Search

BackgroundIn Clostridioides difficile infection (CDI), the relationship between clinical, microbial, and temporal/epidemiological trends, disease severity and adverse outcomes is incompletely understood. In a follow-up to our study from 2010–2013, we evaluate stool toxin levels and C. difficile polymerase chain reaction (PCR) ribotypes. We hypothesized that elevated stool toxins and infection with ribotype 027 associate with adverse outcomes.MethodsIn 565 subjects at the University of Michigan with CDI diagnosed by positive testing for toxins A/B by enzyme immunoassay (EIA) or PCR for the tcdB gene, we quantified stool toxin levels via a modified cell cytotoxicity assay (CCA), isolated C. difficile by anaerobic culture, and performed PCR ribotyping. Severe CDI was defined by Infectious Diseases Society of America (IDSA) criteria, and primary outcomes were all-cause 30-day mortality and a composite of colectomy, intensive care unit admission, and/or death attributable to CDI within 30 days. Analyses included bivariable tests and logistic regression.Results199 samples were diagnosed by EIA; 447 were diagnosed by PCR. Toxin positivity associated with IDSA severity but not primary outcomes. In 2016, compared with 2010–2013, ribotype 106 newly emerged, accounting for 10.6% of strains, ribotype 027 fell from 16.5% to 9.3%, and ribotype 014–027 remained stable at 18.9%. Ribotype 014–020 associated with IDSA severity and 30-day mortality (P = .001).ConclusionsToxin positivity by EIA and CCA associated with IDSA severity but not with subsequent adverse outcomes. The molecular epidemiology of C. difficile has shifted, which may have implications for the optimal diagnostic strategy for and clinical severity of CDI.

Klebsiella commonly colonizes the intestinal tract of hospitalized patients and is a leading cause of health care-associated infections. Colonization is associated with subsequent infection, but the factors determining this progression are unclear. A cohort study was performed, in which intensive care and hematology/oncology patients with Klebsiella colonization based on rectal swab culture were enrolled and monitored for infection for 90 days after a positive swab. Electronic medical records were analyzed for patient factors associated with subsequent infection, and variables of potential significance in a bivariable analysis were used to build a final multivariable model. Concordance between colonizing and infecting isolates was assessed by wzi capsular gene sequencing. Among 2,087 hospitalizations from 1,978 colonized patients, 90 cases of infection (4.3%) were identified. The mean time to infection was 20.6 ± 24.69 (range, 0 to 91; median, 11.5) days. Of 86 typed cases, 68 unique wzi types were identified, and 69 cases (80.2%) were colonized with an isolate of the same type prior to infection. Based on multivariable modeling, overall comorbidities, depression, and low albumin levels at the time of rectal swab collection were independently associated with subsequent Klebsiella infection (i.e., cases). Despite the high diversity of colonizing strains of Klebsiella, there is high concordance with subsequent infecting isolates, and progression to infection is relatively quick. Readily accessible data from the medical record could be used by clinicians to identify colonized patients at an increased risk of subsequent Klebsiella infection. IMPORTANCE Klebsiella is a leading cause of health care-associated infections. Patients who are intestinally colonized with Klebsiella are at a significantly increased risk of subsequent infection, but only a subset of colonized patients progress to disease. Colonization offers a potential window of opportunity to intervene and prevent these infections, if the patients at greatest risk could be identified. To identify patient factors associated with infection in colonized patients, we studied 1,978 colonized patients. We found that patients with a higher burden of underlying disease in general, depression in particular, and low albumin levels in a blood test were more likely to develop infection. However, these variables did not completely predict infection, suggesting that other host and microbial factors may also be important. The clinical variables associated with infection are readily available in the medical record and could serve as the foundation for developing an integrated risk assessment of Klebsiella infection in hospitalized patients.

Summary: Background: Acute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs. Methods: CNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist and physicians trained in intensive care medicine. Chest radiograph data were acquired from four US hospitals. Findings: In an internal test set of 1560 chest radiographs from 455 patients with acute hypoxaemic respiratory failure, a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89–0·94). In the subgroup of 413 images reviewed by at least six physicians, its AUROC was 0·93 (95% CI 0·88–0·96), sensitivity 83·0% (95% CI 74·0–91·1), and specificity 88·3% (95% CI 83·1–92·8). Among images with zero of six ARDS annotations (n=155), the median CNN probability was 11%, with six (4%) assigned a probability above 50%. Among images with six of six ARDS annotations (n=27), the median CNN probability was 91%, with two (7%) assigned a probability below 50%. In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85–0·91). When radiographs annotated as equivocal were excluded, the AUROC was 0·93 (0·92–0·95). Interpretation: A CNN can be trained to achieve expert physician-level performance in ARDS detection on chest radiographs. Further research is needed to evaluate the use of these algorithms to support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research. Funding: National Institutes of Health, Department of Defense, and Department of Veterans Affairs.

Background COVID-19 has led to an unprecedented strain on health care facilities across the United States. Accurately identifying patients at an increased risk of deterioration may help hospitals manage their resources while improving the quality of patient care. Here, we present the results of an analytical model, Predicting Intensive Care Transfers and Other Unforeseen Events (PICTURE), to identify patients at high risk for imminent intensive care unit transfer, respiratory failure, or death, with the intention to improve the prediction of deterioration due to COVID-19. Objective This study aims to validate the PICTURE model’s ability to predict unexpected deterioration in general ward and COVID-19 patients, and to compare its performance with the Epic Deterioration Index (EDI), an existing model that has recently been assessed for use in patients with COVID-19. Methods The PICTURE model was trained and validated on a cohort of hospitalized non–COVID-19 patients using electronic health record data from 2014 to 2018. It was then applied to two holdout test sets: non–COVID-19 patients from 2019 and patients testing positive for COVID-19 in 2020. PICTURE results were aligned to EDI and NEWS scores for head-to-head comparison via area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve. We compared the models’ ability to predict an adverse event (defined as intensive care unit transfer, mechanical ventilation use, or death). Shapley values were used to provide explanations for PICTURE predictions. Results In non–COVID-19 general ward patients, PICTURE achieved an AUROC of 0.819 (95% CI 0.805-0.834) per observation, compared to the EDI’s AUROC of 0.763 (95% CI 0.746-0.781; n=21,740; P Conclusions The PICTURE model is more accurate in predicting adverse patient outcomes for both general ward patients and COVID-19 positive patients in our cohorts compared to the EDI. The ability to consistently anticipate these events may be especially valuable when considering potential incipient waves of COVID-19 infections. The generalizability of the model will require testing in other health care systems for validation.

BackgroundKlebsiella commonly colonizes the intestinal tract of hospitalized patients and is a leading cause of healthcare-associated infections. Colonization is associated with subsequent infection, but the factors determining this progression are unclear.MethodsIntensive care and hematology/oncology patients were screened for Klebsiella colonization by rectal swab culture and monitored for infection for 90 days after a positive swab. Electronic medical records were analyzed for patient factors associated with subsequent infection, and variables of potential significance in bivariable analysis were used to build a final multivariable model. Concordance between colonizing and infecting isolates was assessed by wzi capsular gene sequencing.ResultsAmong 2087 hospital encounters from 1978 colonized patients, 90 cases of infection (4.3%) were identified. Mean time to infection was 20.6 ±24.69 (range 0-91, median 11.5) days. Of 86 typed cases, 68 unique wzi types were identified and 69 cases (80.2%) were colonized with an isolate of the same type prior to infection. Based on multivariable modeling, overall comorbidities, depression and low albumin level at the time of rectal swab were independently associated with subsequent Klebsiella infection.ConclusionsDespite the high diversity of colonizing strains of Klebsiella, there is high concordance with subsequent infecting isolates and progression to infection is relatively quick. Readily accessible data from the medical record could be used by clinicians to identify colonized patients at increased risk of subsequent Klebsiella infection.ImportanceKlebsiella is a leading cause of healthcare-associated infections. Patients who are intestinally colonized with Klebsiella are at significantly increased risk of subsequent infection, but only a subset of colonized patients progress to disease. Colonization offers a potential window of opportunity to intervene and prevent these infections, if the patients at greatest risk could be identified. To identify patient factors associated with infection in colonized patients, we studied 1978 colonized patients. We found that patients with a higher burden of underlying disease in general, depression in particular, and low albumin in a blood test were more likely to be a case of infection. However, these variables did not completely predict infection, suggesting that other host and microbial factors may also be important. The average time to infection was 3 weeks, suggesting that there is time to intervene and prevent Klebsiella infections in hospitalized patients.

This article concerns the PhysioNet/Computing in Cardiology Challenge 2020 which focused on building computational methods to identify cardiac abnormalities from 12-lead ECGs. Our team, MCIRCC, utilized a large secondary dataset of 12-lead ECGs obtained from the Section of Electrophysiology at the University of Michigan, called the MUSE dataset, to pre-train multiple residual neural networks that were later re-trained on the challenge dataset. To do so, the diagnosis statements that existed in our dataset were utilized to assign the same labels to our ECGs as the challenge data. After parameter optimization, we selected a subset of top performing models and created an ensemble model that achieved a challenge validation score of 0.616, and full test score of 0.141, placing us 27th out of 41 teams in the official ranking.

Background:Clostridioides difficile infection (CDI) frequently recurs after initial treatment. Predicting recurrent CDI (rCDI) early in the disease course can assist clinicians in their decision making and improve outcomes. However, predictions based on clinical criteria alone are not accurate and/or do not validate other results. Here, we tested the hypothesis that circulating and stool-derived inflammatory mediators predict rCDI. Methods: Consecutive subjects with available specimens at diagnosis were included if they tested positive for toxigenic C. difficile (+enzyme immunoassay [EIA] for glutamate dehydrogenase and toxins A/B, with reflex to PCR for the tcdB gene for discordants). Stool was thawed on ice, diluted 1:1 in PBS with protease inhibitor, centrifuged, and used immediately. A 17-plex panel of inflammatory mediators was run on a Luminex 200 machine using a custom antibody-linked bead array. Prior to analysis, all measurements were normalized and log-transformed. Stool toxin activity levels were quantified using a custom cell-culture assay. Recurrence was defined as a second episode of CDI within 100 days. Ordination characterized variation in the panel between outcomes, tested with a permutational, multivariate ANOVA. Machine learning via elastic net regression with 100 iterations of 5-fold cross validation selected the optimal model and the area under the receiver operator characteristic curve (AuROC) was computed. Sensitivity analyses excluding those that died and/or lived >100 km away were performed. Results: We included 186 subjects, with 95 women (51.1%) and average age of 55.9 years (±20). More patients were diagnosed by PCR than toxin EIA (170 vs 55, respectively). Death, rCDI, and no rCDI occurred in 32 (17.2%), 36 (19.4%), and 118 (63.4%) subjects, respectively. Ordination revealed that the serum panel was associated with rCDI (P = .007) but the stool panel was not. Serum procalcitonin, IL-8, IL-6, CCL5, and EGF were associated with recurrence. The machine-learning models using the serum panel predicted rCDI with AuROCs between 0.74 and 0.8 (Fig. 1). No stool inflammatory mediators independently predicted rCDI. However, stool IL-8 interacted with toxin activity to predict rCDI (Fig. 2). These results did not change significantly upon sensitivity analysis. Conclusions: A panel of serum inflammatory mediators predicted rCDI with up to 80% accuracy, but the stool panel alone was less successful. Incorporating toxin activity levels alongside inflammatory mediator measurements is a novel, promising approach to studying stool-derived biomarkers of rCDI. This approach revealed that stool IL-8 is a potential biomarker for rCDI. These results need to be confirmed both with a larger dataset and after adjustment for clinical covariates.Funding: NoneDisclosure: Vincent Young is a consultant for Bio-K+ International, Pantheryx, and Vedanta Biosciences.

Background Clostridium difficile infection (CDI) has high incidence in the United States, but less so in East Asian countries such as Taiwan. The reason for this is not understood, but microbial studies could reveal important epidemiologic insights. We hypothesized that the circulating strains of C. difficile and the gut microbiota differ between the United States and Taiwan. Methods Patients with diarrhea ± CDI from the University of Michigan and Chang Gung Memorial Hospital were included. CDI was defined by + enzyme immunoassay for the glutamate dehydrogenase gene and toxins A/B, with reflex to tcdB gene PCR for discordants. C. difficile was isolated by anaerobic culture and characterized by PCR ribotype. The fecal microbiota was assessed by sequence analysis of 16S rRNA-encoding gene amplicons targeting the V4 region. Amplicon sequences were processed using the mothur bioinformatics pipeline, with an operational taxonomic unit (OTU) defined by < = 3% sequence homology. Analysis was performed via logistic regression, principal coordinates (PCoA), and ANOVA. Results Community diversity by Shannon index of CDI- patients was lower (Figure 1); this difference was greater in Taiwan (P < .001, OR = 3.9 per unit Shannon). Taiwanese CDI- patients had lower Bacteroidetes relative abundance (RA) (Figure 2). The Taiwanese CDI- group also differed on PCoA and ANOVA (Figure 3, P < .001). OTU1 (genus Firmicutes) was depleted in CDI+ patients (P < .001, OR = 0.69 per 10% RA increase). Circulating ribotypes (Table 1) differ between countries, with no epidemic strains (R027/R078) present in Taiwan (P = .027). R027 and 014/020 comprised > 50% of US isolates while > 50% of Taiwanese isolates were R002. Conclusion Taiwan and US CDI+ patients differ in dominant ribotypes. It is overall difficult to differentiate diarrheal CDI+ and CDI- patients by the microbiome. Taiwanese CDI- patients are outliers, and possible reasons (e.g., differential burden of parasitic infection; diet) require further study. The increased diversity and lower Bacteroidetes in CDI+ vs. CDI- diarrheal patients contrast with prior studies that instead compared with CDI- non-diarrheal patients. Circulating strains in Taiwan include no epidemic variants; whether this explains the differential incidence needs further study. Disclosures All authors: No reported disclosures.

Background Clostridium difficile infection (CDI) is a major public health concern and frequently results in severe disease, including death. Predicting subsequent complications early in the course can help optimize treatments and improve outcomes. However, models based on clinical criteria alone are not accurate and/or do not validate. We hypothesized that inflammatory mediators from the stool would be biomarkers for severity and complications. Methods Subjects were included after testing positive for toxigenic C. difficile by the clinical microbiology laboratory via enzyme immunoassay (EIA) for glutamate dehydrogenase and toxins A/B, with reflex to tcdB gene PCR for discordants. Stool was thawed on ice, diluted 1:1 with PBS and protease inhibitor, centrifuged, and the supernatant was analyzed by a custom antibody-linked bead array with 17 inflammatory mediators. Measurements were normalized and log-transformed. IDSA severity was defined by serum white blood cell count > 15000 cells/µL or creatinine 1.5-fold above baseline. Primary 30-day outcomes were all-cause mortality and attributable disease-related complications (DRC): ICU admission, colectomy, and/or death. Analyses included principal components, permutational multivariate ANOVA (PERMANOVA), and logistic regression ± L1 regularization and 5-fold cross validation. The area under the receiver operator characteristic curve (AuROC) was computed. Results We included 225 subjects, with 124 females (55.1%), average age 58.5 (±17), and more PCR+ than toxin EIA+ (170 vs. 55, respectively). IDSA severity, death, and DRCs occurred in 79 (35.1%), 14 (6.2%), and 12 (5.3%) subjects, respectively. PCA and PERMANOVA showed IDSA severity (P = 0.009) but not death or DRCs associated with the panel (figure). Several inflammatory mediators associated with IDSA severity and death (table). Machine learning models had AuROCs of 0.77 (IDSA severity), 0.84 (death), and 0.7 (DRCs). Conclusion We found that specific inflammatory mediators from the stool of patients with CDI associate with severity and complications. These results are promising, but need replication in a larger dataset and should be incorporated into models that include clinical covariates prior to deployment. Disclosures All authors: No reported disclosures.

Background The optimal diagnostic strategy for Clostridium difficile infection (CDI) is not known, and no test is shown to clearly differentiate colonization from symptomatic infection. We hypothesized that detection and/or quantification of stool toxins would associate with severe disease and adverse outcomes. Methods We conducted a retrospective cohort study among subjects with CDI diagnosed in 2016 at the University of Michigan. The clinical microbiology laboratory tested for glutamate dehydrogenase antigen and toxins A/B by enzyme immunoassay (EIA). Discordant results reflexed to PCR for the tcdB gene. Stool toxin levels were quantified via a modified cell cytotoxicity assay (CCA). C. difficile was isolated by anaerobic culture and ribotyped. Severe CDI was defined by the IDSA criteria: white blood cell count >15,000 cells/µL or a 1.5-fold increase in serum creatinine above baseline. The primary outcomes were all-cause 30-day mortality and a composite of colectomy, ICU admission, and/or death attributable to CDI within 30 days. Analysis included standard bivariable tests and adjusted models via logistic regression. Results From 565 adult patients, we obtained 646 samples; 199 (30.8%) contained toxins by EIA. Toxin positivity associated with IDSA severity (Table 1), but not our primary outcomes on unadjusted analysis. After adjustment for putative confounders, we still did not observe an association between toxin positivity and our primary outcomes. Stool toxin levels by CCA >6.4 ng/mL associated with IDSA severity (Table 1), but not the primary outcomes. Compared with the period from 2010 to 2013, the circulating ribotypes of C. difficile at our institution changed in 2016. Notably ribotype 106 newly emerged, accounting for 10.6% of strains, and ribotype 027 fell to 9.3% (Table 2). The incidence of ribotype 014-027 has remained stable at 18.9%, but this strain was associated with both IDSA severity and 30-day mortality (OR = 3.32; P = 0.001). Conclusion Toxin detection by EIA/CCA associated with IDSA severity, but this study was unable to confirm an association with subsequent adverse outcomes. The molecular epidemiology of C. difficile has shifted, and this may have implications for the optimal diagnostic strategy for CDI. Disclosures All authors: No reported disclosures.