解码帕金森病诊断:一种基于OCT的可解释AI,具有SHAP/LIME透明度,来自波斯队列研究
Zohreh Ganji1, Farzaneh Nikparast1, Naser Shoeibi2
1Department of Medical Physics, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran; Student research committee, Mashhad University of medical sciences, Mashhad, Iran.
Photodiagnosis and photodynamic therapy
|June 16, 2025
概括
这项研究使用视网膜成像和人工智能更早诊断帕金森病 (PD). 可解释的AI模型识别了用于改善PD检测和管理的关键视网膜生物标志物.
科学领域:
- 眼科医生 眼科 眼科
- 神经学 神经学
- 人工智能的人工智能
背景情况:
- 帕金森病 (PD) 诊断是具有挑战性的,因为主观评估和症状发病迟到.
- 视网膜光连贯断层扫描 (OCT) 提供了神经退行症的非侵入性生物标志物.
- 将OCT与可解释AI (XAI) 整合起来可以提高PD诊断的准确性.
研究的目的:
- 开发和验证可解释的AI框架用于早期帕金森病诊断,使用视网膜OCT生物标志物和临床数据.
- 为了确定关键的OCT和临床特征预测PD.
- 为了提高诊断的透明度和可靠性.
主要方法:
- 一个6层深度神经网络 (DNN) 使用OCT生物标志物 (骨厚度,体积) 和来自波斯队列研究的临床数据 (运动,嗅觉) 开发.
- 合成少数群体过量采样 (SMOTE) 用于解决阶级不平衡 (PD:健康 ≈ 1: 5).
- SHAP和LIME用于模型解释性,提供全球和本地特征解释.
主要成果:
- 可解释的AI框架实现了95.3%的准确性和0.98的PD诊断AUC-ROC.
- 确定的主要生物标志物包括SUPERIOR4厚度 (<120微米) 和体积膨胀 (>0.15毫米3),以及运动和嗅觉缺陷.
- 在保持高特异性 (94.8%) 的同时,SMOTE减少了12%的假阴性.
结论:
- 这项研究提出了一个透明的,基于OCT的AI框架,用于通过视网膜神经退行模式早期检测PD.
- 多式联运,可解释和强大的模型适用于资源有限的设置.
- 建议在不同人群中进行进一步的验证,并对海外国家和地区的协议进行标准化.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
595
07:26Characterizing the Relationship Between Eye Movement Parameters and Cognitive Functions in Non-demented Parkinson's Disease Patients with Eye Tracking
Published on: September 26, 2019
8.0K
相关概念视频
Parkinson's Disease: Overview
723
Neurodegenerative disorders are progressive diseases that cause irreversible damage and loss to neurons in specific brain areas. Examples of these disorders include Parkinson's disease, Alzheimer's disease, Multiple Sclerosis (MS), and Amyotrophic Lateral Sclerosis (ALS). These disorders share characteristics such as proteinopathies, selective neuronal vulnerability, and a complex interplay between genetic and environmental factors. The primary therapeutic goal for these conditions is...
723
Parkinson's Disease: Treatment
391
Neurodegenerative disorders, such as Parkinson's Disease (PD), involve the gradual and irreversible destruction of neurons in particular brain areas. These disorders exhibit standard features like proteinopathies, selective vulnerability of some neurons, and an interaction of intrinsic properties, genetics, and environmental influences in neural injury.
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...
391
