Explainable Machine-Learning Predictions for the Prevention of Hypoxaemia During Surgery
Scott M. Lundberg,Bala G. Nair,Monica S. Vavilala,Mayumi Horibe,Michael J. Eisses,Michael J. Eisses,Trevor Adams,Trevor Adams,David E. Liston,David E. Liston,Daniel King-Wai Low,Daniel King-Wai Low,Shu-Fang Newman,Jerry Kim,Jerry Kim,Su-In Lee +15 more
TLDR
The results suggest that if anaesthesiologists currently anticipate 15% of hypoxaemia events, with the assistance of this system they could anticipate 30%, a large portion of which may benefit from early intervention because they are associated with modifiable factors.Abstract:
Although anaesthesiologists strive to avoid hypoxemia during surgery, reliably predicting future intraoperative hypoxemia is not currently possible. Here, we report the development and testing of a machine-learning-based system that, in real time during general anaesthesia, predicts the risk of hypoxemia and provides explanations of the risk factors. The system, which was trained on minute-by-minute data from the electronic medical records of over fifty thousand surgeries, improved the performance of anaesthesiologists when providing interpretable hypoxemia risks and contributing factors. The explanations for the predictions are broadly consistent with the literature and with prior knowledge from anaesthesiologists. Our results suggest that if anaesthesiologists currently anticipate 15% of hypoxemia events, with this system's assistance they would anticipate 30% of them, a large portion of which may benefit from early intervention because they are associated with modifiable factors. The system can help improve the clinical understanding of hypoxemia risk during anaesthesia care by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics.read more
Citations
More filters
Journal ArticleDOI
High-performance medicine: the convergence of human and artificial intelligence
TL;DR: Over time, marked improvements in accuracy, productivity, and workflow will likely be actualized, but whether that will be used to improve the patient–doctor relationship or facilitate its erosion remains to be seen.
Journal ArticleDOI
From Local Explanations to Global Understanding with Explainable AI for Trees.
Scott M. Lundberg,Scott M. Lundberg,Gabriel G. Erion,Hugh Chen,Alex J. DeGrave,Jordan M. Prutkin,Bala G. Nair,Ronit Katz,Jonathan Himmelfarb,Nisha Bansal,Su-In Lee +10 more
TL;DR: An explanation method for trees is presented that enables the computation of optimal local explanations for individual predictions, and the authors demonstrate their method on three medical datasets.
Journal ArticleDOI
Artificial Intelligence in Healthcare
TL;DR: Recent breakthroughs in AI technologies and their biomedical applications are outlined, the challenges for further progress in medical AI systems are identified, and the economic, legal and social implications of AI in healthcare are summarized.
Journal ArticleDOI
Clinically Applicable AI System for Accurate Diagnosis, Quantitative Measurements, and Prognosis of COVID-19 Pneumonia Using Computed Tomography.
Kang Zhang,Xiaohong Liu,Jun Shen,Zhihuan Li,Ye Sang,Xingwang Wu,Yunfei Zha,Wenhua Liang,Chengdi Wang,Ke Wang,Linsen Ye,Ming Gao,Zhongguo Zhou,Liang Li,Jin Wang,Zehong Yang,Huimin Cai,Jie Xu,Lei Yang,Wenjia Cai,Wenqin Xu,Shaoxu Wu,Wei Zhang,Shanping Jiang,Lianghong Zheng,Xuan Zhang,Li Wang,Liu Lu,Jiaming Li,Haiping Yin,Winston Wang,Oulan Li,Charlotte Zhang,Liang Liang,Tao Wu,Ruiyun Deng,Kang Wei,Yong Zhou,Ting Chen,Johnson Y.N. Lau,Manson Fok,Jianxing He,Tianxin Lin,Weimin Li,Guangyu Wang +44 more
TL;DR: Using a large computed Tomography database from 4,154 patients, an AI system is developed that can diagnose NCP and differentiate it from other common pneumonia and normal controls and is made available globally to assist the clinicians to combat COVID-19.
Journal ArticleDOI
Automated machine learning: Review of the state-of-the-art and opportunities for healthcare.
TL;DR: The existing literature in the field of automated machine learning (AutoML) is reviewed to help healthcare professionals better utilize machine learning models "off-the-shelf" with limited data science expertise to help there to be widespread adoption of AutoML in healthcare.
References
More filters
Journal ArticleDOI
Systematic Review: Process of Forming Academic Service Partnerships to Reform Clinical Education
TL;DR: This study’s findings can provide practical guidelines to steer partnership programs within the academic and clinical bodies, with the aim of providing a collaborative partnership approach to clinical education.
Journal ArticleDOI
Greedy function approximation: A gradient boosting machine.
TL;DR: A general gradient descent boosting paradigm is developed for additive expansions based on any fitting criterion, and specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification.
Proceedings ArticleDOI
XGBoost: A Scalable Tree Boosting System
Tianqi Chen,Carlos Guestrin +1 more
TL;DR: XGBoost as discussed by the authors proposes a sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning to achieve state-of-the-art results on many machine learning challenges.
Proceedings ArticleDOI
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
TL;DR: In this article, the authors propose LIME, a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem.
Journal ArticleDOI
Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review.
Amit X. Garg,Neill K. J. Adhikari,Heather McDonald,M. Patricia Rosas-Arellano,Philip J. Devereaux,Joseph Beyene,Justina Sam,R. Brian Haynes +7 more
TL;DR: Improvement in practitioner performance was associated with CDSSs that automatically prompted users compared with requiring users to activate the system and studies in which the authors were not the developers, as well as other factors.