Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods
Abstract In recent years, the incidence of refractory Mycoplasma pneumoniae pneumonia (RMPP) has significantly risen, posing severe pulmonary and extrapulmonary complications, making early identification a challenge for clinicians. In this retrospective single-center study, we included patients diag...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-02962-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850124495700885504 |
|---|---|
| author | Yuhan Jiang Xu Wang Li Li Yifan Wang Xuelin Wang Yingxue Zou |
| author_facet | Yuhan Jiang Xu Wang Li Li Yifan Wang Xuelin Wang Yingxue Zou |
| author_sort | Yuhan Jiang |
| collection | DOAJ |
| description | Abstract In recent years, the incidence of refractory Mycoplasma pneumoniae pneumonia (RMPP) has significantly risen, posing severe pulmonary and extrapulmonary complications, making early identification a challenge for clinicians. In this retrospective single-center study, we included patients diagnosed with Mycoplasma pneumoniae pneumonia in 2021, categorizing them into RMPP and non-RMPP groups. Univariate regression analysis initially identified variables associated with RMPP. Seven mainstream machine learning methods were then employed to construct predictive models, evaluated for reliability and robustness through tenfold cross-validation and sensitivity analysis. Ultimately, the optimal predictive model was selected using multidimensional metric assessments, and SHAP analysis identified key predictive factors related to RMPP. Twenty-nine factors from various dimensions were found to be associated with RMPP and used to build the predictive model. The XGBoost model demonstrated high predictive capability with an accuracy of 0.80 and an AUC of 0.93. Ten-fold cross-validation and sensitivity analysis confirmed the model’s robustness and reliability. SHAP analysis interpreted the final model with 8 key features. These features include fever duration, macrolide treatment before hospitalization, severe Mycoplasma pneumoniae pneumonia, lactate dehydrogenase, neutrophil-to-lymphocyte ratio, alanine aminotransferase, peak fever, and extensive lung consolidation. This simple, effective predictive model enhances clinicians’ understanding and aids early identification of RMPP. |
| format | Article |
| id | doaj-art-9b739f40c6eb48bdbb3df9b44ef07ea0 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-9b739f40c6eb48bdbb3df9b44ef07ea02025-08-20T02:34:17ZengNature PortfolioScientific Reports2045-23222025-05-0115111110.1038/s41598-025-02962-4Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methodsYuhan Jiang0Xu Wang1Li Li2Yifan Wang3Xuelin Wang4Yingxue Zou5Tianjin Children’s Hospital (Children’s Hospital, Tianin University)Tianjin Women and Children’s Health CenterDepartment of Pediatrics, Second Affiliated Hospital of Guangxi Medical UniversityTianjin Children’s Hospital (Children’s Hospital, Tianin University)Tianjin Children’s Hospital (Children’s Hospital, Tianin University)Tianjin Children’s Hospital (Children’s Hospital, Tianin University)Abstract In recent years, the incidence of refractory Mycoplasma pneumoniae pneumonia (RMPP) has significantly risen, posing severe pulmonary and extrapulmonary complications, making early identification a challenge for clinicians. In this retrospective single-center study, we included patients diagnosed with Mycoplasma pneumoniae pneumonia in 2021, categorizing them into RMPP and non-RMPP groups. Univariate regression analysis initially identified variables associated with RMPP. Seven mainstream machine learning methods were then employed to construct predictive models, evaluated for reliability and robustness through tenfold cross-validation and sensitivity analysis. Ultimately, the optimal predictive model was selected using multidimensional metric assessments, and SHAP analysis identified key predictive factors related to RMPP. Twenty-nine factors from various dimensions were found to be associated with RMPP and used to build the predictive model. The XGBoost model demonstrated high predictive capability with an accuracy of 0.80 and an AUC of 0.93. Ten-fold cross-validation and sensitivity analysis confirmed the model’s robustness and reliability. SHAP analysis interpreted the final model with 8 key features. These features include fever duration, macrolide treatment before hospitalization, severe Mycoplasma pneumoniae pneumonia, lactate dehydrogenase, neutrophil-to-lymphocyte ratio, alanine aminotransferase, peak fever, and extensive lung consolidation. This simple, effective predictive model enhances clinicians’ understanding and aids early identification of RMPP.https://doi.org/10.1038/s41598-025-02962-4Mycoplasma PneumoniaeRefractory Mycoplasma Pneumoniae pneumoniaMachine learningPredictive model |
| spellingShingle | Yuhan Jiang Xu Wang Li Li Yifan Wang Xuelin Wang Yingxue Zou Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods Scientific Reports Mycoplasma Pneumoniae Refractory Mycoplasma Pneumoniae pneumonia Machine learning Predictive model |
| title | Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| title_full | Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| title_fullStr | Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| title_full_unstemmed | Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| title_short | Predicting and interpreting key features of refractory Mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| title_sort | predicting and interpreting key features of refractory mycoplasma pneumoniae pneumonia using multiple machine learning methods |
| topic | Mycoplasma Pneumoniae Refractory Mycoplasma Pneumoniae pneumonia Machine learning Predictive model |
| url | https://doi.org/10.1038/s41598-025-02962-4 |
| work_keys_str_mv | AT yuhanjiang predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods AT xuwang predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods AT lili predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods AT yifanwang predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods AT xuelinwang predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods AT yingxuezou predictingandinterpretingkeyfeaturesofrefractorymycoplasmapneumoniaepneumoniausingmultiplemachinelearningmethods |