Dataset Information

Improving Clinical Translation of Machine Learning Approaches Through Clinician-Tailored Visual Displays of Black Box Algorithms: Development and Validation.

ABSTRACT: BACKGROUND:Despite the promise of machine learning (ML) to inform individualized medical care, the clinical utility of ML in medicine has been limited by the minimal interpretability and black box nature of these algorithms. OBJECTIVE:The study aimed to demonstrate a general and simple framework for generating clinically relevant and interpretable visualizations of black box predictions to aid in the clinical translation of ML. METHODS:To obtain improved transparency of ML, simplified models and visual displays can be generated using common methods from clinical practice such as decision trees and effect plots. We illustrated the approach based on postprocessing of ML predictions, in this case random forest predictions, and applied the method to data from the Left Ventricular (LV) Structural Predictors of Sudden Cardiac Death (SCD) Registry for individualized risk prediction of SCD, a leading cause of death. RESULTS:With the LV Structural Predictors of SCD Registry data, SCD risk predictions are obtained from a random forest algorithm that identifies the most important predictors, nonlinearities, and interactions among a large number of variables while naturally accounting for missing data. The black box predictions are postprocessed using classification and regression trees into a clinically relevant and interpretable visualization. The method also quantifies the relative importance of an individual or a combination of predictors. Several risk factors (heart failure hospitalization, cardiac magnetic resonance imaging indices, and serum concentration of systemic inflammation) can be clearly visualized as branch points of a decision tree to discriminate between low-, intermediate-, and high-risk patients. CONCLUSIONS:Through a clinically important example, we illustrate a general and simple approach to increase the clinical translation of ML through clinician-tailored visual displays of results from black box algorithms. We illustrate this general model-agnostic framework by applying it to SCD risk prediction. Although we illustrate the methods using SCD prediction with random forest, the methods presented are applicable more broadly to improving the clinical translation of ML, regardless of the specific ML algorithm or clinical application. As any trained predictive model can be summarized in this manner to a prespecified level of precision, we encourage the use of simplified visual displays as an adjunct to the complex predictive model. Overall, this framework can allow clinicians to peek inside the black box and develop a deeper understanding of the most important features from a model to gain trust in the predictions and confidence in applying them to clinical care.

SUBMITTER: Wongvibulsin S

PROVIDER: S-EPMC7312245 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving Clinical Translation of Machine Learning Approaches Through Clinician-Tailored Visual Displays of Black Box Algorithms: Development and Validation.

Wongvibulsin Shannon S Wu Katherine C KC Zeger Scott L SL

JMIR medical informatics 20200609 6

<h4>Background</h4>Despite the promise of machine learning (ML) to inform individualized medical care, the clinical utility of ML in medicine has been limited by the minimal interpretability and black box nature of these algorithms.<h4>Objective</h4>The study aimed to demonstrate a general and simple framework for generating clinically relevant and interpretable visualizations of black box predictions to aid in the clinical translation of ML.<h4>Methods</h4>To obtain improved transparency of ML, ...[more]

PMID: 32515746

Similar Datasets

Project description:Software systems typically have an input domain that can be subdivided into sub-domains, each of which generates similar or related outputs. Testing it on the boundaries between these sub-domains is critical to ensure high-quality software. Therefore, boundary value analysis and testing have been a fundamental part of the software testing toolbox for a long time and are typically taught early to software engineering students. Despite its many argued benefits, boundary value analysis for a given software specification or application is typically described in abstract terms. This allows for variation in how testers apply it and in the benefits they see. Additionally, its adoption has been limited since it requires a specification or model to be analysed. We propose an automated black-box boundary value detection method to support software testers in performing systematic boundary value analysis. This dynamic method can be utilized even without a specification or model. The proposed method is based on a metric referred to as the program derivative, which quantifies the level of boundariness of test inputs. By combining this metric with search algorithms, we can identify and rank pairs of inputs as good boundary candidates, i.e., inputs that are in close proximity to each other but with outputs that are far apart. We have implemented the AutoBVA approach and evaluated it on a curated dataset of example programs. Furthermore, we have applied the approach broadly to a sample of 613 functions from the base library of the Julia programming language. The approach could identify boundary candidates that highlight diverse boundary behaviours in over 70% of investigated systems under test. The results demonstrate that even a simple variant of the program derivative, combined with broad sampling and search over the input space, can identify interesting boundary candidates for a significant portion of the functions under investigation. In conclusion, we also discuss the future extension of the approach to encompass more complex systems under test cases and datatypes.

Project description:We propose a BlackBox Counterfactual Explainer, designed to explain image classification models for medical applications. Classical approaches (e.g., , saliency maps) that assess feature importance do not explain how imaging features in important anatomical regions are relevant to the classification decision. Such reasoning is crucial for transparent decision-making in healthcare applications. Our framework explains the decision for a target class by gradually exaggerating the semantic effect of the class in a query image. We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation. Our proposed loss function preserves essential details (e.g., support devices) in the generated images. We used counterfactual explanations from our framework to audit a classifier trained on a chest X-ray dataset with multiple labels. Clinical evaluation of model explanations is a challenging task. We proposed clinically-relevant quantitative metrics such as cardiothoracic ratio and the score of a healthy costophrenic recess to evaluate our explanations. We used these metrics to quantify the counterfactual changes between the populations with negative and positive decisions for a diagnosis by the given classifier. We conducted a human-grounded experiment with diagnostic radiology residents to compare different styles of explanations (no explanation, saliency map, cycleGAN explanation, and our counterfactual explanation) by evaluating different aspects of explanations: (1) understandability, (2) classifier's decision justification, (3) visual quality, (d) identity preservation, and (5) overall helpfulness of an explanation to the users. Our results show that our counterfactual explanation was the only explanation method that significantly improved the users' understanding of the classifier's decision compared to the no-explanation baseline. Our metrics established a benchmark for evaluating model explanation methods in medical images. Our explanations revealed that the classifier relied on clinically relevant radiographic features for its diagnostic decisions, thus making its decision-making process more transparent to the end-user.

Project description:BackgroundIndividuals with cognitive impairment and their families place a high value on receiving a dementia diagnosis, but clinician approaches vary. There is a need for research investigating experiences of giving and receiving dementia diagnoses. The current study aimed to investigate clinician approaches to giving dementia diagnoses as part of a larger study investigating patient, caregiver, and clinician experiences during the diagnosis encounter.MethodInvestigators conducted telephone interviews with Florida-based clinicians who give dementia diagnoses either rarely or commonly. Interviews employed a semi-structured interview guide querying communication practices used by clinicians when giving dementia diagnoses and how clinicians learned to give dementia diagnoses. Investigators used a descriptive qualitative design to conduct a thematic analysis of data.ResultsFifteen Florida-based clinicians participated, representing diverse backgrounds related to gender, race/ethnicity, specialty, and practice setting. Participants reported using patient- and family-centered communication practices including checking patient understanding, communicating empathically, and involving family members. Some clinicians explicitly asked patients and/or family members about their preferences regarding diagnosis disclosure; many clinicians tailored their disclosure based on patient and family characteristics or reactions. Some clinicians reported using specific diagnoses, while others used general terms such as "memory disorder." Clinicians reported positively framing information, including instilling hope, focusing on healthy behaviors, and discussing symptom management. Finally, clinicians provided patient/family education and arranged follow up. Clinicians reported learning approaches to dementia diagnosis disclosure through formal training and self-education.ConclusionsDiverse Florida-based clinicians described dementia disclosure practices largely consistent with published guidance, but clinicians varied on approaches relating to soliciting patient disclosure preferences and terminology used. Clinicians caring for diverse populations described that cultural background affects the disclosure process, but more research is needed regarding this finding and best practices for individuals from different backgrounds.

Dataset Information

Improving Clinical Translation of Machine Learning Approaches Through Clinician-Tailored Visual Displays of Black Box Algorithms: Development and Validation.

Publications

Improving Clinical Translation of Machine Learning Approaches Through Clinician-Tailored Visual Displays of Black Box Algorithms: Development and Validation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets