Machine-learning based prediction of prognostic risk factors in patients with invasive candidiasis infection and bacterial bloodstream infection: a singled centered retrospective study

The application of machine learning in clinical microbiology and infectious diseases

With the development of artificial intelligence(AI) in computer science and statistics, it has been further applied to the medical field. These applications include the management of infectious diseases, in which machine learning has created inroads in clinical microbiology, radiology, genomics, and the analysis of electronic health record data. Especially, the role of machine learning in microbiology has gradually become prominent, and it is used in etiological diagnosis, prediction of antibiotic resistance, association between human microbiome characteristics and complex host diseases, prognosis judgment, and prevention and control of infectious diseases. Machine learning in the field of microbiology mainly adopts supervised learning and unsupervised learning, involving algorithms from classification and regression to clustering and dimensionality reduction. This Review explains crucial concepts in machine learning for unfamiliar readers, describes machine learning's current applications in clinical microbiology and infectious diseases, and summarizes important approaches clinicians must be aware of when evaluating research using machine learning.

Risk and Prognostic Factors for Bloodstream Infections Due to Clonally Transmitted Acinetobacter baumannii ST2 with armA, blaOXA-23, and blaOXA-66: A Retrospective Study

Background

Multidrug-resistant Acinetobacter baumannii (MDR-AB) is a major cause of bacterial bloodstream infections (BSIs), associated with high morbidity and mortality. The risk and prognostic factors for BSIs caused by clonally transmitted A. baumannii ST2, carrying armA, blaOXA-23 and blaOXA-66, remain unclear.

Methods

We retrospectively analyzed 97 hospitalized patients with A. baumannii BSI (January 2019-May 2022). Whole-genome sequencing and bioinformatic analysis characterized the strains. Clinical data were reviewed to identify risk factors for secondary BSIs, A. baumannii BSIs with mixed infections involving extra-bloodstream pathogens, and mortality predictors.

Results

High-risk clone sequence type (ST) 2 was identified in 87 isolates (89.7%), with 86 exhibiting clonal dissemination. Carbapenems and aminoglycosides resistance occurred in 78.4% of strains, linked to armA, blaOXA-23, and blaOXA-66. Patients' median age was 56.6 years (range: 11-93), with males comprising 62.9%. Elderly patients (>65 years) accounted for 40.2%, 85.6% had hospital stays >10 days, and 84.5% had ICU admissions. Adverse outcomes were observed in 55.7% of cases. ICU admission (OR = 5.144, 95% CI: 1.290-20.511, P = 0.020) and open injury (OR = 5.998, 95% CI: 1.164-30.892, P = 0.032) were specific risk factors significantly associated with BSIs, while the presence of three or more underlying diseases (OR = 6.419, 95% CI: 2.074-19.866, P = 0.001) was significantly associated with increased mortality risk.

Conclusion

The majority of A. baumannii strains causing BSIs in this study belonged to multidrug-resistant ST2 lineage, harboring armA, blaOXA-23 and blaOXA-66. Risk factors for secondary and mixed infections included prolonged ICU stays, mechanical ventilation (≥7 days), and open injuries, while poor prognosis was linked to severe comorbidities and extended invasive ventilation. Targeted infection control strategies are critical to reducing mechanical ventilation duration and managing open injuries in high-risk patients.

Artificial intelligence in hospital infection prevention: an integrative review

Background

Hospital-acquired infections (HAIs) represent a persistent challenge in healthcare, contributing to substantial morbidity, mortality, and economic burden. Artificial intelligence (AI) offers promising potential for improving HAIs prevention through advanced predictive capabilities.

Objective

To evaluate the effectiveness, usability, and challenges of AI models in preventing, detecting, and managing HAIs.

Methods

This integrative review synthesized findings from 42 studies, guided by the SPIDER framework for inclusion criteria. We assessed the quality of included studies by applying the TRIPOD checklist to individual predictive studies and the AMSTAR 2 tool for reviews.

Results

AI models demonstrated high predictive accuracy for the detection, surveillance, and prevention of multiple HAIs, with models for surgical site infections and urinary tract infections frequently achieving area-under-the-curve (AUC) scores exceeding 0.80, indicating strong reliability. Comparative data suggest that while both machine learning and deep learning approaches perform well, some deep learning models may offer slight advantages in complex data environments. Advanced algorithms, including neural networks, decision trees, and random forests, significantly improved detection rates when integrated with EHRs, enabling real-time surveillance and timely interventions. In resource-constrained settings, non-real-time AI models utilizing historical EHR data showed considerable scalability, facilitating broader implementation in infection surveillance and control. AI-supported surveillance systems outperformed traditional methods in accurately identifying infection rates and enhancing compliance with hand hygiene protocols. Furthermore, Explainable AI (XAI) frameworks and interpretability tools such as Shapley additive explanations (SHAP) values increased clinician trust and facilitated actionable insights. AI also played a pivotal role in antimicrobial stewardship by predicting the emergence of multidrug-resistant organisms and guiding optimal antibiotic usage, thereby reducing reliance on second-line treatments. However, challenges including the need for comprehensive clinician training, high integration costs, and ensuring compatibility with existing workflows were identified as barriers to widespread adoption.

Discussion

The integration of AI in HAI prevention and management represents a potentially transformative shift in enhancing predictive capabilities and supporting effective infection control measures. Successful implementation necessitates standardized validation protocols, transparent data reporting, and the development of user-friendly interfaces to ensure seamless adoption by healthcare professionals. Variability in data sources and model validations across studies underscores the necessity for multicenter collaborations and external validations to ensure consistent performance across diverse healthcare environments. Innovations in non-real-time AI frameworks offer viable solutions for scaling AI applications in low- and middle-income countries (LMICs), addressing the higher prevalence of HAIs in these regions.

Conclusions

Artificial Intelligence stands as a transformative tool in the fight against hospital-acquired infections, offering advanced solutions for prevention, surveillance, and management. To fully realize its potential, the healthcare sector must prioritize rigorous validation standards, comprehensive data quality reporting, and the incorporation of interpretability tools to build clinician confidence. By adopting scalable AI models and fostering interdisciplinary collaborations, healthcare systems can overcome existing barriers, integrating AI seamlessly into infection control policies and ultimately enhancing patient safety and care quality. Further research is needed to evaluate cost-effectiveness, real-world applications, and strategies (e.g., clinician training and the integration of explainable AI) to improve trust and broaden clinical adoption.

In silico method and bioactivity evaluation to discover novel antimicrobial agents targeting FtsZ protein: Machine learning, virtual screening and antibacterial mechanism study

This research paper utilizes a fused-in-silico approach alongside bioactivity evaluation to identify active FtsZ inhibitors for drug discovery. Initially, ROC-guided machine learning was employed to obtain almost 13182 compounds from three libraries. After conducting virtual screening to assess the affinity of 2621 acquired compounds, cluster analysis and bonding model analysis led to the discovery of five hit compounds. Additionally, antibacterial activity assays and time-killing kinetics revealed that T3995 could eliminate Staphylococcus aureus ATCC6538 and Bacillus subtilis ATCC9732, with MIC values of 32 and 2 μg/mL. Further morphology and FtsZ polymerization assays indicated that T3995 could be an antimicrobial inhibitor by targeting FtsZ protein. Moreover, hemolytic toxicity evaluation demonstrated that T3995 is safe at or below 16 ug/mL concentration. Additionally, bonding model analysis explained how the compound T3995 can display antimicrobial activity by targeting the FtsZ protein. In conclusion, this study presents a promising FtsZ inhibitor that was discovered through a fused computer method and bioactivity evaluation.

Machine Learning Models in Sepsis Outcome Prediction for ICU Patients: Integrating Routine Laboratory Tests-A Systematic Review

Background. Sepsis presents significant diagnostic and prognostic challenges, and traditional scoring systems, such as SOFA and APACHE, show limitations in predictive accuracy. Machine learning (ML)-based predictive survival models can support risk assessment and treatment decision-making in the intensive care unit (ICU) by accounting for the numerous and complex factors that influence the outcome in the septic patient. Methods. A systematic literature review of studies published from 2014 to 2024 was conducted using the PubMed database. Eligible studies investigated the development of ML models incorporating commonly available laboratory and clinical data for predicting survival outcomes in adult ICU patients with sepsis. Study selection followed the PRISMA guidelines and relied on predefined inclusion criteria. All records were independently assessed by two reviewers, with conflicts resolved by a third senior reviewer. Data related to study design, methodology, results, and interpretation of the results were extracted in a predefined grid. Results. Overall, 19 studies were identified, encompassing primarily logistic regression, random forests, and neural networks. Most used datasets were US-based (MIMIC-III, MIMIC-IV, and eICU-CRD). The most common variables used in model development were age, albumin levels, lactate levels, and ventilator. ML models demonstrated superior performance metrics compared to conventional methods and traditional scoring systems. The best-performing model was a gradient boosting decision tree, with an area under curve of 0.992, an accuracy of 0.954, and a sensitivity of 0.917. However, several critical limitations should be carefully considered when interpreting the results, such as population selection bias (i.e., single center studies), small sample sizes, limited external validation, and model interpretability. Conclusions. Through real-time integration of routine laboratory and clinical data, ML-based tools can assist clinical decision-making and enhance the consistency and quality of sepsis management across various healthcare contexts, including ICUs with limited resources.

Advancing Patient Safety: The Future of Artificial Intelligence in Mitigating Healthcare-Associated Infections: A Systematic Review

BACKGROUND

Healthcare-associated infections are infections that patients acquire during hospitalization or while receiving healthcare in other facilities. They represent the most frequent negative outcome in healthcare, can be entirely prevented, and pose a burden in terms of financial and human costs. With the development of new AI and ML algorithms, hospitals could develop new and automated surveillance and prevention models for HAIs, leading to improved patient safety. The aim of this review is to systematically retrieve, collect, and summarize all available information on the application and impact of AI in HAI surveillance and/or prevention.

METHODS

We conducted a systematic review of the literature using PubMed and Scopus to find articles related to the implementation of artificial intelligence in the surveillance and/or prevention of HAIs.

RESULTS

We identified a total of 218 articles, of which only 35 were included in the review. Most studies were conducted in the US (n = 10, 28.6%) and China (n = 5; 14.3%) and were published between 2021 and 2023 (26 articles, 74.3%) with an increasing trend over time. Most focused on the development of ML algorithms for the identification/prevention of surgical site infections (n = 18; 51%), followed by HAIs in general (n = 9; 26%), hospital-acquired urinary tract infections (n = 5; 9%), and healthcare-associated pneumonia (n = 3; 9%). Only one study focused on the proper use of personal protective equipment (PPE) and included healthcare workers as the study population. Overall, the trend indicates that several AI/ML models can effectively assist clinicians in everyday decisions, by identifying HAIs early or preventing them through personalized risk factors with good performance. However, only a few studies have reported an actual implementation of these models, which proved highly successful. In one case, manual workload was reduced by nearly 85%, while another study observed a decrease in the local hospital's HAI incidence from 1.31% to 0.58%.

CONCLUSIONS

AI has significant potential to improve the prevention, diagnosis, and management of healthcare-associated infections, offering benefits such as increased accuracy, reduced workloads, and cost savings. Although some AI applications have already been tested and validated, adoption in healthcare is hindered by barriers such as high implementation costs, technological limitations, and resistance from healthcare workers. Overcoming these challenges could allow AI to be more widely and cost-effectively integrated, ultimately improving patient care and infection management.

A machine learning model for early candidemia prediction in the intensive care unit: Clinical application

Candidemia often poses a diagnostic challenge due to the lack of specific clinical features, and delayed antifungal therapy can significantly increase mortality rates, particularly in the intensive care unit (ICU). This study aims to develop a machine learning predictive model for early candidemia diagnosis in ICU patients, leveraging their clinical information and findings. We conducted this study with a cohort of 334 patients admitted to the ICU unit at Ji Ning NO.1 people's hospital in China from Jan. 2015 to Dec. 2022. To ensure the model's reliability, we validated this model with an external group consisting of 77 patients from other sources. The candidemia to bacteremia ratio is 1:1. We collected relevant clinical procedures and eighteen key examinations or tests features to support the recursive feature elimination (RFE) algorithm. These features included total bilirubin, age, platelet count, hemoglobin, CVC, lymphocyte, Duration of stay in ICU and so on. To construct the candidemia diagnosis model, we employed random forest (RF) algorithm alongside other machine learning methods and conducted internal and external validation with training and testing sets allocated in a 7:3 ratio. The RF model demonstrated the highest area under the receiver operating characteristic (AUC) with values of 0.87 and 0.83 for internal and external validation, respectively. To evaluate the importance of features in predicting candidemia, Shapley additive explanation (SHAP) values were calculated and results revealed that total bilirubin and age were the most important factors in the prediction model. This advancement in candidemia prediction holds significant promise for early intervention and improved patient outcomes in the ICU setting, where timely diagnosis is of paramount crucial.

Global Epidemiology of Invasive Infections by Uncommon Candida Species: A Systematic Review

Emerging and uncommon Candida species have been reported as an increasing cause of invasive Candida infections (ICI). We aim to systematize the global epidemiology associated with emergent uncommon Candida species responsible for invasive infections in adult patients. A systematic review (from 1 January 2001 to 28 February 2023) regarding epidemiological, clinical, and microbiological data associated to invasive Candida infections by uncommon Candida spp. were collected. In total, 1567 publications were identified, and 36 were selected according to inclusion criteria (45 cases). The chosen studies covered: C. auris (n = 21), C. haemulonii (n = 6), C. fermentati (n = 4), C. kefyr (n = 4), C. norvegensis (n = 3), C. nivariensis (n = 3), C. bracarensis (n = 1), C. duobushaemulonii (n = 1), C. blankii (n = 1), and C. khanbhai (n = 1). Over the recent years, there has been an increase in the number of invasive infections caused by uncommon Candida spp. Asia and Europe are the continents with the most reported cases. The challenges in strain identification and antifungal susceptibility interpretation were significant. The absence of clinical breakpoints for the susceptibility profile determination for uncommon Candida spp. makes interpretation and treatment options a clinical challenge. It is crucial that we focus on new and accessible microbiology techniques to make fast and accurate diagnostics and treatments.

Knowledge and acceptance of artificial intelligence and its applications among the physicians working in military medical centers affiliated with Aja University: A cross-sectional study

BACKGROUND

The use of artificial intelligence (AI) in medical sciences promises many benefits. Applying the benefits of this science in developing countries is still in the development stage. This important point depends considerably on the knowledge and acceptance levels of physicians.

MATERIALS AND METHODS

This study was a cross-sectional descriptive-analytical study that was conducted on 169 medical doctors using a purposive sampling method. To collect data, questionnaires were used to obtain demographic characteristics, a questionnaire to investigate the knowledge of AI and its applications, and an acceptability questionnaire to investigate AI. For data analysis, SPSS (Statistical Package for the Social Sciences) version 22 and appropriate descriptive and inferential statistical tests were used, and a significance level of < 0.05 was considered.

RESULTS

Most of the participants (102) were male (60.4%), married (144) (85.20%), had specialized doctorate education (97) (57.4%), and had average work experience of 10.78 ± 6.67 years. The mean and standard deviation of knowledge about AI were 9.54 ± 3.04, and acceptability was 81.64 ± 13.83. Multiple linear regressions showed that work history (P = 0.017) and history of participation in AI training courses (P = 0.007) are effective in knowledge and acceptability of AI.

CONCLUSION

The knowledge and acceptability of the use of AI among the studied physicians were at an average level. However, due to the importance of using AI in medical sciences and the inevitable use of this technology in the near future, especially in medical sciences in crisis, war, and military conditions, it is necessary for the policymakers of the health system to improve the knowledge and methods of working with this technology in the medical staff in addition to providing the infrastructure.

Risk Factors for 30-Day Mortality of Community-Acquired Bloodstream Infection Patients in Changsha City, Hunan Province, China

Purpose

To analyze the factors affecting patients' prognoses based on the community acquired-bloodstream infection patient data from 2017 to 2021.

Patients and Methods

The data of 940 patients were retrieved, having at least one positive bilateral blood culture within 48 hours of hospitalization, and grouped into survivor and non-survivor groups. The clinical characteristics, laboratory results, causative pathogen and other indicators were collected and compared, and risk factors were identified by applying Cox proportional hazard regression model to the data.

Results

Community acquired-bloodstream infection is most commonly caused by Escherichia coli, Klebsiella species and Staphylococcus hominis. Among the total of 940 selected patients, 52 (5.5%) died during hospitalization. The demographic parameters like age and gender, clinical protocols like maintenance hemodialysis, glucocorticoid use during hospitalization, catheter placement, procaicitonin, total protein, albumin, creatinine, uric acid contents and Sequential Organ Failure Assessment scores were significantly different between the survivor and non-survivor groups. The survival analysis results revealed that age (HR=1.02, 95% CI: 1.00-1.05, P=0.002), glucocorticoid use during hospitalization (HR=3.69, 95% CI: 1.62-8.37, P=0.021) and Sequential Organ Failure Assessment score (HR=1.10, 95% CI: 1.03-1.18, P=0.004) might be the risk factors affecting 30-day mortality in patients with community acquired-bloodstream infection.

Conclusion

The identified risk factors may help guide clinical treatment protocol for patients with community acquired-bloodstream infection, providing more effective treatment strategy selection with improved clinical outcomes.

Prediction of candidemia with machine learning techniques: state of the art

In this narrative review, we discuss studies assessing the use of machine learning (ML) models for the early diagnosis of candidemia, focusing on employed models and the related implications. There are currently few studies evaluating ML techniques for the early diagnosis of candidemia as a prediction task based on clinical and laboratory features. The use of ML tools holds promise to provide highly accurate and real-time support to clinicians for relevant therapeutic decisions at the bedside of patients with suspected candidemia. However, further research is needed in terms of sample size, data quality, recognition of biases and interpretation of model outputs by clinicians to better understand if and how these techniques could be safely adopted in daily clinical practice.

Hospital Acquired Sepsis, Disease Prevalence, and Recent Advances in Sepsis Mitigation

Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection, commonly associated with nosocomial transmission. Gram-negative bacterial species are particularly problematic due to the release of the lipopolysaccharide toxins upon cell death. The lipopolysaccharide toxin of E. coli has a greater immunogenic potential than that of other Gram-negative bacteria. The resultant dysregulation of the immune system is associated with organ failure and mortality, with pregnant women, ICU patients, and neonates being particularly vulnerable. Additionally, sepsis recovery patients have an increased risk of re-hospitalisation, chronic illness, co-morbidities, organ damage/failure, and a reduced life expectancy. The emergence and increasing prevalence of antimicrobial resistance in bacterial and fungal species has impacted the treatment of sepsis patients, leading to increasing mortality rates. Multidrug resistant pathogens including vancomycin-resistant Enterococcus, beta lactam-resistant Klebsiella, and carbapenem-resistant Acinetobacter species are associated with an increased risk of mortality. To improve the prognosis of sepsis patients, predominantly high-risk neonates, advances must be made in the early diagnosis, triage, and control of sepsis. The identification of suitable biomarkers and biomarker combinations, coupled with machine learning and artificial intelligence, show promise in early detection protocols. Rapid diagnosis of sepsis in patients is essential to inform on clinical treatment, especially with resistant infectious agents. This timely review aims to discuss sepsis prevalence, aetiology, and recent advances towards disease mitigation and control.

Mitochondrial phosphate carrier plays an important role in virulence of Candida albicans

Candida albicans is a common fungal pathogen that can cause life-threatening infections. MIR1 is considered to be a mitochondrial phosphate carrier of C. albicans, while its role in virulence has not been fully elucidated. In this study, we found that mir1Δ/Δ mutant exhibited severe virulence defect in both nematode and murine models. Further mechanism studies revealed that the mir1Δ/Δ mutant grew more slowly than the wild-type strain and showed severe filamentation defects on the hypha-inducing agar media, including YPD + serum, Lee, Spider + glucose, SLAD, SLD, and YPS. Furthermore, the loss of MIR1 resulted in unfermentable carbon utilisation defect, ATP decrease, and reactive oxygen species (ROS) accumulation in C. albicans. Antioxidant proanthocyanidins, vitamin E, and N-acetyl cysteine (NAC) could reduce intracellular ROS levels and partially rescue the filamentation defects of the mir1Δ/Δ mutant. Accordingly, hypha-specific genes, as well as CEK1 and RIM101 were down-regulated in the mir1Δ/Δ mutant, and this down-regulation could be partially rescued by the addition of the antioxidant NAC. Collectively, MIR1 plays an important role in C. albicans mitochondrial function, filamentation and virulence, and would be a promising antifungal target.

Efficacy of Random Forest Models in Predicting Multidrug-Resistant Gram-Negative Bacterial Nosocomial Infections Compared to Traditional Logistic Regression Models

This study evaluates whether random forest (RF) models are as effective as traditional Logistic Regression (LR) models in predicting multidrug-resistant Gram-negative bacterial nosocomial infections. Data were collected from 541 patients with hospital-acquired Gram-negative bacterial infections at two tertiary-level hospitals in Urumqi, Xinjiang, China, from August 2022 to November 2023. Relevant literature informed the selection of significant predictors based on patients' pre-infection clinical information and medication history. The data were split into a training set of 379 cases and a validation set of 162 cases, adhering to a 7:3 ratio. Both RF and LR models were developed using the training set and subsequently evaluated on the validation set. The LR model achieved an accuracy of 84.57%, sensitivity of 82.89%, specificity of 80.10%, positive predictive value of 84%, negative predictive value of 85.06%, and a Yoden index of 0.69. In contrast, the RF model demonstrated superior performance with an accuracy of 89.51%, sensitivity of 90.79%, specificity of 88.37%, positive predictive value of 87.34%, negative predictive value of 91.57%, and a Yoden index of 0.79. Receiver operating characteristic curve analysis revealed an area under the curve of 0.91 for the LR model and 0.94 for the RF model. These findings indicate that the RF model surpasses the LR model in specificity, sensitivity, and accuracy in predicting hospital-acquired multidrug-resistant Gram-negative infections, showcasing its greater potential for clinical application.

Applications of artificial intelligence in the field of oral and maxillofacial pathology: a systematic review and meta-analysis

BACKGROUND

Since AI algorithms can analyze patient data, medical records, and imaging results to suggest treatment plans and predict outcomes, they have the potential to support pathologists and clinicians in the diagnosis and treatment of oral and maxillofacial pathologies, just like every other area of life in which it is being used. The goal of the current study was to examine all of the trends being investigated in the area of oral and maxillofacial pathology where AI has been possibly involved in helping practitioners.

METHODS

We started by defining the important terms in our investigation's subject matter. Following that, relevant databases like PubMed, Scopus, and Web of Science were searched using keywords and synonyms for each concept, such as "machine learning," "diagnosis," "treatment planning," "image analysis," "predictive modelling," and "patient monitoring." For more papers and sources, Google Scholar was also used.

RESULTS

The majority of the 9 studies that were chosen were on how AI can be utilized to diagnose malignant tumors of the oral cavity. AI was especially helpful in creating prediction models that aided pathologists and clinicians in foreseeing the development of oral and maxillofacial pathology in specific patients. Additionally, predictive models accurately identified patients who have a high risk of developing oral cancer as well as the likelihood of the disease returning after treatment.

CONCLUSIONS

In the field of oral and maxillofacial pathology, AI has the potential to enhance diagnostic precision, personalize care, and ultimately improve patient outcomes. The development and application of AI in healthcare, however, necessitates careful consideration of ethical, legal, and regulatory challenges. Additionally, because AI is still a relatively new technology, caution must be taken when applying it to this industry.

Procalcitonin and C-reactive protein as diagnostic biomarkers in COVID-19 and Non-COVID-19 sepsis patients: a comparative study

BACKGROUND

This study aimed to assess and compare procalcitonin (PCT) and C-reactive protein (CRP) levels between COVID-19 and non-COVID-19 sepsis patients. Additionally, we evaluated the diagnostic efficiency of PCT and CRP in distinguishing between Gram-positive (GP) and Gram-negative (GN) bacterial infections. Moreover, we explored the associations of PCT with specific pathogens in this context.

METHODS

The study included 121 consecutive sepsis patients who underwent blood culture testing during the COVID-19 epidemic. PCT and CRP were measured, and reverse transcriptase-polymerase chain reaction (RT-PCR) was employed for the detection of COVID-19 nucleic acid. The Mann-Whitney U-test was used to compare PCT and CRP between the COVID-19 and non-COVID-19 groups. Receiver operating characteristic (ROC) curves were generated to compare PCT and CRP levels in the GN group versus the GP group for assessing the diagnostic efficiency. The kruskal-Wallis H test was applied to assess the impact of specific pathogen groups on PCT concentrations.

RESULTS

A total of 121 sepsis patients were categorized into a COVID-19 group (n = 25) and a non-COVID-19 group (n = 96). No significant differences in age and gender were observed between the COVID-19 and non-COVID-19 groups. The comparison of biomarkers between these groups showed no statistically significant differences. The optimal cut-off values for PCT and CRP in differentiating between GP and GN infections were 1.03 ng/mL and 34.02 mg/L, respectively. The area under the ROC curve was 0.689 (95% confidence interval (CI) 0.591-0.786) for PCT and 0.611 (95% CI 0.505-0.717) for CRP. The diagnostic accuracy was 69.42% for PCT and 58.69% for CRP. The study found a significant difference in PCT levels among specific groups of pathogens (P < 0.001), with the highest levels observed in Escherichia coli infections. The frequency of Staphylococcus spp. positive results was significantly higher (36.0%) in COVID-19 compared to non-COVID-19 sepsis patients (P = 0.047).

CONCLUSION

Sepsis patients with COVID-19 revealed a significantly higher culture positivity for staphylococcus spp. than the non-COVID-19 group. Both PCT and CRP showed moderate diagnostic efficiency in differentiating between GP and GN bacterial infections. PCT showed potential utility in identifying E. coli infections compared to other pathogens.

Invasive Candidiasis in Patients with Solid Tumors: A Single-Center Retrospective Study

Background

Invasive candidiasis (ICs) is one of the common causes of death in patients with solid tumors. However, studies on the clinical characteristics of ICs with solid tumors are limited.

Methods

The purpose of this study was to retrospectively analyse the clinical characteristics, laboratory results and risk factor prediction of inpatients with ICs and solid tumors. We reviewed the clinical data and candida specimen information of hospitalized patients diagnosed with solid tumors combined with ICs at the First Hospital of China Medical University from January 2016 to December 2020. Multivariate logistic regression analysis was used to assess the prognostic factors associated with mortality in these patients.

Results

A total of 243 ICs patients with solid tumors were included in this study. The average ± SD age was 62.8 ± 11.7 (range: 27-93 years old), of which nearly 41% were ≥ 65 years old (99/243, 40.7%), and most were male (162/243, 66.6%). Most patients had malignant tumors of the digestive system. The most common candida was Candida parapsilosis (101/243, 41.5%), followed by Candida guilliermondii (83/243, 34.1%), Candida albicans (32/243, 13.1%), Candida glabrata (17/243, 6.9%), Candida tropicalis (7/243, 2.8%) and Candida krusei (3/243, 1.2%). Multivariate logistic regression analysis showed that the length of stay in the ICU, urinary catheter, total parenteral nutrition, stay in the ICU, renal failure and neutrophil count were prognostic factors related to death.

Conclusion

In this study, based on the clinical data of solid tumor patients with ICs in the past 5 years, the results showed that the length of stay in the ICU, urinary catheter, total parenteral nutrition, stay in the ICU, renal failure and neutrophil count were identified as the main prognostic factors. This study can be used to help clinicians carry out early intervention for high-risk patients.

Periodontitis is associated with the development of fungal sinusitis: A nationwide 12-year follow-up study

AIM

The incidence of fungal sinusitis is increasing; however, its pathophysiology has not been investigated previously. We investigate the effect of periodontitis on the incidence of fungal sinusitis over a 12-year follow-up period using nationwide population-based data.

MATERIALS AND METHODS

The periodontitis group was randomly selected from the National Health Insurance Service database. The non-periodontitis group was obtained by propensity score matching considering several variables. The primary end point was the diagnosis of sinonasal fungal balls (SFBs) and invasive fungal sinusitis (IFS).

RESULTS

The periodontitis and non-periodontitis groups included 12,442 and 12,442 individuals, respectively. The overall adjusted hazard ratio (aHR) for SFBs in the periodontitis group was 1.46 (p = .002). In subgroup analysis, the aHR for SFBs was 1.59 (p = 0.008) for those with underlying chronic kidney disease (CKD), 1.58 (p = .022) for those with underlying atopic dermatitis, 1.48 (p = .019) for those with chronic obstructive pulmonary disease (COPD), and 1.36 (p = .030) for those with diabetes mellitus (DM), but these values are applicable only when considering the relationship between periodontitis and SFB. The aHR for IFS in the periodontitis group was higher than in the non-periodontitis group (2.80; p = .004).

CONCLUSIONS

The risk of SFBs and IFS increased after diagnosis of periodontitis. This trend is often more severe in patients with DM, COPD, or CKD, but this association with underlying diseases is applicable only when considering the association between periodontitis and fungal sinusitis.

Random forest model can predict the prognosis of hospital-acquired Klebsiella pneumoniae infection as well as traditional logistic regression model

OBJECTIVE

To explore if random forest (RF) model can predict the prognosis of hospital-acquired Klebsiella pneumoniae infection as well as traditional logistic regression(LR) model.

METHODS

A total of 254 cases of hospital-acquired Klebsiella pneumoniae infection in a tertiary hospital in Beijing from January 2016 to December 2020 were retrospectively collected. Appropriate influencing factors were selected by referring to relevant articles from the aspects of basic clinical information and contact history before infection, and divided into a training set and a test set. Both the RF and LR models were trained by the training set, and using testing set to compare these two models.

RESULTS

The prediction accuracy of the LR model was 87.0%, the true positive rate of the LR model was 94.7%; the false negative rate of the LR model was 5.3%; the false positive rate of the LR model was 35%; the true negative rate of the LR model was 65%; the sensitivity of the LR model for the prognosis prediction of hospital-acquired Klebsiella pneumoniae infection was 94.7%; and the specificity was 65%. The prediction accuracy of the RF model was 89.6%; the true positive rate of the RF model was 92.1%; the false negative rate of the RF model was 7.9%; the false positive rate of the RF model was 21.4%; the true negative rate of the RF model was 78.6%; the sensitivity of the RF model for the prognosis prediction of hospital-acquired Klebsiella pneumoniae infection was 92.1%; and the specificity was 78.6%. ROC curve shows that the area under curve(AUC) of the LR model was 0.91, and that of the RF model was 0.95.

CONCLUSION

The RF model has higher specificity, sensitivity, and accuracy for the prognostic prediction of hospital-acquired Klebsiella pneumoniae infection than the LR model and has greater clinical application prospects.

Prediction of Prognostic Risk Factors in Patients with Invasive Candidiasis and Cancer: A Single-Centre Retrospective Study

Background

Invasive candidiasis is a common cancer-related complication with a high fatality rate. If patients with a high risk of dying in the hospital are identified early and accurately, physicians can make better clinical judgments. However, epidemiological analyses and mortality prediction models of cancer patients with invasive candidiasis remain limited.

Method

A set of 40 potential risk factors was acquired in a sample of 258 patients with both invasive candidiasis and cancer. To begin, risk factors for Candida albicans vs. non-Candida albicans infections and persistent vs. nonpersistent Candida infections were analysed using classic statistical methods. Then, we applied three machine learning models (random forest, logistic regression, and support vector machine) to identify prognostic indicators related to mortality. Prediction performance of different models was assessed by precision, recall, F1 score, accuracy, and AUC.

Results

Of the 258 patients both with invasive candidiasis and cancer included in the analysis. The median age of patients was 62 years, and 95 (36.82%) patients were older than 65 years, of which 178 (66.28%) were male. And 186 (72.1%) patients underwent surgery 2 weeks before data collection, 100 (39.1%) patients stayed in ICU during hospitalisation, 99 (38.4%) patients had bacterial blood infection, 85 (32.9%) patients had persistent invasive candidiasis, and 41 (15.9%) patients died within 30 days. The usage of drainage catheter and prolonged length of hospitalisation are the dominant risk factors for non-Candida albicans infections and persistent Candida infections, respectively. Risk factors, such as septic shock, history of surgery within the past 2 weeks, usage of drainage tubes, length of stay in ICU, total parenteral nutrition, serum creatinine level, fungal antigen, stay in ICU during hospitalisation, and total bilirubin level, were significant predictors of death. The RF model outperformed the LR and SVM models. Precision, recall, F1 score, accuracy, and AUC for RF were 64.29%, 75.63%, 69.23%, 89.61%, and 91.28%.

Conclusions

In this study, the machine learning-based models accurately predicted the prognosis of cancer and invasive candidiasis patients. The algorithm could be used to help clinicians in high-risk patients' early intervention.

Diagnoses Based on C-Reactive Protein Point-of-Care Tests

C-reactive protein (CRP) is an important part of the immune system's reaction to various pathological impulses such as bacterial infections, systemic inflammation, and internal organ failures. An increased CRP level serves to diagnose the mentioned pathological states. Both standard laboratory methods and simple point-of-care devices such as lateral flow tests and immunoturbidimetric assays serve for the instrumental diagnoses based on CRP. The current method for CRP has many flaws and limitations in its use. Biosensor and bioassay analytical devices are presently researched by many teams to provide more sensitive and better-suited tools for point-of-care tests of CRP in biological samples when compared to the standard methods. This review article is focused on mapping the diagnostical relevance of CRP, the applicability of the current analytical methods, and the recent innovations in the measurement of CRP level.