What is the clinical evidence from this study?

Study design: Observational. Population: Hemorrhagic stroke. Intervention: Machine learning models. Primary outcome: 90-day prognosis and in-hospital mortality.

What does this research mean for the field?

Random forest models provide superior prediction of 90-day functional prognosis while logistic regression is more effective for in-hospital mortality in hemorrhagic stroke patients, with initial NIHSS and admission location serving as the primary predictive factors. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

May 9, 2025Scientific ReportsOpen Access

Machine learning-based prediction of 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients

View Full Paper

Ask AI

Bookmark

Key result

Random forest best predicts 90-day stroke prognosis, while logistic regression best predicts in-hospital mortality.

Why the study?

Can machine learning models accurately predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients?

Population

Hemorrhagic stroke patients from a national Stroke Registry (January 2014 to July 2022)

Design

Cohort

Follow-up

90 days

Authors

AAAhmad A. AbujaberHamad General Hospital IAIbrahem AlbalkhiAlfaisal University YIYahia ImamCornell University

Discussion

Member takes

Implication

Machine learning models, particularly Random Forest and Logistic Regression, can effectively predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients using registry data.

Study Design

Type

Observational

Multicenter

Yes

Structured PICO

Can machine learning models accurately predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients?

Population

Hemorrhagic stroke patients from a national Stroke Registry evaluated for 90-day prognosis and in-hospital mortality.

Exposure

Machine learning models (Random forest, logistic regression, XGboost, support vector machines, and decision trees) for outcome prediction

Outcome

90-day prognosis and in-hospital mortalityhard clinical

Machine learning models, particularly Random Forest and Logistic Regression, can effectively predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients using registry data.

Limitations

Lack of comprehensive external validation

Cite This Study

Abujaber et al. (2025) conducted an observational in Hemorrhagic stroke. Machine learning models was evaluated on 90-day prognosis and in-hospital mortality. Random forest demonstrated superior performance in predicting 90-day prognosis, while logistic regression was more effective for in-hospital mortality, with NIHSS as a key predictor.

synapsesocial.com/papers/6a10b29b326831f8a26442cc https://doi.org/10.1038/s41598-025-90944-x

View Full Paper

Ask AI

Bookmark

May 9, 2025Scientific ReportsOpen Access

Machine learning-based prediction of 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients

View Full Paper

Ask AI

Bookmark

Key result

Random forest best predicts 90-day stroke prognosis, while logistic regression best predicts in-hospital mortality.

Why the study?

Can machine learning models accurately predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients?

Population

Hemorrhagic stroke patients from a national Stroke Registry (January 2014 to July 2022)

Design

Cohort

Follow-up

90 days

Authors

AAAhmad A. AbujaberHamad General Hospital IAIbrahem AlbalkhiAlfaisal University YIYahia ImamCornell University

Discussion

Member takes

Implication

Machine learning models, particularly Random Forest and Logistic Regression, can effectively predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients using registry data.

Study Design

Type

Observational

Multicenter

Yes

Structured PICO

Can machine learning models accurately predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients?

Population

Hemorrhagic stroke patients from a national Stroke Registry evaluated for 90-day prognosis and in-hospital mortality.

Exposure

Machine learning models (Random forest, logistic regression, XGboost, support vector machines, and decision trees) for outcome prediction

Outcome

90-day prognosis and in-hospital mortalityhard clinical

Machine learning models, particularly Random Forest and Logistic Regression, can effectively predict 90-day prognosis and in-hospital mortality in hemorrhagic stroke patients using registry data.

Limitations

Lack of comprehensive external validation

Cite This Study

synapsesocial.com/papers/6a10b29b326831f8a26442cc https://doi.org/10.1038/s41598-025-90944-x

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark