Classification of infectious diseases based on chemiluminescent signatures of phagocytes in whole blood

Emerging infectious disease surveillance using a hierarchical diagnosis model and the Knox algorithm

Emerging infectious diseases are a critical public health challenge in the twenty-first century. The recent proliferation of such diseases has raised major social and economic concerns. Therefore, early detection of emerging infectious diseases is essential. Subjects from five medical institutions in Beijing, China, which met the spatial-specific requirements, were analyzed. A quality control process was used to select 37,422 medical records of infectious diseases and 56,133 cases of non-infectious diseases. An emerging infectious disease detection model (EIDDM), a two-layer model that divides the problem into two sub-problems, i.e., whether a case is an infectious disease, and if so, whether it is a known infectious disease, was proposed. The first layer model adopts the binary classification model TextCNN-Attention. The second layer is a multi-classification model of LightGBM based on the one-vs-rest strategy. Based on the experimental results, a threshold of 0.5 is selected. The model results were compared with those of other models such as XGBoost and Random Forest using the following evaluation indicators: accuracy, sensitivity, specificity, positive predictive value, and negative predictive value. The prediction performance of the first-layer TextCNN is better than that of other comparison models. Its average specificity for non-infectious diseases is 97.57%, with an average negative predictive value of 82.63%, indicating a low risk of misdiagnosing non-infectious diseases as infectious (i.e., a low false positive rate). Its average positive predictive value for eight selected infectious diseases is 95.07%, demonstrating the model's ability to avoid misdiagnoses. The overall average accuracy of the model is 86.11%. The average prediction accuracy of the second-layer LightGBM model for emerging infectious diseases reaches 90.44%. Furthermore, the response time of a single online reasoning using the LightGBM model is approximately 27 ms, which makes it suitable for analyzing clinical records in real time. Using the Knox method, we found that all the infectious diseases were within 2000 m in our case, and a clustering feature of spatiotemporal interactions (P < 0.05) was observed as well. Performance testing and model comparison results indicated that the EIDDM is fast and accurate and can be used to monitor the onset/outbreak of emerging infectious diseases in real-world hospitals.

Deep learning model for multi-classification of infectious diseases from unstructured electronic medical records

Purpose

Predictively diagnosing infectious diseases helps in providing better treatment and enhances the prevention and control of such diseases. This study uses actual data from a hospital. A multiple infectious disease diagnostic model (MIDDM) is designed for conducting multi-classification of infectious diseases so as to assist in clinical infectious-disease decision-making.

Methods

Based on actual hospital medical records of infectious diseases from December 2012 to December 2020, a deep learning model for multi-classification research on infectious diseases is constructed. The data includes 20,620 cases covering seven types of infectious diseases, including outpatients and inpatients, of which training data accounted for 80%, i.e., 16,496 cases, and test data accounted for 20%, i.e., 4124 cases. Through the auto-encoder, data normalization and sparse data densification processing are carried out to improve the model training effect. A residual network and attention mechanism are introduced into the MIDDM model to improve the performance of the model.

Result

MIDDM achieved improved prediction results in diagnosing seven kinds of infectious diseases. In the case of similar disease diagnosis characteristics and similar interference factors, the prediction accuracy of disease classification with more sample data is significantly higher than the prediction accuracy of disease classification with fewer sample data. For instance, the training data for viral hepatitis, influenza, and hand foot and mouth disease were 2954, 3924, and 3015 respectively and the corresponding test accuracy rates were 99.86%, 98.47%, and 97.31%. There is less training data for syphilis, infectious diarrhea, and measles, i.e., 1208, 575, and 190 respectively and the corresponding test accuracy rates were noticeably lower, i.e., 83.03%, 87.30%, and42.11%. We also compared the MIDDM model with the models used in other studies. Using the same input data, taking viral hepatitis as an example, the accuracy of MIDDM is 99.44%, which is significantly higher than that of XGBoost (96.19%), Decision tree (90.13%), Bayesian method (85.19%), and logistic regression (91.26%). Other diseases were also significantly better predicted by MIDDM than by these three models.

Conclusion

The application of the MIDDM model to multi-class diagnosis and prediction of infectious diseases can improve the accuracy of infectious-disease diagnosis. However, these results need to be further confirmed via clinical randomized controlled trials.

A systematic map of medical data preprocessing in knowledge discovery

BACKGROUND AND OBJECTIVE

Datamining (DM) has, over the last decade, received increased attention in the medical domain and has been widely used to analyze medical datasets in order to extract useful knowledge and previously unknown patterns. However, historical medical data can often comprise inconsistent, noisy, imbalanced, missing and high dimensional data. These challenges lead to a serious bias in predictive modeling and reduce the performance of DM techniques. Data preprocessing is, therefore, an essential step in knowledge discovery as regards improving the quality of data and making it appropriate and suitable for DM techniques. The objective of this paper is to review the use of preprocessing techniques in clinical datasets.

METHODS

We performed a systematic map of studies regarding the application of data preprocessing to healthcare and published between January 2000 and December 2017. A search string was determined on the basis of the mapping questions and the PICO categories. The search string was then applied in digital databases covering the fields of computer science and medical informatics in order to identify relevant studies. The studies were initially selected by reading their titles, abstracts and keywords. Those that were selected at that stage were then reviewed using a set of inclusion and exclusion criteria in order to eliminate any that were not relevant. This process resulted in 126 primary studies.

RESULTS

Selected studies were analyzed and classified according to their publication years and channels, research type, empirical type and contribution type. The findings of this mapping study revealed that researchers have paid a considerable amount of attention to preprocessing in medical DM in last decade. A significant number of the selected studies used data reduction and cleaning preprocessing tasks. Moreover, the disciplines in which preprocessing have received most attention are: cardiology, endocrinology and oncology.

CONCLUSIONS

Researchers should develop and implement standards for an effective integration of multiple medical data types. Moreover, we identified the need to perform literature reviews.

Sour Cherries but Not Apples Added to the Regular Diet Decrease Resting and fMLP-Stimulated Chemiluminescence of Fasting Whole Blood in Healthy Subjects

OBJECTIVE

Berry fruits rich in anthocyanins have antioxidant and anti-inflammatory properties. Blood phagocytes are an important source of oxidants that contribute to inflammatory response and oxidative stress. We examined the effect of sour cherry consumption on luminol-enhanced whole blood chemiluminescence (LBCL) reflecting oxidants generation by circulating phagocytes in healthy subjects.

METHODS

Thirty-four and 29 healthy subjects (on a regular diet) consumed 500 g of sour cherries containing 346.5 mg of total anthocyanins or 500 g of anthocyanin-free apples everyday (between 1100 and 1400 hours) for 30 days. Twenty-four volunteers without any dietary intervention served as the control with respect to LBCL changes over the study period. Fasting blood and spot morning urine samples were collected before and after the fruit courses and after the 10-day wash-out period to measure resting and agonist (fMLP)-induced LBCL, blood cell count, concentration of various phenolics, and plasma antioxidant activity.

RESULTS

Sour cherries inhibited (p < 0.05) median resting LBCL (by 29.5% and 33.7%) and fMLP-LBCL (by 24.7% and 32.3%) after 30-day consumption and after 10-day wash-out, respectively. No changes in LBCL were noted in the apple consumers and controls. Increased urinary levels of chlorogenic, 4-hydroxyhippuric, and 3-hydroxyhippuric acids occasionally correlated negatively with resting and fMLP-LBCL in sour cherry consumers. Other measured variables did not change in all groups over the study period.

CONCLUSIONS

The inhibition of resting and agonist-induced LBCL suggests that regular sour cherry consumption may suppress the formation of reactive oxygen species by circulating phagocytes and decrease the risk of systemic imbalance between oxidants and antioxidants. This may be attributed to the anthocyanins in sour cherry and be one of mechanisms of the health-promoting effects of consumption of anthocyanin-rich fruits.

Accelerated reactivity of blood granulocytes in patients with atopic bronchial asthma out of exacerbation

Reactive oxygen species (ROS) are important in bronchial asthma (BA) pathogenesis owing to accumulation of activated granulocytes in the lungs. But the ROS-producing activity of the cells is insufficiently understood in the blood of BA patients. This study analyzes the kinetics of phagocyte respiratory burst in the blood to improve the methods of BA patients monitoring. Patients with atopic BA out of exacerbation (n=60) and healthy controls (n=43) were recruited. The time-course of respiratory response to opsonized zymosan (OZ) was recorded in the whole blood using luminol-dependent chemiluminescence (CL), and its activation kinetics (lag-time, rate, amplitude, ROS production) was calculated. The discriminative power of ROS generation kinetics was defined by Receiver Operating Characteristic (ROC) curve analysis. Standard physiological respiratory parameters of patients did not differ from the controls. More rapid response to OZ was recorded in BA patient samples versus the controls. The primed state of phagocytes in the blood of BA patients was corroborated by significant weakening formyl peptide priming effect. The adhesion of granulocytes to cultured human endothelial cells was two-fold higher in BA patients versus controls. ROC curve analysis exhibited good discriminative effectiveness of the CL kinetics to compare BA individuals with the controls. The highest power (86% sensitivity and 90% specificity) was achieved at a linear combination of the parameters. We assume that the assessment of phagocyte reactivity based on the analysis of the response kinetic profile is a good test for monitoring of the state in BA patients.

The effect of storage on whole blood chemiluminescence measurement of equine neutrophils

The aim of this study was to determine the effect of duration and temperature of sample storage on whole blood chemiluminescence measurement results. Venous blood from 18 clinically healthy Polish half-bred horses aged 4 to 11 years were used in the study. Luminol dependent chemiluminescence (CL) was used to measure neutrophil oxygen metabolism in whole blood. Blood samples were examined for spontaneous CL and stimulated by a surface receptor stimulus as well as extra-receptor stimulus. The assay was performed in two parallel experimental sets with samples stored at 4 and 22 °C, respectively. Whole blood CL was estimated at 2, 6, 24, 48, 72, 96 and 120 h after collection. The study demonstrated that temperature and duration of sample storage are factors that determine the quality of CL measurements of whole blood in horses. The study concluded that samples should be stored at 4 °C and the assay should be performed as early as possible. It was also shown that the viability period of horse blood for CL assays is relatively long. Material stored at room temperature for 24 h and even up to 48 h at 4 °C did not show any significant decrease in spontaneous or stimulated chemiluminescence.