Dataset Information

Event Prediction Model Considering Time and Input Error Using Electronic Medical Records in the Intensive Care Unit: Retrospective Study.

ABSTRACT:

Background

In the era of artificial intelligence, event prediction models are abundant. However, considering the limitation of the electronic medical record-based model, including the temporally skewed prediction and the record itself, these models could be delayed or could yield errors.

Objective

In this study, we aim to develop multiple event prediction models in intensive care units to overcome their temporal skewness and evaluate their robustness against delayed and erroneous input.

Methods

A total of 21,738 patients were included in the development cohort. Three events-death, sepsis, and acute kidney injury-were predicted. To overcome the temporal skewness, we developed three models for each event, which predicted the events in advance of three prespecified timepoints. Additionally, to evaluate the robustness against input error and delays, we added simulated errors and delayed input and calculated changes in the area under the receiver operating characteristic curve (AUROC) values.

Results

Most of the AUROC and area under the precision-recall curve values of each model were higher than those of the conventional scores, as well as other machine learning models previously used. In the error input experiment, except for our proposed model, an increase in the noise added to the model lowered the resulting AUROC value. However, the delayed input did not show the performance decreased in this experiment.

Conclusions

For a prediction model that was applicable in the real world, we considered not only performance but also temporal skewness, delayed input, and input error.

SUBMITTER: Sung M

PROVIDER: S-EPMC8603167 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:OBJECTIVES:Healthcare process carries important prognostic information for patients, but the healthcare processes of laboratory tests have not yet been investigated for patients in the intensive care unit (ICU). The study aimed to investigate the effect of healthcare processes of laboratory tests on hospital mortality, with the hypothesis that the addition of healthcare processes could improve the discrimination for mortality outcome. DESIGN:The study included 12 laboratory tests. There were two dimensions for each laboratory test. One was the pathophysiology value; and the other was the healthcare process variables including the clock hour, the number of measurements and the measurement time from ICU admission. Generalised additive model was employed to investigate the effect of continuous variables on mortality. Generalised linear models with and without healthcare process variables were compared for their discrimination power. SETTING:ICUs in an US-based hospital. PARTICIPANTS:Adult patients included in the critical care big data Medical Information Mart for Intensive Care. PRIMARY AND SECONDARY OUTCOME MEASURES:The hospital mortality was the primary outcome. RESULTS:A total of 52?963 adult patients with complete ICU stay information were included for analysis. The mortality rate was 12.3%. Lower number of tests such as 1-3 times were associated with the lowest mortality for most laboratory tests. However, the hematocrit, glucose and potassium required 6-10 measurements for the first 24?hours to reach the lowest mortality rate. In n of the 12 prediction models involving laboratory tests, the addition of healthcare process variables was associated with significantly increased area under receiver operating characteristics. CONCLUSIONS:The study showed that healthcare processes of laboratory tests were independently associated with hospital mortality. The addition of healthcare processes to the pathophysiology value could increase the discrimination for mortality outcome.

Project description:BackgroundMost of the previous studies focused on central line-associated bloodstream infection (CLABSI), while non-central line-associated bloodstream infection (N-CLABSI) was poorly studied. This study was performed to investigate the clinical impacts and risk factors for N-CLABSI in intensive care unit (ICU) patients.MethodsAn observational study was conducted in an adult general ICU. The electronic medical records from 2013 to 2017 of all patients aged ≥ 18 years admitted to the ICU > 2 days were analyzed retrospectively. Patients with N-CLABSI and without N-CLABSI or with CLABSI were compared for clinical features and outcomes. Predicted death in ICU included death in ICU and discharging from ICU against medical advice because of critical conditions and the desire to pass away at home. Propensity score (PS) matching was used to ensure that both two groups had similar baseline characteristics. Multivariate regression models were used to confirm whether N-CLABSI was an independent risk factor for each of the outcomes and to analyze the risk factors for N-CLABSI in ICU patients.ResultsOf 5046 patients included, 155 developed 168 ICU-acquired N-CLABSI episodes (2.1 episodes per 1000 patient-days) in the ICU, accounted for the majority of nosocomial bloodstream infections (NBSIs; 71.8%). After PS matching, patients with N-CLABSI had prolonged length of stay (LOS) in ICU (median 15 days, p < 0.001) and LOS in hospital (median 13 days, p < 0.001), excess hospitalization costs (median, $27,668 [in US dollar 2017, 1:6.75], p < 0.001), and increased mortality in ICU (8.8%, p = 0.013) and predicted mortality in ICU (22.7%, p < 0.001), compared with those without N-CLABSI. There were no significant differences in all the outcomes between N-CLABSI and CLABSI. N-CLABSI was an independent risk factor for each of the outcomes. Gastrointestinal bleeding (adjusted odds ratio [aOR] 2.30), trauma (aOR 2.52), pancreatitis (aOR 3.45), surgical operation (aOR 1.82), intravascular catheters (aOR 2.93), sepsis (aOR 1.69), pneumonia (aOR 1.53), intraabdominal infection (IAI, aOR 8.37), or healthcare-associated infections other than NBSI, pneumonia, and IAI (aOR 3.89) were risk factors for N-CLABSI in ICU patients.ConclusionsN-CLABSI was associated with similar poor outcomes with CLABSI, including prolonged LOS in ICU and in hospital and increased hospitalization costs and predicted mortality in ICU. The risk factors for N-CLABSI identified in this study provide further insight in preventing N-CLABSI.