Data-driven modeling of supercritical CO₂ processing with optimized machine learning: prediction of clobetasol propionate solubility - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Modeling Clobetasol Propionate Solubility in Supercritical CO₂ Using Enhanced Machine Learning Techniques

  • By

  • Nidal H. Abu-Hamdeh

  • Mohammed N. Ajour

  • September 7, 2026

Share

  • 1

    Machine learning models were developed to predict Clobetasol Propionate solubility in supercritical CO₂ based on temperature and pressure.

  • 2

    Adaptive Boosting (AdaBoost) was utilized to enhance the performance of Decision Tree, Lasso, and Gaussian Process Regression models.

  • 3

    The models achieved R2 scores of 0.934, 0.977, and 0.813, with the Gaussian Process Regression model being the most accurate.

  • 4

    The study utilized a dataset of 45 rows with temperature and pressure values to assess CP solubility under supercritical conditions.

  • 5

    The Firefly Algorithm was employed to optimize the machine learning models and determine their unknown coefficients.

Original Source(s)

Data-driven modeling of supercritical CO₂ processing with optimized machine learning: prediction of clobetasol propionate solubility

  • by Nidal H. Abu-Hamdeh, Mohammed N. Ajour

  • September 7, 2026

Related Content

Cellulitis-like cutaneous cryptococcosis revealing disseminated infection in a kidney transplant recipient: a case report and systematic review

What shapes patient attitudes toward TBP skin cancer screening?

Expert consensus highlights communication, privacy, and staff interactions as priorities for a proposed patient-reported experience measure.

10 states that support physician work-life balance

These 10 states have paid family or medical leave programs and health, wellness, peer support, or monitoring resources available to physicians or other health professionals.