How big data and AI improve perioperative management and outcome - Scientific Faculty Room
ESAIC Academy. Presenters F. 03/22/22; 348432
Faculty / Presenters
REGULAR CONTENT
Login now to access Regular content available to all registered users.
Apple
Google (online)
Office 365 (online)
Outlook
Outlook.com (online)
Yahoo
Abstract
Discussion Forum (0)
Rate & Comment (0)
Scientific Summary:
The technology behind the growth of artificial intelligence (AI) has a great potential to impact the perioperative arena and the intensive care unit. This webinar, hosted by Prof. Teodora Nicolescu from Oklahoma University, USA, discusses how to effectively utilize AI to improve the quality of care and patient safety.
The webinar begins with speakers, Prof Elean Begnami and Dr. Valentina Bellni, both from the University of Parma, Italy. Dr. Bellini begins by asking whether data analytics drive behavioural changes that may improve the quality of anaesthesia. She reviews a brief history of big data in medicine and anaesthesiology and discusses issues with big data, including the dimensional limits and the high possibility of background noise that makes it difficult to identify results with clinical significance.
Dr. Bellini continues by discussing machine learning, the branch of artificial intelligence that uses computer algorithms capable of learning from experience. Of the numerous advantages of these technologies, the primary goal within the medical field is predictive capabilities. She reviews several studies on how machine learning enhances operating room management to demonstrate that using this technology is both feasible and can obtain accurate predictive estimates. In addition, artificial intelligence plays a vital role in precision medical medicine by monitoring risks and outcomes and clinical decision making. Finally, Dr. Bellini concludes her discussion by pointing out several challenges facing AI in clinical practice: poor quality data, ethical and legal issues, and a lack of educational programmes.
The second speaker, Dr. Matthieu Komorowski, from Imperial College London, UK, discusses how data analytics and insights can drive decision-making in perioperative situations. Machine learning is a set of computational tools that generate knowledge from data and is divided into three pillars; supervised learning, unsupervised learning, and reinforced learning. Supervised learning functions as a mapping between a set of data and labels. Unsupervised learning involves data clustering and dimensionality reduction. And finally, reinforced learning pertains to modelling the decision process to maximize desirable outcomes.
Dr. Komorowski discusses closed-loop systems for drug delivery whereby clinicians set physiological parameters that result in a feedback loop to adjust therapy accordingly. He reviews several studies demonstrating the use of this system in perioperative settings. Unfortunately, there is currently a gap between the expected and observed results and states that to maximize the use of these technologies, we must maximize the perceived usefulness and ease of use. Although machine learning is becoming a core component of decision driving mechanisms, it is a piece of the puzzle that will lead to improving patient care and safety.
The technology behind the growth of artificial intelligence (AI) has a great potential to impact the perioperative arena and the intensive care unit. This webinar, hosted by Prof. Teodora Nicolescu from Oklahoma University, USA, discusses how to effectively utilize AI to improve the quality of care and patient safety.
The webinar begins with speakers, Prof Elean Begnami and Dr. Valentina Bellni, both from the University of Parma, Italy. Dr. Bellini begins by asking whether data analytics drive behavioural changes that may improve the quality of anaesthesia. She reviews a brief history of big data in medicine and anaesthesiology and discusses issues with big data, including the dimensional limits and the high possibility of background noise that makes it difficult to identify results with clinical significance.
Dr. Bellini continues by discussing machine learning, the branch of artificial intelligence that uses computer algorithms capable of learning from experience. Of the numerous advantages of these technologies, the primary goal within the medical field is predictive capabilities. She reviews several studies on how machine learning enhances operating room management to demonstrate that using this technology is both feasible and can obtain accurate predictive estimates. In addition, artificial intelligence plays a vital role in precision medical medicine by monitoring risks and outcomes and clinical decision making. Finally, Dr. Bellini concludes her discussion by pointing out several challenges facing AI in clinical practice: poor quality data, ethical and legal issues, and a lack of educational programmes.
The second speaker, Dr. Matthieu Komorowski, from Imperial College London, UK, discusses how data analytics and insights can drive decision-making in perioperative situations. Machine learning is a set of computational tools that generate knowledge from data and is divided into three pillars; supervised learning, unsupervised learning, and reinforced learning. Supervised learning functions as a mapping between a set of data and labels. Unsupervised learning involves data clustering and dimensionality reduction. And finally, reinforced learning pertains to modelling the decision process to maximize desirable outcomes.
Dr. Komorowski discusses closed-loop systems for drug delivery whereby clinicians set physiological parameters that result in a feedback loop to adjust therapy accordingly. He reviews several studies demonstrating the use of this system in perioperative settings. Unfortunately, there is currently a gap between the expected and observed results and states that to maximize the use of these technologies, we must maximize the perceived usefulness and ease of use. Although machine learning is becoming a core component of decision driving mechanisms, it is a piece of the puzzle that will lead to improving patient care and safety.
Scientific Summary:
The technology behind the growth of artificial intelligence (AI) has a great potential to impact the perioperative arena and the intensive care unit. This webinar, hosted by Prof. Teodora Nicolescu from Oklahoma University, USA, discusses how to effectively utilize AI to improve the quality of care and patient safety.
The webinar begins with speakers, Prof Elean Begnami and Dr. Valentina Bellni, both from the University of Parma, Italy. Dr. Bellini begins by asking whether data analytics drive behavioural changes that may improve the quality of anaesthesia. She reviews a brief history of big data in medicine and anaesthesiology and discusses issues with big data, including the dimensional limits and the high possibility of background noise that makes it difficult to identify results with clinical significance.
Dr. Bellini continues by discussing machine learning, the branch of artificial intelligence that uses computer algorithms capable of learning from experience. Of the numerous advantages of these technologies, the primary goal within the medical field is predictive capabilities. She reviews several studies on how machine learning enhances operating room management to demonstrate that using this technology is both feasible and can obtain accurate predictive estimates. In addition, artificial intelligence plays a vital role in precision medical medicine by monitoring risks and outcomes and clinical decision making. Finally, Dr. Bellini concludes her discussion by pointing out several challenges facing AI in clinical practice: poor quality data, ethical and legal issues, and a lack of educational programmes.
The second speaker, Dr. Matthieu Komorowski, from Imperial College London, UK, discusses how data analytics and insights can drive decision-making in perioperative situations. Machine learning is a set of computational tools that generate knowledge from data and is divided into three pillars; supervised learning, unsupervised learning, and reinforced learning. Supervised learning functions as a mapping between a set of data and labels. Unsupervised learning involves data clustering and dimensionality reduction. And finally, reinforced learning pertains to modelling the decision process to maximize desirable outcomes.
Dr. Komorowski discusses closed-loop systems for drug delivery whereby clinicians set physiological parameters that result in a feedback loop to adjust therapy accordingly. He reviews several studies demonstrating the use of this system in perioperative settings. Unfortunately, there is currently a gap between the expected and observed results and states that to maximize the use of these technologies, we must maximize the perceived usefulness and ease of use. Although machine learning is becoming a core component of decision driving mechanisms, it is a piece of the puzzle that will lead to improving patient care and safety.
The technology behind the growth of artificial intelligence (AI) has a great potential to impact the perioperative arena and the intensive care unit. This webinar, hosted by Prof. Teodora Nicolescu from Oklahoma University, USA, discusses how to effectively utilize AI to improve the quality of care and patient safety.
The webinar begins with speakers, Prof Elean Begnami and Dr. Valentina Bellni, both from the University of Parma, Italy. Dr. Bellini begins by asking whether data analytics drive behavioural changes that may improve the quality of anaesthesia. She reviews a brief history of big data in medicine and anaesthesiology and discusses issues with big data, including the dimensional limits and the high possibility of background noise that makes it difficult to identify results with clinical significance.
Dr. Bellini continues by discussing machine learning, the branch of artificial intelligence that uses computer algorithms capable of learning from experience. Of the numerous advantages of these technologies, the primary goal within the medical field is predictive capabilities. She reviews several studies on how machine learning enhances operating room management to demonstrate that using this technology is both feasible and can obtain accurate predictive estimates. In addition, artificial intelligence plays a vital role in precision medical medicine by monitoring risks and outcomes and clinical decision making. Finally, Dr. Bellini concludes her discussion by pointing out several challenges facing AI in clinical practice: poor quality data, ethical and legal issues, and a lack of educational programmes.
The second speaker, Dr. Matthieu Komorowski, from Imperial College London, UK, discusses how data analytics and insights can drive decision-making in perioperative situations. Machine learning is a set of computational tools that generate knowledge from data and is divided into three pillars; supervised learning, unsupervised learning, and reinforced learning. Supervised learning functions as a mapping between a set of data and labels. Unsupervised learning involves data clustering and dimensionality reduction. And finally, reinforced learning pertains to modelling the decision process to maximize desirable outcomes.
Dr. Komorowski discusses closed-loop systems for drug delivery whereby clinicians set physiological parameters that result in a feedback loop to adjust therapy accordingly. He reviews several studies demonstrating the use of this system in perioperative settings. Unfortunately, there is currently a gap between the expected and observed results and states that to maximize the use of these technologies, we must maximize the perceived usefulness and ease of use. Although machine learning is becoming a core component of decision driving mechanisms, it is a piece of the puzzle that will lead to improving patient care and safety.
Code of conduct/disclaimer available in General Terms & Conditions
{{ help_message }}
{{filter}}