Improving genetic risk modeling of dementia from real-world data in underrepresented populations
Ontology highlight
ABSTRACT:
SUBMITTER: Fu M
PROVIDER: S-EPMC11345412 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundGenetic risk modeling for dementia offers significant benefits, but studies based on real-world data, particularly for underrepresented populations, are limited.MethodsWe employed an Elastic Net model for dementia risk prediction using single-nucleotide polymorphisms prioritized by functional genomic data from multiple neurodegenerative disease genome-wide association studies. We compared this model with APOE and polygenic risk score models across genetic ancestry groups, using electronic health records from UCLA Health for discovery and All of Us cohort for validation.ResultsOur model significantly outperforms other models across multiple ancestries, improving the area-under-precision-recall curve by 21-61% and the area-under-the-receiver-operating characteristic by 10-21% compared to the APOEand the polygenic risk score models. We identified shared and ancestry-specific risk genes and biological pathways, reinforcing and adding to existing knowledge.ConclusionsOur study highlights benefits of integrating functional mapping, multiple neurodegenerative diseases, and machine learning for genetic risk models in diverse populations. Our findings hold potential for refining precision medicine strategies in dementia diagnosis.
| S-EPMC10896371 | biostudies-literature
Project description:BackgroundGenetic risk modeling for dementia offers significant benefits, but studies based on real-world data, particularly for underrepresented populations, are limited.MethodsWe employed an Elastic Net model for dementia risk prediction using single-nucleotide polymorphisms prioritized by functional genomic data from multiple neurodegenerative disease genome-wide association studies. We compared this model with APOE and polygenic risk score models across genetic ancestry groups, using electronic health records from UCLA Health for discovery and All of Us cohort for validation.ResultsOur model significantly outperforms other models across multiple ancestries, improving the area-under-precision-recall curve by 21-61% and the area-under-the-receiver-operating characteristic by 10-21% compared to the APOE and the polygenic risk score models. We identified shared and ancestry-specific risk genes and biological pathways, reinforcing and adding to existing knowledge.ConclusionsOur study highlights benefits of integrating functional mapping, multiple neurodegenerative diseases, and machine learning for genetic risk models in diverse populations. Our findings hold potential for refining precision medicine strategies in dementia diagnosis.
| S-EPMC10871463 | biostudies-literature
Project description:The objective of the study is to identify healthcare events leading to a diagnosis of dementia from a large real-world dataset. This study uses a data-driven approach to identify temporally ordered pairs and trajectories of healthcare codes in the electronic health record (EHR). This allows for discovery of novel temporal risk factors leading to an outcome of interest that may otherwise be unobvious. We identified several known (Down syndrome RR = 116.1, thiamine deficiency RR = 76.1, and Parkinson's disease RR = 41.1) and unknown (Brief psychotic disorder RR = 68.6, Toxic effect of metals RR = 40.4, and Schizoaffective disorders RR = 40.0) factors for a specific dementia diagnosis. The associations with the greatest risk for any dementia diagnosis were found to be primarily related to mental health (Brief psychotic disorder RR = 266.5, Dissociative and conversion disorders RR = 169.8), or neurologic conditions or procedures (Dystonia RR = 121.9, Lumbar Puncture RR = 119.0). Trajectory and clustering analysis identified factors related to cerebrovascular disorders, as well as diagnoses which increase the risk of toxic imbalances. The results of this study have the ability to provide valuable insights into potential patient progression towards dementia and improve recognition of patients at risk for developing dementia.
| S-EPMC10730574 | biostudies-literature
Project description: Not available
| S-EPMC10082651 | biostudies-literature
Project description:BackgroundThe research community has historically failed to enroll diverse groups of participants in dementia clinical trials. A unique aspect of dementia care research is the requirement of a study partner, who can attest to the care recipient's clinical and functional capacity. The aim of this study is to assess racial and ethnic differences and the importance of various trial considerations among dementia caregivers, in their decision to participate in clinical research as study partners.MethodWe embedded a vignette about a hypothetical dementia clinical trial in a nationally representative survey of U.S. dementia caregivers, oversampling non-Hispanic Black and Hispanic caregivers. Dementia caregivers were asked about their willingness to participate in the trial with their care recipient and rated the importance of nine considerations in hypothetical decisions to participate. Caregiver demographic characteristics were analyzed as predictors of trial participation in a base demographic model. In a second reasons model caregiver demographic characteristics and the rated importance of the nine considerations were separately analyzed as predictors; both models used survey-weighted logistic regression.ResultThe sample consisted of 610 dementia caregivers, including 156 non-Hispanic Black and 122 Hispanic caregiver participants. In the base demographic model, hypothetical trial participation was negatively associated with older caregiver age (OR (odds ratio) = 0.72, p = < 0.001). In the reasons model, the rated importance of a social responsibility to help others by participating in research was significantly associated with participation (OR = 1.56, p = 0.049), while the importance of the possibility of the care recipient experiencing serious side effects was negatively associated with participation (OR = 0.51, p = 0.003). In both models there was no significant difference in hypothetical participation between non-Hispanic Black and non-Hispanic White caregivers, or between Hispanic and non-Hispanic White caregivers.ConclusionHispanic and non-Hispanic Black dementia caregivers were not less likely than non-Hispanic White dementia caregivers to participate in a hypothetical dementia clinical trial. Our study suggests that failures to recruit diverse populations in dementia clinical research are not attributable to less willingness among members of underrepresented groups but may instead reflect structural barriers and historic exclusion from trial participation.
| S-EPMC11476697 | biostudies-literature
Project description:BackgroundLow household income (HI), comorbidities and female sex are associated with an increased risk of dementia. The aim of this study was to measure the mediating effect of comorbidity and HI on the excess risk due to gender in relation to the incidence and prevalence of dementia in the general population.MethodsA retrospective and observational study using real-world data analysed all people over 60 who were registered with the Basque Health Service in Gipuzkoa. The study measured HI level, the Charlson comorbidity index (CCI), age and sex. The prevalence and incidence of dementia were analysed using logistic regression and Poisson regression models, respectively, adjusted by HI, sex, comorbidity and age. We estimated the combined mediation effect of HI and comorbidity on the prevalence of dementia associated with gender.ResultsOf the 221,777 individuals, 3.85% (8,549) had a diagnosis of dementia as of 31 December 2021. Classification by the CCI showed a gradient with 2.90% in CCI 0-1, 10.60% in CCI 2-3 and 18.01% in CCI > 3. Both low HI and gender were associated with a higher crude prevalence of dementia. However, in the CCI-adjusted model, women had an increased risk of dementia, while HI was no longer statistically significant. The incidence analysis produced similar results, although HI was not significant in any model. The CCI was significantly higher for men and for people with low HI. The mediation was statistically significant, and the CCI and HI explained 79% of the gender effect.ConclusionsComorbidity and low HI act as mediators in the increased risk of dementia associated with female sex. Given the difference in the prevalence of comorbidities by HI, individual interventions to control comorbidities could not only prevent dementia but also reduce inequalities, as the risk is greater in the most disadvantaged population.
| S-EPMC10905946 | biostudies-literature
Project description:Alzheimer's disease (AD), as the most common form of dementia and leading cause for disability and death in old age, represents a major burden to healthcare systems worldwide. For the development of disease-modifying interventions and treatments, the detection of cognitive changes at the earliest disease stages is crucial. Recent advancements in mobile consumer technologies provide new opportunities to collect multi-dimensional data in real-life settings to identify and monitor at-risk individuals. Based on evidence showing that deficits in spatial navigation are a common hallmark of dementia, we assessed whether a memory clinic sample of patients with subjective cognitive decline (SCD) who still scored normally on neuropsychological assessments show differences in smartphone-assisted wayfinding behavior compared with cognitively healthy older and younger adults. Guided by a mobile application, participants had to find locations along a short route on the medical campus of the Magdeburg university. We show that performance measures that were extracted from GPS and user input data distinguish between the groups. In particular, the number of orientation stops was predictive of the SCD status in older participants. Our data suggest that subtle cognitive changes in patients with SCD, whose risk to develop dementia in the future is elevated, can be inferred from smartphone data, collected during a brief wayfinding task in the real world.
| S-EPMC11449328 | biostudies-literature
Project description:BackgroundWhether or not patients with gastroesophageal reflux disease (GERD) have a higher risk of developing subsequent dementia remains unknown, and no observational evidence from population-based data is available. This study was to determine whether patients with GERD have a higher future risk of developing dementia.MethodsFor the period 2000-2012, datasets from the Longitudinal Health Insurance Database (LHID, subset of National Health Insurance Research Database in Taiwan) were analyzed. Definition of GERD was based on ICD-9-CM codes 530.11 and 530.81 and prescriptions for PPIs. After matching gender, age, index year, and comorbidities, each GERD patient was matched with four control patients without GERD. Future risk of dementia was evaluated, and sensitivity analysis of subgroups was conducted to clarify the potential association.ResultsIn the present study, 13,570 patients were included in the GERD cohort and 54,280 patients were included in the control cohort. Patients with GERD showed higher risk developing dementia than control group, with an aHR of 1.34 (95% C.I., 1.07, 1.67). In GERD patients between above 70 years old, the risk of developing dementia was higher than that of the control groups (aHR = 1.34; 95% C.I., 1.01, 1.77).ConclusionPatients with GERD showed higher incidence of dementia, and elder patients had the highest risk of developing dementia. Clinicians should be concern of the association between GERD and dementia and should develop strategies to prevent dementia while managing patients with GERD.
| S-EPMC9014245 | biostudies-literature
Project description:ObjectivesWe propose a framework of health outcomes modeling with dynamic decision making and real-world data (RWD) to evaluate the potential utility of novel risk prediction models in clinical practice. Lung transplant (LTx) referral decisions in cystic fibrosis offer a complex case study.MethodsWe used longitudinal RWD for a cohort of adults (n = 4247) from the Cystic Fibrosis Foundation Patient Registry to compare outcomes of an LTx referral policy based on machine learning (ML) mortality risk predictions to referral based on (1) forced expiratory volume in 1 second (FEV1) alone and (2) heterogenous usual care (UC). We then developed a patient-level simulation model to project number of patients referred for LTx and 5-year survival, accounting for transplant availability, organ allocation policy, and heterogenous treatment effects.ResultsOnly 12% of patients (95% confidence interval 11%-13%) were referred for LTx over 5 years under UC, compared with 19% (18%-20%) under FEV1 and 20% (19%-22%) under ML. Of 309 patients who died before LTx referral under UC, 31% (27%-36%) would have been referred under FEV1 and 40% (35%-45%) would have been referred under ML. Given a fixed supply of organs, differences in referral time did not lead to significant differences in transplants, pretransplant or post-transplant deaths, or overall survival in 5 years.ConclusionsHealth outcomes modeling with RWD may help to identify novel ML risk prediction models with high potential real-world clinical utility and rule out further investment in models that are unlikely to offer meaningful real-world benefits.
| S-EPMC9311314 | biostudies-literature
Project description:Slow patient enrollment or failing to enroll the required number of patients is a disruptor of clinical trial timelines. To meet the planned trial recruitment, site selection strategies are used during clinical trial planning to identify research sites that are most likely to recruit a sufficiently high number of subjects within trial timelines. We developed a machine learning approach that outperforms baseline methods to rank research sites based on their expected recruitment in future studies. Indication level historical recruitment and real-world data are used in the machine learning approach to predict patient enrollment at site level. We define covariates based on published recruitment hypotheses and examine the effect of these covariates in predicting patient enrollment. We compare model performance of a linear and a non-linear machine learning model with common industry baselines that are constructed from historical recruitment data. Performance of the methodology is evaluated and reported for two disease indications, inflammatory bowel disease and multiple myeloma, both of which are actively being pursued in clinical development. We validate recruitment hypotheses by reviewing the covariates relationship with patient recruitment. For both indications, the non-linear model significantly outperforms the baselines and the linear model on the test set. In this paper, we present a machine learning approach to site selection that incorporates site-level recruitment and real-world patient data. The model ranks research sites by predicting the number of recruited patients and our results suggest that the model can improve site ranking compared to common industry baselines.
| S-EPMC10927105 | biostudies-literature