Assessing bioartificial organ function: the 3P model framework and its validation.

Area of Science:

• Biomedical Engineering
• Regenerative Medicine
• Organoid Technology

Background:

• Significant advancements in fabricating in vitro organs, particularly bioartificial livers, have been achieved.
• A lack of standardized methods for predictive assessment of in vitro liver function hinders progress.
• Existing research methodologies for in vitro liver models are diverse, leading to data standardization challenges.

Purpose of the Study:

• To introduce a novel machine learning framework, the "3P model," for assessing in vitro liver function.
• To identify critical fabrication parameters influencing key liver functions, specifically albumin and urea secretion.
• To establish a predictive approach for evaluating the functional sustainability of bioartificial liver models.

Main Methods:

• Utilized a decade of experimental data from diverse in vitro liver culture platform studies.
• Developed and applied a machine learning-based regression model to analyze fabrication parameters and functional outcomes.
• Conducted statistical analysis to evaluate the functional sustainability and identify critical parameters.

Main Results:

• The developed 3P model effectively captured patterns in experimental findings, despite data diversity and scarcity.
• Identified key fabrication parameters that significantly impact albumin and urea secretion in in vitro liver models.
• Demonstrated the model's capability in predicting functional maintenance capacity.

Conclusions:

• The machine learning-based 3P model provides a novel framework for predictive assessment of in vitro liver function.
• Insights gained can optimize culture conditions and enhance the functional evaluation of bioartificial livers.
• This approach sets a precedent for future machine learning applications in bioartificial organ research.