# Investigation of Factors Related to the Week 1 Cumulated Ambulation Score in Patients With Proximal Femoral Fractures Post-surgery Using Decision Tree Analysis

## TL;DR

This study identifies factors affecting early post-surgery mobility in elderly patients with hip fractures, emphasizing knee strength and dementia as key predictors.

## Contribution

The novel use of decision tree analysis to identify knee extension strength and dementia as primary factors influencing early mobility in hip fracture patients.

## Key findings

- Knee extension muscle strength (MMT) at week 1 post-surgery was the primary factor influencing the Cumulated Ambulation Score.
- Dementia presence significantly impacted outcomes in patients with lower knee extension strength.
- The decision tree model achieved 64% accuracy in predicting Week 1 CAS outcomes.

## Abstract

This study aimed to identify factors associated with the Cumulated Ambulation Score (CAS) in the first week post-surgery (Week 1 CAS) in patients with proximal femoral fractures. Proximal femoral fractures are prevalent in the elderly, with rising incidence rates and significant social and functional implications. The ability to walk postoperatively is a critical determinant of patient prognosis.

The study included 53 patients out of 79 who underwent surgery for proximal femoral fractures at the orthopedics department of Oita Oka Hospital from January 2021 to December 2021. Exclusion criteria were pre-existing walking difficulties, inability to be evaluated in the first postoperative week, non-weight bearing post-surgery, and complications during hospitalization. The physical therapy program followed Oita Oka Hospital's clinical path, starting ambulation with a walker within the first week post-surgery. Data collected included patient background, surgical techniques, pre-injury ambulatory status, and pre-admission residential environment. Physical function assessments one week postoperatively included range of motion (ROM), manual muscle testing (MMT), pain evaluation (NRS), and CAS. Statistical analyses involved the Shapiro-Wilk test, independent t-test, Mann-Whitney U test, chi-square test, and decision tree analysis using classification and regression trees (CART).

Patients were categorized into 'favorable' and 'poor' groups based on Week 1 CAS. Significant differences in dementia presence and pre-admission living environment were noted between groups. Knee extension MMT at Week 1 postoperatively showed a significant difference. The decision tree analysis identified knee extension MMT as the primary variable, with a threshold of 3.5. In patients with MMT below 3.5, dementia presence was a secondary factor, with 81% in the poor CAS group. In patients with MMT above 3.5, knee extension strength continued to be significant. The model's accuracy was 64%, with precision at 71%, recall at 63%, and an F1-score of 0.67.

The study highlights knee extension MMT and dementia presence as significant factors influencing Week 1 CAS in patients with proximal femoral fractures. The poor CAS group had a higher proportion of dementia and weaker knee extension MMT.

Dementia hinders rehabilitation effectiveness, impacting recovery in knee extension strength and CAS. The decision tree analysis provided an intuitive understanding of variable interrelationships, emphasizing knee extension strength as the primary factor, followed by dementia in cases with lower MMT scores.

This study elucidated factors related to Week 1 CAS in postoperative patients with proximal femoral fractures. Knee extension MMT emerged as the initial factor, followed by the presence of dementia, influencing Week 1 CAS. These findings are crucial for rehabilitation planning and long-term prognostic predictions in this patient population. However, the study's limitations include potential selection bias and a small sample size, necessitating further research for enhanced predictive accuracy.