Artificial Intelligence and Machine Learning in Anesthesiology

Connor, Chris

doi:10.1097/aln.0000000000002694

Cited by 152 publications

(114 citation statements)

References 94 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…11 The HPI is a supervised ML algorithm, meaning it was trained to classify labeled outputs to predict a desired or undesired event. 24,25 Supervised ML algorithms are trained on a labeled data set (ie, the training set), after which its predictive accuracy is tested on new data (ie, the test set). Events were binary labeled as hypotensive (MAP <65 mm Hg) or nonhypotensive (MAP >75 mm Hg).…”

Section: Developmental Process Of the Hpimentioning

confidence: 99%

One of the first validations of an artificial intelligence algorithm for clinical use: The impact on intraoperative hypotension prediction and clinical decision-making

Ven

Veelo

Wijnberge

et al. 2021

Surgery

View full text Add to dashboard Cite

Section: Developmental Process Of the Hpimentioning

confidence: 99%

One of the first validations of an artificial intelligence algorithm for clinical use: The impact on intraoperative hypotension prediction and clinical decision-making

Ven

Veelo

Wijnberge

et al. 2021

Surgery

View full text Add to dashboard Cite

“…Recently, the theoretical concepts on machine learning in medicine have been excellently described elsewhere,[25] just as its application in anaesthetic and critical care practice has been described in detail too. [262728]…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Intraoperative hypotension and its prediction

Vos

Scheeren

2019

Indian J Anaesth

View full text Add to dashboard Cite

Intraoperative hypotension (IOH) very commonly accompanies general anaesthesia in patients undergoing major surgical procedures. The development of IOH is unwanted, since it is associated with adverse outcomes such as acute kidney injury and myocardial injury, stroke and mortality. Although the definition of IOH is variable, harm starts to occur below a mean arterial pressure (MAP) threshold of 65 mmHg. The odds of adverse outcome increase for increasing duration and/or magnitude of IOH below this threshold, and even short periods of IOH seem to be associated with adverse outcomes. Therefore, reducing the hypotensive burden by predicting and preventing IOH through proactive appropriate treatment may potentially improve patient outcome. In this review article, we summarise the current state of the prediction of IOH by the use of so-called machine-learning algorithms. Machine-learning algorithms that use high-fidelity data from the arterial pressure waveform, may be used to reveal 'traits' that are unseen by the human eye and are associated with the later development of IOH. These algorithms can use large datasets for 'training', and can subsequently be used by clinicians for haemodynamic monitoring and guiding therapy. A first clinically available application, the hypotension prediction index (HPI), is aimed to predict an impending hypotensive event, and additionally, to guide appropriate treatment by calculated secondary variables to asses preload (dynamic preload variables), contractility (dP/dtmax), and afterload (dynamic arterial elastance, Eadyn). In this narrative review, we summarise the current state of the prediction of hypotension using such novel, automated algorithms and we will highlight HPI and the secondary variables provided to identify the probable origin of the (impending) hypotensive event.

show abstract

“…Precision medicine incorporating artificial intelligence may be a game-changer and has many potential applications for pain management [54]. Electronic health records, despite their shortcomings, provide large datasets that have the potential to inform medical decision making and improve patient care [55]. Neural networks may help to identify factors that predispose patients to experience greater than expected pain after surgery and predict pain trajectories.…”

Section: Future Research Directionsmentioning

confidence: 99%

The role of regional analgesia in personalized postoperative pain management

Chitnis

Tang

Mariano

2020

Korean J Anesthesiol

View full text Add to dashboard Cite

Pain management plays a fundamental role in enhanced recovery after surgery pathways. The concept of multimodal analgesia in providing a balanced and effective approach to perioperative pain management is widely accepted and practiced, with regional anesthesia playing a pivotal role. Nerve block techniques can be utilized to achieve the goals of enhanced recovery, whether it be the resolution of ileus or time to mobilization. However, the recent expansion in the number and types of nerve block approaches can be daunting for general anesthesiologists. Which is the most appropriate regional technique to choose, and what skills and infrastructure are required for its implementation? A multidisciplinary team-based approach for defining the goals is essential, based on each patient's needs, and incorporating patient, surgical, and social factors. This review provides a framework for a personalized approach to postoperative pain management with an emphasis on regional anesthesia techniques.

show abstract

Artificial Intelligence and Machine Learning in Anesthesiology

Cited by 152 publications

References 94 publications

One of the first validations of an artificial intelligence algorithm for clinical use: The impact on intraoperative hypotension prediction and clinical decision-making

One of the first validations of an artificial intelligence algorithm for clinical use: The impact on intraoperative hypotension prediction and clinical decision-making

Intraoperative hypotension and its prediction

The role of regional analgesia in personalized postoperative pain management

Contact Info

Product

Resources

About