A retrospective cohort study was performed in the English secondary care setting utilising national whole system datasets. Data cleaning and subsequent statistical analyses were performed in R version 3.3.3, utilising R-packages data.table, survival, etm, mvna and mstate, available at CRAN (available at http://cran.r-project.org) [14–17].

This study was set in English acute NHS hospitals [18].

Approval to utilise pseudo-anonymised data was given by Public Health England in the form of an internal data access agreement, in line with their internal Information Governance procedure. Consent was not obtained as routinely collected data were analysed pseudo-anonymously. Analysis of these data to inform on the epidemiology of bacteria associated with healthcare associated infections and antimicrobial resistance are among the stated purposes for which PHE is authorised to retain and utilise the data used in this work.

Descriptive statistics were summarised using median and interquartile ranges for continuous variables, and proportions (represented by percentages) for categorical variables.

Previous literature has stated the need to control for time dependency bias and/or competing risks, as well as potential patient/hospital confounders, when investigating the impact of resistance and hospital onset infections on hospital LoS and in-hospital mortality [23,24]. This led to both multistate models (accounting for time-dependency and competing risk bias) and time-dependent hazard models (additionally accounting for patient/hospital covariates) being constructed.

Utilising an Aalen-Johansen estimator to estimate cumulative incidence of in-hospital death, whilst accounting for competing risks, found that 1.29% (95% CI; 1.28%– 1.30%) of non-infected patients experience in-hospital mortality compared to 14.33% (95% CI; 13.74%– 14.94%) of E. coli bacteraemia patients (S1 Table) within 45 days after admission. Such results show that the 95% CIs do not cross, indicating statistical significance. This is also seen for all tested antibiotic susceptibility exposure groups apart from gentamicin (S1 Table).

Comparing the unadjusted and adjusted subdistribution HR (SHR) estimated utilising a subdistribution hazard approach (Table 3) shows that adjusting for patient and hospital covariates reduces the strength of the association between resistance to all tested antibiotics and in-hospital mortality. Though, E. coli bacteraemia (regardless of susceptibility profile) still was associated with an increased subdistribution hazard of in-hospital death; almost six-fold.

From the multi-state model it was estimated that E. coli bacteraemia is associated with 3.87 (95% CI; 3.69–4.04) excess hospital days (Table 4). With third generation cephalosporin and piperacillin/tazobactam resistance having the largest association with increased LoS, in comparison to the other tested antibiotics. Third generation cephalosporin was associated with 1.58 (95% CI; 0.84–2.31) excess days compared to equivalent third generation cephalosporin susceptible infections. Ciprofloxacin resistance was not significantly associated with excess LoS in the time adjusted model.

Comparing all exposures of interest to the baseline “non-infected” non-exposed group provided the estimates displayed in Fig 3 (see S2 Table for numerical estimates). This suggests that excess LoS associated with susceptible infections is between three and four days, whilst excess LoS associated with resistant infections is larger, but also more varied and uncertain (dependant on the type of antibiotic resistance).

The Cox proportional hazards models results (Table 5) show that, having accounted for patient characteristics and hospital characteristics on admission, an E. coli bacteraemia still significantly was associated with a reduced hazard of experiencing a discharge event (alive or dead). Resistance, in all tested, was found to also have a significant association with a reduced hazard of experiencing discharge event (Table 5). Just focusing on those with a LoS of greater than two days from admission, third generation cephalosporin and piperacillin/tazobactam resistance had the strongest association with the hazard of experiencing a discharge event [HR = 0.69 (95% CI; 0.64–0.74) for both] (Table 5). This is consistent with the multistate model results.

To provide age and sex-adjusted estimates of LoS (in days) and incidence of mortality (in terms of cumulative incidence at day 45), the same multistate model methods utilised above were performed on subgroups. E. coli bacteraemia was associated with in-hospital mortality and excess LoS in all subgroups. Resistance was not clearly associated with the cumulative incidence of in-hospital mortality in most subgroups tested for most antibiotic susceptibilities (see Table 6 and S3 Table). This is consistent with the subdistribution hazard results.

Third-generation cephalosporin resistance and piperacillin/tazobactam resistance were the only individual antibiotic resistance profiles that were associated with LoS outcomes when subgroups were tested. Results for these antibiotic susceptibility profiles are provided in Tables 6. Comparing results across the different subgroup analyses presented in Tables 6 highlights that having an E. coli bacteraemia was associated with stronger effects among younger subgroups, whilst resistance was associated with larger effects among the older subgroups, in terms of average excess length of stay. For other subgroup estimates related to other antibiotic exposure groups of interest refer to S3 Table.

Community-onset cases had substantially larger estimates of excess LoS [3.32 days (95% CI; 3.13–3.51)] compared to hospital-onset cases [0.96 days (95% CI; 0.84–1.08)]. Meanwhile, hospital-onset cases had a significantly higher in-hospital mortality incidence. In-hospital death cumulative incidence was 30.80% (95% CI; 28.02–33.79%) for hospital-onset versus 12.10% (95% CI; 11.51–12.72%) for community onset.

Applying the Department of Health Reference cost for an excess bed-day [28] to the estimates for excess LoS gives a cost per spell of per in-patient with E. coli bacteraemia of £1,020 (95% CI;£970 –£1,070). Utilising this cost per spell and number of spells, the estimated annual cost burden to hospitals due to E. coli bacteraemia in 2011/12 was £14,346,400 (Table 7). Adjusting only for time dependency bias, excess annual costs associated with third generation cephalosporin resistance and piperacillin/tazobactam (comparative to if these had been susceptible infections) were £366,600 (95% CI; £194,927 –£550,000) and £275,400 (95% CI; £105,200 - £436,600) respectively (Table 7). That is to say, if all third generation cephalosporin resistant infections had been susceptible it was estimated that £366,600 would not have been spent on those infections (based on reduced LoS).

A study estimating the impact of third generation cephalosporin resistant and susceptible Enterobacteriaceae bloodstream infections in Europe found susceptible infections (compared to “non-infected”) to have an excess LoS of 4.36 days (95% CI; 3.91–4.81) [11]. This is similar to our estimate of 3.71 days (95% CI; 3.29–4.13) for any E. coli bacteraemia. However, the impact of resistance in the European study was higher than in ours. We estimated resistance to third generation cephalosporins to increase LoS (comparative to susceptible controls) by 1.58 (95% CI; 0.84–2.31) days, compared to their estimate of 3.53 days (95% CI; 2.08–4.96) [11]. However, this could partly be due to the lower reliance on third generation cephalosporins in England than in Europe [29,30], though the impact of all other antibiotic resistances (such as piperacillin/tazobactam) was still less than 3 days in our analysis. This could also be due to the inclusion of “non-tested” into our susceptible group, which could mean our results are conservative. This is the first study estimating the impact of other antibiotic resistances on LoS (with regards to E. coli bacteraemia), such as piperacillin/tazobactam or ciprofloxacin, whilst adjusting for time dependency and patient characteristics. Ciprofloxacin was found to not have a significant impact on LoS across the multistate model analyses. One reason for this observation could be the reduced usage of such fluoroquinolones in England, in an attempt to reduce Clostridium difficile infections [31].

In terms of impact on mortality, when adjusting for competing risks and patient covariates (utilising subdistribution hazards and subgroup cumulative incidence of in-hospital mortality), a significant impact of resistance was not generally seen. This is not in agreement with a comparable European study on Enterobacteriaceae-related bacteraemia, which found third generation cephalosporin resistance to have a significant impact [HR = 1.63 (95% CI: 1.13–2.35)] [11]. This again could be due to a lower reliance on such antibiotics in England [29,30], or due to reduced study power in the subgroup analyses. Our results are in agreement with an earlier European study, which found such resistance in E. coli bacteraemia was not significantly associated with mortality [HR = 2.5 (95% CI; 0.9–6.8)] [8], though the cited study had limited power to detect a true effect as evidenced by the wide confidence intervals. A study on 30-day all-cause mortality utilising similar data-sources found that ciprofloxacin did have a significant impact on mortality, whereas our analysis did not find ciprofloxacin resistance to be significantly associated with in-hospital mortality [12]. This may be as our results adjust for patient comorbidity, something the aforementioned study was unable to do due to data limitations [12]. Our adjustment for patient comorbidity (the modified Elixhauser comorbidity index [26]) was dependent on ICD-10 codes for the index hospitalization, which may therefore include conditions which developed post-bacteraemia episode. However, this risk was reduced by only utilising the codes stated in the initial Finished Consultant Episode of a patient’s hospital spell.

E. coli bacteraemia was found in this study to cause a considerable cost burden in terms of excess LoS. This, in addition to the increase in the incidence in E. coli bacteraemia seen over the past few years and the recent policy to attempt to reduce Gram-negative bacteraemia in NHS hospitals [6,32], would suggest evidence-based national bacteraemia treatment guidance may be beneficial. The study showed that it was not just resistant infections that had a large cost impact, but that antibiotic susceptible E. coli bacteraemia are associated with substantial excess costs too. This would indicate that there is a need to tackle E. coli bacteraemia in general, not just focus on reducing resistant infections.

While there has been investment through initiatives to encourage infection control in the hospital setting [4–6], in this study hospital-onset infections accounted for less than a quarter of all E. coli bacteraemia cases, suggesting purely hospital focused initiatives may be limited in their impact. In addition, subgroup analysis suggests that community onset infections are associated with a larger burden in terms of excess LoS. This would indicate that policies to improve the treatment of less serious infections (such as urinary tract infections) arising in the community that can develop into bacteraemia [20] could be something to be further investigated in terms of reducing the cost burden of E. coli bacteraemia. However, it should be noted that community-onset healthcare-associated infections were not distinguished from community-onset community-associated infections when estimating the impact of such infections.

Our study is the first to estimate excess LoS associated with antibiotic resistant bloodstream infections utilising a multistate model methodology and a nationally representative dataset, providing a large sample size of over 8 million non-exposed spells and over 14,000 exposed spells. It provides the first national estimate on the annual cost burden of E. coli bacteraemia. Our study accounts for time-dependency bias and additional covariates in estimating excess LoS. Both the Cox models and multistate models are in agreement that piperacillin/tazobactam and third generation are associated with the largest impact on time to discharge/excess LoS, with ciprofloxacin estimated to have either the least or a non-significant impact. This agreement across different models (with different structures) reduces the likelihood that such conclusions due to type one error.

One limitation of this study is that it is retrospective in nature and a cohort study based on data collected for other purposes, meaning that some data used may have been wrongly coded, missing or skewed. For example, the laboratory data collected on resistance profiles was from a voluntary database, meaning certain institutions with certain characteristics may more commonly report these isolate results. However, PHE has stated within national surveillance reports that the susceptibility surveillance data reported from LabBase2 are nationally representative, with an ascertainment rate of over 84% (in relation to mandatory E. coli surveillance) in 2012–2013 [7, 32]. Our analysis did not include antibiotic exposure, since data were not available, though did account for timing of infection through time dependent covariates and multistate methodology [16,27].

A further limitation of our study is that we cannot exclude the possibility that our results, despite adjustment for patient demographics and comorbidities, are overestimating the impact of E. coli bacteraemia on in-hospital mortality and LoS. For example, we did not have information about potential time-dependent confounders that could confound the association between hospital-acquired bacteraemia and in-hospital mortality and length of stay, such as the evolution of underlying severity of illness or invasive producers. If such data would be available, g-methods like marginal structural models with inverse probability weighting could be used to adjust for potential time-dependent confounders.[33]. It should also be reiterated that the results of this analysis are only related to excess hospital days and deaths occurring during the first 45 days of patient’s stay. However, this captures the vast majority of infections, and aligns this research with previous work [11].

Inherently the multistate model methodology only accounts for time dependency bias and does not correct for patient or hospital characteristics, however, subgroup analyses were performed to provide estimates in relation to different sample populations. Though subgroup analyses provide useful estimates in clinical practice, this led to smaller sample sizes and thus reduced statistical power. Nonetheless, in all tests the number of resistant cases was above that of 100, providing similar numbers of resistance cases as utilised in previous estimations of antimicrobial resistance hospital burden [8,11].

Place of onset was also compared utilising subgroup analysis, however the cut-off for inclusion in each category (2 days post-admission for inclusion in hospital-onset) is arbitrary and may incorporate bias in its current form. In addition, there is no analysis in trends over time, as the scale of this analysis is limited to one year (July 2011 –June 2012). However, until the 2016/17 incentives to reduce Gram-negative bloodstream infections there were no national changes in governmental recommendations for the treatment of E. coli bloodstream infections [34], meaning that the estimates should be generalizable outside the years in the study cohort. Carbapenem resistance was not investigated individually, given that there were only 11 cases in our sample, though was included as a potential resistance for the “resistant to one or more of the tested antibiotics” group. Carbapenem resistance is a major cause for concern [35], and investigation into the current and potential future impact of such resistance is needed.

The impact of resistance on mortality, LoS and subsequent costs was estimated by grouping tested-susceptible and non-tested subjects. This approach may have introduced bias, as those not-tested could theoretically be resistant, however descriptive and time-to-event statistics were utilised to verify this assumption. Bias introduced in this sense would mean our estimates are likely conservative. The costing does not account for any additional drug costs, procedural costs, ‘infection prevention and control’ costs, or costs due to subsequent treatment in the community or readmission to hospital, meaning our estimates are likely conservative. However, recent literature suggests that LoS is a key cost factor when estimating the costs of hospital-onset infections [23], meaning our estimates likely account for a key proportion of costs. Our costing is an average unit cost of a hospital bed day and applied to all admission types, in reality a patient who was in intensive care could likely cost much more. Co-resistance was not taken into account within our analysis, since each infection type was analysed in the Cox and multistate models separately, to reduce computational complexity. Levels of co-resistance have remained stables over recent years within such infections [36].

Furthermore, in-hospital all-cause mortality is utilised as an outcome rather than total attributable mortality or 30-day mortality. Further data linkage for both cases and non-exposed to the office of national statistics mortality dataset would allow the full impact of infection on mortality, utilising Cox proportional hazards models, to be investigated in future research.