Comparison of Unplanned Intensive Care Unit Readmission Scores: A Prospective Cohort Study

Rosa, Régis Goulart; Roehrig, Cintia; Oliveira, Roselaine Pinheiro de; Maccari, Juçara Gasparetto; Antônio, Ana Carolina Peçanha; Castro, Priscylla de Souza; Neto, Felippe Leopoldo Dexheimer; Balzano, Patrícia de Campos; Teixeira, Cassiano

doi:10.1371/journal.pone.0143127

Cited by 41 publications

(55 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Points-based scores such as the Acute Physiology and Chronic Health (APACHE) score [21] and the Simplified Acute Physiology Score (SAPS) [22] are routinely used in ICUs to evaluate severity of illness and predict mortality risk; they may also be useful in predicting the risk of readmission [23]. However, a recent study comparing several scores used to predict the risk of readmission within 48 hours from discharge determined only moderate discrimination power (area under the receiver operating characteristic curve between 0.65 and 0.67) [24]. It is plausible that the application of novel machine learning algorithms to EMR data could lead to more accurate predictions.…”

Section: Introductionmentioning

confidence: 99%

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk

Barbieri

Kemp

Perez‐Concha

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Background: Deep learning algorithms achieve high classification accuracy in many applications but their integration into clinical processes remains scarce, partly due to their perceived lack of transparency. Attention layers in deep neural networks increase model interpretability by identifying which components of the input are attended to at any point in time. Objective: To evaluate the feasibility of using an attention-based neural network for predicting the risk of readmission within 30 days of discharge from the intensive care unit (ICU) based on longitudinal electronic medical record (EMR) data and to leverage the interpretability of the model to describe patients-at-risk. Methods: A "time-aware attention" model was trained using publicly available EMR data (MIMIC-III) associated with 45,298 ICU stays for 33,150 patients. The analysed EMR data included static (patient demographics) and timestamped variables (diagnoses, procedures, medications, and vital signs). Bayesian inference was used to compute the posterior distribution of network weights. The prediction accuracy of the proposed model was compared with several baseline models, including recursive neural networks and logistic regression, and evaluated based on average precision, AUROC, and F 1 -Score. Odds ratios (ORs) associated with an increased risk of readmission were computed for static variables. Diagnoses, procedures, and medications were ranked according to the associated risk of readmission. The model was also used to generate reports with predicted risk (and associated uncertainty) justified by specific diagnoses, procedures, medications, and vital signs. Results: A Bayesian ensemble of 10 time-aware attention models could be trained to predict the risk of readmission within 30 days of discharge from the ICU and led to the highest predictive accuracy (average precision: 0.282, AUROC: 0.738, F 1 -Score: 0.353). Male gender, number of recent admissions, age, admission location, insurance type, and ethnicity were all associated with risk of readmission. A longer length of stay in the ICU was found to reduce the risk of readmission (OR: 0.909, 95% credible interval: 0.902, 0.916). Groups of patients at risk included those requiring cardiovascular or ventilatory support, those with poor nutritional state, and those for whom standard medical care was not suitable, e.g. due to contraindications to surgery or medications. Conclusions:The presented deep learning model considers the full clinical history of a patient and can be used to gain insight into the patient population at increased risk of readmission. Ultimately, the development of interpretable machine learning techniques such as proposed here is necessary to allow the integration of predictive models in clinical processes.

show abstract

Section: Introductionmentioning

confidence: 99%

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk

Barbieri

Kemp

Perez‐Concha

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…It was also lower in comparison with the data from the Dutch National Intensive Care Evaluation (NICE) registry, in which a readmission rate of 8.2% was noted among 42,040 ICU admissions [15]. Additionally, Polish patients were generally hospitalized for much longer in the ICU in comparison with other countries [15,24,25]. These findings are not surprising.…”

Section: Discussionmentioning

confidence: 67%

Readmissions to General ICUs in a Geographic Area of Poland Are Seemingly Associated with Better Outcomes

Grochla

Saucha

Cieśla

et al. 2020

IJERPH

View full text Add to dashboard Cite

Background: Various factors can contribute to high mortality rates in intensive care units (ICUs). Here, we intended to define a population of patients readmitted to general ICUs in Poland and to identify independent predictors of ICU readmission. Methods: Data derived from adult ICU admissions from the Silesian region of Poland were analyzed. First-time ICU readmissions (≤30 days from ICU discharge after index admissions) were compared with first-time ICU admissions. Pre-admission and admission variables that independently influenced the need for ICU readmission were identified. Results: Among the 21,495 ICU admissions, 839 were first-time readmissions (3.9%). Patients readmitted to the ICU had lower mean APACHE II (21.2 ± 8.0 vs. 23.2 ± 8.8, p < 0.001) and TISS-28 scores (33.7 ± 7.4 vs. 35.2 ± 7.8, p < 0.001) in the initial 24 h following ICU admission, compared to first-time admissions. ICU readmissions were associated with lower mortality vs. first-time admissions (39.2% vs. 44.3%, p = 0.004). Independent predictors for ICU readmission included the admission from a surgical ward (among admission sources), chronic respiratory failure, cachexia, previous stroke, chronic neurological diseases (among co-morbidities), and multiple trauma or infection (among primary reasons for ICU admission). Conclusions: High mortality associated with first-time ICU admissions is associated with a lower mortality rate during ICU readmissions.

show abstract

“…Other studies have shown that determining the best timing for ICU discharge is usually based on subjective intuitions and that readmission prediction tools can help physicians in this endeavor, provided their performance and ease of adoption (5,6). As traditional scores based on logistic regression or Cox proportional hazards models such as the Stability and Workload Index for Transfer score (SWIFT) or the LACE index have failed to meet expectations (6)(7)(8)(9)(10), numerous prediction models using machine learning have been proposed in the recent past, several of which trained and evaluated on the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC-II or MIMIC-III) open database (11)(12)(13)(14)(15). MIMIC-III is a large ICU EHR database widely accessible to researchers internationally under a data use agreement, allowing clinical studies to be reproduced and benchmarked (16,17).…”

Section: Introductionmentioning

confidence: 99%

Accurate and reproducible prediction of ICU readmissions

Nguyen

2019

Preprint

View full text Add to dashboard Cite

Readmission in the intensive care unit (ICU) is associated with poor clinical outcomes and high costs. Traditional scoring methods to help clinicians deciding whether a patient is ready for discharge have failed to meet expectations, paving the way for machine learning based approaches. Freely available datasets such as MIMIC-III have served as benchmarking media to compare such tools. We used the OMOP-CDM version of MIMIC-III (MIMIC-OMOP) to train and evaluate a lightweight tree boosting method to predict readmission in ICU at different time points after discharge (3, 7, 15 and 30 days), outperforming existing solutions with an AUROC of 0.802 (SD=0.011) and a recall of 0.837 (SD=0.016) for 3-days readmission. ICU readmission | MIMIC | OMOP-CDM | gradient boostingCorrespondence: dinh-phong.nguyen@aphp.fr

show abstract

Comparison of Unplanned Intensive Care Unit Readmission Scores: A Prospective Cohort Study

Cited by 41 publications

References 28 publications

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk

Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk

Readmissions to General ICUs in a Geographic Area of Poland Are Seemingly Associated with Better Outcomes

Accurate and reproducible prediction of ICU readmissions

Contact Info

Product

Resources

About