Identification of Patients with Nontraumatic Intracranial Hemorrhage Using Administrative Claims Data

Joblessness, decreased income, and disability in intensive care unit survivors of nontraumatic intracranial hemorrhage in South Korea

OBJECTIVES

To examine the proportions of unemployment, decreased household income, and newly acquired disability, and their impact on long-term mortality after intensive care unit (ICU) admission due to nontraumatic intracranial hemorrhage (IH).

MATERIALS AND METHODS

This nationwide population-based retrospective cohort study enrolled adult patients admitted to the ICU because of nontraumatic IH between 2010 and 2018 in South Korea. Patients who were alive ≥365 days after ICU admission were defined as nontraumatic IH survivors.

RESULTS

In total, 104,086 nontraumatic IH survivors were included in the final analysis. Among them, 7,225 (6.9 %) experienced job loss, 25,709 (24.7 %) experienced decreased household income, and 20,938 (20.1 %) had newly acquired disabilities, of whom 14,188 (13.6 %) had newly acquired brain disabilities. Male sex, increased duration of intensive care unit stay, comorbid status, hospital admission through the emergency room, nontraumatic intracerebral hemorrhage, receipt of surgery, mechanical ventilatory support, and increased total cost of hospitalization were associated with job loss, decreased household income, and newly acquired disabilities. However, these changes were not significantly associated with 2-year all-cause mortality (adjusted hazard ratio: 1.00, 95 % confidence interval: 0.95, 1.06; P = 0.997).

CONCLUSIONS

Many nontraumatic IH survivors experienced unemployment, decreased household income, and newly acquired disability one year after ICU admission in South Korea. Some factors were potential risk factors for these changes, but the changes were not associated with 2-year all-cause mortality.

Machine learning-based patient classification system for adults with stroke: A systematic review

OBJECTIVE

To evaluate the existing evidence of a machine learning-based classification system that stratifies patients with stroke.

METHODS

The authors carried out a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations for a review article. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched from January 2015 to February 2021.

RESULTS

There are twelve studies included in this systematic review. Fifteen algorithms were used in the included studies. The most common forms of machine learning (ML) used to classify stroke patients were the support vector machine (SVM) (n = 8 studies), followed by random forest (RF) (n = 7 studies), decision tree (DT) (n = 4 studies), gradient boosting (GB) (n = 4 studies), neural networks (NNs) (n = 3 studies), deep learning (n = 2 studies), and k-nearest neighbor (k-NN) (n = 2 studies), respectively. Forty-four features of inputs were used in the included studies, and age and gender are the most common features in the ML model.

DISCUSSION

There is no single algorithm that performed better or worse than all others at classifying patients with stroke, in part because different input data require different algorithms to achieve optimal outcomes.