Quantitative Analysis of the Causes of Falls in Adult Hospitalized Patients Based on the Perspective of Text Mining.

Abstract

Objective: This study harnesses the power of text mining to quantitatively investigate the causative factors of falls in adult inpatients, offering valuable references and guidance for fall prevention measures within hospitals.

Methods: Employing KH Coder 3.0, a cutting-edge text mining software, we performed co-occurrence network analysis and text clustering on fall incident reports of 2,772 adult patients from a nursing quality control platform in a particular city in Jiangsu Province, spanning January 2017 to December 2022.

Results: Among the 2,772 patients who fell, 80.23% were aged above 60, and 73.27% exhibited physical frailty. Text clustering yielded 16 distinct categories, with four clusters implicating patient factors, four linking falls to toileting processes, four highlighting dynamic interplays between patients, the environment, and objects, and another four clusters revealing the influence of patient-caregiver interactions in causing falls.

Conclusion: This study highlights the complex, multifactorial nature of falls in adult inpatients. Effective prevention requires a collaborative effort among healthcare staff, patients, and caregivers, focusing on patient vulnerabilities, environmental factors, and improved care coordination. By strengthening these aspects, hospitals can significantly reduce fall risks and promote patient safety.