Establishment of a Machine Learning-Based Predictive Model for Klebsiella pneumoniae Liver Abscess
1Senior Department of Oncology, Chinese PLA General Hospital, Beijing, 100039, People's Republic of China.
Purpose:
To investigate the clinical and ultrasonographic characteristics of pyogenic liver abscess (PLA) caused by Klebsiella pneumoniae (K-PLA) and non-Klebsiella pneumoniae pathogens, and to develop machine learning models for the differential diagnosis of K-PLA.
Materials And Methods:
In this retrospective study, patients clinically diagnosed with PLA and confirmed by ultrasound-guided puncture at the Fifth Medical Center of PLA General Hospital between April 2013 and December 2020 were enrolled. Based on the causative pathogens, patients were categorized into K-PLA and non-K-PLA groups. Baseline data, including ultrasonographic features, clinical characteristics, and laboratory findings, were collected. The Boruta algorithm was employed for feature selection, and four machine learning models-Deep Learning-Fully Connected Neural Network (deeplearning), Distributed Random Forest (drf), Gradient Boosting Machine (gbm), and Generalized Linear Model (glm)-were developed to diagnose K-PLA. The models were validated using 5-fold cross-validation.
Results:
A total of 201 patients with bacterial liver abscess were included (median age: 57 years; range: 49-66; 136 males), comprising 134 K-PLA cases and 67 non-K-PLA cases. The Boruta algorithm identified seven significant predictive variables: history of diabetes, history of hepatocellular carcinoma, history of biliary tract disease, history of infectious diseases, duration of fever, body temperature, and alanine aminotransferase (ALT) levels. Using these variables, the four machine learning models were constructed. In the training set, the area under the receiver operating characteristic curve (AUC) for predicting K-PLA was 0.716 (deeplearning), 0.999 (drf), 0.922 (gbm), and 0.718 (glm). In the validation set, the corresponding AUC values were 0.799, 0.763, 0.848, and 0.805, respectively.
Conclusion:
This study successfully established four machine learning models for predicting the risk of K-PLA, with the gbm-based model demonstrating the highest diagnostic performance. These models may facilitate early clinical diagnosis and treatment of K-PLA, thereby reducing antibiotic misuse.
Insights
Machine learning models can differentiate pyogenic liver abscesses (PLA) caused by Klebsiella pneumoniae (K-PLA) from other pathogens. The Gradient Boosting Machine model showed the highest diagnostic performance, aiding early K-PLA diagnosis and reducing antibiotic misuse.
Area of Science:
- Hepatology
- Infectious Diseases
- Machine Learning in Medicine
Background:
- Pyogenic liver abscess (PLA) diagnosis can be challenging.
- Differentiating Klebsiella pneumoniae (K-PLA) from other pathogens is crucial for targeted treatment.
Purpose of the Study:
- To analyze clinical and ultrasonographic features of K-PLA versus non-K-PLA.
- To develop and validate machine learning models for K-PLA differential diagnosis.
Main Methods:
- Retrospective study of 201 PLA patients (2013-2020).
- Feature selection using Boruta algorithm identified key predictive variables.
- Four machine learning models (deeplearning, drf, gbm, glm) were developed and validated using 5-fold cross-validation.
Main Results:
- Seven significant predictors identified: diabetes, hepatocellular carcinoma, biliary tract disease, infectious diseases history, fever duration, body temperature, and ALT levels.
- Gradient Boosting Machine (gbm) model achieved the highest AUC (0.922 training, 0.848 validation).
- Distributed Random Forest (drf) showed an AUC of 0.999 in the training set.
Conclusions:
- Machine learning models effectively predict K-PLA risk.
- The gbm model demonstrated superior diagnostic performance for K-PLA.
- These models can aid early clinical diagnosis, optimize treatment, and reduce antibiotic misuse.
More Related Videos
09:17A Robust Pneumonia Model in Immunocompetent Rodents to Evaluate Antibacterial Efficacy against S. pneumoniae, H. influenzae, K. pneumoniae, P. aeruginosa or A. baumannii
Published on: January 2, 2017
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020