โก Quick Summary
A recent study has developed a radiomics-based model to predict the success of US-guided percutaneous irrigation (US-PICT) for patients suffering from shoulder calcific tendinopathy. The model achieved an impressive AUC of 0.88, demonstrating its potential to enhance clinical decision-making.
๐ Key Details
- ๐ Dataset: 84 patients undergoing US-PICT
- ๐งฉ Features used: Clinical data and radiomic features from ultrasound images
- โ๏ธ Technology: Machine Learning models including Random Forest, XGBoost, and Support Vector Machines
- ๐ Performance: Best model achieved AUC of 0.88, sensitivity of 0.90, and positive predictive value of 0.92
๐ Key Takeaways
- ๐ Radiomics can significantly enhance the prediction of treatment outcomes for shoulder calcific tendinopathy.
- ๐ก Machine Learning models were effectively utilized to analyze both clinical and radiomic data.
- ๐ฉโ๐ฌ External validation confirmed the model’s generalizability with an AUC of 0.78.
- ๐ The study highlights the importance of combining radiomic features with clinical data for better predictive accuracy.
- ๐ Conducted by a team of researchers from various institutions, showcasing collaborative efforts in medical research.
- ๐ SHAP analysis was used to interpret the model’s predictions, emphasizing the impact of selected features.
- ๐ This model could guide clinicians in making informed decisions regarding treatment options.
๐ Background
Shoulder calcific tendinopathy is a common condition that primarily affects the rotator cuff tendons, leading to significant pain and functional impairment. Traditional methods for predicting patient outcomes after treatments like US-PICT have been limited, often resulting in uncertainty for both patients and healthcare providers. The integration of radiomics and machine learning presents a promising avenue for improving predictive capabilities in this area.
๐๏ธ Study
The study involved 84 patients who underwent US-PICT, with data collected on various clinical and demographic factors. Radiomic features were extracted from ultrasound images, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was employed to identify key features predictive of treatment outcomes. Several machine learning models were tested to analyze the data, focusing on the extent of calcium removal.
๐ Results
The study’s findings revealed that the combined model, which integrated radiomic features with clinical data, achieved an impressive AUC of 0.88 (95% CI 0.73-0.99). The model demonstrated a positive predictive value of 0.92 and a sensitivity of 0.90. In external testing, the model maintained a respectable AUC of 0.78, indicating its robustness and applicability across different patient cohorts.
๐ Impact and Implications
The development of this radiomics model represents a significant advancement in the management of shoulder calcific tendinopathy. By providing a reliable method for predicting treatment outcomes, clinicians can make more informed decisions, potentially improving patient satisfaction and reducing the burden of ineffective treatments. This approach could pave the way for similar applications in other musculoskeletal conditions, enhancing the overall quality of care.
๐ฎ Conclusion
This study underscores the transformative potential of radiomics and machine learning in predicting patient outcomes for US-PICT in shoulder calcific tendinopathy. As we continue to explore these innovative technologies, we anticipate a future where predictive analytics can significantly enhance clinical decision-making and patient care. Further research is encouraged to validate these findings and expand their applicability in clinical settings.
๐ฌ Your comments
What are your thoughts on the use of radiomics in predicting treatment outcomes? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Ultrasound radiomics predict the success of US-guided percutaneous irrigation for shoulder calcific tendinopathy.
Abstract
OBJECTIVE: Calcific tendinopathy, predominantly affecting rotator cuff tendons, leads to significant pain and tendon degeneration. Although US-guided percutaneous irrigation (US-PICT) is an effective treatment for this condition, prediction of patient’ s response and long-term outcomes remains a challenge. This study introduces a novel radiomics-based model to forecast patient outcomes, addressing a gap in the current predictive methodologies.
MATERIALS AND METHODS: The study involved 84 patients who underwent US-PICT, with data collected on clinical and demographic factors, alongside radiomic features extracted from ultrasound images. Key radiomic features predictive of the outcome were discerned through Least Absolute Shrinkage and Selection Operator (LASSO) method. Machine Learning models, including Random Forest, XGBoost, and Support Vector Machines, were employed to analyze the radiomics, the clinical and the combined dataset, focusing on calcium removal extent. An external testing was conducted using an independent cohort from a different institution to assess the model’s generalizability.ย Metrics were calculated for the best-performing models, namely area under the curve (AUC) score, sensitivity, specificity, precision or positive predictive value, and negative predictive value.
RESULTS: The selected features were merged with clinical data, notably the calcification’s maximum diameter. This enriched dataset was fed into classification models. The superior model achieved an AUC of 0.88 (95% CI 0.73-0.99), with a positive predictive value of 0.92 and a sensitivity of 0.90. In external testing, the combined model achieved an AUC of 0.78. SHAP analysis was employed to highlight the impact of the selected features on the optimal model’s effectiveness.
CONCLUSION: The developed radiomics model offers a promising tool for predicting outcomes of US-PICT, potentially guiding clinical decision-making.
Author: [‘Triantafyllou M’, ‘Vassalou EE’, ‘Klontzas ME’, ‘Tosounidis TH’, ‘Marias K’, ‘Karantanas AH’]
Journal: Jpn J Radiol
Citation: Triantafyllou M, et al. Ultrasound radiomics predict the success of US-guided percutaneous irrigation for shoulder calcific tendinopathy. Ultrasound radiomics predict the success of US-guided percutaneous irrigation for shoulder calcific tendinopathy. 2025; (unknown volume):(unknown pages). doi: 10.1007/s11604-024-01725-x