Temporal characterization of Alzheimer's Disease with sequences of clinical records.

BACKGROUND: Alzheimer's Disease (AD) is a complex clinical phenotype with unprecedented social and economic tolls on an ageing global population. Real-world data (RWD) from electronic health records (EHRs) offer opportunities to accelerate precision drug development and scale epidemiological research on AD. A precise characterization of AD cohorts is needed to address the noise abundant in RWD. METHODS: We conducted a retrospective cohort study to develop and test computational models for AD cohort identification using clinical data from 8 Massachusetts healthcare systems. We mined temporal representations from EHR data using the transitive sequential pattern mining algorithm (tSPM) to train and validate our models. We then tested our models against a held-out test set from a review of medical records to adjudicate the presence of AD. We trained two classes of Machine Learning models, using Gradient Boosting Machine (GBM), to compare the utility of AD diagnosis records versus the tSPM temporal representations (comprising sequences of diagnosis and medication observations) from electronic medical records for characterizing AD cohorts. FINDINGS: In a group of 4985 patients, we identified 219 tSPM temporal representations (i.e., transitive sequences) of medical records for constructing the best classification models. The models with sequential features improved AD classification by a magnitude of 3-16 percent over the use of AD diagnosis codes alone. The computed cohort included 663 patients, 35 of whom had no record of AD. Six groups of tSPM sequences were identified for characterizing the AD cohorts. INTERPRETATION: We present sequential patterns of diagnosis and medication codes from electronic medical records, as digital markers of Alzheimer's Disease. Classification algorithms developed on sequential patterns can replace standard features from EHRs to enrich phenotype modelling. FUNDING: National Institutes of Health: the National Institute on Aging (RF1AG074372) and the National Institute of Allergy and Infectious Diseases (R01AI165535).

Characterizing Clinical and Neuropathological Traits of APOE Haplotypes in African Americans and Europeans.

BACKGROUND: The APOEɛ4 allele is the largest genetic risk factor for late-onset Alzheimer's disease (AD). Recent literature suggested that the contribution of APOEɛ4 to AD risk could be population-specific, with ɛ4 conferring a lower risk to Blacks or African Americans. OBJECTIVE: To investigate the effect of APOE haplotypes on AD risk in individuals with European ancestry (EU) and Blacks or African Americans (AA). METHODS: We selected data from 1) the National Alzheimer's Coordinating Center: a total of 3,486 AD cases and 4,511 controls (N = 7,997, 60% female) with genotypes from the Alzheimer's Disease Genetics Consortium (ADGC), and 2) the Rush University Religious Orders Study and Memory and Aging Project (ROSMAP) cohort with 578 AD and 670 controls (N = 1,248, 60% female). Using ɛ3 homozygotes as the reference, we compared the association of various APOE haplotypes with the clinical and neuropathological correlates of dementia in AA and EU. RESULTS: In both cohorts, we find no difference in the odds or age of onset of AD among the ɛ4-linked haplotypes defined by rs769449 within either AA or EU. Additionally, while APOEɛ4 was associated with a faster rate of decline, no differences were found in rate of decline, clinical or neuropathological features among the ɛ4-linked haplotypes. Further analysis with other variants near the APOE locus failed to identify any effect modification. CONCLUSION: Our study finds similar effects of the ɛ4-linked haplotypes defined by rs769449 on AD as compared to ɛ3 in both AA and EU. Future studies are required to understand the heterogeneity of APOE conferred risk of AD among various genotypes and populations.

Cognitive Profile and its Association with Neuroimaging Markers of Non-Demented Cerebral Amyloid Angiopathy Patients in a Stroke Unit.

BACKGROUND: Cerebral amyloid angiopathy (CAA) is increasingly recognized as a cause of cognitive impairment in the elderly, but the cognitive profile in patients with the disease has not been well characterized. OBJECTIVE: To characterize the neuropsychological profile of CAA patients without dementia and to determine the association between cognitive performance in different domains and neuroimaging lesions characteristic of CAA. METHODS: Fifty-eight non-demented CAA patients were compared to 138 cognitively normal subjects using a standard neuropsychological test battery. Total brain volume (TBV), white matter hyperintensities, number of lobar cerebral microbleeds, hippocampal volume, and cortical superficial siderosis in all CAA patients were assessed. The association between these neuroimaging markers and neuropsychological performance in different cognitive domains in the CAA group were analyzed. RESULTS: Patients with CAA had significantly worse performance on all individual neuropsychological domains tested, when compared to the cognitive normal group. The cognitive decline of CAA patients was most noticeable in tests for processing speed with a Z score of -1.92±1.56 (mean±SD), then followed by executive function (-0.93±1.01), episodic memory (-0.87±1.29), semantic fluency (-0.73±1.06), and attention (-0.42±0.98). TBV of the CAA patients was correlated with processing speed (ß= 0.335, p = 0.03) and executive function (ß= 0.394, p = 0.01). CONCLUSIONS: Non-demented patients with CAA had cognitive deficits in multiple areas. Lower TBV was related to slower processing speed and worse executive function.

Genetic and environmental contributions to the development of alcohol dependence in male twins.

BACKGROUND: Information on the heritability of the development of alcohol dependence could provide a better understanding of the importance of genetic components in disease transition. OBJECTIVE: To examine the genetic and nongenetic contributions to the age at onset of regular alcohol use, the age at diagnosis of alcohol dependence, and the transition from regular alcohol use to alcohol dependence. DESIGN: Classic twin study. SETTING: General community. PARTICIPANTS: This study included 3372 twin pairs of known zygosity from the Vietnam Era Twin Registry. The diagnosis of DSM-III-R-defined alcohol dependence and related information were obtained through telephone-administered interviews conducted in 1992. MAIN OUTCOME MEASURES: Standardized proportions due to genetic vs nongenetic factors of the total variation in twin resemblance on the age at onset of regular alcohol use, the age at meeting criteria for a diagnosis of alcohol dependence, and the transition period from regular alcohol use to a diagnosis of alcohol dependence. RESULTS: Genetic influence accounted for 49% of the variation in the age at diagnosis of alcohol dependence. After adjusting for co-occurring psychiatric diseases, additive genetic factors still explained more than 37% of the variance in age at onset of alcohol dependence and at least 25% of the variance in the transition period between regular drinking and the diagnosis of alcohol dependence. Additionally, after grouping participants as early and late regular users of alcohol, the genetic effects on the transition period for early regular users were statistically significantly greater than those for late regular users. CONCLUSION: Our results demonstrate a substantial heritable basis for alcohol dependence according to its developmental sequence, including age at onset of regular use, age at diagnosis, and the transition period between regular use and diagnosis.

Genetic and environmental contributions to age of onset of alcohol dependence symptoms in male twins.

AIMS: To investigate genetic and environmental influences on the development of specific alcohol dependence symptoms. DESIGN AND PARTICIPANTS: A classical twin study of 3372 male-male twin pairs in the Vietnam Era Twin (VET) Registry based on telephone interviews about alcohol use. MEASUREMENTS: The nine diagnostic symptoms according to the Diagnostic and Statistical Manual of Mental Disorder, version III (revised) (DSM-III-R) definition of alcohol dependence. Symptoms were grouped into those based on impaired control, biological effects and social consequences (Beresford's classification) or early versus late symptoms (Nelson's classification). Survival models with random effects were used to examine the age of onset of each symptom. FINDINGS: Approximately 38% of the variation in age of onset of each symptom group based on Beresford's classification is due to additive genetic factors. The age of onset of late symptoms from Nelson's classification appears to be most affected by genetic factors. Estimates of genetic effects for impaired control symptoms are greatly decreased when twins with comorbid psychiatric disorders are excluded. CONCLUSIONS: Our results support the heritability of age of onset of DSM-III-R-defined symptoms for alcohol dependence. However, no symptom group in Beresford's classification could be identified as more heritable than other symptom groups. A strong association between genetic vulnerability and co-occurring diseases for symptoms indicative of impaired control could be found. In addition, our findings show that the late symptom group could be a good candidate for subsequent genetic research.

The application of a random effects model to censored twin data.

The authors propose a random effects model to analyze the latent genetic and environmental effects on determining censored outcomes in twin studies. In this model, six normally distributed random effects are used to describe the correlation within twin pairs. The authors employ a Monte Carlo Expectation-Maximization approach for obtaining maximum likelihood estimates of fixed effects and the variances of random effects. The variances of the random effects are reparameterized to be equivalent to genetic and environmental effects in traditional twin models. The authors illustrate this model using data from the Vietnam Era Twin Registry to explore the magnitude of the genetic influence on twin similarity for the age of onset of alcohol abuse. Our results show genetic factors contribute about one third of twin similarity in the age of onset of alcohol abuse in male twins. The application of this model to twin data is discussed.