Building ICU In-hospital Mortality Prediction Model with Federated Learning

Background: Mortality prediction models, developed with the goal of improving risk stratification in hospitalized heart failure (HF) patients, show good performance characteristics in the datasets in which they were developed but have not been validated in external populations. Methods: We used a novel multi-hospital dataset [HealthFacts (Cerner Corp)] derived from the electronic health record (years 2010-2012). We examined the performance of four published HF inpatient mortality prediction models developed using data from: the Acute Decompensated Heart Failure National Registry (ADHERE), the Enhanced Feedback for Effective Cardiac Treatment (EFFECT) study, and the Get With the Guidelines-Heart Failure (GWTG-HF) registry. We compared to an administrative HF mortality prediction model (Premier model) that includes selected patient demographics, comorbidities, prior heart failure admissions, and therapies administered (e.g., inotropes, mechanical ventilation) in the first 2 hospital days. We also compared to a model that uses clinical data but is not heart failure-specific: the Laboratory-Based Acute Physiology Score (LAPS2). We included patients aged ≥18 years admitted with HF to one of 62 hospitals in the database. We applied all 6 models to the data and calculated the c-statistics. Results: We identified 13,163 patients ≥18 years old with a diagnosis of heart failure. Median age was 74 years; approximately half were women; 65% of patients were white and 27% were black. In-hospital mortality was 4.3%. Bland-Altman plots revealed that, at higher predicted mortality, the Premier model outperformed the clinical models. Discrimination of the models varied: ADHERE model (0.68); EFFECT (0.70); GWTG-HF, Peterson (0.69); GWTG-HF, Eapen (0.70); LAPS2 (0.74); Premier (0.81) (Figure). Conclusions: Clinically-derived inpatient heart failure mortality models exhibited similar performance with c statistics hovering around 0.70. A generic clinical mortality prediction model (LAPS2) had slightly better performance, as did a detailed administrative model. Any of these models may be useful for severity adjustment in comparative effectiveness studies of heart failure patients. When clinical data are not available, the administrative model performs similarly to clinical models.

Download Full-text

Development and validation of a scoring system for mortality prediction and application of standardized W statistics to assess the performance of emergency departments

BMC Emergency Medicine ◽

10.1186/s12873-021-00466-8 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Jinwoo Jeong ◽

Sung Woo Lee ◽

Won Young Kim ◽

Kap Su Han ◽

Su Jin Kim ◽

...

Keyword(s):

Emergency Department ◽

Hospital Mortality ◽

Prediction Model ◽

Receiver Operating Characteristic ◽

Scoring System ◽

Operating Characteristic ◽

Mortality Prediction ◽

Mortality Prediction Model ◽

National Emergency ◽

Receiver Operating

Abstract Background In-hospital mortality and short-term mortality are indicators that are commonly used to evaluate the outcome of emergency department (ED) treatment. Although several scoring systems and machine learning-based approaches have been suggested to grade the severity of the condition of ED patients, methods for comparing severity-adjusted mortality in general ED patients between different systems have yet to be developed. The aim of the present study was to develop a scoring system to predict mortality in ED patients using data collected at the initial evaluation and to validate the usefulness of the scoring system for comparing severity-adjusted mortality between institutions with different severity distributions. Methods The study was based on the registry of the National Emergency Department Information System, which is maintained by the National Emergency Medical Center of the Republic of Korea. Data from 2016 were used to construct the prediction model, and data from 2017 were used for validation. Logistic regression was used to build the mortality prediction model. Receiver operating characteristic curves were used to evaluate the performance of the prediction model. We calculated the standardized W statistic and its 95% confidence intervals using the newly developed mortality prediction model. Results The area under the receiver operating characteristic curve of the developed scoring system for the prediction of mortality was 0.883 (95% confidence interval [CI]: 0.882–0.884). The Ws score calculated from the 2016 dataset was 0.000 (95% CI: − 0.021 – 0.021). The Ws score calculated from the 2017 dataset was 0.049 (95% CI: 0.030–0.069). Conclusions The scoring system developed in the present study utilizing the parameters gathered in initial ED evaluations has acceptable performance for the prediction of in-hospital mortality. Standardized W statistics based on this scoring system can be used to compare the performance of an ED with the reference data or with the performance of other institutions.

Download Full-text

Machine-learning-based COVID-19 mortality prediction model and identification of patients at low and high risk of dying

Critical Care ◽

10.1186/s13054-021-03749-5 ◽

2021 ◽

Vol 25 (1) ◽

Author(s):

Mohammad M. Banoei ◽

Roshan Dinparastisaleh ◽

Ali Vaeli Zadeh ◽

Mehdi Mirsaeidi

Keyword(s):

Machine Learning ◽

High Risk ◽

Hospital Mortality ◽

Prediction Model ◽

Biochemical Markers ◽

Mortality Prediction ◽

Blood Biochemical ◽

Mortality Prediction Model ◽

Predict Hospital Mortality ◽

Risk Patients

Abstract Background The coronavirus disease 2019 (COVID-19) pandemic caused by the SARS-Cov2 virus has become the greatest health and controversial issue for worldwide nations. It is associated with different clinical manifestations and a high mortality rate. Predicting mortality and identifying outcome predictors are crucial for COVID patients who are critically ill. Multivariate and machine learning methods may be used for developing prediction models and reduce the complexity of clinical phenotypes. Methods Multivariate predictive analysis was applied to 108 out of 250 clinical features, comorbidities, and blood markers captured at the admission time from a hospitalized cohort of patients (N = 250) with COVID-19. Inspired modification of partial least square (SIMPLS)-based model was developed to predict hospital mortality. Prediction accuracy was randomly assigned to training and validation sets. Predictive partition analysis was performed to obtain cutting value for either continuous or categorical variables. Latent class analysis (LCA) was carried to cluster the patients with COVID-19 to identify low- and high-risk patients. Principal component analysis and LCA were used to find a subgroup of survivors that tends to die. Results SIMPLS-based model was able to predict hospital mortality in patients with COVID-19 with moderate predictive power (Q2 = 0.24) and high accuracy (AUC > 0.85) through separating non-survivors from survivors developed using training and validation sets. This model was obtained by the 18 clinical and comorbidities predictors and 3 blood biochemical markers. Coronary artery disease, diabetes, Altered Mental Status, age > 65, and dementia were the topmost differentiating mortality predictors. CRP, prothrombin, and lactate were the most differentiating biochemical markers in the mortality prediction model. Clustering analysis identified high- and low-risk patients among COVID-19 survivors. Conclusions An accurate COVID-19 mortality prediction model among hospitalized patients based on the clinical features and comorbidities may play a beneficial role in the clinical setting to better management of patients with COVID-19. The current study revealed the application of machine-learning-based approaches to predict hospital mortality in patients with COVID-19 and identification of most important predictors from clinical, comorbidities and blood biochemical variables as well as recognizing high- and low-risk COVID-19 survivors.

Download Full-text