Evidence map›Paper›PMID 41402794›Full record

ArticleBMC pulmonary medicine2025

Association of albumin-bilirubin grade with prognosis in ICU patients with pulmonary edema: a retrospective cohort study and a predictive model based on machine learning.

Jiaxu Yao, Wanlin Zheng, Chang You, Yingqi Yang, Ziyan Zhao, Jiahao Wang, Liming Wu, Shaowen Tang

Abstract read
In one paragraph

Article in BMC pulmonary medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.

0numbers the graph read from it
0cells of the map it votes in
1citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

1 citing paper in PubMed.

  1. Article
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

8 authors.

Jiaxu YaoThe First School of Clinical Medicine, Nanjing Medical University, Nanjing, 211166, China.
Wanlin ZhengSchool of Public Health, Nanjing Medical University, Nanjing, 211166, China.
Chang YouSchool of Stomatology, Nanjing Medical University, Nanjing, 211166, China.
Yingqi YangThe Second School of Clinical Medicine, Nanjing Medical University, Nanjing, 211166, China.
Ziyan ZhaoSchool of Rehabilitation Medicine, Nanjing Medical University, Nanjing, 211166, China.
Jiahao WangThe First School of Clinical Medicine, Nanjing Medical University, Nanjing, 211166, China.
Liming WuDepartment of First Drum Tower Clinical College, Nanjing Medical University, Nanjing, 211166, China. wlim1003@163.com.
Shaowen TangDepartment of Epidemiology and Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, 211166, China. tomswen@njmu.edu.cn.

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

backgroundThe Albumin-Bilirubin (ALBI) grade was initially used to assess liver reserve function in patients with cirrhosis and has since been applied in the prognostic evaluation of various diseases. This study explored the relationship between the ALBI grade and the prognosis of patients with pulmonary edema (PE).

methodsWe conducted a retrospective analysis with 1,562 ICU patients with pulmonary edema from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. This study investigated the correlation between the ALBI grade and prognosis in patients diagnosed with acute or chronic pulmonary edema at different stages of the disease. Kaplan-Meier survival analysis, multivariate Cox regression, and ROC curves were used to evaluate the prognostic value of ALBI. Kaplan‒Meier survival curves and multivariate Cox proportional hazards regression models assessed the associations between ALBI grade and short-term and long-term prognoses. Receiver operating characteristic (ROC) analysis was used to evaluate the prognostic prediction ability, sensitivity, specificity, and area under the curve (AUC) of short-term and long-term ALBI grades of PE. Subgroup analyses were also conducted. The Boruta algorithm was used to assess the predictive ability of ALBI, and a predictive model was built using machine learning algorithms. Machine learning algorithms including Gradient Boosting Machine (GBM), Random Survival Forest (RSF), Lasso Cox Regression (Lasso_Cox), etc., were employed to build predictive models.

resultsThis study included a cohort of 1,562 participants. Cox proportional hazards models revealed independent associations between ALBI grade and 30-, 90-, 180-day, and 1-year outcomes in PE patients before and after confounder adjustment. The survival curves indicated that patients with an ALBI grade of 3 (-1.39 to 3) had lower survival rates at 30, 90, and 180 days and 1 year. High ALBI grade (Grade 3) was independently associated with increased mortality at 30 days (HR = 47.4, 95% CI: 6.55-344), 90 days (HR = 8.56, 95% CI: 4.11-17.8), and 1 year (HR = 8.01, 95% CI: 4.58-14.0). The AUC values for ALBI in predicting 30-day and 1-year mortality were 0.741 and 0.700, respectively. Subgroup analysis revealed no significant interactions between ALBI grade and any subgroup. Elevated ALBI levels were associated with increased short-term and long-term all-cause mortality (ACM) in PE patients, suggesting that the ALBI grade may be an independent prognostic factor across disease stages.

conclusionThe ALBI grade is significantly associated with ACM and prognosis in PE patients, which provides a scientific basis for the development of precise treatment strategies.

Indexed as

BilirubinMachine LearningPulmonary EdemaSerum AlbuminAgedFemaleHumansIntensive Care UnitsKaplan-Meier EstimateMaleMiddle AgedPrognosisProportional Hazards ModelsRetrospective StudiesROC CurveBilirubinSerum AlbuminAlbumin-Bilirubin gradeAll-cause mortalityMedical information mart for intensive Care-IVPrognosisPulmonary edema

Identifiers

PMID41402794
PMCPMC12709848

What OpenQuestion holds

Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.