Screening for Alzheimer's Disease Based on Raman Spectroscopy of Blood

摘要- 阿尔茨海默氏病（AD）是一种进行性神经退行性疾病，估计影响620万人 AD是美国人的第六大死因，是进行性和不可治愈的;痴呆症状 在数年内逐渐恶化。在早期阶段，记忆丧失是轻微的，但在晚期AD，个体 失去了进行对话和对环境做出反应的能力。AD是一种毁灭性的疾病， 为个人及其家庭带来巨大的情感、经济和身体挑战。在AD中，病理性 变化可能在痴呆症发作前20年出现，这提供了一个独特的机会窗口。 旨在保护认知健康和延缓疾病进展的干预措施。不过有 目前没有诊断工具可以广泛应用于临床前AD的检测。当潜在地 有效的治疗在潜在疾病病理过程的后期开始（即，在认知能力下降之后， 但在实际情况中，预防的真正效果并没有实现。为了满足对无障碍环境的迫切需要， 早期和临床前AD的诊断工具，早期阿尔茨海默氏症诊断建议开发一种筛查 基于拉曼光谱技术与机器学习（ML）模型相结合， 基于血液中发现的多种生物标志物的贡献来检测光谱特征变化。 这项技术有可能通过让患者早期识别出 AD的迹象，因此开始预防干预措施和积极监测疾病进展， 痴呆症的发病，并保持大脑健康更长的时间。这种工具也将在以下方面具有重要的效用： 急需的新AD疗法的临床试验，促进健康志愿者的招募和选择 和处于疾病进展的各个阶段的AD患者。初步结果表明，该方法可以 区分不同阶段的AD患者和健康对照者的血液生化成分。 该团队还开发了一种新方法，使用固体样品的自动映射来检测超小 通过防止生物标志物留下被聚焦激光询问的小体积， 在光谱采集期间。第一阶段项目将在调整过程中提供消除风险的关键方面， 将该技术转化为临床商业应用，并通过盲测提供可行性证明。具体 本STTR项目的目标是：1）优化一种可扩展的，快速的方法来获得和分析拉曼 2）开发用于分析拉曼光谱数据的ML算法方法;以及 3)在盲测中验证了基于拉曼光谱的方法。成功完成拟议研究 将定位早期阿尔茨海默氏症诊断进行初步临床试验的第二阶段，并推进讨论 与潜在的行业合作伙伴建立伙伴关系，将拟议的方法发展成为一个立场， 单独诊断测试或可能的伴随诊断。

Abstract - Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects an estimated 6.2 million Americans and the 6th leading cause of death in the U.S. AD is progressive and incurable; dementia symptoms gradually worsen over a number of years. In its early stages, memory loss is mild, but in late-stage AD, individuals lose the ability to carry on a conversation and respond to their environment. AD is a devastating condition that creates vast emotional, financial, and physical challenges for the person and their family. In AD, pathological changes may arise up to 20 years before the onset of dementia, providing a unique window of opportunity for interventions aimed at preserving cognitive health and delaying disease progression. However, there is currently no diagnostic tool that can be widely applied for the detection of preclinical AD. When potentially effective therapies are initiated late in the underlying disease pathology process (i.e., after cognitive decline is apparent), the true impact of prevention is not achieved. In response to the critical need for an accessible diagnostic tool for early and preclinical AD, Early Alzheimer’s Diagnostics proposes to develop a screening technology based on Raman Spectroscopy combined with machine learning (ML) models trained to detect spectral signature changes based on the contribution of multiple biomarkers found in the blood. The proposed technology has the potential to greatly improve outcomes by allowing patients to identify early signs of AD, and therefore start preventive interventions and active monitoring of disease progression, delaying the onset of dementia, and preserving brain health for longer. Such a tool would also have significant utility in clinical trials for critically needed new AD therapies, facilitating recruitment and selection of healthy volunteers and AD patients at various stages of disease progression. Preliminary results show that the approach can differentiate the biochemical composition of blood from patients at different stages of AD from healthy controls. The team has also developed a novel method using automated mapping of solid samples to detect ultra-small amounts of biomarkers by preventing them from leaving a small volume interrogated by the focused laser light during spectral acquisition. This Phase I project will provide de-risk key aspects in the process of adapting the technology into a clinical commercial application and provide proof-of-feasibility via a blind test. The Specific Aims of this STTR project are: 1) Optimize a scalable, rapid methodology for obtaining and analyzing Raman spectral data from blood serum; 2) Develop ML algorithm approaches for analyzing Raman spectral data; and 3) Validate the Raman spectroscopy-based approach in a blind test. Successful completion of proposed research will position Early Alzheimer’s Diagnostics to perform initial clinical trials in Phase II, and advance discussions with potential industry partners to establish partnerships to develop the proposed approach into either a stand- alone diagnostic test or possible companion diagnostic.