Dataset Information

Incorporation of Suppression of Tumorigenicity 2 into Random Survival Forests for Enhancing Prediction of Short-Term Prognosis in Community-ACQUIRED Pneumonia.

ABSTRACT: (1) Background: Biomarker and model development can help physicians adjust the management of patients with community-acquired pneumonia (CAP) by screening for inpatients with a low probability of cure early in their admission; (2) Methods: We conducted a 30-day cohort study of newly admitted adult CAP patients over 20 years of age. Prognosis models to predict the short-term prognosis were developed using random survival forest (RSF) method; (3) Results: A total of 247 adult CAP patients were studied and 208 (84.21%) of them reached clinical stability within 30 days. The soluble form of suppression of tumorigenicity-2 (sST2) was an independent predictor of clinical stability and the addition of sST2 to the prognosis model could improve the performance of the prognosis model. The C-index of the RSF model for predicting clinical stability was 0.8342 (95% CI, 0.8086-0.8598), which is higher than 0.7181 (95% CI, 0.6933-0.7429) of CURB 65 score, 0.8025 (95% CI, 0.7776-8274) of PSI score, and 0.8214 (95% CI, 0.8080-0.8348) of cox regression. In addition, the RSF model was associated with adverse clinical events during hospitalization, ICU admissions, and short-term mortality; (4) Conclusions: The RSF model by incorporating sST2 was more accurate than traditional methods in assessing the short-term prognosis of CAP patients.

SUBMITTER: Zhang T

PROVIDER: S-EPMC9605170 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Incorporation of Suppression of Tumorigenicity 2 into Random Survival Forests for Enhancing Prediction of Short-Term Prognosis in Community-ACQUIRED Pneumonia.

Zhang Teng T Zeng Yifeng Y Lin Runpei R Xue Mingshan M Liu Mingtao M Li Yusi Y Zhen Yingjie Y Li Ning N Cao Wenhan W Wu Sixiao S Zhu Huiqing H Zhao Qi Q Sun Baoqing B

Journal of clinical medicine 20221012 20

(1) Background: Biomarker and model development can help physicians adjust the management of patients with community-acquired pneumonia (CAP) by screening for inpatients with a low probability of cure early in their admission; (2) Methods: We conducted a 30-day cohort study of newly admitted adult CAP patients over 20 years of age. Prognosis models to predict the short-term prognosis were developed using random survival forest (RSF) method; (3) Results: A total of 247 adult CAP patients were stu ...[more]

PMID: 36294336

Similar Datasets

Project description:BackgroundThe prognosis of patients hospitalized with community-acquired pneumonia (CAP) with regards to intensive care unit (ICU) admission, short- and long-term mortality is correlated with patient's comorbidities. For patients hospitalized for CAP, including P-CAP, we assessed the prognostic impact of comorbidities known as at-risk (AR) or high-risk (HR) of pneumococcal CAP (P-CAP), and of the number of combined comorbidities.MethodsData on hospitalizations for CAP among the French 50+ population were extracted from the 2014 French Information Systems Medicalization Program (PMSI), an exhaustive national hospital discharge database maintained by the French Technical Agency of Information on Hospitalization (ATIH). Their admission diagnosis, comorbidities (nature, risk type and number), other characteristics, and their subsequent hospital stays within the year following their hospitalization for CAP were analyzed. Logistic regression models were used to assess the associations between ICU transfer, short- and 1-year in-hospital mortality and all covariates.ResultsFrom 182,858 patients, 149,555 patients aged ≥ 50 years (nonagenarians 17.8%) were hospitalized for CAP in 2014, including 8270 with P-CAP. Overall, 33.8% and 90.5% had ≥ 1 HR and ≥ 1 AR comorbidity, respectively. Cardiac diseases were the most frequent AR comorbidity (all CAP: 77.4%). Transfer in ICU occurred for 5.4% of CAP patients and 19.4% for P-CAP. Short-term and 1-year in-hospital mortality rates were 10.9% and 23% of CAP patients, respectively, significantly lower for P-CAP patients: 9.2% and 19.8% (HR 0.88 [95% CI 0.84-0.93], p < .0001). Both terms of mortality increased mostly with age, and with the number of comorbidities and combination of AR and HR comorbidities, in addition of specific comorbidities.ConclusionsNot only specific comorbidities, but also the number of combined comorbidities and the combination of AR and HR comorbidities may impact the outcome of hospitalized CAP and P-CAP patients.

Dataset Information

Incorporation of Suppression of Tumorigenicity 2 into Random Survival Forests for Enhancing Prediction of Short-Term Prognosis in Community-ACQUIRED Pneumonia.

Publications

Incorporation of Suppression of Tumorigenicity 2 into Random Survival Forests for Enhancing Prediction of Short-Term Prognosis in Community-ACQUIRED Pneumonia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets