Dataset Information

Improving the phenotype risk score as a scalable approach to identifying patients with Mendelian disease.

ABSTRACT:

Objective

The Phenotype Risk Score (PheRS) is a method to detect Mendelian disease patterns using phenotypes from the electronic health record (EHR). We compared the performance of different approaches mapping EHR phenotypes to Mendelian disease features.

Materials and methods

PheRS utilizes Mendelian diseases descriptions annotated with Human Phenotype Ontology (HPO) terms. In previous work, we presented a map linking phecodes (based on International Classification of Diseases [ICD]-Ninth Revision) to HPO terms. For this study, we integrated ICD-Tenth Revision codes and lab data. We also created a new map between HPO terms using customized groupings of ICD codes. We compared the performance with cases and controls for 16 Mendelian diseases using 2.5 million de-identified medical records.

Results

PheRS effectively distinguished cases from controls for all 15 positive controls and all approaches tested (P < 4 × 1016). Adding lab data led to a statistically significant improvement for 4 of 14 diseases. The custom ICD groupings improved specificity, leading to an average 8% increase for precision at 100 (-2% to 22%). Eight of 10 adults with cystic fibrosis tested had PheRS in the 95th percentile prio to diagnosis.

Discussion

Both phecodes and custom ICD groupings were able to detect differences between affected cases and controls at the population level. The ICD map showed better precision for the highest scoring individuals. Adding lab data improved performance at detecting population-level differences.

Conclusions

PheRS is a scalable method to study Mendelian disease at the population level using electronic health record data and can potentially be used to find patients with undiagnosed Mendelian disease.

SUBMITTER: Bastarache L

PROVIDER: S-EPMC6857501 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving the phenotype risk score as a scalable approach to identifying patients with Mendelian disease.

Bastarache Lisa L Hughey Jacob J JJ Goldstein Jeffrey A JA Bastraache Julie A JA Das Satya S Zaki Neil Charles NC Zeng Chenjie C Tang Leigh Anne LA Roden Dan M DM Denny Joshua C JC

Journal of the American Medical Informatics Association : JAMIA 20191201 12

<h4>Objective</h4>The Phenotype Risk Score (PheRS) is a method to detect Mendelian disease patterns using phenotypes from the electronic health record (EHR). We compared the performance of different approaches mapping EHR phenotypes to Mendelian disease features.<h4>Materials and methods</h4>PheRS utilizes Mendelian diseases descriptions annotated with Human Phenotype Ontology (HPO) terms. In previous work, we presented a map linking phecodes (based on International Classification of Diseases [I ...[more]

PMID: 31609419

Similar Datasets

Project description:ObjectiveMany healthcare systems employ population-based risk scores to prospectively identify patients at high risk of poor outcomes, but it is unclear whether single point-in-time scores adequately represent future risk. We sought to identify and characterize latent subgroups of high-risk patients based on risk score trajectories.Study designObservational study of 7289 patients discharged from Veterans Health Administration (VA) hospitals during a 1-week period in November 2012 and categorized in the top 5th percentile of risk for hospitalization.MethodsUsing VA administrative data, we calculated weekly risk scores using the validated Care Assessment Needs model, reflecting the predicted probability of hospitalization. We applied the non-parametric k-means algorithm to identify latent subgroups of patients based on the trajectory of patients' hospitalization probability over a 2-year period. We then compared baseline sociodemographic characteristics, comorbidities, health service use, and social instability markers between identified latent subgroups.ResultsThe best-fitting model identified two subgroups: moderately high and persistently high risk. The moderately high subgroup included 65% of patients and was characterized by moderate subgroup-level hospitalization probability decreasing from 0.22 to 0.10 between weeks 1 and 66, then remaining constant through the study end. The persistently high subgroup, comprising the remaining 35% of patients, had a subgroup-level probability increasing from 0.38 to 0.41 between weeks 1 and 52, and declining to 0.30 at study end. Persistently high-risk patients were older, had higher prevalence of social instability and comorbidities, and used more health services.ConclusionsOn average, one third of patients initially identified as high risk stayed at very high risk over a 2-year follow-up period, while risk for the other two thirds decreased to a moderately high level. This suggests that multiple approaches may be needed to address high-risk patient needs longitudinally or intermittently.

Project description:BackgroundAlzheimer's disease (AD) is a heterogeneously progressive neurodegeneration disorder with varied rates of deterioration, either between subjects or within different stages of a certain subject. Estimating the course of AD at early stages has treatment implications. We aimed to analyze disease progression to identify distinct patterns in AD trajectory.MethodsWe proposed a deep learning model to identify underlying patterns in the trajectory from cognitively normal (CN) to a state of mild cognitive impairment (MCI) to AD dementia, by jointly predicting time-to-conversion and clustering out distinct subgroups characterized by comprehensive features as well as varied progression rates. We designed and validated our model on the ADNI dataset (1370 participants). Prediction of time-to-conversion in AD trajectory was used to validate the expression of the identified patterns. Causality between patterns and time-to-conversion was further inferred using Mendelian randomization (MR) analysis. External validation was performed on the AIBL dataset (233 participants).FindingsThe proposed model clustered out patterns characterized by significantly different biomarkers and varied progression rates. The discovered patterns also showed a strong prediction ability, as indicated by hazard ratio (CN→MCI, HR = 3.51, p < 0.001; MCI→AD, HR = 8.11, p < 0.001), C-Index (CN→MCI, 0.618; MCI→AD, 0.718), and AUC (CN→MCI, 3 years 0.802, 5 years 0.876; MCI→AD, 3 years 0.914, 5 years 0.957). In the external validation cohort, our model demonstrated competitive performance on conversion time prediction (CN→MCI, C-Index = 0.693; MCI→AD, C-Index = 0.752). Moreover, suggestive associations between CN→MCI/MCI→AD patterns with four/three SNPs were mediated and MR analysis indicated a causal link between MCI→AD patterns and time-to-conversion in the first three years.InterpretationOur proposed model identifies biologically and clinically meaningful patterns from real-world data and provides promising performance on time-to-conversion prediction in AD trajectory, which could promote the understanding of disease progression, facilitate clinical trial design, and provide potential for decision-making.FundingThe National Key Research and Development Program of China, the Key R&D Program of Zhejiang, and the National Nature Science Foundation of China.

Project description:ImportanceExposure to bullying is a prevalent experience with adverse consequences throughout the life span. Individual vulnerabilities and traits, such as preexisting mental health problems, may be associated with increased likelihood of experiencing bullying. Identifying such individual vulnerabilities and traits is essential for a better understanding of the etiology of exposure to bullying and for tailoring effective prevention.ObjectiveTo identify individual vulnerabilities and traits associated with exposure to bullying in childhood and adolescence.Design, setting, and participantsFor this study, data were drawn from the Avon Longitudinal Study of Parents and Children (ALSPAC), a population-based birth cohort study. The initial ALSPAC sample consisted of 14 062 children born to women residing in Avon, United Kingdom, with an expected date of delivery between April 1, 1991, and December 31, 1992. Collection of the ALSPAC data began in September 6, 1990, and the last follow-up assessment of exposure to bullying was conducted when participants were 13 years of age. Data analysis was conducted from November 1, 2017, to January 1, 2019.ExposuresThe polygenic score approach was used to derive genetic proxies that indexed vulnerabilities and traits. A total of 35 polygenic scores were computed for a range of mental health vulnerabilities (eg, depression) and traits related to cognition (eg, intelligence), personality (eg, neuroticism), and physical measures (eg, body mass index), as well as negative controls (eg, osteoporosis).Main outcomes and measuresSingle and multi-polygenic score regression models were fitted to test the association between indexed traits and exposure to bullying. Children completed the Bullying and Friendship Interview Schedule at the ages of 8, 10, and 13 years. A mean score of exposure to bullying across ages was used as the main outcome.ResultsA total of 5028 genotyped individuals (2481 boys and 2547 girls) with data on exposure to bullying were included. Among the 35 initially included polygenic scores, 11 were independently associated with exposure to bullying; no significant association was detected for the 24 remaining scores. In multivariable analyses, 5 polygenic scores were associated with exposure to bullying; the largest associations were present for genetic risk relating to mental health vulnerabilities, including diagnosis of depression (standardized b = 0.065; 95% CI, 0.035-0.095) and attention-deficit/hyperactivity disorder (standardized b = 0.063; 95% CI, 0.035-0.091), followed by risk taking (standardized b = 0.041; 95% CI, 0.013-0.069), body mass index (standardized b = 0.036; 95% CI, 0.008-0.064), and intelligence (standardized b = -0.031; 95% CI, -0.059 to 0.003).Conclusion and relevanceUsing the multi-polygenic score approach, the findings implicate preexisting mental health vulnerabilities as risk factors for exposure to bullying. A mechanistic understanding of how these vulnerabilities link to exposure of bullying is important to inform prevention strategies.

Project description:BACKGROUND: Vitamin D deficiency is associated with increased cardiovascular disease risk in observational studies. Whether these associations are causal is not clear. Loss-of-function mutations in the filaggrin gene result in up to 10% higher serum vitamin D concentrations, supposedly due to a decreased UV-protection of the keratinocytes. We used a Mendelian randomization approach to estimate the causal effect of vitamin D status on serum lipids, blood pressure, body mass index, waist circumference, and the metabolic syndrome. METHODS: Three population based studies were included, Monica10 (2,656 individuals aged 40-71 years), Inter99 (6,784 individuals aged 30-60 years), and Health2006 (3,471 individuals aged 18-69 years) conducted in 1993-94, 1999-2001, and 2006-2008, respectively. Participants were genotyped for the two most common filaggrin gene mutations in European descendants R501X and 2282del4, in all three studies and further for the R2447X mutation in the Inter99 and Health2006 studies. Filaggrin genotype was used as instrumental variable for vitamin D status. Baseline measurements of serum 25-hydroxyvitamin D were performed in all three studies. RESULTS: Instrumental variable analyses showed a 23.8% (95% confidence interval, CI 3.0, 48.6) higher HDL cholesterol level and a 30.5% (95% CI: 0.8, 51.3) lower serum level of triglycerides per doubling of vitamin D. These associations were, however, not statistically significant when applying the Bonferroni adjusted significance level. The remaining lipids showed non-significant changes in a favorable direction. Doubling of vitamin D gave a non-significantly lower odds ratio = 0.26 (95% CI: 0.06, 1.17) of the metabolic syndrome. There were no statistically significant causal effects of vitamin D status on blood pressure, body mass index, or waist circumference. CONCLUSION: Our results support a causal effect of higher vitamin D status on a more favorable lipid profile, although more studies in other populations are needed to confirm our results.

Dataset Information

Improving the phenotype risk score as a scalable approach to identifying patients with Mendelian disease.

Objective

Materials and methods

Results

Discussion

Conclusions

Publications

Improving the phenotype risk score as a scalable approach to identifying patients with Mendelian disease.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets