predicting recurrent c.diff infection with emr data 1201


figure 2. Model Calibration Using the Validation Dataset. For both plots, the X axis shows predicted rates of recurrent CDI in 5% increments, while the Y axis shows the actual observed rates (with associated 95% confidence intervals) in the validation dataset for all observations with that predicted level of risk. The dotted line shows what would be found were calibration to be perfect. For both the Zilberberg and Enhanced models, calibration is poor: calibration fails at levels above 10% predicted risk. Observed rates do not approach predicted rates, meaning that both models over-predict recurrent CDI. Additional calibration figures, including Hosmer-Lemeshow plots, are provided in the Appendix.


highly granular EMR data (eg, vital signs, laboratory tests, composite severity of illness scores, and longitudinal comor- bidity), the models and underlying data had poor ability to predict rCDI. We formally tested a common assumption made by many investigators (ie, that deaths can simply be excluded from the numerator). We found that this approach is justified, and that including patients who die prior to the conclusion of the follow-up period did not improve prediction. Lastly, we found that shortening the length of follow-up to 30 days resulted in worse model performance. Some authors have reported better model performance.


Examination of these other studies paints a less optimistic picture. Hu et al10 report the use of machine-learning appro- aches and a c statistic of 0.80 in their validation dataset. How- ever, this study had a very small sample size (N=110, with N =64 in the validation dataset) and did not employ cross- validation (ie, no formal assessment of the possibility thatmodel performance in a different population might be poor). We were able to achieve c statistics that were this high in our derivation dataset, but these apparently successful models demonstrated considerable instability during cross-validation. We did not pursue them further and chose more parsimonious models. Contrary to previous literature reports, some predictors (eg,


specific antibiotic exposures) were of limited value, particu- larly in models that included severity of illness. This probably reflects the fact that severity of illness is highly correlated (and may, in fact, be the underlying risk factor) with other pre- dictors (eg, intensive care and antibiotics known to predispose


for CDI). We deliberately focused on predicting rCDI in iCDI cases, though previous CDI is a well-known risk factor for recurrence. It is possible that, had we included prior CDI as a predictor, we might have achieved better model performance. However, models that included the COPS2 score (a long- itudinal comorbidity measure that captures information from the preceding 12 months) did not perform much better. Multiple investigators, using a variety of statistical approa-


ches, including machine-learning methods, have been unable to produce static models with better performance using the currently available set of predictors. While it is true that many predictors reach statistical significance in bivariate analyses (particularly when the sample size is large), the clinical sig- nificance may be muted because the relative proportions of patients with and without recurrence are not that different. Further, it is clear that the risk factors (age, antibiotic expo- sure, severity of illness) that place an individual at risk for iCDI are also risk factors for rCDI. Thus, future efforts ought to be placed on identifying better predictors rather than on using different statistical approaches with the currently available predictors. New predictors may include newer biomarkers (eg, indicators of underlying predisposition to recurrence), environ- mental factors (eg, proximity to other CDI patients, presence of C. difficile spores4), behavioral aspects (eg, handwashing), and/ormolecular markers (eg, information on specific C. difficile strains). It is also important to consider rCDI in an ecological context, and future predictive models may need to be explicit about including environmental and ecological predictors


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92  |  Page 93  |  Page 94  |  Page 95  |  Page 96  |  Page 97  |  Page 98  |  Page 99  |  Page 100  |  Page 101  |  Page 102  |  Page 103  |  Page 104  |  Page 105  |  Page 106  |  Page 107  |  Page 108  |  Page 109  |  Page 110  |  Page 111  |  Page 112  |  Page 113  |  Page 114  |  Page 115  |  Page 116  |  Page 117  |  Page 118  |  Page 119  |  Page 120  |  Page 121  |  Page 122  |  Page 123  |  Page 124  |  Page 125  |  Page 126  |  Page 127  |  Page 128  |  Page 129  |  Page 130  |  Page 131  |  Page 132  |  Page 133  |  Page 134  |  Page 135  |  Page 136  |  Page 137  |  Page 138  |  Page 139  |  Page 140  |  Page 141  |  Page 142  |  Page 143  |  Page 144