⚡ Quick Summary
This study investigates the use of an artificial intelligence (AI) model to predict lower extremity joint moments during walking in patients with cerebral palsy (CP). The model demonstrated a moderate performance with an accuracy of 85.2% for predicting acceptable joint moments, highlighting its potential for clinical gait analysis.
🔍 Key Details
- 📊 Dataset: 622 patients with cerebral palsy
- ⚙️ Technology: AI model predicting joint moments based on joint kinematics
- 🏷️ Labeling System: Green (acceptable), Yellow (acceptable with caution), Red (unacceptable)
- 📈 Performance Metrics: Accuracy of 85.2%, F-score of 92% for hip joint moment predictions
🔑 Key Takeaways
- 🤖 AI integration in clinical gait analysis shows promise for improving patient assessments.
- 📊 The hip joint
- 📉 More severe conditions in patients correlated with an increase in Red-labeled predictions.
- 🔍 Significant differences in normalized root mean square error (nRMSE) were found among the labels.
- 🧩 The study utilized a three-step approach to evaluate the AI model’s feasibility in clinical settings.
- 📊 ANOVA tests confirmed the validity of the established thresholds for labeling joint moments.
- 🌟 The AI model’s performance was rated as moderate, indicating room for improvement.
- 🗂️ The study was published in PLoS One, contributing to the growing body of literature on AI in healthcare.
📚 Background
The integration of artificial intelligence in healthcare has been a topic of increasing interest, particularly in the realm of gait analysis. Patients with cerebral palsy often experience challenges in mobility, making accurate assessments of their gait crucial for effective treatment. Traditional methods of gait analysis can be time-consuming and subjective, leading researchers to explore AI as a potential solution for enhancing accuracy and efficiency in clinical settings.
🗒️ Study
This study aimed to critically evaluate the feasibility of an AI model that predicts lower extremity joint moments during walking in patients with cerebral palsy. The researchers employed a three-step approach, which included establishing clinically relevant thresholds for joint moments, exploring the relationship between gait kinematics and joint moments, and developing a linear discrimination analysis (LDA) model to predict labels for newly predicted joint moments.
📈 Results
The findings revealed that the hip joint had the largest population of Green labels (84%), indicating acceptable joint moments, while the ankle joint had the smallest proportion (50%). The LDA model achieved an impressive accuracy of 85.2% and an F-score of 92% for predicting Green labels in hip joint moments. Additionally, the study found that more severe patient conditions were associated with an increase in Red-labeled predictions, underscoring the model’s potential to inform clinical decision-making.
🌍 Impact and Implications
The implications of this study are significant for the field of rehabilitation and gait analysis. By demonstrating the effectiveness of AI in predicting joint moments, healthcare professionals may be able to utilize these models to enhance patient assessments and tailor interventions more effectively. This could lead to improved outcomes for individuals with cerebral palsy and potentially other populations with gait abnormalities. The integration of AI into clinical routines could revolutionize how gait analysis is conducted, making it more efficient and reliable.
🔮 Conclusion
This study highlights the promising role of artificial intelligence in clinical gait analysis for patients with cerebral palsy. While the AI model’s performance was rated as moderate, the findings indicate a valuable step towards integrating AI into clinical practice. Continued research and refinement of these models could pave the way for more accurate and efficient assessments, ultimately improving patient care and outcomes in rehabilitation settings.
💬 Your comments
What are your thoughts on the integration of AI in clinical gait analysis? Do you believe it can significantly improve patient outcomes? Let’s start a conversation! 💬 Leave your thoughts in the comments below or connect with us on social media:
Can we use lower extremity joint moments predicted by the artificial intelligence model during walking in patients with cerebral palsy in the clinical gait analysis?
Abstract
Several studies have highlighted the advantages of employing artificial intelligence (AI) models in gait analysis. However, the credibility and practicality of integrating these models into clinical gait routines remain uncertain. This study critically evaluates an AI model’s ability to predict lower extremity joint moments during gait in patients with cerebral palsy (CP). We employed a three-step approach to assess the feasibility of a previously developed AI model that predicted joint moments during walking for 622 patients with CP, using joint kinematics as input. First, we established clinically relevant thresholds for lower extremity joint moments, categorizing into three labels: acceptable (Green), acceptable with caution (Yellow), and unacceptable (Red). This categorization was based on the normalized root mean square error (nRMSE) between lab-measured and predicted joint moments. We explored the relationship between gait kinematics and joint moments by correlating the kinematic inputs with their respective output labels. Finally, we developed a linear discrimination analysis (LDA) model to predict labels for newly predicted joint. Assessing the validity of thresholds, an ANOVA one-way analysis and Bonferroni post-hoc statistical tests were performed to find significant differences between the nRMSE values for each label. The hip joint exhibited the largest population of Green labels (84%), while the ankle joint had the smallest (50%). Regressive differences in joint kinematics and gait profile scores were observed across all labels. The LDA model achieved an accuracy of 85.2% and an F-score of 92% for predicting Green label in hip joint moment. Additionally, more severe patient conditions were associated with an increase in Red-labeled predictions. Our findings highlight significant differences in nRMSE among labels, demonstrating the effectiveness of the proposed thresholds for labeling joint moments. Overall, the AI model’s performance was rated as moderate, and the three-step approach proved valuable for assessing the feasibility of AI models in clinical settings.
Author: [‘Salami F’, ‘Ozates ME’, ‘Arslan YZ’, ‘Wolf SI’]
Journal: PLoS One
Citation: Salami F, et al. Can we use lower extremity joint moments predicted by the artificial intelligence model during walking in patients with cerebral palsy in the clinical gait analysis?. Can we use lower extremity joint moments predicted by the artificial intelligence model during walking in patients with cerebral palsy in the clinical gait analysis?. 2025; 20:e0320793. doi: 10.1371/journal.pone.0320793