A Preliminary Prediction Model of Pediatric Mycoplasma Pneumoniae Pneumonia Based on Routine Blood Parameters by Using Machine Learning Method

Overview

Journal BMC Infect Dis

Publisher Biomed Central

Specialty Infectious Diseases

Date 2024 Jul 18

PMID 39026207

Authors

Xuelian Peng

Yulong Liu

Bo Zhang

Chunyan Yang

Jian Dong

Chen Yong

Baoru Han

Jin Li

Affiliations

Soon will be listed here.

Abstract

Background: The prevalence and severity of pediatric Mycoplasma pneumoniae pneumonia (MPP) poses a significant threat to the health and lives of children. In this study, we aim to systematically evaluate the value of routine blood parameters in predicting MPP and develop a robust and generalizable ensemble artificial intelligence (AI) model to assist in identifying patients with MPP.

Methods: We collected 27 features, including routine blood parameters and hs-CRP levels, from patients admitted to The Affiliated Dazu's Hospital of Chongqing Medical University with or without MPP between January, 2023 and January, 2024. A classification model was built using seven machine learning (ML) algorithms to develop an integrated prediction tool for diagnosing MPP. It was evaluated on both an internal validation set (982 individuals) and an external validation set (195 individuals). The primary outcome measured the accuracy of the model in predicting MPP.

Results: The GBDT is state-of-the-art based on 27 features. Following inter-laboratory cohort testing, the GBDT demonstrated an AUC, accuracy, specificity, sensitivity, PPV, NPV, and F1-score of 0.980 (0.938-0.995), 0.928 (0.796-0.970), 0.929 (0.717-1.000), 0.926 (0.889-0.956), 0.922 (0.727-1.000), 0.937 (0.884-0.963), and 0.923 (0.800-0.966) in stratified 10-fold cross-validation. A GBDT-based AI Lab was developed to facilitate the healthcare providers in remote and impoverished areas.

Conclusions: The GBDT-based AI Lab tool, with high sensitivity and specificity, could help discriminate between pediatric MPP infection and non-MPP infection based on routine blood parameters. Moreover, a user-friendly webpage tool for AI Lab could facilitate healthcare providers in remote and impoverished areas where advanced technologies are not accessible.

References

Qu J, Chen S, Bao F, Gu L, Cao B . Molecular characterization and analysis of Mycoplasma pneumoniae among patients of all ages with community-acquired pneumonia during an epidemic in China. Int J Infect Dis. 2019; 83:26-31. DOI: 10.1016/j.ijid.2019.03.028. View

Katsushima Y, Katsushima F, Suzuki Y, Seto J, Mizuta K, Nishimura H . Characteristics of Mycoplasma pneumoniae infection identified on culture in a pediatric clinic. Pediatr Int. 2014; 57(2):247-52. DOI: 10.1111/ped.12513. View

Ahn J, Cho H, Li D, Choi M, Lee J, Eun B . Efficacy of tetracyclines and fluoroquinolones for the treatment of macrolide-refractory Mycoplasma pneumoniae pneumonia in children: a systematic review and meta-analysis. BMC Infect Dis. 2021; 21(1):1003. PMC: 8465761. DOI: 10.1186/s12879-021-06508-7. View

Mohr F, van Rijn J . Fast and Informative Model Selection Using Learning Curve Cross-Validation. IEEE Trans Pattern Anal Mach Intell. 2023; 45(8):9669-9680. DOI: 10.1109/TPAMI.2023.3251957. View

Zhang Z, Wan R, Yuan Q, Dou H, Tu P, Shi D . Cell damage and neutrophils promote the infection of Mycoplasma pneumoniae and inflammatory response. Microb Pathog. 2022; 169:105647. DOI: 10.1016/j.micpath.2022.105647. View

Theodosiou A, Read R . Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician. J Infect. 2023; 87(4):287-294. DOI: 10.1016/j.jinf.2023.07.006. View

Ling Y, Zhang T, Guo W, Zhu Z, Tian J, Cai C . Identify clinical factors related to Mycoplasma pneumoniae pneumonia with hypoxia in children. BMC Infect Dis. 2020; 20(1):534. PMC: 7374650. DOI: 10.1186/s12879-020-05270-6. View

Shi W, Zhao L, Li S, Xu G, Zeng Y . Serological diagnosis of Mycoplasma pneumoniae infection by using the mimic epitopes. World J Microbiol Biotechnol. 2018; 34(6):82. DOI: 10.1007/s11274-018-2467-y. View

Xu M, Li Y, Shi Y, Liu H, Tong X, Ma L . Molecular epidemiology of Mycoplasma pneumoniae pneumonia in children, Wuhan, 2020-2022. BMC Microbiol. 2024; 24(1):23. PMC: 10792977. DOI: 10.1186/s12866-024-03180-0. View

10.

Lourda M, Dzidic M, Hertwig L, Bergsten H, Palma Medina L, Sinha I . High-dimensional profiling reveals phenotypic heterogeneity and disease-specific alterations of granulocytes in COVID-19. Proc Natl Acad Sci U S A. 2021; 118(40). PMC: 8501786. DOI: 10.1073/pnas.2109123118. View

11.

Peng H, Siddiqui M, Rhind S, Zhang J, da Luz L, Beckett A . Artificial intelligence and machine learning for hemorrhagic trauma care. Mil Med Res. 2023; 10(1):6. PMC: 9933281. DOI: 10.1186/s40779-023-00444-0. View

12.

Zhang F, Wang H, Liu L, Su T, Ji B . Machine learning model for the prediction of gram-positive and gram-negative bacterial bloodstream infection based on routine laboratory parameters. BMC Infect Dis. 2023; 23(1):675. PMC: 10566101. DOI: 10.1186/s12879-023-08602-4. View

13.

Kutty P, Jain S, Taylor T, Bramley A, Diaz M, Ampofo K . Mycoplasma pneumoniae Among Children Hospitalized With Community-acquired Pneumonia. Clin Infect Dis. 2018; 68(1):5-12. PMC: 6552676. DOI: 10.1093/cid/ciy419. View

14.

Peiffer-Smadja N, Rawson T, Ahmad R, Buchard A, Georgiou P, Lescure F . Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clin Microbiol Infect. 2019; 26(5):584-595. DOI: 10.1016/j.cmi.2019.09.009. View

15.

Izumikawa K . Clinical Features of Severe or Fatal Mycoplasma pneumoniae Pneumonia. Front Microbiol. 2016; 7:800. PMC: 4888638. DOI: 10.3389/fmicb.2016.00800. View

16.

Cai G, Huang F, Gao Y, Li X, Chi J, Xie J . Artificial intelligence-based models enabling accurate diagnosis of ovarian cancer using laboratory tests in China: a multicentre, retrospective cohort study. Lancet Digit Health. 2024; 6(3):e176-e186. DOI: 10.1016/S2589-7500(23)00245-5. View

17.

Chen L, Yuan L, Sun T, Liu R, Huang Q, Deng S . The performance of VCS(volume, conductivity, light scatter) parameters in distinguishing latent tuberculosis and active tuberculosis by using machine learning algorithm. BMC Infect Dis. 2023; 23(1):881. PMC: 10725592. DOI: 10.1186/s12879-023-08531-2. View

18.

Deo R . Machine Learning in Medicine. Circulation. 2015; 132(20):1920-30. PMC: 5831252. DOI: 10.1161/CIRCULATIONAHA.115.001593. View

19.

Balish M . Mycoplasma pneumoniae, an underutilized model for bacterial cell biology. J Bacteriol. 2014; 196(21):3675-82. PMC: 4248795. DOI: 10.1128/JB.01865-14. View

20.

Li J, Luu L, Wang X, Cui X, Huang X, Fu J . Metabolomic analysis reveals potential biomarkers and the underlying pathogenesis involved in pneumonia. Emerg Microbes Infect. 2022; 11(1):593-605. PMC: 8865114. DOI: 10.1080/22221751.2022.2036582. View