20 SUPLEMENTO LIQUIDOS 2025 Finalmente, el análisis basado en IA, junto con algoritmos de aprendizaje automático, se utiliza para analizar los datos de monitorización ambiental, detectar patrones de contaminación y predecir los riesgos antes de que ocurran. Este enfoque predictivo permite una toma de decisiones proactiva y reduce el riesgo de contaminación, lo que minimiza así las interrupciones en la producción 11 Referencias 1. ISO. ISO 14644, Cleanrooms and Associated Controlled Environments Standards (2015). 2. Thermo Fisher Scientific. Rapid Sterility Testing: Overcoming Challenges in Cell Therapy Production. www.thermofisher.com, Oct. 30, 2024. 3. Whyte, W. Cleanroom Technology: Fundamentals of Design, Testing and Operation; Wiley, 2010. 4. Agalloco, J.; Akers, J. Advanced Aseptic Processing and Biopharmaceutical Manufacturing;CRC Press, 2016. 5. Sandle, T. Cleanroom Microbiology for the Non-Microbiologist; CRC Press, 2019. 6. Jallow, J. Rapid Sterility Testing for Cell and Gene Therapy Treatments. americanpharmaceuticalreview.com, Dec. 1, 2023. 7. USP. USP General Chapter <71>, Sterility Tests. USP-NF (Rockville, Md., 2023). 8. PDA. Sterility Testing of Pharmaceutical Products. PDA Technical Report No. 33 (2019). 9. Khuu, H. M; Stock, F.; McGann, M.; et al. Comparison of Automated Culture Systems With a CFR/USP-Compliant Method for Sterility Testing of Cell-Therapy Products. Cytotherapy 2004, 6 (3), 183–195. DOI: 10.1080/14653240410005997 10. Xiao, Y.; Zhang, L.; Yang, B.; et al. Application of Next Generation Sequencing Technology on Contamination Monitoring in Microbiology Laboratory. Biosaf Health 2019, 1 (1), 25–31. DOI: 10.1016/j.bsheal.2019.02.003 11. Bradshaw, N. Using AI and Machine Learning in Cleanroom Contamination Control. blog.curemd.com (accessed March 7, 2025). PT EDICIONES VR - AULA VIRTUAL
RkJQdWJsaXNoZXIy NzE4NDM5