Vogelgsang Jonathan, Dan Shu, Lally Anna P, Chatigny Michael, Vempati Sangeetha, Abston Joshua, Durning Peter T, Oakley Derek H, McCoy Thomas H, Klengel Torsten, Berretta Sabina
Department of Psychiatry, McLean Hospital Harvard Medical School Belmont Massachusetts USA.
Harvard Brain Tissue Resource Center, McLean Hospital Harvard Medical School Belmont Massachusetts USA.
Alzheimers Dement (Amst). 2023 Sep 22;15(3):e12464. doi: 10.1002/dad2.12464. eCollection 2023 Jul-Sep.
Transdiagnostic dimensional phenotypes are essential to investigate the relationship between continuous symptom dimensions and pathological changes. This is a fundamental challenge to work, as assessments of phenotypic concepts need to rely on existing records.
We adapted well-validated methodologies to compute National Institute of Mental Health Research Domain Criteria (RDoC) scores using natural language processing (NLP) from electronic health records (EHRs) obtained from brain donors and tested whether cognitive domain scores were associated with Alzheimer's disease neuropathological measures.
Our results confirm an association of EHR-derived cognitive scores with neuropathological findings. Notably, higher neuropathological load, particularly neuritic plaques, was associated with higher cognitive burden scores in the frontal (ß = 0.38, = 0.0004), parietal (ß = 0.35, P = 0.0008), temporal (ß = 0.37, P = 0.0004) and occipital (ß = 0.37, P = 0.0003) lobes.
This proof-of-concept study supports the validity of NLP-based methodologies to obtain quantitative measures of RDoC clinical domains from EHR. The associations may accelerate brain research beyond classical case-control designs.
跨诊断维度表型对于研究连续症状维度与病理变化之间的关系至关重要。这是一项工作中的基本挑战，因为表型概念的评估需要依赖现有记录。
我们采用经过充分验证的方法，利用自然语言处理（NLP）从脑捐赠者的电子健康记录（EHR）中计算美国国立精神卫生研究所研究领域标准（RDoC）分数，并测试认知领域分数是否与阿尔茨海默病神经病理学指标相关。
我们的结果证实了源自EHR的认知分数与神经病理学发现之间的关联。值得注意的是，更高的神经病理学负荷，尤其是神经炎性斑块，与额叶（β = 0.38，P = 0.0004）、顶叶（β = 0.35，P = 0.0008）、颞叶（β = 0.37，P = 0.0004）和枕叶（β = 0.37，P = 0.0003）的更高认知负担分数相关。
这项概念验证研究支持了基于NLP的方法从EHR中获取RDoC临床领域定量测量的有效性。这些关联可能会加速超越经典病例对照设计的脑研究。
