Systematic review on the definition and predictors of severe Clostridiodes difficile infection

Machine Learning-Based Prediction Models for Clostridioides difficile Infection: A Systematic Review

INTRODUCTION

Despite research efforts, predicting Clostridioides difficile incidence and its outcomes remains challenging. The aim of this systematic review was to evaluate the performance of machine learning (ML) models in predicting C. difficile infection (CDI) incidence and complications using clinical data from electronic health records.

METHODS

We conducted a comprehensive search of databases (OVID, Embase, MEDLINE ALL, Web of Science, and Scopus) from inception up to September 2023. Studies employing ML techniques for predicting CDI or its complications were included. The primary outcome was the type and performance of ML models assessed using the area under the receiver operating characteristic curve.

RESULTS

Twelve retrospective studies that evaluated CDI incidence and/or outcomes were included. The most commonly used ML models were random forest and gradient boosting. The area under the receiver operating characteristic curve ranged from 0.60 to 0.81 for predicting CDI incidence, 0.59 to 0.80 for recurrence, and 0.64 to 0.88 for predicting complications. Advanced ML models demonstrated similar performance to traditional logistic regression. However, there was notable heterogeneity in defining CDI and the different outcomes, including incidence, recurrence, and complications, and a lack of external validation in most studies.

DISCUSSION

ML models show promise in predicting CDI incidence and outcomes. However, the observed heterogeneity in CDI definitions and the lack of real-world validation highlight challenges in clinical implementation. Future research should focus on external validation and the use of standardized definitions across studies.

The Strain and the Clinical Outcome of Clostridioides difficile Infection: A Meta-analysis

Background

The association between bacterial strains and clinical outcomes in Clostridioides difficile infection (CDI) has yielded conflicting results across studies. We conducted a systematic review and meta-analyses to assess the impact of these strains.

Methods

Five electronic databases were used to identify studies reporting CDI severity, complications, recurrence, or mortality according to strain type from inception to June 2022. Random effect meta-analyses were conducted to assess outcome proportions and risk ratios (RRs).

Results

A total of 93 studies were included: 44 reported recurrences, 50 reported severity or complications, and 55 reported deaths. Pooled proportions of complications were statistically comparable between NAP1/BI/R027 and R001, R078, and R106. Pooled attributable mortality was 4.8% with a gradation in patients infected with R014/20 (1.7%), R001 (3.8%), R078 (5.3%), and R027 (10.2%). Higher 30-day all-cause mortality was observed in patients infected with R001, R002, R027, and R106 (range, 20%-25%).NAP1/BI/R027 was associated with several unfavorable outcomes: recurrence 30 days after the end of treatment (pooled RR, 1.98; 95% CI, 1.02-3.84); admission to intensive care, colectomy, or CDI-associated death (1.88; 1.09-3.25); and 30-day attributable mortality (1.96; 1.23-3.13). The association between harboring the binary toxin gene and 30-day all-cause mortality did not reach significance (RR, 1.6 [0.9-2.9]; 7 studies).

Conclusions

Numerous studies were excluded due to discrepancies in the definition of the outcomes and the lack of reporting of important covariates. NAP1/BI/R027, the most frequently reported and assessed strain, was associated with unfavorable outcomes. However, there were not sufficient data to reach significant conclusions on other strains.

Clostridioides difficile Infection: Clinical Practice and Health Outcomes in 6 Large Tertiary Hospitals in Eastern Australia

Background

Clostridioides difficile infection (CDI) is associated with significant morbidity and mortality in both healthcare and community settings. We aimed to define the predisposing factors, risks for severe disease, and mortality determinants of CDI in eastern Australia over a 1-year period.

Methods

This is an observational retrospective study of CDI in hospitalized patients aged ≥18 years in 6 tertiary institutions from 1 January 2016 to 31 December 2016. Patients were identified through laboratory databases and medical records of participating institutions. Clinical, imaging, and laboratory data were input into an electronic database hosted at a central site.

Results

A total of 578 patients (578 CDI episodes) were included. Median age was 65 (range, 18-99) years and 48.2% were male. Hospital-onset CDI occurred in 64.0%. Recent antimicrobial use (41.9%) and proton pump inhibitor use (35.8%) were common. Significant risk factors for severe CDI were age <65 years (P < .001), malignancy within the last 5 years (P < .001), and surgery within the previous 30 days (P < .001). Significant risk factors for first recurrence included severe CDI (P = .03) and inflammatory bowel disease (P = .04). Metronidazole was the most common regimen for first episodes of CDI with 65.2% being concordant with Australian treatment guidelines overall. Determinants for death at 60 days included age ≥65 years (P = .01), severe CDI (P < .001), and antibiotic use within the prior 30 days (P = .02). Of those who received metronidazole as first-line therapy, 10.1% died in the 60-day follow-up period, compared to 9.8% of those who received vancomycin (P = .86).

Conclusions

Patients who experience CDI are vulnerable and require early diagnosis, clinical surveillance, and effective therapy to prevent complications and improve outcomes.

Performance of Clostridioides difficile infection severity scores and risk factors related to 30-day all-cause mortality in patients with cancer

PURPOSE

There are currently no standard definitions for assessing the severity of Clostridioides difficile infection (CDI) in cancer patients. We evaluated the performance of scoring systems for severity and analyzed risk factors for mortality in a cancer cohort.

METHODS

We conducted an observational study in patients with cancer and CDI. We calculated the incidence of hospital-onset (HO-CDI) and community-onset health-care facility associated (CO-HCFA-CDI) episodes. We classified severity using five prognostic scales and calculated sensitivity, specificity, positive (PPV), and negative predictive values (NPV) for mortality and intensive care unit (ICU) admission. In addition, multivariate regression was performed to assess variables associated with mortality.

RESULTS

The HO-CDI and CO-HCFA-CDI incidence rates were 3.7 cases/10,000 patient-days and 1.9 cases/1,000 admissions, respectively. ESCMID criteria showed the higher sensitivity (97%, 95% CI; 85-100%) and NPV (98%, 95% CI; 85-100%), while ATLAS (≥ 6 points) had the highest specificity (95%, 95% CI; 90-98%) for 30-day all-cause mortality; similar performance was observed for ICU admission. Characteristics associated with fatal outcome were neutropenia (≤ 100 cells/ml) (aOR; 3.03, 95% CI; 1.05-8.74, p = 0.040), male gender (aOR; 2.90, 95% CI; 1.08-7.80, p = 0.034), high serum creatinine (aOR; 1.71, 95% CI; 1.09-2.70, p = 0.020), and albumin (aOR; 0.17, 95% CI; 0.07-0.42, p < 0.001).

CONCLUSIONS

Some of the current scales may not be appropriate to discriminate severity in patients with cancer. The variables in this study associated with unfavorable outcomes could be evaluated in prospective studies to develop prognostic scores that identify susceptible patients, especially in immunocompromised populations.

Impact of Clostridioides Difficle Infection and its Therapy on Nutritional Status

PURPOSE OF REVIEW

Clostridiodes difficile infection (CDI) is a leading nosocomial cause of increased morbidity and mortality in hospitalized patients and the presentation can vary from asymptomatic infection to severe fulminant colitis and sepsis. It can significantly impact nutritional status in hospitalized patients and lead to longer length of stay with increased morbidity and mortality.

RECENT FINDINGS

An interplay of various intrinsic and extrinsic factors such as systemic inflammation, diarrheal losses, and impact of isolation influence the nutritional status of patients with CDI. While diarrheal losses can lead to dehydration and electrolyte disturbances, isolation can further hamper adequate nutritional support and make early signs of malnutrition overlooked. Similar detrimental impacts on nutritional status can also be observed in other bacterial and viral colonic infections. While prompt diagnosis and early treatment is crucial to prevent mortality, emphasis on nutritional rehabilitation can help reduce morbidity and promote recovery in CDI. Initiation of early feeding in critically sick patients with close monitoring for early signs of malnutrition promotes favorable outcomes.

Treatment and Outcomes of Clostridioides difficile Infection in Switzerland: A Two-Center Retrospective Cohort Study

Objectives: Clostridioides difficile infection (CDI) is the leading cause of healthcare-associated diarrhea, often complicated by severe infection and recurrence with increased morbidity and mortality. Data from large cohorts in Switzerland are scarce. We aimed to describe diagnostic assays, treatment, outcomes, and risk factors for CDI in a large cohort of patients in Switzerland. Methods: We conducted a retrospective cohort study of CDI episodes diagnosed in patients from two tertiary care hospitals in Switzerland. During a 3-month follow-up, we used a composite outcome combining clinical cure at day 10, recurrence at week 8, or death, to evaluate a patient’s response. Unfavorable outcomes consisted in the occurrence of any of these events. Results: From January 2014 to December 2018, we included 826 hospitalized patients with documented CDI. Overall, 299 patients (36.2%) had a severe infection. Metronidazole was used in 566 patients (83.7%), compared to 82 patients (12.1%) treated with vancomycin and 28 patients (4.1%) treated with fidaxomicin. Overall mortality at week 8 was at 15.3% (112/733). Eighty-six patients (12.7%) presented with clinical failure at day 10, and 78 (14.9%) presented with recurrence within 8 weeks; 269 (39.8%) met the composite outcome of death, clinical failure, or recurrence. The Charlson Comorbidity Index score (p < 0.001), leukocytes > 15 G/L (p = 0.008), and the use of metronidazole (p = 0.012) or vancomycin (p = 0.049) were factors associated with the composite outcome. Conclusions: Our study provides valuable insights on CDI treatment and outcomes in Switzerland, highlights the heterogeneity in practices among centers, and underlines the need for the active monitoring of clinical practices and their impact on clinical outcomes through large multicentric cohorts.

Validation of Clinical Risk Models for Clostridioides difficile-Attributable Outcomes

Clostridioides difficile is the leading health care-associated pathogen, leading to substantial morbidity and mortality; however, there is no widely accepted model to predict C. difficile infection severity. Most currently available models perform poorly or were calibrated to predict outcomes that are not clinically relevant. We sought to validate six of the leading risk models (Age Treatment Leukocyte Albumin Serum Creatinine (ATLAS), C. difficile Disease (CDD), Zar, Hensgens, Shivashankar, and C. difficile Severity Score (CDSS)), guideline severity criteria, and PCR cycle threshold for predicting C. difficile-attributable severe outcomes (inpatient mortality, colectomy/ileostomy, or intensive care due to sepsis). Models were calculated using electronic data available within ±48 h of diagnosis (unavailable laboratory measurements assigned zero points), calibrated using a large retrospective cohort of 3,327 inpatient infections spanning 10 years, and compared using receiver operating characteristic (ROC) and precision-recall curves. ATLAS achieved the highest area under the ROC curve (AuROC) of 0.781, significantly better than the next best performing model (Zar 0.745; 95% confidence interval of AuROC difference 0.0094–0.6222; P = 0.008), and highest area under the precision-recall curve of 0.232. Current IDSA/SHEA severity criteria demonstrated moderate performance (AuROC 0.738) and PCR cycle threshold performed the worst (0.531). The overall predictive value for all models was low, with a maximum positive predictive value of 37.9% (ATLAS cutoff ≥9). No clinical model performed well on external validation, but ATLAS did outperform other models for predicting clinically relevant C. difficile-attributable outcomes at diagnosis. Novel markers should be pursued to augment or replace underperforming clinical-only models.

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

Background

Invasive candidal infection combined with bacterial bloodstream infection is one of the common nosocomial infections that is also the main cause of morbidity and mortality. The incidence of invasive Candidal infection with bacterial bloodstream infection is increasing year by year worldwide, but data on China is still limited.

Methods

We included 246 hospitalised patients who had invasive candidal infection combined with a bacterial bloodstream infection from January 2013 to January 2018; we collected and analysed the relevant epidemiological information and used machine learning methods to find prognostic factors related to death (training set and test set were randomly allocated at a ratio of 7:3).

Results

Of the 246 patients with invasive candidal infection complicated with a bacterial bloodstream infection, the median age was 63 years (53.25–74), of which 159 (64.6%) were male, 109 (44.3%) were elderly patients (> 65 years), 238 (96.7%) were hospitalised for more than 10 days, 168 (68.3%) were admitted to ICU during hospitalisation, and most patients had records of multiple admissions within 2 years (167/246, 67.9%). The most common blood index was hypoproteinemia (169/246, 68.7%), and the most common inducement was urinary catheter use (210/246, 85.4%). Moreover, the most frequently infected fungi and bacteria were Candida parapsilosis and Acinetobacter baumannii, respectively. The main predictors of death prognosis by machine learning method are serum creatinine level, age, length of stay, stay in ICU during hospitalisation, serum albumin level, C-Reactive protein (CRP), leukocyte count, neutrophil count, Procalcitonin (PCT), and total bilirubin level.

Conclusion

Our results showed that the most common candida and bacteria infections were caused by Candida parapsilosis and Acinetobacter baumannii, respectively. The main predictors of death prognosis are serum creatinine level, age, length of stay, stay in ICU during hospitalisation, serum albumin level, CRP, leukocyte count, neutrophil count, PCT and total bilirubin level.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07125-8.

Prediction of in-hospital mortality of Clostriodiodes difficile infection using critical care database: a big data-driven, machine learning approach

RESEARCH OBJECTIVES

Clostriodiodes difficile infection (CDI) is a major cause of healthcare-associated diarrhoea with high mortality. There is a lack of validated predictors for severe outcomes in CDI. The aim of this study is to derive and validate a clinical prediction tool for CDI in-hospital mortality using a large critical care database.

METHODOLOGY

The demographics, clinical parameters, laboratory results and mortality of CDI were extracted from the Medical Information Mart for Intensive Care-III (MIMIC-III) database. We subsequently trained three machine learning models: logistic regression (LR), random forest (RF) and gradient boosting machine (GBM) to predict in-hospital mortality. The individual performances of the models were compared against current severity scores (Clostridiodes difficile Associated Risk of Death Score (CARDS) and ATLAS (Age, Treatment with systemic antibiotics, leukocyte count, Albumin and Serum creatinine as a measure of renal function) by calculating area under receiver operating curve (AUROC). We identified factors associated with higher mortality risk in each model.

SUMMARY OF RESULTS

From 61 532 intensive care unit stays in the MIMIC-III database, there were 1315 CDI cases. The mortality rate for CDI in the study cohort was 18.33%. AUROC was 0.69 (95% CI, 0.60 to 0.76) for LR, 0.71 (95% CI, 0.62 to 0.77) for RF and 0.72 (95% CI, 0.64 to 0.78) for GBM, while previously AUROC was 0.57 (95% CI, 0.51 to 0.65) for CARDS and 0.63 (95% CI, 0.54 to 0.70) for ATLAS. Albumin, lactate and bicarbonate were significant mortality factors for all the models. Free calcium, potassium, white blood cell, urea, platelet and mean blood pressure were present in at least two of the three models.

CONCLUSION

Our machine learning derived CDI in-hospital mortality prediction model identified pertinent factors that can assist critical care clinicians in identifying patients at high risk of dying from CDI.