In recent years, machine learning methods have been rapidly implemented in the medical domain. However, current state-of-the-art methods usually produce opaque, black-box models. To address the lack of model transparency, substantial attention has been given to develop interpretable machine learning methods. In the medical domain, counterfactuals can provide example-based explanations for predictions, and show practitioners the modifications required to change a prediction from an undesired to a desired state. In this paper, we propose a counterfactual explanation solution for predicting the survival of cardiovascular ICU patients, by representing their electronic health record as a sequence of medical events, and generating counterfactuals by adopting and employing a text style-transfer technique. Experimental results on the MIMIC-III dataset strongly suggest that text style-transfer methods can be effectively adapted for the problem of counterfactual explanations in healthcare applications and can achieve competitive performance in terms of counterfactual validity, BLEU-4 and local outlier metrics. 

In recent years, machine learning methods have been rapidly adopted in the medical domain. However, current state-of-the-art medical mining methods usually produce opaque, black-box models. To address the lack of model transparency, substantial attention has been given to developing interpretable machine learning models. In the medical domain, counterfactuals can provide example-based explanations for predictions, and show practitioners the modifications required to change a prediction from an undesired to a desired state. In this paper, we propose a counterfactual solution MedSeqCF for preventing the mortality of three cohorts of ICU patients, by representing their electronic health records as medical event sequences, and generating counterfactuals by adopting and employing a text style-transfer technique. We propose three model augmentations for MedSeqCF to integrate additional medical knowledge for generating more trustworthy counterfactuals. Experimental results on the MIMIC-III dataset strongly suggest that augmented style-transfer methods can be effectively adapted for the problem of counterfactual explanations in healthcare applications and can further improve the model performance in terms of validity, BLEU-4, local outlier factor, and edit distance. In addition, our qualitative analysis of the results by consultation with medical experts suggests that our style-transfer solutions can generate clinically relevant and actionable counterfactual explanations.

Counterfactual explanations can provide sample-based explanations of features required to modify from the original sample to change the classification result from an undesired state to a desired state; hence it provides interpretability of the model. Previous work of LatentCF presents an algorithm for image data that employs auto-encoder models to directly transform original samples into counterfactuals in a latent space representation. In our paper, we adapt the approach to time series classification and propose an improved algorithm named LatentCF++ which introduces additional constraints in the counterfactual generation process. We conduct an extensive experiment on a total of 40 datasets from the UCR archive, comparing to current state-of-the-art methods. Based on our evaluation metrics, we show that the LatentCF++ framework can with high probability generate valid counterfactuals and achieve comparable explanations to current state-of-the-art. Our proposed approach can also generate counterfactuals that are considerably closer to the decision boundary in terms of margin difference.

In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose Glacier, a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of Glacier against three competitors. Our findings suggest that Glacier outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover, Glacier obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of Glacier to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.

Among recent developments in time series forecasting methods, deep forecasting models have gained popularity as they can utilize hidden feature patterns in time series to improve forecasting performance. Nevertheless, the majority of current deep forecasting models are opaque, hence making it challenging to interpret the results. While counterfactual explanations have been extensively employed as a post-hoc approach for explaining classification models, their application to forecasting models still remains underexplored. In this paper, we formulate the novel problem of counterfactual generation for time series forecasting, and propose an algorithm, called ForecastCF, that solves the problem by applying gradient-based perturbations to the original time series. The perturbations are further guided by imposing constraints to the forecasted values. We experimentally evaluate ForecastCF using four state-of-the-art deep model architectures and compare to two baselines. ForecastCF outperforms the baselines in terms of counterfactual validity and data manifold closeness, while generating meaningful and relevant counterfactuals for various forecasting tasks.

Applying deep learning models for healthcare-related forecasting applications has been widely adopted, such as leveraging glucose monitoring data of diabetes patients to predict hyperglycaemic or hypoglycaemic events. However, most deep learning models are considered black-boxes; hence, the model predictions are not interpretable and may not offer actionable insights into medical practitioners’ decisions. Previous work has shown that counterfactual explanations can be applied in forecasting tasks by suggesting counterfactual changes in time series inputs to achieve the desired forecasting outcome. This study proposes a generalized multivariate forecasting setup of counterfactual generation by introducing a novel approach, COMET, which imposes three domain-specific constraint mechanisms to provide counterfactual explanations for glucose forecasting. Moreover, we conduct the experimental evaluation using two diabetes patient datasets to demonstrate the effectiveness of our proposed approach in generating realistic counterfactual changes in comparison with a baseline approach. Our qualitative analysis evaluates examples to validate that the counterfactual samples are clinically relevant and can effectively lead the patients to achieve a normal range of predicted glucose levels by suggesting changes to the treatment variables.