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

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.

Innovative strategies against superbugs: Developing an AI-CDSS for precise Stenotrophomonas maltophilia treatment.

OBJECTIVES: The World Health Organization named Stenotrophomonas maltophilia (SM) a critical multi-drug resistant threat, necessitating rapid diagnostic strategies. Traditional culturing methods require up to 96 h, including 72 h for bacterial growth, identification with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) through protein profile analysis, and 24 h for antibiotic susceptibility testing. In this study, we aimed at developing an artificial intelligence-clinical decision support system (AI-CDSS) by integrating MALDI-TOF MS and machine learning to quickly identify levofloxacin and trimethoprim/sulfamethoxazole resistance in SM, optimizing treatment decisions. METHODS: We selected 8,662 SM from 165,299 MALDI-TOF MS-analysed bacterial specimens, collected from a major medical centre and four secondary hospitals. We exported mass-to-charge values and intensity spectral profiles from MALDI-TOF MS .mzML files to predict antibiotic susceptibility testing results, obtained with the VITEK-2 system using machine learning algorithms. We optimized the models with GridSearchCV and 5-fold cross-validation. RESULTS: We identified distinct spectral differences between resistant and susceptible SM strains, demonstrating crucial resistance features. The machine learning models, including random forest, light-gradient boosting machine, and XGBoost, exhibited high accuracy. We established an AI-CDSS to offer healthcare professionals swift, data-driven advice on antibiotic use. CONCLUSIONS: MALDI-TOF MS and machine learning integration into an AI-CDSS significantly improved rapid SM resistance detection. This system reduced the identification time of resistant strains from 24 h to minutes after MALDI-TOF MS identification, providing timely and data-driven guidance. Combining MALDI-TOF MS with machine learning could enhance clinical decision-making and improve SM infection treatment outcomes.

Monitoring coronavirus disease progression and clinical impact through quantitative viral load testing.

BACKGROUND: The viral load (VL) in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-infected individuals is critical for improving clinical treatment strategies, care, and decisions. Several studies have reported that the initial SARS-CoV-2 VL is associated with disease severity and mortality. Cycle threshold (Ct) values and/or copies/mL are often used to quantify VL. However, a multitude of platforms, primer/probe sets of different SARS-CoV-2 target genes, and reference material manufacturers may cause inconsistent interlaboratory interpretations. The first International Standard for SARS-CoV-2 RNA quantitative assays has allowed diagnostic laboratories to transition SARS-CoV-2 VL results into international units per milliliter (IU/mL). The Cobas SARS-CoV-2 Duo quantitative assay provides VL results expressed in IU/mL. MATERIALS AND METHODS: We enrolled 145 and 50 SARS-CoV-2-positive, hospitalized and 50-negative individuals at the Tri-Service General Hospital, Taiwan from January to May 2022. Each participant's electronic medical record was reviewed to determine asymptomatic, mild, moderate, and severe cases. Nasopharyngeal swabs were collected using universal transport medium. We investigated the association of SARS-CoV-2 VL with disease severity using the Cobas SARS-CoV-2 Duo quantitative assay and its functionality in clinical assessment and decision making to further improve clinical treatment strategies. Limit of detection (LOD) was assessed. RESULTS: All 50 SARS-CoV-2-negative samples confirmed negative for SARS-CoV-2, demonstrating 100 % specificity of the Cobas SARS-CoV-2 Duo assay. Patients with severe symptoms had longer hospital stays, and the length of hospital stay (30.56 days on average) positively correlated with the VL (8.22 ± 1.21 log10 IU/mL). Asymptomatic patients had the lowest VL (5.54 ± 2.06 log10 IU/mL) at admission and the shortest hospital stay (14.1 days on average). CONCLUSIONS: VL is associated with disease severity and duration of hospitalization; therefore, its quantification should be considered when making clinical care decisions and treatment strategies. The Cobas SARS-CoV-2 Duo assay provides a commutable unitage IU/mL for interlaboratory interpretations.

Host-Pathogen Interactions in K. pneumoniae Urinary Tract Infections: Investigating Genetic Risk Factors in the Taiwanese Population.

BACKGROUND: Klebsiella pneumoniae (K. pneumoniae) urinary tract infections pose a significant challenge in Taiwan. The significance of this issue arises because of the growing concerns about the antibiotic resistance of K. pneumoniae. Therefore, this study aimed to uncover potential genomic risk factors in Taiwanese patients with K. pneumoniae urinary tract infections through genome-wide association studies (GWAS). METHODS: Genotyping data are obtained from participants with a history of urinary tract infections enrolled at the Tri-Service General Hospital as part of the Taiwan Precision Medicine Initiative (TPMI). A case-control study employing GWAS is designed to detect potential susceptibility single-nucleotide polymorphisms (SNPs) in patients with K. pneumoniae-related urinary tract infections. The associated genes are determined using a genome browser, and their expression profiles are validated via the GTEx database. The GO, Reactome, DisGeNET, and MalaCards databases are also consulted to determine further connections between biological functions, molecular pathways, and associated diseases between these genes. RESULTS: The results identified 11 genetic variants with higher odds ratios compared to controls. These variants are implicated in processes such as adhesion, protein depolymerization, Ca2+-activated potassium channels, SUMOylation, and protein ubiquitination, which could potentially influence the host immune response. CONCLUSIONS: This study implies that certain risk variants may be linked to K. pneumoniae infections by affecting diverse molecular functions that can potentially impact host immunity. Additional research and follow-up studies are necessary to elucidate the influence of these risk variants on infectious diseases and develop targeted interventions for mitigating the spread of K. pneumoniae urinary tract infections.

Clinical Evaluation of Direct Reverse Transcription PCR for Detection of SARS-CoV-2 Compared to Conventional RT-PCR in Patients with Positive Rapid Antigen Test Results during Circulation of Emerging Viral Variants.

The emergence of the Omicron (B.1.1.529) variant of SARS-CoV-2 has precipitated a new global wave of the COVID-19 pandemic. The rapid identification of SARS-CoV-2 infection is imperative for the effective mitigation of transmission. Diagnostic modalities such as rapid antigen testing and real-time reverse transcription polymerase chain reaction (RT-PCR) offer expedient turnaround times of 10-15 min and straightforward implementation. This preliminary study assessed the correlation between outcomes of commercially available rapid antigen tests for home use and conventional reverse transcription polymerase chain reaction (RT-PCR) assays using a limited set of clinical specimens. Patients aged 5-99 years presenting to the emergency department for SARS-CoV-2 testing were eligible for enrollment (n = 5652). Direct PCR and conventional RT-PCR were utilized for the detection of SARS-CoV-2. The entire cohort of 5652 clinical specimens was assessed by both modalities to determine the clinical utility of the direct RT-PCR assay. Timely confirmation of SARS-CoV-2 infection may attenuate viral propagation and guide therapeutic interventions. Additionally, direct RT-PCR as a secondary confirmatory test for at-home rapid antigen test results demonstrated sensitivity comparable to conventional RT-PCR, indicating utility for implementation in laboratories globally, especially in resource-limited settings with constraints on reagents, equipment, and skilled personnel. In summary, direct RT-PCR enables the detection of SARS-CoV-2 with a sensitivity approaching that of conventional RT-PCR while offering expedient throughput and shorter turnaround times. Moreover, direct RT-PCR provides an open-source option for diagnostic laboratories worldwide, particularly in low- and middle-income countries.

Epidemiology and clinical characteristics of hospitalized adults with respiratory syncytial virus infection at a medical center in northern Taiwan.

The study aimed to describe respiratory syncytial virus infections among hospitalized adults between January 2021 and February 2023 from a single medical center in Taiwan. Clinical information from infected patients with RSV was via medical charts review. The incidence of RSV during the study period among adult inpatients showed seasonal variation and could be up to around 2 % in peak season. Among 19 patients identified, the major comorbidity was chronic heart disease (10/19; 52.6 %) followed by chronic pulmonary disease (5/19; 26.3 %) and diabetes mellitus (5/19; 26.3 %). A quarter of infected patients required intensive care with overall mortality reached 26.3 % and the readmission rates within 30 days after was 15.8 %. Our study results suggests that RSV infections among adults could cause a substantial disease burden on healthcare systems.