Artificial Intelligence-Clinical Decision Support System in Infectious Disease Control: Combatting Multidrug-Resistant Klebsiella pneumoniae with Machine Learning

Abstract

Purpose: The World Health Organization has identified Klebsiella pneumoniae (KP) as a significant threat to global public health. The rising threat of carbapenem-resistant Klebsiella pneumoniae (CRKP) leads to prolonged hospital stays and higher medical costs, necessitating faster diagnostic methods. Traditional antibiotic susceptibility testing (AST) methods demand at least 4 days, requiring 3 days on average for culturing and isolating the bacteria and identifying the species using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), plus an extra day for interpreting AST results. This lengthy process makes traditional methods too slow for urgent clinical situations requiring rapid decision-making, potentially hindering prompt treatment decisions, especially for fast-spreading infections such as those caused by CRKP. This research leverages a cutting-edge diagnostic method that utilizes an artificial intelligence-clinical decision support system (AI-CDSS). It incorporates machine learning algorithms for the swift and precise detection of carbapenem-resistant and colistin-resistant strains.

Patients and methods: We selected 4307 KP samples out of a total of 52,827 bacterial samples due to concerns about multi-drug resistance using MALDI-TOF MS and Vitek-2 systems for AST. It involved thorough data preprocessing, feature extraction, and machine learning model training fine-tuned with GridSearchCV and 5-fold cross-validation, resulting in high predictive accuracy, as demonstrated by the receiver operating characteristic and area under the curve (AUC) scores, laying the groundwork for our AI-CDSS.

Results: MALDI-TOF MS analysis revealed distinct intensity profiles differentiating CRKP and susceptible strains, as well as colistin-resistant Klebsiella pneumoniae (CoRKP) and susceptible strains. The Random Forest Classifier demonstrated superior discriminatory power, with an AUC of 0.96 for detecting CRKP and 0.98 for detecting CoRKP.

Conclusion: Integrating MALDI-TOF MS with machine learning in an AI-CDSS has greatly expedited the detection of KP resistance by approximately 1 day. This system offers timely guidance, potentially enhancing clinical decision-making and improving treatment outcomes for KP infections.

Keywords: MALDI-TOF MS; antibiotic stewardship; carbapenem; colistin; diagnostic accuracy.

Figure 1

Flowchart of the study design. Commencing with the study focus and progressing to data collection. The pathway splits into specimen selection for CRKP (carbapenem-resistant Klebsiella pneumoniae) and colistin-resistant Klebsiella pneumoniae (CoRKP). Following this, data preprocessing and feature extraction take place, pinpointing vital m/z ratio segments for the development of a machine learning model. This model undergoes training and evaluation to ensure its accuracy and reliability. The final step is the deployment of the artificial intelligence-clinical decision support system (AI-CDSS). The table on the web page shows example outputs, including bacteria type, patient ID, antibiotics tested, predicted resistance probability, and final prediction (“R” for resistant or “S” for susceptible).

Figure 2

Comparative analysis of average intensity distribution in m/z ratio segments for different Klebsiella pneumoniae strains. This figure illustrates the variations in average intensity across mass-to-charge (m/z) ratio segments. (A) shows the mass spectrum for carbapenem-resistant Klebsiella pneumoniae (CRKP, depicted in blue) compared to carbapenem-susceptible Klebsiella pneumoniae (CSKP, depicted in red), highlighting their distinct spectral profiles. (B) depicts the mass spectrum for colistin-resistant Klebsiella pneumoniae (CoRKP, depicted in blue) versus colistin-susceptible Klebsiella pneumoniae (CoSKP, depicted in red), showcasing the spectral differences.

Figure 3

MALDI-TOF spectrum with feature importance for Klebsiella pneumoniae. This figure illustrates the feature importance on the MALDI-TOF spectrum for identifying carbapenem-resistant Klebsiella pneumoniae (CRKP) and colistin-resistant Klebsiella pneumoniae (CoRKP). The color gradient from blue to red indicates increasing feature importance, emphasizing critical regions in the spectrum for detecting resistance. (A) shows the intensity distribution across the m/z ratio segments for CRKP. (B) displays the intensity distribution for CoRKP.

Figure 4

Mean peak intensity comparison for Klebsiella pneumoniae strains. The bar charts illustrate the differential expression of these m/z segments, providing a visual metric of resistance markers, with carbapenem-resistant Klebsiella pneumoniae (CRKP) and colistin-resistant Klebsiella pneumoniae (CoRKP) shown in red and carbapenem-susceptible Klebsiella pneumoniae (CSKP) and colistin-susceptible Klebsiella pneumoniae (CoSKP) shown in blue. (A) compares the mean peak intensity for the top 10 distinguishing m/z ratio segments between CRKP and CSKP, which include 2068–2073, 2181–2186, 2689–2694, 2760–2767, 2856–2861, 3851–3856, 4363–4368, 5278–5283, 5379–5384, and 7698–7708. (B) compares the mean peak intensity for the top 10 distinguishing m/z ratio segments between CoRKP and CoSKP, which include 2181–2186, 2638–2643, 2760–2774, 3850–3855, 4518–4523, 5278–5283, 7703–7708, 7741–7751, 9133–9145, and 10281–10,290.

Figure 5

Receiver operating characteristic (ROC) curves evaluating the performance of various machine learning classifiers. (A) illustrates the true-positive rate against the false-positive rate for detecting carbapenem-resistant Klebsiella pneumoniae (CRKP), with the area under the curve (AUC) indicating each classifier’s discriminative power. (B) shows the ROC curve for detecting colistin-resistant Klebsiella pneumoniae (CoRKP), highlighting the classifiers’ effectiveness and AUC values reflecting their accuracy in distinguishing resistant strains.