# In-depth analysis of risk factors for postoperative pulmonary infection in patients with basal ganglia haemorrhage and construction of prediction model: based on domestic and international cutting-edge clinical research and big data analysis

## TL;DR

This paper identifies risk factors for postoperative lung infections in patients with basal ganglia haemorrhage and builds a prediction model to help clinicians identify high-risk patients early.

## Contribution

The study introduces a novel prediction model for postoperative pulmonary infections in basal ganglia haemorrhage patients based on clinical and big data analysis.

## Key findings

- Smoking history, ventilator use duration, preoperative tracheal intubation, vomiting, and GCS scores are independent risk factors for postoperative lung infections.
- A prediction model was developed to identify high-risk patients early, improving clinical decision-making.
- The model was validated using a 7:3 training and validation set of 317 patients.

## Abstract

Basal ganglia haemorrhage is a common and serious cerebrovascular disease with a high rate of disability and mortality. Postoperative patients often face many complications, among which pulmonary infection is particularly prominent. Lung infections not only significantly prolong patients’ hospital stay and increase healthcare costs, but also greatly affect the prognostic regression of patients, and may even lead to a rapid deterioration of the condition, which is one of the most important causes of death in patients with basal ganglia haemorrhage.

To investigate the high-risk factors for the development of postoperative pulmonary infections in patients with basal ganglia haemorrhage and to develop a predictive model.

A total of 317 patients were collected in this study, of which 126 patients developed postoperative lung infections; the patients enrolled in this study were randomly divided into a training set and a validation set according to the ratio of 7:3, of which 221 were in the training set and 96 were in the validation set. Past medical history, smoking and alcohol consumption, and relevant information during hospitalisation were collected separately to study the correlation factors affecting the emergence of postoperative lung infection in patients, and to establish a prediction model.

The potentially relevant factors were included in a one-way logistic regression and after analysing the results, a history of smoking, duration of ventilator use, preoperative tracheal intubation, preoperative vomiting, and preoperative GCS (Glasgow Coma Scale) scores were identified as potential risk factors for the development of postoperative pulmonary infections in patients with basal ganglia haemorrhage, p < 0.2; The data obtained were further included in a multifactorial review, and smoking history, duration of ventilator use, preoperative tracheal intubation, preoperative vomiting, and preoperative GCS scores were independent risk factors for the development of postoperative pulmonary infections in patients with basal ganglia haemorrhage, p < 0.05.

The prediction model derived from this study provides a powerful tool for clinicians to identify patients at high risk of postoperative lung infection at an early stage.