What Do You See in this Patient? Behavioral Testing of Clinical NLP Models

• URL: http://arxiv.org/abs/2111.15512v1
• Date: Tue, 30 Nov 2021 15:52:04 GMT
• Title: What Do You See in this Patient? Behavioral Testing of Clinical NLP Models
• Authors: Betty van Aken, Sebastian Herrmann, Alexander L\"oser
• Abstract summary: We introduce an extendable testing framework that evaluates the behavior of clinical outcome models regarding changes of the input. We show that model behavior varies drastically even when fine-tuned on the same data and that allegedly best-performing models have not always learned the most medically plausible patterns.
• Score: 69.09570726777817
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Decision support systems based on clinical notes have the potential to improve patient care by pointing doctors towards overseen risks. Predicting a patient's outcome is an essential part of such systems, for which the use of deep neural networks has shown promising results. However, the patterns learned by these networks are mostly opaque and previous work revealed flaws regarding the reproduction of unintended biases. We thus introduce an extendable testing framework that evaluates the behavior of clinical outcome models regarding changes of the input. The framework helps to understand learned patterns and their influence on model decisions. In this work, we apply it to analyse the change in behavior with regard to the patient characteristics gender, age and ethnicity. Our evaluation of three current clinical NLP models demonstrates the concrete effects of these characteristics on the models' decisions. They show that model behavior varies drastically even when fine-tuned on the same data and that allegedly best-performing models have not always learned the most medically plausible patterns.

Related papers

• Ethical considerations of use of hold-out sets in clinical prediction model management [0.4194295877935868]
  We focus on the ethical principles of beneficence, non-maleficence, autonomy and justice. We also discuss statistical issues arising from different hold-out set sampling methods.
  arXiv  Detail & Related papers  (2024-06-05T11:42:46Z)
• Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery [6.1521675665532545]
  In medical imaging, discerning the rationale behind an AI model's predictions is crucial for evaluating its reliability. We propose an explainable model that is equipped with both decision reasoning and feature identification capabilities. By implementing our method, we can efficiently identify and visualise class-specific features leveraged by the data-driven model.
  arXiv  Detail & Related papers  (2024-05-23T19:00:38Z)
• Towards a Transportable Causal Network Model Based on Observational Healthcare Data [1.333879175460266]
  We propose a novel approach that combines selection diagrams, missingness graphs, causal discovery and prior knowledge into a single graphical model. We learn this model from data comprising two different cohorts of patients. The resulting causal network model is validated by expert clinicians in terms of risk assessment, accuracy and explainability.
  arXiv  Detail & Related papers  (2023-11-13T13:23:31Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• This Patient Looks Like That Patient: Prototypical Networks for Interpretable Diagnosis Prediction from Clinical Text [56.32427751440426]
  In clinical practice such models must not only be accurate, but provide doctors with interpretable and helpful results. We introduce ProtoPatient, a novel method based on prototypical networks and label-wise attention. We evaluate the model on two publicly available clinical datasets and show that it outperforms existing baselines.
  arXiv  Detail & Related papers  (2022-10-16T10:12:07Z)
• Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability [82.29775890542967]
  Estimating personalized effects of treatments is a complex, yet pervasive problem. Recent developments in the machine learning literature on heterogeneous treatment effect estimation gave rise to many sophisticated, but opaque, tools. We use post-hoc feature importance methods to identify features that influence the model's predictions.
  arXiv  Detail & Related papers  (2022-06-16T17:59:05Z)
• Towards Trustworthy Cross-patient Model Development [3.109478324371548]
  We study differences in model performance and explainability when trained for all patients and one patient at a time. The results show that patients' demographics has a large impact on the performance and explainability and thus trustworthiness.
  arXiv  Detail & Related papers  (2021-12-20T10:51:04Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.