Use of common blood parameters for the differential diagnosis of childhood infections

Wang, Weiying; Li, Shu Hua

doi:10.1371/journal.pone.0273236

Cited by 4 publications

(3 citation statements)

References 28 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SBI group exhibited lower hemoglobin levels and higher CRP levels, aligning with findings from prior studies [ 27 , 28 ]. The inflammatory response to an infection, characterized by the secretion of interleukin-6 (IL-6) in significant amounts, could be a primary factor contributing to anemia [ 29 , 30 ].…”

Section: Discussionsupporting

confidence: 89%

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

Liu,

Chen,

Dong

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

Background Serious bacterial infections (SBIs) are linked to unplanned hospital admissions and a high mortality rate. The early identification of SBIs is crucial in clinical practice. Objective This study aims to establish and validate clinically applicable models designed to identify SBIs in patients with infective fever. Methods Clinical data from 945 patients with infective fever, encompassing demographic and laboratory indicators, were retrospectively collected from a 2200-bed teaching hospital between January 2013 and December 2020. The data were randomly divided into training and test sets at a ratio of 7:3. Various machine learning (ML) algorithms, including Boruta, Lasso (least absolute shrinkage and selection operator), and recursive feature elimination, were utilized for feature filtering. The selected features were subsequently used to construct models predicting SBIs using logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) with 5-fold cross-validation. Performance metrics, including the receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), accuracy, sensitivity, and other relevant parameters, were used to assess model performance. Considering both model performance and clinical needs, 2 clinical timing-sequence warning models were ultimately confirmed using LR analysis. The corresponding predictive nomograms were then plotted for clinical use. Moreover, a physician, blinded to the study, collected additional data from the same center involving 164 patients during 2021. The nomograms developed in the study were then applied in clinical practice to further validate their clinical utility. Results In total, 69.9% (661/945) of the patients developed SBIs. Age, hemoglobin, neutrophil-to-lymphocyte ratio, fibrinogen, and C-reactive protein levels were identified as important features by at least two ML algorithms. Considering the collection sequence of these indicators and clinical demands, 2 timing-sequence models predicting the SBI risk were constructed accordingly: the early admission model (model 1) and the model within 24 hours of admission (model 2). LR demonstrated better stability than RF and XGBoost in both models and performed the best in model 2, with an AUC, accuracy, and sensitivity of 0.780 (95% CI 0.720-841), 0.754 (95% CI 0.698-804), and 0.776 (95% CI 0.711-832), respectively. XGBoost had an advantage over LR in AUC (0.708, 95% CI 0.641-775 vs 0.686, 95% CI 0.617-754), while RF achieved better accuracy (0.729, 95% CI 0.673-780) and sensitivity (0.790, 95% CI 0.728-844) than the other 2 approaches in model 1. Two SBI-risk prediction nomograms were developed for clinical use based on LR, and they exhibited good performance with an accuracy of 0.707 and 0.750 and a sensitivity of 0.729 and 0.927 in clinical application. Conclusions The clinical timing-sequence warning models demonstrated efficacy in predicting SBIs in patients suspected of having infective fever and in clinical application, suggesting good potential in clinical decision-making. Nevertheless, additional prospective and multicenter studies are necessary to further confirm their clinical utility.

show abstract

Section: Discussionsupporting

confidence: 89%

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

Liu,

Chen,

Dong

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…A recent study also mentioned that hemoglobin values might be significantly different between M. pneumoniae infection and other groups of infection in pediatric patients. [ 22 ] Another study of severe M. pneumoniae infection also suggested that ESR values could be decreased after the medication treatment. [ 23 ] ESR has also been reported to be associated with the target protein expression of M. pneumoniae infection in pediatric patients.…”

Section: Discussionmentioning

confidence: 99%

The relationship between Mycoplasma and Kawasaki disease in pediatric patients: An updated systematic review and meta-analysis

Cheng,

Zheng,

Gao

et al. 2023

Arch Rheumatol

View full text Add to dashboard Cite

Objectives: This study aimed to clarify the relationship between Mycoplasma pneumoniae (M. pneumoniae) and Kawasaki disease by conducting an updated systemic review and meta-analysis of published studies. Materials and methods: Studies mentioning M. pneumoniae and Kawasaki disease before October 2022 were included in this meta-analysis. The pooled prevalence was calculated, and the log odds ratio in the random effects model was applied to estimate the pooled prevalence of M. pneumoniae infection in pediatric patients with Kawasaki disease. In addition, the clinical parameters, such as hemoglobin and erythrocyte sedimentation rate, were analyzed. Six studies with a total of 1,859 pediatric patients with Kawasaki disease were enrolled. The focused outcome was the pooled prevalence and clinical parameters. Results: The pooled prevalence of M. pneumoniae infection was statistically significant in pediatric patients with Kawasaki disease. In addition, the values of hemoglobin and erythrocyte sedimentation rate were significantly different between M. pneumoniae-infected and non-M. pneumoniae-infected patients with Kawasaki disease. Other clinical parameters were not significantly different between M. pneumoniae-infected and non-M. pneumoniae-infected patients with Kawasaki disease. Conclusion: The results suggest that M. pneumoniae infection is significantly prevalent in pediatric patients with Kawasaki disease. The lower values of hemoglobin and erythrocyte sedimentation rate in M. pneumoniae-infected patients with Kawasaki disease might be needed to investigate further.

show abstract

“…On the other hand, blood test is commonly performed in most outpatients, and is an important guide for diagnosing the presence, type, and severity of infection. It is commonly applied for differing viral infections from bacterial infections in practice ( 3 ). In addition to complete blood panel ( 4 , 5 ), related hematological parameters, such as neutrophil-to-lymphocyte ratio (NLR) ( 6 , 7 ), platelet-to-lymphocyte ratio (PLR) ( 8 ), and lymphocyte (LYM) multiplied by platelet (LYM*PLT) ( 9 ), are reported to be important screening indicators in infectious diseases.…”

Section: Introductionmentioning

confidence: 99%

The blood routine test holds screening values for influenza A in 2023: a retrospective study

Hong,

Lv,

et al. 2024

Transl Pediatr

View full text Add to dashboard Cite

Background Influenza A is the most common viral pathogen isolated from pediatric clinics during influenza seasons. Some young patients with influenza manifest rapid progression with high fever and severe sequelae, such as pneumonia and meningitis. Therefore, early diagnosis and prompt treatment are highly important. Specific diagnostic tests currently include antigen detection, antibody detection, nucleic acid test and virus isolation. Rapid antigen testing is the most commonly adopted method in the outpatient setting, but false negative results are frequently observed, which causes delayed treatment and severe outcome. Routine blood test is the most commonly used detection for the outpatients. Incorporating specific blood cell counts into rapid antigen test may overcome some technical issues and enable accurate early diagnosis. Methods We enrolled 537 children with influenza-like symptoms like fever or respiratory symptoms from pediatric outpatients and 110 children without infectious diseases for control. Routine blood tests detected by a routine analyzer and influenza A virus antigen detection were performed in the patients. Significant blood routine parameters between groups were examined by statistical tests. Parameters in routine blood test were assessed by the receiver operating characteristic curve to find the screening indicators of influenza A. Multivariate logistic regression were used to establish the optimal combinations of blood routine parameters in our screening model. Results Two subgroups were set according to age: ≤6 years old group and >6 years old group. In each group, patients were further divided into three subgroups: the influenza A-positive-result group (A+ group) (n=259), influenza A-negative-result group (A− group) (n=277) and healthy control group (H group) (n=110). Most routine blood parameters showed significant differences among the three subgroups in each age group. Notably, lymphocyte (LYM) number, platelet (PLT) number, lymphocyte-to-monocyte ratio (LMR) and LYM multiplied by PLT (LYM*PLT) exhibited extremely significant differences. Using A− group as a reference based on the area under the curve (AUC), both age groups had a similar trend. For A− group, the optimal cutoff value of LYM*PLT was 221.6, the AUC, the sensitivity and specificity were 0.6830, 55.71% and 76.92% in the ≤6 years old group. Meanwhile, the cutoff value of LYM*PLT was 196.7, and the AUC, the sensitivity and specificity were 0.6448, 53.97% and 70.81%, respectively in the >6 years old group. Screening model based on multivariate logistic regression model revealed that LYM*PLT was the optimal parameter combinations in ≤6 years old group (AUC =0.7202), while LYM and PLT were the optimal parameter combinations in >6 years old group (AUC =0.6760). Conclusions Several blood routine parameters in children with influenza A demonstrate differential levels in both age subgroups. The LYM*PLT exhibits the potential scr...

show abstract

Use of common blood parameters for the differential diagnosis of childhood infections

Cited by 4 publications

References 28 publications

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

Clinical Timing-Sequence Warning Models for Serious Bacterial Infections in Adults Based on Machine Learning: Retrospective Study

The relationship between Mycoplasma and Kawasaki disease in pediatric patients: An updated systematic review and meta-analysis

The blood routine test holds screening values for influenza A in 2023: a retrospective study

Contact Info

Product

Resources

About