorithm was confirmed by an independent test set. Random forest and support vector machine models demonstrated the highest accuracy of 85% and 82.1%, respectively. The models demonstrated better sensitivity than specificity and better negative predictive value than positive predictive value. The F1 score was higher for the random forest than for the support vector machine model, 85.2% and 82.3%, respectively. This study might have significant clinical applications, helping healthcare providers identify children with COVID-19 in the early stage, prior to PCR and/or antigen testing. Additionally, machine-learning algorithms could improve overall testing efficiency with no extra costs for the healthcare facility.

Development and validation of explainable machine-learning models for carotid atherosclerosis early screening

BACKGROUND

Carotid atherosclerosis (CAS), an important factor in the development of stroke, is a major public health concern. The aim of this study was to establish and validate machine learning (ML) models for early screening of CAS using routine health check-up indicators in northeast China.

METHODS

A total of 69,601 health check-up records from the health examination center of the First Hospital of China Medical University (Shenyang, China) were collected between 2018 and 2019. For the 2019 records, 80% were assigned to the training set and 20% to the testing set. The 2018 records were used as the external validation dataset. Ten ML algorithms, including decision tree (DT), K-nearest neighbors (KNN), logistic regression (LR), naive Bayes (NB), random forest (RF), multiplayer perceptron (MLP), extreme gradient boosting machine (XGB), gradient boosting decision tree (GBDT), linear support vector machine (SVM-linear), and non-linear support vector machine (SVM-nonlinear), were used to construct CAS screening models. The area under the receiver operating characteristic curve (auROC) and precision-recall curve (auPR) were used as measures of model performance. The SHapley Additive exPlanations (SHAP) method was used to demonstrate the interpretability of the optimal model.

RESULTS

A total of 6315 records of patients undergoing carotid ultrasonography were collected; of these, 1632, 407, and 1141 patients were diagnosed with CAS in the training, internal validation, and external validation datasets, respectively. The GBDT model achieved the highest performance metrics with auROC of 0.860 (95% CI 0.839-0.880) in the internal validation dataset and 0.851 (95% CI 0.837-0.863) in the external validation dataset. Individuals with diabetes or those over 65 years of age showed low negative predictive value. In the interpretability analysis, age was the most important factor influencing the performance of the GBDT model, followed by sex and non-high-density lipoprotein cholesterol.

CONCLUSIONS

The ML models developed could provide good performance for CAS identification using routine health check-up indicators and could hopefully be applied in scenarios without ethnic and geographic heterogeneity for CAS prevention.

Application and utility of boosting machine learning model based on laboratory test in the differential diagnosis of non-COVID-19 pneumonia and COVID-19

BACKGROUND

Non-Coronavirus disease 2019 (COVID-19) pneumonia and COVID-19 have similar clinical features but last for different periods, and consequently, require different treatment protocols. Therefore, they must be differentially diagnosed. This study uses artificial intelligence (AI) to classify the two forms of pneumonia using mainly laboratory test data.

METHODS

Various AI models are applied, including boosting models known for deftly solving classification problems. In addition, important features that affect the classification prediction performance are identified using the feature importance technique and SHapley Additive exPlanations method. Despite the data imbalance, the developed model exhibits robust performance.

RESULTS

eXtreme gradient boosting, category boosting, and light gradient boosted machine yield an area under the receiver operating characteristic of 0.99 or more, accuracy of 0.96-0.97, and F1-score of 0.96-0.97. In addition, D-dimer, eosinophil, glucose, aspartate aminotransferase, and basophil, which are rather nonspecific laboratory test results, are demonstrated to be important features in differentiating the two disease groups.

CONCLUSIONS

The boosting model, which excels in producing classification models using categorical data, excels in developing classification models using linear numerical data, such as laboratory tests. Finally, the proposed model can be applied in various fields to solve classification problems.

Disruption vs. evolution in laboratory medicine. Current challenges and possible strategies, making laboratories and the laboratory specialist profession fit for the future

Since beginning of medical diagnostics, laboratory specialists have done an amazing job, continuously improving quality, spectrum and speed of laboratory tests, currently contributing to the majority of medical decision making. These improvements are mostly of an incremental evolutionary fashion, meaning improvements of current processes. Sometimes these evolutionary innovations are of a radical fashion, such as the invention of automated analyzers replacing manual testing or the implementation of mass spectrometry, leading to one big performance leap instead of several small ones. In few cases innovations may be of disruptive nature. In laboratory medicine this would be applicable to digitalization of medicine or the decoding of the human genetic material. Currently, laboratory medicine is again facing disruptive innovations or technologies, which need to be adapted to as soon as possible. One of the major disruptive technologies is the increasing availability and medical use of artificial intelligence. It is necessary to rethink the position of the laboratory specialist within healthcare settings and the added value he or she can provide to patient care. The future of the laboratory specialist profession is bright, as it the only medical profession comprising such vast experience in patient diagnostics. However, laboratory specialists need to develop strategies to provide this expertise, by adopting to the quickly evolving technologies and demands. This opinion paper summarizes some of the disruptive technologies as well as strategies to secure and/or improve the quality of diagnostic patient care and the laboratory specialist profession.

Outcome prediction in hospitalized COVID-19 patients: Comparison of the performance of five severity scores

Background

The aim of our study was to externally validate the predictive capability of five developed coronavirus disease 2019 (COVID-19)-specific prognostic tools, including the COVID-19 Spanish Society of Infectious Diseases and Clinical Microbiology (SEIMC), Shang COVID severity score, COVID-intubation risk score-neutrophil/lymphocyte ratio (IRS-NLR), inflammation-based score, and ventilation in COVID estimator (VICE) score.

Methods

The medical records of all patients hospitalized for a laboratory-confirmed COVID-19 diagnosis between May 2021 and June 2021 were retrospectively analyzed. Data were extracted within the first 24 h of admission, and five different scores were calculated. The primary and secondary outcomes were 30-day mortality and mechanical ventilation, respectively.

Results

A total of 285 patients were enrolled in our cohort. Sixty-five patients (22.8%) were intubated with ventilator support, and the 30-day mortality rate was 8.8%. The Shang COVID severity score had the highest numerical area under the receiver operator characteristic (AUC-ROC) (AUC 0.836) curve to predict 30-day mortality, followed by the SEIMC score (AUC 0.807) and VICE score (AUC 0.804). For intubation, both the VICE and COVID-IRS-NLR scores had the highest AUC (AUC 0.82) compared to the inflammation-based score (AUC 0.69). The 30-day mortality increased steadily according to higher Shang COVID severity scores and SEIMC scores. The intubation rate exceeded 50% in the patients stratified by higher VICE scores and COVID-IRS-NLR score quintiles.

Conclusion

The discriminative performances of the SEIMC score and Shang COVID severity score are good for predicting the 30-day mortality of hospitalized COVID-19 patients. The COVID-IRS-NLR and VICE showed good performance for predicting invasive mechanical ventilation (IMV).

Lethality risk markers by sex and age-group for COVID-19 in Mexico: a cross-sectional study based on machine learning approach

BACKGROUND

Mexico ranks fifth worldwide in the number of deaths due to COVID-19. Identifying risk markers through easily accessible clinical data could help in the initial triage of COVID-19 patients and anticipate a fatal outcome, especially in the most socioeconomically disadvantaged regions. This study aims to identify markers that increase lethality risk in patients diagnosed with COVID-19, based on machine learning (ML) methods. Markers were differentiated by sex and age-group.

METHODS

A total of 11,564 cases of COVID-19 in Mexico were extracted from the Epidemiological Surveillance System for Viral Respiratory Disease. Four ML classification methods were trained to predict lethality, and an interpretability approach was used to identify those markers.

RESULTS

Models based on Extreme Gradient Boosting (XGBoost) yielded the best performance in a test set. This model achieved a sensitivity of 0.91, a specificity of 0.69, a positive predictive value of 0.344, and a negative predictive value of 0.965. For female patients, the leading markers are diabetes and arthralgia. For males, the main markers are chronic kidney disease (CKD) and chest pain. Dyspnea, hypertension, and polypnea increased the risk of death in both sexes.

CONCLUSIONS

ML-based models using an interpretability approach successfully identified risk markers for lethality by sex and age. Our results indicate that age is the strongest demographic factor for a fatal outcome, while all other markers were consistent with previous clinical trials conducted in a Mexican population. The markers identified here could be used as an initial triage, especially in geographic areas with limited resources.

Computational method for aromatase-related proteins using machine learning approach

Human aromatase enzyme is a microsomal cytochrome P450 and catalyzes aromatization of androgens into estrogens during steroidogenesis. For breast cancer therapy, third-generation aromatase inhibitors (AIs) have proven to be effective; however patients acquire resistance to current AIs. Thus there is a need to predict aromatase-related proteins to develop efficacious AIs. A machine learning method was established to identify aromatase-related proteins using a five-fold cross validation technique. In this study, different SVM approach-based models were built using the following approaches like amino acid, dipeptide composition, hybrid and evolutionary profiles in the form of position-specific scoring matrix (PSSM); with maximum accuracy of 87.42%, 84.05%, 85.12%, and 92.02% respectively. Based on the primary sequence, the developed method is highly accurate to predict the aromatase-related proteins. Prediction scores graphs were developed using the known dataset to check the performance of the method. Based on the approach described above, a webserver for predicting aromatase-related proteins from primary sequence data was developed and implemented at https://bioinfo.imtech.res.in/servers/muthu/aromatase/home.html. We hope that the developed method will be useful for aromatase protein related research.

Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases

Controlling infectious diseases is a major health priority because they can spread and infect humans, thus evolving into epidemics or pandemics. Therefore, early detection of infectious diseases is a significant need, and many researchers have developed models to diagnose them in the early stages. This paper reviewed research articles for recent machine-learning (ML) algorithms applied to infectious disease diagnosis. We searched the Web of Science, ScienceDirect, PubMed, Springer, and IEEE databases from 2015 to 2022, identified the pros and cons of the reviewed ML models, and discussed the possible recommendations to advance the studies in this field. We found that most of the articles used small datasets, and few of them used real-time data. Our results demonstrated that a suitable ML technique depends on the nature of the dataset and the desired goal. Moreover, heterogeneous data could ensure the model's generalization, while big data, many features, and a hybrid model will increase the resulting performance. Furthermore, using other techniques such as deep learning and NLP to extract vast features from unstructured data is a powerful approach to enhancing the performance of ML diagnostic models.