Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations

• URL: http://arxiv.org/abs/2301.11315v2
• Date: Sun, 29 Jan 2023 14:38:09 GMT
• Title: Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations
• Authors: Mingquan Lin, Yuyun Xiao, Bojian Hou, Tingyi Wanyan, Mohit Manoj Sharma, Zhangyang Wang, Fei Wang, Sarah Van Tassel, Yifan Peng
• Abstract summary: Primary open-angle glaucoma (POAG) is the leading cause of blindness in the United States. Deep learning has been widely used to detect POAG using fundus images. Human bias in clinical diagnosis may be reflected and amplified in the widely-used deep learning models.
• Score: 64.91773761529183
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: In the United States, primary open-angle glaucoma (POAG) is the leading cause of blindness, especially among African American and Hispanic individuals. Deep learning has been widely used to detect POAG using fundus images as its performance is comparable to or even surpasses diagnosis by clinicians. However, human bias in clinical diagnosis may be reflected and amplified in the widely-used deep learning models, thus impacting their performance. Biases may cause (1) underdiagnosis, increasing the risks of delayed or inadequate treatment, and (2) overdiagnosis, which may increase individuals' stress, fear, well-being, and unnecessary/costly treatment. In this study, we examined the underdiagnosis and overdiagnosis when applying deep learning in POAG detection based on the Ocular Hypertension Treatment Study (OHTS) from 22 centers across 16 states in the United States. Our results show that the widely-used deep learning model can underdiagnose or overdiagnose underserved populations. The most underdiagnosed group is female younger (< 60 yrs) group, and the most overdiagnosed group is Black older (>=60 yrs) group. Biased diagnosis through traditional deep learning methods may delay disease detection, treatment and create burdens among under-served populations, thereby, raising ethical concerns about using deep learning models in ophthalmology clinics.

Related papers

• Can Machine Learning Assist in Diagnosis of Primary Immune Thrombocytopenia? A feasibility study [12.4123972735841]
  Primary Immune thrombocytopenia (ITP) is a rare autoimmune disease characterised by immune-mediated destruction of peripheral blood platelets in patients. There is no established test to confirm the disease and no biomarker with which one can predict the response to treatment and outcome. We conduct a feasibility study to check if machine learning can be applied effectively for diagnosis of ITP using routine blood tests and demographic data in a non-acute outpatient setting.
  arXiv  Detail & Related papers  (2024-05-31T01:04:46Z)
• Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling [49.52787013516891]
  Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.
  arXiv  Detail & Related papers  (2024-05-14T17:15:28Z)
• Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging [13.141767097232796]
  Self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. It is crucial to ensure that these AI models do not mirror or amplify human biases, thereby disadvantaging historically marginalized groups such as females or Black patients. This study investigates the algorithmic fairness of state-of-the-art vision-language foundation models in chest X-ray diagnosis across five globally-sourced datasets.
  arXiv  Detail & Related papers  (2024-02-22T18:59:53Z)
• OpenAPMax: Abnormal Patterns-based Model for Real-World Alzheimer's Disease Diagnosis [9.316162293112738]
  We propose an open-set recognition model, OpenAPMax, based on the anomaly pattern to address Alzheimer's disease diagnosis. We evaluate the performance of the proposed method with recent open-set recognition, where we obtain state-of-the-art results.
  arXiv  Detail & Related papers  (2023-07-03T11:21:09Z)
• Deep Reinforcement Learning Framework for Thoracic Diseases Classification via Prior Knowledge Guidance [49.87607548975686]
  The scarcity of labeled data for related diseases poses a huge challenge to an accurate diagnosis. We propose a novel deep reinforcement learning framework, which introduces prior knowledge to direct the learning of diagnostic agents. Our approach's performance was demonstrated using the well-known NIHX-ray 14 and CheXpert datasets.
  arXiv  Detail & Related papers  (2023-06-02T01:46:31Z)
• Automatic Classification of Neuromuscular Diseases in Children Using Photoacoustic Imaging [77.32032399775152]
  Neuromuscular diseases (NMDs) cause a significant burden for both healthcare systems and society. They can lead to severe progressive muscle weakness, muscle degeneration, contracture, deformity and progressive disability.
  arXiv  Detail & Related papers  (2022-01-27T16:37:19Z)
• Assessing glaucoma in retinal fundus photographs using Deep Feature Consistent Variational Autoencoders [63.391402501241195]
  glaucoma is challenging to detect since it remains asymptomatic until the symptoms are severe. Early identification of glaucoma is generally made based on functional, structural, and clinical assessments. Deep learning methods have partially solved this dilemma by bypassing the marker identification stage and analyzing high-level information directly to classify the data.
  arXiv  Detail & Related papers  (2021-10-04T16:06:49Z)
• ADiag: Graph Neural Network Based Diagnosis of Alzheimer's Disease [0.0]
  Alzheimer's Disease (AD) is the most widespread neurodegenerative disease, affecting over 50 million people across the world. Currently, only qualitative means of testing are employed in the form of scoring performance on a battery of cognitive tests. We have developed ADiag, a novel quantitative method to diagnose AD through GraphSAGE Network and Dense Differentiable Pooling (DDP) analysis. Preliminary tests of ADiag have revealed a robust accuracy of 83%, vastly outperforming other qualitative and quantitative diagnostic techniques.
  arXiv  Detail & Related papers  (2021-01-08T06:23:30Z)
• A Smartphone-based System for Real-time Early Childhood Caries Diagnosis [76.71303610807156]
  Early childhood caries (ECC) is the most common, yet preventable chronic disease in children under the age of 6. In this study, we propose a multistage deep learning-based system for cavity detection. We integrate the deep learning system into an easy-to-use mobile application that can diagnose ECC from an early stage and provide real-time results to untrained users.
  arXiv  Detail & Related papers  (2020-08-17T21:11:19Z)
• COVID-19 in differential diagnosis of online symptom assessments [3.322985051936811]
  COVID-19 pandemic has magnified an already existing trend of people looking for healthcare solutions online. Traditional symptom checkers are based on manually curated expert systems that are inflexible and hard to modify. In this paper we present an approach that combines the strengths of traditional AI expert systems and novel deep learning models.
  arXiv  Detail & Related papers  (2020-08-07T18:10:42Z)

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.