Limits...
Using electronic health record collected clinical variables to predict medical intensive care unit mortality

View Article: PubMed Central - PubMed

ABSTRACT

Background: Clinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability and mortality prediction in the ICU.

Objective: Develop and evaluate an algorithm which more accurately predicts patient mortality in the ICU, using the correlations between widely available clinical variables from the EHR.

Methods: We have developed an algorithm, AutoTriage, which uses eight common clinical variables from the EHR to assign patient mortality risk scores. Each clinical variable produces a subscore, and combinations of two or three discretized clinical variables also produce subscores. A combination of weighted subscores produces the overall score. We validated the performance of this algorithm in a retrospective study on the MIMIC III medical ICU dataset.

Results: AutoTriage 12 h mortality prediction yields an Area Under Receiver Operating Characteristic value of 0.88 (95% confidence interval 0.86 to 0.88). At a sensitivity of 80%, AutoTriage maintains a specificity of 81% with a diagnostic odds ratio of 16.26.

Conclusions: Through the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction methods.

No MeSH data available.


Distribution of consecutive hours of threshold breach prior to death for AutoTriage ≥ −2 in black, and Modified Early Warning Score (MEWS) ≥ 3 in red.(For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
© Copyright Policy - CC BY-NC-ND
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC5037117&req=5

fig4: Distribution of consecutive hours of threshold breach prior to death for AutoTriage ≥ −2 in black, and Modified Early Warning Score (MEWS) ≥ 3 in red.(For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Mentions: Additional information about patient stability is provided by the duration of their time above a distress threshold. Setting an AutoTriage threshold above −2 identifies patients in distress for longer consecutive periods of time prior to death than MEWS ≥ 3. The distribution of continuous hours above threshold shows more at-risk patients identified, and for longer periods, than standard disease severity scores (Fig. 4). The increased duration between the AutoTriage threshold crossover and the eventual patient decompensation provides earlier warning and greater intervention opportunity for a significant fraction of patients.


Using electronic health record collected clinical variables to predict medical intensive care unit mortality
Distribution of consecutive hours of threshold breach prior to death for AutoTriage ≥ −2 in black, and Modified Early Warning Score (MEWS) ≥ 3 in red.(For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
© Copyright Policy - CC BY-NC-ND
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC5037117&req=5

fig4: Distribution of consecutive hours of threshold breach prior to death for AutoTriage ≥ −2 in black, and Modified Early Warning Score (MEWS) ≥ 3 in red.(For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)
Mentions: Additional information about patient stability is provided by the duration of their time above a distress threshold. Setting an AutoTriage threshold above −2 identifies patients in distress for longer consecutive periods of time prior to death than MEWS ≥ 3. The distribution of continuous hours above threshold shows more at-risk patients identified, and for longer periods, than standard disease severity scores (Fig. 4). The increased duration between the AutoTriage threshold crossover and the eventual patient decompensation provides earlier warning and greater intervention opportunity for a significant fraction of patients.

View Article: PubMed Central - PubMed

ABSTRACT

Background: Clinical decision support systems are used to help predict patient stability and mortality in the Intensive Care Unit (ICU). Accurate patient information can assist clinicians with patient management and in allocating finite resources. However, systems currently in common use have limited predictive value in the clinical setting. The increasing availability of Electronic Health Records (EHR) provides an opportunity to use medical information for more accurate patient stability and mortality prediction in the ICU.

Objective: Develop and evaluate an algorithm which more accurately predicts patient mortality in the ICU, using the correlations between widely available clinical variables from the EHR.

Methods: We have developed an algorithm, AutoTriage, which uses eight common clinical variables from the EHR to assign patient mortality risk scores. Each clinical variable produces a subscore, and combinations of two or three discretized clinical variables also produce subscores. A combination of weighted subscores produces the overall score. We validated the performance of this algorithm in a retrospective study on the MIMIC III medical ICU dataset.

Results: AutoTriage 12 h mortality prediction yields an Area Under Receiver Operating Characteristic value of 0.88 (95% confidence interval 0.86 to 0.88). At a sensitivity of 80%, AutoTriage maintains a specificity of 81% with a diagnostic odds ratio of 16.26.

Conclusions: Through the multidimensional analysis of the correlations between eight common clinical variables, AutoTriage provides an improvement in the specificity and sensitivity of patient mortality prediction over existing prediction methods.

No MeSH data available.