Dataset Information

Updating mortality risk estimation in intensive care units from high-dimensional electronic health records with incomplete data.

ABSTRACT:

Background

The risk of mortality in intensive care units (ICUs) is currently addressed by the implementation of scores using admission data. Their performances are satisfactory when complications occur early after admission; however, they may become irrelevant in the case of long hospital stays. In this study, we developed predictive models of short-term mortality in the ICU from longitudinal data.

Methods

Using data collected throughout patients' stays of at least 48 h from the MIMIC-III database, several statistical learning approaches were compared, including deep neural networks and penalized regression. Missing data were handled using complete-case analysis or multiple imputation.

Results

Complete-case analyses from 19 predictors showed good discrimination (AUC > 0.77 for several approaches) to predict death between 12 and 24 h onward, yet excluded 75% of patients from the initial target cohort, as data was missing for some of the predictors. Multiple imputation allowed us to include 70 predictors and keep 95% of patients, with similar performances.

Conclusion

This proof-of-concept study supports that automated analysis of electronic health records can be of great interest throughout patients' stays as a surveillance tool. Although this framework relies on a large set of predictors, it is robust to data imputation and may be effective early after admission, when data are still scarce.

SUBMITTER: Bouvarel B

PROVIDER: S-EPMC10466694 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Updating mortality risk estimation in intensive care units from high-dimensional electronic health records with incomplete data.

Bouvarel Bertrand B Carrat Fabrice F Lapidus Nathanael N

BMC medical informatics and decision making 20230830 1

<h4>Background</h4>The risk of mortality in intensive care units (ICUs) is currently addressed by the implementation of scores using admission data. Their performances are satisfactory when complications occur early after admission; however, they may become irrelevant in the case of long hospital stays. In this study, we developed predictive models of short-term mortality in the ICU from longitudinal data.<h4>Methods</h4>Using data collected throughout patients' stays of at least 48 h from the M ...[more]

PMID: 37648995

Similar Datasets

Project description:ImportanceThe extent to which financial considerations alter intensive care unit (ICU) decision making is poorly understood.ObjectivesTo characterize the prevalence and nature of financial considerations documented in narrative clinical records and their association with patient-level demographic and clinical features.Design, setting, and participantsIn silico cohort study applying natural language processing to narrative notes from the Medical Information Mart for Intensive Care (MIMIC-III) study. Data from all individuals hospitalized between June 1, 2001, and October 31, 2012, in the ICU of Beth Israel Deaconess Medical Center were analyzed from April 1 to April 30, 2018.Main outcomes and measurePresence of financial considerations in narrative clinical notes.ResultsAmong 46 146 index ICU admissions, 1936 patients (4.2%) were identified with at least 1 note reflecting financial considerations during the ICU stay. Of these 1936 patients, 1135 (58.6%) were male, with a mean (SD) age of 38.8 (28.4) years and mean (SD) length of stay of 21.7 (27.1) days. Among the remaining 44 210 admissions in the cohort, 24 780 (56.1%) were male, with a mean (SD) age of 48.6 (32.1) years and mean (SD) length of stay of 9.2 (11.4) days. Among the 46 146 admissions, 142 (0.3%) included notes describing a change in the discharge plan, 142 (0.3%) describing a change in the treatment plan, and 303 (0.7%) describing a change in medication or previous nonadherence to medication associated with financial considerations. In logistic regression models adjusted for age, sex, marital status, and insurance type, longer hospital stays were significantly associated with the presence of financial notes (odds ratio, 1.01; 95% CI, 1.01-1.01).Conclusions and relevanceIn this study, among patients in the ICU, clinical notes document the association of financial considerations with care decisions. Although such notes likely underestimate the frequency of such considerations, they highlight the need to develop better systematic approaches to understanding how financial constraints may alter care decisions in US health systems.

Project description:BackgroundDespite the high mortality in patients with pneumonia admitted to an ICU, data on risk factors for death remain limited.MethodsIn this secondary analysis of PROTECT (Prophylaxis for Thromboembolism in Critical Care Trial), we focused on the patients admitted to ICU with a primary diagnosis of pneumonia. The primary outcome for this study was 90-day hospital mortality and the secondary outcome was 90-day ICU mortality. Cox regression model was conducted to examine the relationship between baseline and time-dependent variables and hospital and ICU mortality.ResultsSix hundred sixty seven patients admitted with pneumonia (43.8 % females) were included in our analysis, with a mean age of 60.7 years and mean APACHE II score of 21.3. During follow-up, 111 patients (16.6 %) died in ICU and in total, 149 (22.3 %) died in hospital. Multivariable analysis demonstrated significant independent risk factors for hospital mortality including male sex (hazard ratio (HR) = 1.5, 95 % confidence interval (CI): 1.1 - 2.2, p-value = 0.021), higher APACHE II score (HR = 1.2, 95 % CI: 1.1 - 1.4, p-value < 0.001 for per-5 point increase), chronic heart failure (HR = 2.9, 95 % CI: 1.6 - 5.4, p-value = 0.001), and dialysis (time-dependent effect: HR = 2.7, 95 % CI: 1.3 - 5.7, p-value = 0.008). Higher APACHE II score (HR = 1.2, 95 % CI: 1.1 - 1.4, p-value = 0.002 for per-5 point increase) and chronic heart failure (HR = 2.6, 95 % CI: 1.3 - 5.0, p-value = 0.004) were significantly related to risk of death in the ICU.ConclusionIn this study using data from a multicenter thromboprophylaxis trial, we found that male sex, higher APACHE II score on admission, chronic heart failure, and dialysis were independently associated with risk of hospital mortality in patients admitted to ICU with pneumonia. While high illness severity score, presence of a serious comorbidity (heart failure) and need for an advanced life support (dialysis) are not unexpected risk factors of mortality, male sex might necessitate further exploration. More studies are warranted to clarify the effect of these risk factors on survival in critically ill patients admitted to ICU with pneumonia.Trial registrationClinicalTrials.gov Identifier: NCT00182143 .

Dataset Information

Updating mortality risk estimation in intensive care units from high-dimensional electronic health records with incomplete data.

Background

Methods

Results

Conclusion

Publications

Updating mortality risk estimation in intensive care units from high-dimensional electronic health records with incomplete data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets