Assessing the Performance of a Modified LACE Index (LACE-rt) to Predict Unplanned Readmission After Discharge in a Community Teaching Hospital

Abstract

BackgroundThe LACE index was designed to predict early death or unplanned readmission after discharge from hospital to the community. However, implementing the LACE tool in real time in a teaching hospital required practical unavoidable modifications.ObjectiveThe purpose of this study was to validate the implementation of a modified LACE index (LACE-rt) and test its ability to predict readmission risk using data in a hospital setting.MethodsData from the Canadian Institute for Health Information’s Discharge Abstract Database (DAD), the National Ambulatory Care Reporting System (NACRS), and the hospital electronic medical record for one large community hospital in Toronto, Canada, were used in this study. A total of 3855 admissions from September 2013 to July 2014 were analyzed (N=3855) using descriptive statistics, regression analysis, and receiver operating characteristic analysis. Prospectively collected data from DAD and NACRS were linked to inpatient data.ResultsThe LACE-rt index was a fair test to predict readmission risk (C statistic=.632). A LACE-rt score of 10 is a good threshold to differentiate between patients with low and high readmission risk; the high-risk patients are 2.648 times more likely to be readmitted than those at low risk. The introduction of LACE-rt had no significant impact on readmission reduction.ConclusionsThe LACE-rt is a fair tool for identifying those at risk of readmission. A collaborative cross-sectoral effort that includes those in charge of providing community-based care is needed to reduce readmission rates. An eHealth solution could play a major role in streamlining this collaboration.

Feasibility Study of Monitoring Deterioration of Outpatients Using Multimodal Data Collected by Wearables

“…"E" stands for number of emergency department visit. In our experiment, the threshold of LACE index is 10 (as suggested by [15,22,35]), which means the patients will be predicted as readmitted if their LACE index are larger than 10. The KNN model outperforms the LACE index in terms of sensitivity, PPV and overall accuracy, which demonstrates the feasibility of predicting the deterioration risk of patient via the data passively collected by Fitbit.…”

“…Wang [35] claimed that LACE index might not accurately predict 30-day readmission of congestive heart failure patients discharged from hospital. LACE-rt, as a real-time version of LACE index, was invented to predict readmission using the length of stay during the previous acute care admission [15]. However, LACE-rt underestimates the readmission rates by not taking early death into account [15].…”

“…LACE-rt, as a real-time version of LACE index, was invented to predict readmission using the length of stay during the previous acute care admission [15]. However, LACE-rt underestimates the readmission rates by not taking early death into account [15].…”

“…There is also the case where the yield of one sensing modality is significantly higher than the other. For example, Figure 2b show that user 6,13,15,16,19,20 have much higher step yield than their heart rate yield. On the other hand, only user 11 has heart rate yield which is significantly larger than its step yield.…”

Evaluation of factors and patterns influencing the 30-day readmission rate at a tertiary-level hospital in a resource-constrained setting in Cape Town, South Africa

“…High-risk patients are 2.6 times more likely to be re admitted than those at low risk. [5,6,18] The LACE tool has been validated to correlate well with the risk of 30-day readmission. According to Au et al, [4] use of this model exhibited a 20.5% net reclassification improvement over the Charlston score alone.…”