Dimensional clinical phenotyping using post-mortem brain donor medical records: Association with neuropathology

Abstract

INTRODUCTIONTransdiagnostic 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. METHODSWe 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 Alzheimers disease (AD) neuropathological measures. RESULTSOur 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 ({beta}=0.38, p=0.0004), parietal ({beta}=0.35, p=0.0008), temporal ({beta}=0.37, p=0. 0004) and occipital ({beta}=0.37, p=0.0003) lobes. DISCUSSIONThis proof of concept study supports the validity of NLP-based methodologies to obtain quantitative measures of RDoC clinical domains from postmortem EHR.