Invasive liver abscess syndrome caused by Klebsiella pneumoniae: first Tanzanian experience

Machine learning models for prediction of invasion Klebsiella pneumoniae liver abscess syndrome in diabetes mellitus: a singled centered retrospective study

OBJECTIVE

This study aimed to develop and validate a machine learning algorithm-based model for predicting invasive Klebsiella pneumoniae liver abscess syndrome(IKPLAS) in diabetes mellitus and compare the performance of different models.

METHODS

The clinical signs and data on the admission of 213 diabetic patients with Klebsiella pneumoniae liver abscesses were collected as variables. The optimal feature variables were screened out, and then Artificial Neural Network, Support Vector Machine, Logistic Regression, Random Forest, K-Nearest Neighbor, Decision Tree, and XGBoost models were established. Finally, the model's prediction performance was evaluated by the ROC curve, sensitivity (recall), specificity, accuracy, precision, F1-score, Average Precision, calibration curve, and DCA curve.

RESULTS

Four features of hemoglobin, platelet, D-dimer, and SOFA score were screened by the recursive elimination method, and seven prediction models were established based on these variables. The AUC (0.969), F1-Score(0.737), Sensitivity(0.875) and AP(0.890) of the SVM model were the highest among the seven models. The KNN model showed the highest specificity (1.000). Except that the XGB and DT models over-estimates the occurrence of IKPLAS risk, the other models' calibration curves are a good fit with the actual observed results. Decision Curve Analysis showed that when the risk threshold was between 0.4 and 0.8, the net rate of intervention of the SVM model was significantly higher than that of other models. In the feature importance ranking, the SOFA score impacted the model significantly.

CONCLUSION

An effective prediction model of invasion Klebsiella pneumoniae liver abscess syndrome in diabetes mellitus could be established by a machine learning algorithm, which had potential application value.

Case Series on Endogenous Klebsiella pneumoniae Endophthalmitis: More Than Meets the Eye

Endogenous endophthalmitis (EE) is a rare but potentially sight-threatening disease with an appreciable mortality rate. Diabetes mellitus remains the most frequently associated condition especially in the Asian population, which potentiates Klebsiella pneumoniae involvement. Endogenous Klebsiella pneumoniae endophthalmitis (EKE) usually has a poor final visual outcome despite treatment with intravitreal and systemic antibiotics. We report three cases of EKE with systemic involvement Klebsiella pneumoniae invasive syndrome (KPIS). KPIS was diagnosed in three patients with multiple comorbidities who presented with a blurring of vision and eye redness. Patient 1 was a 63-year-old Malay man diagnosed with left eye panophthalmitis with multifocal liver and prostate abscesses. He underwent drainage of the liver abscess and eventually evisceration of the left eye due to scleral perforation. Patient 2 was a 66-year-old Malay woman diagnosed with left eye endophthalmitis. Due to hemodynamic instability, vitrectomy was delayed and eventually sustained corneal perforation and eviscerated. The patient eventually succumbed to infection. Patient 3 was a 42-year-old Malay woman diagnosed with KPIS, renal abscess, lung abscess, and left endogenous endophthalmitis. She underwent a vitrectomy but her postoperative vision remained poor. All patients received multiple intravitreal antibiotics and systemic antibiotics. KPIS is frequently associated with catastrophic disabilities. Our cases highlight the importance of an early suspicion of systemic involvement in patients presenting with EKE. Prompt diagnosis, emergent radiographic evaluation, early adequate drainage, and appropriate treatment with antibiotics potentially improve survival and visual prognosis.