Risk factors and prediction model of severe pertussis in infants &lt; 12 months of age in Tianjin, China

Zhang, Cui; Zong, Yanmei; Wang, Zhe; Wang, Li; Li, Ying; Yang, Yuejie

doi:10.1186/s12879-021-07001-x

Cited by 2 publications

(4 citation statements)

References 21 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the patients with pertussis are under 5.7 months, more comprehensive physical examinations are required for further prediction. The cutoff value 5.7 months was consistent with the previous study [22]. Further, in accordance with the vaccination regulation in China, infants should receive three doses of pertussis vaccine at three, four, and five months after birth.…”

Section: Discussionsupporting

confidence: 86%

“…Existing methods for determing severe pertussis are pertussis severity scoring (PSS) and a predictive model developed in [22]. PSS [9] was a scoring system developed based on a review of the literature [5,12,17] and refined after statistic validation.…”

Section: Discussionmentioning

confidence: 99%

“…However, the scoring system is only a shortcut for determining the severity of patients' current situation rather than predicting whether the patients will become severe as the disease progress. [22] developed a logistic regression based on eight predictors. This development procedure is similar to the construction procedure of step-two prediction.…”

Section: Discussionmentioning

confidence: 99%

“…However, previous studies have mainly focused on detecting pertussis in the pediatric population [11,14] and predicting number of pertussis incidences using time series models such as ARIMA and ARIMA-ERNN [20]. A logistic regression model [22] has also been developed to predict severe pertussis among patients with pertussis, but it relies on hospital stay as a critical factor and is not applicable to outpatients. Furthermore, many factors included in existing models are costly and unnecessary for all patients with pertussis.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Machine Learning based Two-Step Cascading Method for Severe Pertussis Prediction

Hong

Kang²,

Mi³

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Pertussis is a highly contagious respiratory illness that can cause severe complications, particularly in children. However, predicting which patients with pertussis are at risk of developing severe symptoms remains a challenge in clinical practice. In this study, we developed a two-step cascading machine learning pipeline to predict severe pertussis in patients with the disease. Study Design This work retrospectively involved both outpatients and inpatients with pertussis between March 2011 and December 2018 from Capital Institute of Pediatrics. We developed a two-step cascading prediction pipeline for severe pertussis in both outpatients and inpatients based on logistic regression models and nomograms. The pipeline selected potential severe pertussis patients with high sensitivity in the first step and predicted severe pertussis patients with high specificity in the second step using additional information. Further, the second step of pipeline was tested on a held-out test set of 17 inpatients with pertussis patients enrolled since December 2018. Results This work split the enrolled patients into training cohort and validation cohort in a 7:3 ratio. The first-step machine learning models included onset age (months) as a predictor and achieved a sensitivity of 0.923 (95% CI, 0.778-1.00) in the validation cohort. The second-step machine learning model consisted of five variables: white blood cell count, globulin usage, fever, paroxysmal cyanosis, and increased leukocyte levels. The validation cohort showed an accuracy of 0.797, AUC of 0.920 (95% CI, 0.832-1.000), sensitivity of 0.647 (95% CI, 0.413-0.827), and specificity of 0.846 (95% CI, 0.725-0.920). Nomograms were developed based on the machine learning models, and the calibration curves indicated a good fit. Conclusion This study developed a severe pertussis prediction pipeline using machine learning models, which demonstrated high sensitivity in the first step and high accuracy in the second step. The pipeline provides a useful screening and prediction workflow for severe pertussis patients, and the inclusion of nomograms enhances its practicality for clinical use. Overall, this pipeline has potential to improve the early identification and management of severe pertussis cases.

show abstract

Section: Discussionsupporting

confidence: 86%