Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics

• URL: http://arxiv.org/abs/2004.13515v4
• Date: Wed, 2 Dec 2020 15:11:18 GMT
• Title: Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics
• Authors: Philippe Burlina, Neil Joshi, William Paul, Katia D. Pacheco, Neil M. Bressler
• Abstract summary: This study evaluated generative methods to potentially AI bias when diagnosing diabetic retinopathy. Deep learning systems (DLS) face concepts at test/inference time they were not initially trained on. Findings illustrate how data imbalance and domain generalization can lead to disparity of accuracy across subpopulations.
• Score: 5.34430209078787
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This study evaluated generative methods to potentially mitigate AI bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance, or domain generalization which occurs when deep learning systems (DLS) face concepts at test/inference time they were not initially trained on. The public domain Kaggle-EyePACS dataset (88,692 fundi and 44,346 individuals, originally diverse for ethnicity) was modified by adding clinician-annotated labels and constructing an artificial scenario of data imbalance and domain generalization by disallowing training (but not testing) exemplars for images of retinas with DR warranting referral (DR-referable) and from darker-skin individuals, who presumably have greater concentration of melanin within uveal melanocytes, on average, contributing to retinal image pigmentation. A traditional/baseline diagnostic DLS was compared against new DLSs that would use training data augmented via generative models for debiasing. Accuracy (95% confidence intervals [CI]) of the baseline diagnostics DLS for fundus images of lighter-skin individuals was 73.0% (66.9%, 79.2%) vs. darker-skin of 60.5% (53.5%, 67.3%), demonstrating bias/disparity (delta=12.5%) (Welch t-test t=2.670, P=.008) in AI performance across protected subpopulations. Using novel generative methods for addressing missing subpopulation training data (DR-referable darker-skin) achieved instead accuracy, for lighter-skin, of 72.0% (65.8%, 78.2%), and for darker-skin, of 71.5% (65.2%,77.8%), demonstrating closer parity (delta=0.5%) in accuracy across subpopulations (Welch t-test t=0.111, P=.912). Findings illustrate how data imbalance and domain generalization can lead to disparity of accuracy across subpopulations, and show that novel generative methods of synthetic fundus images may play a role for debiasing AI.

Related papers

• Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images [0.0]
  Diabetic retinopathy (DR) is one of the major complications in diabetic patients' eyes. This study aims to evaluate the accuracy of artificial intelligence (AI) in diagnosing DR.
  arXiv  Detail & Related papers  (2025-04-08T05:38:53Z)
• Artificial Intelligence-Based Triaging of Cutaneous Melanocytic Lesions [0.8864540224289991]
  Pathologists are facing an increasing workload due to a growing volume of cases and the need for more comprehensive diagnoses. We developed an artificial intelligence (AI) model for triaging cutaneous melanocytic lesions based on whole slide images.
  arXiv  Detail & Related papers  (2024-10-14T13:49:04Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Clinical Melanoma Diagnosis with Artificial Intelligence: Insights from a Prospective Multicenter Study [1.2397589403129072]
  AI has proven to be helpful for enhancing melanoma detection. Existing studies are limited by low sample sizes, too homogenous datasets, or lack of inclusion of rare melanoma subtypes. We assessed 'All Data are Ext' (ADAE), an established open-source algorithm for detecting melanomas, by comparing its diagnostic accuracy to that of dermatologists.
  arXiv  Detail & Related papers  (2024-01-25T14:03:54Z)
• Toward Clinically Trustworthy Deep Learning: Applying Conformal Prediction to Intracranial Hemorrhage Detection [0.0]
  This study is a retrospective study of 491 non-contrast head CTs from the CQ500 dataset, in which three senior radiologists annotated slices containing intracranial hemorrhage (ICH) A DL model was trained on 146 patients (10,815 slices) from the definite data (training dataset) to perform ICH localization and classification for five classes of ICH. The uncertainty-aware DL model was tested on 8,401 definite and challenging cases to assess its ability to identify challenging cases.
  arXiv  Detail & Related papers  (2024-01-16T02:26:29Z)
• DDxT: Deep Generative Transformer Models for Differential Diagnosis [51.25660111437394]
  We show that a generative approach trained with simpler supervised and self-supervised learning signals can achieve superior results on the current benchmark. The proposed Transformer-based generative network, named DDxT, autoregressively produces a set of possible pathologies, i.e., DDx, and predicts the actual pathology using a neural network.
  arXiv  Detail & Related papers  (2023-12-02T22:57:25Z)
• Deep neural network improves the estimation of polygenic risk scores for breast cancer [3.9918594409417576]
  Polygenic risk scores (PRS) estimate the genetic risk of an individual for a complex disease based on many genetic variants across the whole genome. A deep neural network (DNN) was found to outperform alternative machine learning techniques and established statistical algorithms.
  arXiv  Detail & Related papers  (2023-07-24T13:35:36Z)
• Generative models improve fairness of medical classifiers under distribution shifts [49.10233060774818]
  We show that learning realistic augmentations automatically from data is possible in a label-efficient manner using generative models. We demonstrate that these learned augmentations can surpass ones by making models more robust and statistically fair in- and out-of-distribution.
  arXiv  Detail & Related papers  (2023-04-18T18:15:38Z)
• Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism [65.70943212672023]
  Deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs. dataset of 70 panoramic radiographs (PRs) from 70 different subjects of age between 49 to 60 was used.
  arXiv  Detail & Related papers  (2021-10-19T00:03:57Z)
• SOUL: An Energy-Efficient Unsupervised Online Learning Seizure Detection Classifier [68.8204255655161]
  Implantable devices that record neural activity and detect seizures have been adopted to issue warnings or trigger neurostimulation to suppress seizures. For an implantable seizure detection system, a low power, at-the-edge, online learning algorithm can be employed to dynamically adapt to neural signal drifts. SOUL was fabricated in TSMC's 28 nm process occupying 0.1 mm2 and achieves 1.5 nJ/classification energy efficiency, which is at least 24x more efficient than state-of-the-art.
  arXiv  Detail & Related papers  (2021-10-01T23:01:20Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• Interpretable Survival Prediction for Colorectal Cancer using Deep Learning [2.9084170197404844]
  We developed a deep learning system (DLS) for predicting disease specific survival for stage II and III colorectal cancer. We generated human-interpretable histologic features by clustering embeddings from a deep-learning based image-similarity model. Our approach can be used to explain predictions from a prognostic deep learning model and uncover potentially-novel prognostic features.
  arXiv  Detail & Related papers  (2020-11-17T21:57:16Z)

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.