Prediction of atelectasis in Mycoplasma pneumoniae pneumonia using a SHapley Additive exPlanations-interpretable machine learning model - Takeaways - MDSpire

Prediction of atelectasis in Mycoplasma pneumoniae pneumonia using a SHapley Additive exPlanations-interpretable machine learning model

  • By

  • Jia Sun

  • Wang Tengfei

  • Mengsi Li

  • Mian Wang

  • May 11, 2026

  • 0 min

Share

  • 1

    The study evaluated KNN, SVM, and NN models for predicting atelectasis risk in children with Mycoplasma pneumoniae pneumonia.

  • 2

    The neural network model outperformed others with an AUC of 0.89 and accuracy of 0.82 in predicting atelectasis.

  • 3

    SHAP analysis identified neutrophil percentage, serum amyloid A, and C-reactive protein as key predictive variables.

  • 4

    Machine learning models provide non-invasive tools for early identification and management of atelectasis in pediatric patients.

  • 5

    The study highlights the potential of machine learning in improving clinical outcomes for children with pneumonia-related complications.

Original Source(s)

Prediction of atelectasis in Mycoplasma pneumoniae pneumonia using a SHapley Additive exPlanations-interpretable machine learning model

  • by Jia Sun, Wang Tengfei, Mengsi Li, Mian Wang

  • May 11, 2026

Related Content

GLP-1 Drugs Tied to Lower Addiction Risk

In a target-trial emulation of more than 600,000 veterans, GLP-1 RA initiators saw fewer new substance use disorders—and patients with existing SUDs had fewer overdoses, hospitalizations, and deaths.

Recurrent pleuropulmonary blastoma type III initially misclassified as embryonal rhabdomyosarcoma on limited biopsy: a case report with pathogenic DICER1 variant

Gene Therapy Reaches XLRS Milestone

Atsena Therapeutics reports positive interim data for XLRS gene therapy

  • May 25, 2026

  • 3 min