Key result
Machine learning algorithms predict in-hospital mortality from first-day admission data with ~0.90 AUC.
Why the study?
Early identification of patients at high risk of in-hospital death is essential to aid medical decision making and resource allocation.
Can machine learning models using early hospitalization data accurately predict in-hospital mortality?
Observational (n=123,729)
No
Can machine learning models using early hospitalization data accurately predict in-hospital mortality?
Machine learning models utilizing early electronic medical records and socio-determinants of health can accurately predict in-hospital mortality within 30 days of admission.
This is the authors' abstract. We don't add key points for this paper.
BACKGROUND: In France an average of 4% of hospitalized patients die during their hospital stay. To aid medical decision making and the attribution of resources, within a few days of admission the identification of patients at high risk of dying in hospital is essential. METHODS: We used de-identified routine patient data available in the first 2 days of hospitalization in a French University Hospital (between 2016 and 2018) to build models predicting in-hospital mortality (at ≥ 2 and ≤ 30 days after admission). We tested nine different machine learning algorithms with repeated 10-fold cross-validation. Models were trained with 283 variables including age, sex, socio-determinants of health, laboratory test results, procedures (Classification of Medical Acts), medications (Anatomical Therapeutic Chemical code), hospital department/unit and home address (urban, rural etc.). The models were evaluated using various performance metrics. The dataset contained 123,729 admissions, of which the outcome for 3542 was all-cause in-hospital mortality and 120,187 admissions (no death reported within 30 days) were controls. RESULTS: The support vector machine, logistic regression and Xgboost algorithms demonstrated high discrimination with a balanced accuracy of 0.81 (95%CI 0.80-0.82), 0.82 (95%CI 0.80-0.83) and 0.83 (95%CI 0.80-0.83) and AUC of 0.90 (95%CI 0.88-0.91), 0.90 (95%CI 0.89-0.91) and 0.90 (95%CI 0.89-0.91) respectively. The most predictive variables for in-hospital mortality in all three models were older age (greater risk), and admission with a confirmed appointment (reduced risk). CONCLUSION: We propose three highly discriminating machine-learning models that could improve clinical and organizational decision making for adult patients at hospital admission.
Answers are grounded in this paper and cite their sources.
May support early mortality risk stratification from admission data; leaves open prospective validation before clinical use.
No takes yet. Share an insight, caveat, or question.
Stoessel et al. (2023) conducted an observational in In-hospital mortality (n=123,729). Machine learning predictive models (Xgboost, Logistic Regression, SVM) vs. Dummy classifier was evaluated on Prediction of in-hospital mortality (AUC for Xgboost) (95% CI 0.89-0.91). Machine learning algorithms, including Xgboost, logistic regression, and support vector machines, accurately predicted in-hospital mortality using first-day admission data with an AUC of 0.90.
Synapse has enriched 10 related papers. Consider them for comparative context: