Simple hemogram to support the decision-making of COVID-19 diagnosis using clusters analysis with self-organizing maps neural network

Towards Improved XAI-Based Epidemiological Research into the Next Potential Pandemic

By applying AI techniques to a variety of pandemic-relevant data, artificial intelligence (AI) has substantially supported the control of the spread of the SARS-CoV-2 virus. Along with this, epidemiological machine learning studies of SARS-CoV-2 have been frequently published. While these models can be perceived as precise and policy-relevant to guide governments towards optimal containment policies, their black box nature can hamper building trust and relying confidently on the prescriptions proposed. This paper focuses on interpretable AI-based epidemiological models in the context of the recent SARS-CoV-2 pandemic. We systematically review existing studies, which jointly incorporate AI, SARS-CoV-2 epidemiology, and explainable AI approaches (XAI). First, we propose a conceptual framework by synthesizing the main methodological features of the existing AI pipelines of SARS-CoV-2. Upon the proposed conceptual framework and by analyzing the selected epidemiological studies, we reflect on current research gaps in epidemiological AI toolboxes and how to fill these gaps to generate enhanced policy support in the next potential pandemic.

Oral contraceptives in adolescents: a retrospective population-based study on blood pressure and metabolic dysregulation

PURPOSE

This study aimed to explore the relationship between oral contraceptive use and blood pressure values and in a national cohort of women adolescents and to investigate the level of coexistence of the high blood pressure levels, dyslipidemia or insulin resistance.

METHODS

This is a retrospective cohort study that evaluated data form 14,299 adolescents aged 14 to 17 years. Crude and race-and age-adjusted analyses were performed using Poisson regression to estimate the prevalence ratios. Data clustering analysis was performed using machine learning approaches supported by an unsupervised neural network of self-organizing maps.

RESULTS

We found that 14.5% (n = 2076) of the women adolescents use oral contraceptives. Moreover, an increased prevalence of high blood pressure, dyslipidemia, and insulin resistance (all P < 0.001) was observed among adolescents who use oral contraceptives as compared to those who do not. Our analysis also showed that 2.3% of adolescents using oral contraceptives had both high blood pressure levels and dyslipidemia, whereas 3.2% had high blood pressure levels combined with insulin resistance (all P < 0.001). The algorithmic investigative approach demonstrated that total cholesterol, LDLc, HDLc, insulin, and HOMA-IR were the most predicted variables to assist classificatory association in the context of oral contraceptive use among women adolescents with high blood pressure.

CONCLUSIONS

These findings suggest that oral contraceptives were associated with an increased prevalence of high blood pressure, dyslipidemia, and insulin resistance among women adolescents. Although the indication of this therapy is adequate to avoid unintended pregnancies, their use must be based on rigorous individual evaluation and under constant control of the cardiometabolic risk factors.

COVID-19 diagnosis using clinical markers and multiple explainable artificial intelligence approaches: A case study from Ecuador

The COVID-19 pandemic erupted at the beginning of 2020 and proved fatal, causing many casualties worldwide. Immediate and precise screening of affected patients is critical for disease control. COVID-19 is often confused with various other respiratory disorders since the symptoms are similar. As of today, the reverse transcription-polymerase chain reaction (RT-PCR) test is utilized for diagnosing COVID-19. However, this approach is sometimes prone to producing erroneous and false negative results. Hence, finding a reliable diagnostic method that can validate the RT-PCR test results is crucial. Artificial intelligence (AI) and machine learning (ML) applications in COVID-19 diagnosis has proven to be beneficial. Hence, clinical markers have been utilized for COVID-19 diagnosis with the help of several classifiers in this study. Further, five different explainable artificial intelligence techniques have been utilized to interpret the predictions. Among all the algorithms, the k-nearest neighbor obtained the best performance with an accuracy, precision, recall and f1-score of 84%, 85%, 84% and 84%. According to this study, the combination of clinical markers such as eosinophils, lymphocytes, red blood cells and leukocytes was significant in differentiating COVID-19. The classifiers can be utilized synchronously with the standard RT-PCR procedure making diagnosis more reliable and efficient.

Construction and effectiveness evaluation of a knowledge-based infectious disease monitoring and decision support system

To improve the hospital's ability to proactively detect infectious diseases, a knowledge-based infectious disease monitoring and decision support system was established based on real medical records and knowledge rules. The effectiveness of the system was evaluated using interrupted time series analysis. In the system, a monitoring and alert rule library for infectious diseases was generated by combining infectious disease diagnosis guidelines with literature and a real medical record knowledge map. The system was integrated with the electronic medical record system, and doctors were provided with various types of real-time warning prompts when writing medical records. The effectiveness of the system's alerts was analyzed from the perspectives of false positive rates, rule accuracy, alert effectiveness, and missed case rates using interrupted time series analysis. Over a period of 12 months, the system analyzed 4,497,091 medical records, triggering a total of 12,027 monitoring alerts. Of these, 98.43% were clinically effective, while 1.56% were invalid alerts, mainly owing to the relatively rough rules generated by the guidelines leading to several false alarms. In addition, the effectiveness of the system's alerts, distribution of diagnosis times, and reporting efficiency of doctors were analyzed. 89.26% of infectious disease cases could be confirmed and reported by doctors within 5 min of receiving the alert, and 77.6% of doctors could complete the filling of 33 items of information within 2 min, which is a reduction in time compared to the past. The timely reminders from the system reduced the rate of missed cases by doctors; the analysis using interrupted time series method showed an average reduction of 4.4037% in the missed-case rate. This study proposed a knowledge-based infectious disease decision support system based on real medical records and knowledge rules, and its effectiveness was verified. The system improved the management of infectious diseases, increased the reliability of decision-making, and reduced the rate of underreporting.

How to diagnose COVID-19 in family practice? Usability of complete blood count as a COVID-19 diagnostic tool: a cross-sectional study in Turkey

OBJECTIVE

COVID-19 is currently diagnosed in hospital settings. An easy and practical diagnosis of COVID-19 is needed in primary care. For this purpose, the usability of complete blood count in the diagnosis of COVID-19 was investigated.

DESIGN

Retrospective, cross-sectional study.

SETTING

Single-centre study in a tertiary university hospital in Erzurum, Turkey.

PARTICIPANTS

Between March 2020 and February 2021, patients aged 18-70 years who applied to the hospital and underwent both complete blood count and reverse-transcription-PCR tests for COVID-19 were included and compared. Conditions affecting the test parameters (oncological-haematological conditions, chronic diseases, drug usage) were excluded.

OUTCOME MEASURE

The complete blood count and COVID-19 results of eligible patients identified using diagnostic codes [U07.3 (COVID-19) or Z03.8 (observation for other suspected diseases and conditions)] were investigated.

RESULTS

Of the 978 patients included, 39.4% (n=385) were positive for COVID-19 and 60.6% (n=593) were negative. The mean age was 41.5±14.5 years, and 53.9% (n=527) were male. COVID-19-positive patients were found to have significantly lower leucocyte, neutrophil, lymphocyte, monocyte, basophil, platelet and immature granulocyte (IG) values (p<0.001). Neutrophil/lymphocyte, neutrophil/monocyte and IG/lymphocyte ratios were also found to be significantly decreased (p<0.001). With logistic regression analysis, low lymphocyte count (OR 0.695; 95% CI 0.597 to 0.809) and low red cell distribution width-coefficient of variation (RDW-CV) (OR 0.887; 95% CI 0.818 to 0.962) were significantly associated with COVID-19 positivity. In receiver operating characteristic analysis, the cut-off values of lymphocyte and RDW-CV were 0.745 and 12.35, respectively.

CONCLUSION

Although our study was designed retrospectively and reflects regional data, it is important to determine that low lymphocyte count and RDW-CV can be used in the diagnosis of COVID-19 in primary care.

Use of Artificial Intelligence in the Search for New Information Through Routine Laboratory Tests: Systematic Review

Background

In recent decades, the use of artificial intelligence has been widely explored in health care. Similarly, the amount of data generated in the most varied medical processes has practically doubled every year, requiring new methods of analysis and treatment of these data. Mainly aimed at aiding in the diagnosis and prevention of diseases, this precision medicine has shown great potential in different medical disciplines. Laboratory tests, for example, almost always present their results separately as individual values. However, physicians need to analyze a set of results to propose a supposed diagnosis, which leads us to think that sets of laboratory tests may contain more information than those presented separately for each result. In this way, the processes of medical laboratories can be strongly affected by these techniques.

Objective

In this sense, we sought to identify scientific research that used laboratory tests and machine learning techniques to predict hidden information and diagnose diseases.

Methods

The methodology adopted used the population, intervention, comparison, and outcomes principle, searching the main engineering and health sciences databases. The search terms were defined based on the list of terms used in the Medical Subject Heading database. Data from this study were presented descriptively and followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses; 2020) statement flow diagram and the National Institutes of Health tool for quality assessment of articles. During the analysis, the inclusion and exclusion criteria were independently applied by 2 authors, with a third author being consulted in cases of disagreement.

Results

Following the defined requirements, 40 studies presenting good quality in the analysis process were selected and evaluated. We found that, in recent years, there has been a significant increase in the number of works that have used this methodology, mainly because of COVID-19. In general, the studies used machine learning classification models to predict new information, and the most used parameters were data from routine laboratory tests such as the complete blood count.

Conclusions

Finally, we conclude that laboratory tests, together with machine learning techniques, can predict new tests, thus helping the search for new diagnoses. This process has proved to be advantageous and innovative for medical laboratories. It is making it possible to discover hidden information and propose additional tests, reducing the number of false negatives and helping in the early discovery of unknown diseases.

Supporting Clinical COVID-19 Diagnosis with Routine Blood Tests Using Tree-Based Entropy Structured Self-Organizing Maps

Data classification is an automatic or semi-automatic process that, utilizing artificial intelligence algorithms, learns the variable and class relationships of a dataset for use a posteriori in situations where the class result is unknown. For many years, work on this topic has been aimed at increasing the hit rates of algorithms. However, when the problem is restricted to applications in healthcare, besides the concern with performance, it is also necessary to design algorithms whose results are understandable by the specialists responsible for making the decisions. Among the problems in the field of medicine, a current focus is related to COVID-19: AI algorithms may contribute to early diagnosis. Among the available COVID-19 data, the blood test is a typical procedure performed when the patient seeks the hospital, and its use in the diagnosis allows reducing the need for other diagnostic tests that can impact the detection time and add to costs. In this work, we propose using self-organizing map (SOM) to discover attributes in blood test examinations that are relevant for COVID-19 diagnosis. We applied SOM and an entropy calculation in the definition of a hierarchical, semi-supervised and explainable model named TESSOM (tree-based entropy-structured self-organizing maps), in which the main feature is enhancing the investigation of groups of cases with high levels of class overlap, as far as the diagnostic outcome is concerned. Framing the TESSOM algorithm in the context of explainable artificial intelligence (XAI) makes it possible to explain the results to an expert in a simplified way. It is demonstrated in the paper that the use of the TESSOM algorithm to identify attributes of blood tests can help with the identification of COVID-19 cases. It providing a performance increase in 1.489% in multiple scenarios when analyzing 2207 cases from three hospitals in the state of São Paulo, Brazil. This work is a starting point for researchers to identify relevant attributes of blood tests for COVID-19 and to support the diagnosis of other diseases.

Use of Machine Learning and Routine Laboratory Tests for Diabetes Mellitus Screening

Most patients with diabetes mellitus are asymptomatic, which leads to delayed and more complex treatment. At the same time, most individuals are routinely subjected to standard clinical laboratory examinations, which create large health datasets over a lifetime. Computer processing has been used to search for health anomalies and predict diseases using clinical examinations. This work studied machine learning models to support the screening of diabetes through routine laboratory tests using data from laboratory tests of 62,496 patients. The classification and regression models used were the K-nearest neighbor, support vector machines, Bayes naïve, random forest models, and artificial neural networks. Glycated hemoglobin, a test used for diabetes diagnosis, was used as the target. Regression models calculated glycated hemoglobin directly and were later classified. The performance of classification computer models has been studied under various subdataset partitions and combinations (e.g., healthy, prediabetic, and diabetes, as well as no healthy and no diabetes). The best single performance was achieved with the artificial neural network model when detecting prediabetes or diabetes. The artificial neural network classification model scored 78.1%, 78.7%, and 78.4% for sensitivity, precision, and F1 scores, respectively, when identifying no healthy group. Other models also had good results, depending on what is desired. Machine learning-based models can predict glycated hemoglobin values from routine laboratory tests and can be used as a screening tool to refer a patient for further testing.