top of page

Our  Biotech
Projects

 

AI (Artifical Intelligence) in Mechanical Ventilation for ICU patients


Present day mechanical ventilators work well in delivering air to diseased lungs,

they are  open loop systems where the input signal, or mode of ventilation, is largely unaffected by its output, the adequacy of ventilation.

As such, those ventilators lack the capacity to assess the patient’s real response to the
delivered breath. An ideal solution is the creation of the autonomous ventilator, a device integrated with algorithms,  that could monitor the patient’s response to ventilation continuously, while adjusting ventilatory parameters to provide the patient with a comfortable, optimally delivered breath based on Algorithms.
Machine learning methods of detecting patient-ventilator asynchrony can  be based on

morphological changes of the pressure and flow signals.

Indeed  AI is able to consider numerous variables and minimize human bias in data classification and mistakes in ventilation strategy. Therefore, the greatest challenge when creating a clinical machine learning model lies in identifying the gold standard that cab be  used in parameters  acquired.

AI technology can be of assistance in helping Doctors deal with information and parametrs
overload . Machine learning algorithms already have been used to analyze data stored in electronic medical records to predict ICU mortality and length of stay, nevertheless the future of AI in the ICU is indeed bright.

​

​

Contact : info@globalmedicalcommunications-gmc.com

​

​

​

​

​

Biblio :

 

npj DIGITAL MEDICINE

Development and validation of a reinforcement learning algorithm to dynamically   optimize mechanical ventilation in critical care

Arne Peine, Published: 19 February 2021

https://www.nature.com/articles/s41746-021-00388-6

​

​

​

Johansson, F. D., Shalit, U. & Sontag, D. Learning Representations for Counterfactual Inference. in Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48 3020–3029 (JMLR.org, 2016)

​

​

​

Alagoz, O., Hsu, H., Schaefer, A. J. & Roberts, M. S. Markov decision processes: a tool for sequential decision making under uncertainty. Med. Decis. Mak. 30, 474–483 (2010).

​

​

https://ai.googleblog.com/2022/02/machine-learning-for-mechanical.html

by Daniel Suo, Software Engineer and Elad Hazan, Research Scientist

​

​

​

​

​

​

​

​

​

​

Image by Possessed Photography
Image by Possessed Photography
Image by Xu Haiwei
bottom of page