Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMeasuring the Stability of EHR- and EKG-based Predictive Models
167
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Databases of electronic health records (EHRs) are increasingly used to inform clinical decisions. Machine learning methods can find patterns in EHRs that are predictive of future adverse outcomes. However, statistical models may be built upon patterns of health-seeking behavior that vary across patient subpopulations, leading to poor predictive performance when training on one patient population and predicting on another. This note proposes two tests to better measure and understand model generalization. We use these tests to compare models derived from two data sources: (i) historical medical records, and (ii) electrocardiogram (EKG) waveforms. In a predictive task, we show that EKG-based models can be more stable than EHR-based models across different patient populations.
rate research
Read More
Machine learning models $-$ now commonly developed to screen, diagnose, or predict health conditions $-$ are evaluated with a variety of performance metrics. An important first step in assessing the practical utility of a model is to evaluate its average performance over an entire population of interest. In many settings, it is also critical that the model makes good predictions within predefined subpopulations. For instance, showing that a model is fair or equitable requires evaluating the models performance in different demographic subgroups. However, subpopulation performance metrics are typically computed using only data from that subgroup, resulting in higher variance estimates for smaller groups. We devise a procedure to measure subpopulation performance that can be more sample-efficient than the typical subsample estimates. We propose using an evaluation model $-$ a model that describes the conditional distribution of the predictive model score $-$ to form model-based metric (MBM) estimates. Our procedure incorporates model checking and validation, and we propose a computationally efficient approximation of the traditional nonparametric bootstrap to form confidence intervals. We evaluate MBMs on two main tasks: a semi-synthetic setting where ground truth metrics are available and a real-world hospital readmission prediction task. We find that MBMs consistently produce more accurate and lower variance estimates of model performance for small subpopulations.
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {em uncertainty}. Quantifying uncertainty is especially critical in real-world settings, which often involve input distributions that are shifted from the training distribution due to a variety of factors including sample bias and non-stationarity. In such settings, well calibrated uncertainty estimates convey information about when a models output should (or should not) be trusted. Many probabilistic deep learning methods, including Bayesian-and non-Bayesian methods, have been proposed in the literature for quantifying predictive uncertainty, but to our knowledge there has not previously been a rigorous large-scale empirical comparison of these methods under dataset shift. We present a large-scale benchmark of existing state-of-the-art methods on classification problems and investigate the effect of dataset shift on accuracy and calibration. We find that traditional post-hoc calibration does indeed fall short, as do several other previous methods. However, some methods that marginalize over models give surprisingly strong results across a broad spectrum of tasks.
In this study we focus on the prediction of basketball games in the Euroleague competition using machine learning modelling. The prediction is a binary classification problem, predicting whether a match finishes 1 (home win) or 2 (away win). Data is collected from the Euroleagues official website for the seasons 2016-2017, 2017-2018 and 2018-2019, i.e. in the new format era. Features are extracted from matches data and off-the-shelf supervised machine learning techniques are applied. We calibrate and validate our models. We find that simple machine learning models give accuracy not greater than 67% on the test set, worse than some sophisticated benchmark models. Additionally, the importance of this study lies in the wisdom of the basketball crowd and we demonstrate how the predicting power of a collective group of basketball enthusiasts can outperform machine learning models discussed in this study. We argue why the accuracy level of this group of experts should be set as the benchmark for future studies in the prediction of (European) basketball games using machine learning.
Predictive modeling based on genomic data has gained popularity in biomedical research and clinical practice by allowing researchers and clinicians to identify biomarkers and tailor treatment decisions more efficiently. Analysis incorporating pathway information can boost discovery power and better connect new findings with biological mechanisms. In this article, we propose a general framework, Pathway-based Kernel Boosting (PKB), which incorporates clinical information and prior knowledge about pathways for prediction of binary, continuous and survival outcomes. We introduce appropriate loss functions and optimization procedures for different outcome types. Our prediction algorithm incorporates pathway knowledge by constructing kernel function spaces from the pathways and use them as base learners in the boosting procedure. Through extensive simulations and case studies in drug response and cancer survival datasets, we demonstrate that PKB can substantially outperform other competing methods, better identify biological pathways related to drug response and patient survival, and provide novel insights into cancer pathogenesis and treatment response.
We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized models log-density. We estimate the Stein discrepancy between the data density $p(x)$ and the model density $q(x)$ defined by a vector function of the data. We parameterize this function with a neural network and fit its parameters to maximize the discrepancy. This yields a novel goodness-of-fit test which outperforms existing methods on high dimensional data. Furthermore, optimizing $q(x)$ to minimize this discrepancy produces a novel method for training unnormalized models which scales more gracefully than existing methods. The ability to both learn and compare models is a unique feature of the proposed method.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
