Vogelgsang Jonathan S, Dan Shu, Lally Anna P, Chatigny Michael, Vempati Sangeetha, Abston Joshua, Durning Peter T, Oakley Derek H, McCoy Thomas H, Klengel Torsten, Berretta Sabina
bioRxiv. 2023 May 5:2023.05.04.539430. doi: 10.1101/2023.05.04.539430.
Transdiagnostic dimensional phenotypes are essential to investigate the relationship between continuous symptom dimensions and pathological changes. This is a fundamental challenge to postmortem work, as assessment of newly developed phenotypic concepts needs to rely on existing records.
We adapted well-validated methodologies to compute NIMH research domain criteria (RDoC) scores using natural language processing (NLP) from electronic health records (EHRs) obtained from post-mortem brain donors and tested whether RDoC cognitive domain scores were associated with hallmark Alzheimer's disease (AD) neuropathological measures.
Our results confirm an association of EHR-derived cognitive scores with hallmark neuropathological findings. Notably, higher neuropathological load, particularly neuritic plaques, was associated with higher cognitive burden scores in the frontal (ß=0.38, p=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 postmortem EHR.
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。这对尸检工作来说是一项根本性挑战，因为对新开发的表型概念进行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）从死后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RDoC认知领域分数是否与典型阿尔茨海默病（AD）神经病理学指标相关。
我们的结果证实了源自EHR的认知分数与典型神经病理学发现之间存在关联。值得注意的是，更高的神经病理学负荷，尤其是神经炎斑块，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）更高的认知负担分数相关。
这项概念验证研究支持基于NLP的方法从死后EHR中获取RDoC临床领域定量测量值的有效性。
