Regression with a right‐censored predictor using inverse probability weighting methods

Matsouaka, Roland; Atem, Folefac

doi:10.1002/sim.8704

Cited by 14 publications

(13 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gradient boosted model (GBM) was used to estimate the propensity score (PS) of patients undergoing TTE examination, so as to minimize the imbalance of variables between the TTE group and the non-TTE group. Using PS as the weight, the inverse probabilities weighting (IPW) model was used to generate a weighted cohort (15). P<0.05 indicates that the difference is statistically significant.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The impact of transthoracic echocardiography on the short-term prognosis of elderly patients in the intensive care unit: a retrospective analysis based on the MIMIC-III database

Shi

Zhu

et al. 2021

Ann Palliat Med

View full text Add to dashboard Cite

Background: Elderly patients in the intensive care unit (ICU) often suffer from cardiac function impairment. Real-time monitoring of cardiac function and structural changes has important clinical significance. Transthoracic echocardiography (TTE) is a convenient, intuitive, and non-invasive real-time examination of the heart, and it has been widely used for intensive care patients. This study aims to analyze the impact of TTE on the prognosis of elderly patients in ICU.Methods: Data from elderly patients in the ICU was obtained from the MIMIC-III 1.4 database, and they were divided into a TTE examination group and a non-TTE examination group. The baseline data of the two groups were compared, and multiple regression analysis, propensity score (PS), compatibility analysis, and other methods were used to analyze the influence of TTE on the prognosis of elderly patients in ICU.Results: A total of 8,952 elderly cases were included, comprising 3,280 cases (36.6%) in the TTE group and 5,672 cases (63.4%) in the non-TTE group. The SAPS score (20.34±5.34 vs. 18.74±5.2, t=13.889, P<0.001) and SOFA score (5.10±3.38 vs. 3.82±2.81, t=19.250, P<0.001) of patients in the TTE group were higher than those of non-TTE group. The rate of patients in the TTE group receiving mechanical ventilation (52.10% vs. 34.80%) and vasoactive drugs (29.30% vs. 15.00%) was significantly higher than that in the non-TTE group. In the PS score compatibility cohort, the 28-day mortality rate of patients in the TTE group was 23.4%, and the 28-day mortality rate of patients in the non-TTE group was 28.7%.The adjusted odd ratio (OR) value was 0.76 (95% CI: 0.65-0.87, P<0.001). Analysis of secondary endpoints showed that patients in the TTE group did not use mechanical ventilation and hypertension drugs for a longer period of time than those in the non-TTE group, and the TTE group patients had significantly more fluid input in the first three days after admission to the ICU than in the non-TTE group.Conclusions: TTE examination can reduce the 28-day mortality risk of elderly critically ill patients.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In clinical practice, these indicators often prompt doctors to perform TTE examinations on patients. Based on this result, IPW was used to standardize the difference between the TTE group and the non-TTE group (15). The results are shown in Table 1.…”

Section: Double Robust Analysismentioning

confidence: 99%

The impact of transthoracic echocardiography on the short-term prognosis of elderly patients in the intensive care unit: a retrospective analysis based on the MIMIC-III database

Shi

Zhu

et al. 2021

Ann Palliat Med

View full text Add to dashboard Cite

show abstract

“…The gradient boosted model (GBM) was used to estimate the propensity score (PS) of the patient's sedation and analgesia program to minimize the imbalance of variables between the two sedation and analgesia programs. With PS as the weight, a weighted queue was generated using an inverse probability weighting (IPW) model (11). A two-sided P<0.05 indicated a statistically significant difference.…”

Section: Discussionmentioning

confidence: 99%

The effects of midazolam or propofol plus fentanyl on ICU mortality: a retrospective study based on the MIMIC-IV database

Sun¹,

Yan²,

Hu³

et al. 2022

Ann Transl Med

View full text Add to dashboard Cite

Background: Patients in the intensive care unit (ICU) are often under stress and fail to cooperate well with invasive treatments. Analgesia and sedation are of great significance for reducing the suffering of patients and ensuring the application and effectiveness of treatment. For better clinical choice, we aimed to explore the effect of the combination of propofol + fentanyl or midazolam + fentanyl on the short-term prognosis of hospitalized patients in the ICU.Methods: According to the inclusion and exclusion criteria, we retrospectively included patients in the MIMIC-IV database receiving midazolam + fentanyl or propofol + fentanyl analgesic and sedative treatment using Structured Query Language (SQL) to extract clinical data from the MIMIC-IV database. The primary endpoint was the death rate within 28 days after the patient was admitted to the ICU. Doubly robust estimation was used to infer the relationship between sedation and analgesia and 28 days outcome. The gradient boosted model (GBM) was used to estimate the propensity score (PS) of the patient's sedation and analgesia program, PS was used as the weight, and the inverse probabilities weighting (IPW) model was used to generate a weighted cohort.Results: In total, 4,188 cases were included, with 2,174 (51.9%) in the propofol group and 2,014 (48.1%) in the midazolam group. In the PS score matching cohort, the 28-day mortality of patients in the midazolam group was 30.8%, and the 28-day mortality of patients in the propofol group was 25.5%. The adjusted odds ratio (OR) value was 1.421 [95% confidence interval (CI): 1.118-1.806, P<0.001]. Patients in the propofol group did not use vasoactive drugs for a longer period of time than the midazolam group, and patients in the propofol group received significantly more fluids than those in the midazolam group in the first three days after admission to the ICU.Conclusions: Compared with midazolam combined with fentanyl, propofol combined with fentanyl for sedation and analgesia can reduce the risk of short-term death in ICU patients.

show abstract

“…However, less attention has been paid to regression problems where the response Y is observed and the covariates are censored. Even though a few semiparametric or nonparametric methods have been proposed to deal with censored covariates, most of the existing methods were designed for linear models 11,20,23,26 or models with only Type I censoring. 5,16,18,19 For estimation under our settings by means of multiple imputation, we construct the nonparametric estimator mMI (u) by extending the idea of conditional multiple imputation of Atem et al 21 The algorithm is summarized as follows:…”

Section: Conditional Multiple Imputation (Mi) Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Nonparametric regression with right‐censored covariate via conditional density function

Jiang

Huang

Xia

2022

Statistics in Medicine

View full text Add to dashboard Cite

Censoring often occurs in data collection. This article, considers nonparametric regression when the covariate is censored under general settings. In contrast to censoring in the response variable in survival analysis, regression with censored covariates is more challenging but less studied in the literature, especially for dependent censoring. We propose to estimate the regression function using conditional hazard rates. The asymptotic normality of our proposed estimator is established. Both theoretical results and simulation studies demonstrate that the proposed method is more efficient than the estimation based on complete observations and other methods, especially when the censoring rate is high. We illustrate the usefulness of the proposed method using a data set from the Framingham heart study and a data set from a randomized placebo‐controlled clinical trial of the drug D‐penicillamine.

show abstract

Regression with a right‐censored predictor using inverse probability weighting methods

Cited by 14 publications

References 58 publications

The impact of transthoracic echocardiography on the short-term prognosis of elderly patients in the intensive care unit: a retrospective analysis based on the MIMIC-III database

The impact of transthoracic echocardiography on the short-term prognosis of elderly patients in the intensive care unit: a retrospective analysis based on the MIMIC-III database

The effects of midazolam or propofol plus fentanyl on ICU mortality: a retrospective study based on the MIMIC-IV database

Nonparametric regression with right‐censored covariate via conditional density function

Contact Info

Product

Resources

About