Gabriel Erion's research while affiliated with University of Washington Seattle and other places
What is this page?
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
Publications (11)
Accurate artificial intelligence (AI) for disease diagnosis could lower healthcare workloads. However, when time or financial resources for gathering input data are limited, as in emergency and critical-care medicine, developing accurate AI models, which typically require inputs for many clinical variables, may be impractical. Here we report a mode...
Hundreds of millions of surgical procedures take place annually across the world, which generate a prevalent type of electronic health record (EHR) data comprising time series physiological signals. Here, we present a transferable embedding method (i.e., a method to transform time series signals into input features for predictive machine learning m...
Recent research has demonstrated that feature attribution methods for deep networks can themselves be incorporated into training; these attribution priors optimize for a model whose attributions have certain desirable properties—most frequently, that particular features are important or unimportant. These attribution priors are often based on attri...
The recent emergence of accurate artificial intelligence (AI) models for disease diagnosis raises the possibility that AI-based clinical decision support could substantially lower the workload of healthcare providers. However, for this to occur, the input data to an AI predictive model, i.e., the patient's features, must themselves be low-cost, tha...
Tree-based machine learning models such as random forests, decision trees and gradient boosted trees are popular nonlinear predictive models, yet comparatively little attention has been paid to explaining their predictions. Here we improve the interpretability of tree-based models through three main contributions. (1) A polynomial time algorithm to...
While deep learning has shown promise in the domain of disease classification from medical images, models based on state-of-the-art convolutional neural network architectures often exhibit performance loss due to dataset shift. Models trained using data from one hospital system achieve high predictive performance when tested on data from the same h...
Two important topics in deep learning both involve incorporating humans into the modeling process: Model priors transfer information from humans to a model by constraining the model's parameters; Model attributions transfer information from a model to humans by explaining the model's behavior. We propose connecting these topics with attribution pri...
Tree-based machine learning models such as random forests, decision trees, and gradient boosted trees are the most popular non-linear predictive models used in practice today, yet comparatively little attention has been paid to explaining their predictions. Here we significantly improve the interpretability of tree-based models through three main c...
Interpreting predictions from tree ensemble methods such as gradient boosting machines and random forests is important, yet feature attribution for trees is often heuristic and not individualized for each prediction. Here we show that popular feature attribution methods are inconsistent, meaning they can lower a feature's assigned importance when t...
We use a deep learning model trained only on a patient's blood oxygenation data (measurable with an inexpensive fingertip sensor) to predict impending hypoxemia (low blood oxygen) more accurately than trained anesthesiologists with access to all the data recorded in a modern operating room. We also provide a simple way to visualize the reason why a...
Citations
... AI technology that can make accurate calculations can reduce medical workload and medical costs (Erion et al., 2022). Besides, in terms of economy and resources, the applications of IMKR will effectively help medical institutions reduce the burden, reduce unnecessary medical investment, and avoid waste of medical resources. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/858242158710784-1581632284831_Q64/Richard-Utarnachitt.jpg)
... The possibility of enabling direct recording with minimum human interference could increase the quality of the data set and let us obtain more precise results [26][27][28]. Furthermore, having a system equipped with the ability to independently record the patient's movements, besides reducing the error rate, could allow for lightening the workload of the medical staff themselves and indirectly reducing the changeover time between different patients [24,[28][29][30][31][32]. Nevertheless, building a tracking system inside a hospital is not a simple task. ...
![[object Object]](https://i1.rgstatic.net/ii/profile.image/278017881460737-1443296036327_Q64/Scott-Lundberg.jpg)
... However, this choice is arbitrary and agnostic to the model and explicand, leading to certain shortcomings. For instance, the straightline path can introduce noise into the attribution due to the saturation effect [17] and the use of a black baseline will result in incomplete attributions [18], [19]. ...
... Several works have considered the general problem of cost-sensitive feature selection in machine learning. These works have tended to provide approximate methods or heuristics for solving the cost-constrained optimization problems associated with such tasks [14][15][16][17]. In healthcare applications, a number of previous works have introduced budget constraints, such as the financial costs of lab tests or clinical preferences, into their proposed machine learning models [18,19]. ...
... Reduce the number of true positives 10 Deep CNN [33] 74.7% When evaluated in cutting-edge healthcare systems, this model performs better in terms of generalization. ...
... Local interpretation (model-agnostic) methods can reveal the impact of features on a specific prediction. One such representative local interpretation method is the SHAP model, which was developed by Lundberg and Lee (2017) in their seminal 2017 paper titled "A Unified Approach to Interpreting Model Predictions" and enhanced by Lundberg et al. (2020). It provides a way to explain the prediction of a machine learning model ("payoff") by attributing the contribution of each feature ("player") to a specific prediction. ...
... The contributions of predictive features to model predictions at the group and individual patient level was evaluated using SHAP (SHapley Additive exPlanations) analysis [34] in the R-based treeshap package [35]. Through inspection of SHAP plots, we investigate three properties of our global RFR model: 1) prognostic predictors through evaluation of the overall importance of each feature in the prediction of min-QIDS and the directionality of important features with respect to predicted outcomes; 2) prescriptive predictors through inspection of SHAP interaction plots illustrating expected changes in outcomes that vary as a function of a predictor's value and treatment type (ECT versus ketamine); and 3) decision paths for individual patients illustrating how observed values of their pretreatment clinical and demographic characteristics produced their predicted treatment outcome. ...
... This approach also provides uncertainty measures of the prediction results. In [27], LSTM technique and an inexpensive fingertip sensor is used to predict oxygen saturation level in individuals with signs of approaching hypoxia. The prediction was more accurate than anaesthesiologists in the operating room. ...
