The analysis of longitudinal data from electronic health records (EHRs) has the potential to improve clinical diagnoses and enable personalized medicine, motivating efforts to identify disease subtypes from patient comorbidity information. Here we introduce an age-dependent topic modeling (ATM) method that provides a low-rank representation of longitudinal records of hundreds of distinct diseases in large EHR datasets. We applied ATM to 282,957 UK Biobank samples, identifying 52 diseases with heterogeneous comorbidity profiles; analyses of 211,908 All of Us samples produced concordant results. We defined subtypes of the 52 heterogeneous diseases based on their comorbidity profiles and compared genetic risk across disease subtypes using polygenic risk scores (PRSs), identifying 18 disease subtypes whose PRS differed significantly from other subtypes of the same disease. We further identified specific genetic variants with subtype-dependent effects on disease risk. In conclusion, ATM identifies disease subtypes with differential genome-wide and locus-specific genetic risk profiles. 

Age-dependent topic modeling of comorbidities in UK Biobank identifies disease subtypes with differential genetic risk.

Longitudinal data from electronic health records (EHR) has immense potential to improve clinical diagnoses and personalised medicine, motivating efforts to identify disease subtypes from age-dependent patient comorbidity information. We introduce an age-dependent topic modelling (ATM) method that provides a low-rank representation of longitudinal records of hundreds of distinct diseases in large EHR data sets. The model learns, and assigns to each individual, topic weights for several disease topics, each of which reflects a set of diseases that tend to co-occur as a function of age. Simulations show that ATM attains high accuracy in distinguishing distinct age-dependent comorbidity profiles. We applied ATM to 282,957 UK Biobank samples, analysing 1,726,144 disease diagnoses spanning 348 diseases with [≥]1,000 incidences. We inferred 10 disease topics optimising model fit. We identified 52 diseases with heterogeneous comorbidity profiles ([≥]500 incidences assigned to each of [≥]2 topics), including breast cancer, type 2 diabetes (T2D), hypertension, and hypercholesterolemia; for most of these diseases, topic assignments were highly age-dependent, suggesting differences in disease aetiology for early-onset vs. late-onset disease. We defined subtypes of the 52 heterogeneous diseases based on the topic assignments, and compared genetic risk across subtypes using polygenic risk scores (PRS). We identified 18 disease subtypes whose PRS differed significantly from other subtypes of the same disease, including a subtype of T2D characterised by cardiovascular comorbidities and a subtype of asthma characterised by dermatological comorbidities. We further identified specific SNPs underlying these differences. For example, the T2D-associated SNP rs1063192 in the CDKN2B locus has a higher odds ratio in the top quartile of cardiovascular topic weight (1.19{+/-}0.02) than in the bottom quartile (1.08{+/-}0.02) (P=4 x 10-5 for difference). In conclusion, ATM identifies disease subtypes with differential genome-wide and locus-specific genetic risk profiles.

/pdf/age-dependent-topic-modelling-of-comorbidities-in-uk-biobank-q24bmeyl.pdf

Age-dependent topic modelling of comorbidities in UK Biobank identifies disease subtypes with differential genetic risk

Coronary artery disease (CAD) remains the leading cause of mortality and morbidity worldwide. Recent advances in large-scale genome-wide association studies have highlighted the potential of genetic risk, captured as polygenic risk scores (PRS), in clinical prevention. However, the current clinical utility of PRS models is limited to identifying high-risk populations based on the top percentiles of genetic susceptibility. While some studies have attempted integrative prediction using genetic and non-genetic factors, many of these studies have been cross-sectional and focused solely on risk stratification. Our primary objective in this study was to integrate unmodifiable (age / genetics) and modifiable (clinical / biometric) risk factors into a prospective prediction framework which also produces actionable and personalized risk estimates for the purpose of CAD prevention in a heterogenous adult population. Thus, we present an integrative, omnigenic, meta-prediction framework that effectively captures CAD risk subgroups, primarily distinguished by degree and nature of genetic risk, with distinct risk reduction profiles predicted from standard clinical interventions. Initial model development considered ~ 2,000 predictive features, including demographic data, lifestyle factors, physical measurements, laboratory tests, medication usage, diagnoses, and genetics. To power our meta-prediction approach, we stratified the UK Biobank into two primary cohorts: 1) a prevalent CAD cohort used to train baseline and prospective predictive models for contributing risk factors and diagnoses, and 2) an incident CAD cohort used to train the final CAD incident risk prediction model. The resultant 10-year incident CAD risk model is composed of 35 derived meta-features from models trained on the prevalent risk cohort, most of which are predicted baseline diagnoses with multiple embedded PRSs. This model achieved an AUC of 0.81 and macro-averaged F1-score of 0.65, outperforming standard clinical scores and prior integrative models. We further demonstrate that individualized risk reduction profiles can be derived from this model, with genetic risk mediating the degree of risk reduction achieved by standard clinical interventions.

Meta-Prediction of Coronary Artery Disease Risk

Abstract Background Evidence from observational studies suggests an association between chronic obstructive pulmonary disease (COPD) and lung cancer. The potential interactions between the immune system and the lungs may play a causative role in COPD and lung cancer and offer therapeutic prospects. However, the causal association and the immune-mediated mechanisms between COPD and lung cancer remain to be determined. Methods We employed a two-sample Mendelian randomization (MR) approach to investigate the causal association between COPD and lung cancer. Additionally, we examined whether immune cell signals were causally related to lung cancer, as well as whether COPD was causally associated with immune cell signals. Furthermore, through two-step Mendelian randomization, we investigated the mediating effects of immune cell signals in the causal association between COPD and lung cancer. Leveraging publicly available genetic data, our analysis included 468,475 individuals of European ancestry with COPD, 492,803 individuals of European ancestry with lung cancer, and 731 immune cell signatures of European ancestry. Additionally, we conducted single-cell transcriptome sequencing analysis on COPD, lung cancer, and control samples to validate our findings. Findings We found a causal association between COPD and lung cancer (odds ratio [OR] = 1.63, 95% confidence interval [CI] = 1.31–2.02, P -value &lt; 0.001). We also observed a causal association between COPD and regulatory T cells (odds ratio [OR] = 1.19, 95% confidence interval [CI] = 1.01–1.40, P -value &lt; 0.05), as well as a causal association between regulatory T cells and lung cancer (odds ratio [OR] = 1.02, 95% confidence interval [CI] = 1.002–1.045, P -value &lt; 0.05). Furthermore, our two-step Mendelian randomization analysis demonstrated that COPD is associated with lung cancer through the mediation of regulatory T cells. These findings were further validated through single-cell sequencing analysis, confirming the mediating role of regulatory T cells in the association between COPD and lung cancer. Interpretation As far as we are aware, we are the first to combine single-celled immune cell data with two-sample Mendelian randomization. Our analysis indicates a causal association between COPD and lung cancer, with regulatory T cells playing an intermediary role. 

Exploring the relationship between Treg-mediated risk in COPD and lung cancer through Mendelian randomization analysis and scRNA-seq data integration.

Background: To construct a meta polygenic risk score (metaPRS) based on PRS of lung cancer and related phenotypes. We also aimed to assess its prediction of lung cancer risk and implication for screening.Methods: A total of 2,180 genetic variants were used to develop a PRS for lung cancer, three PRSs for different histopathologic subtypes, and 17 PRSs for lung cancer-related risk factors, respectively. These PRSs were then integrated into a meta polygenic risk score (metaPRS) for lung cancer using the elastic-net Cox regression model with data from the UK Biobank (N=442,508). The predictive effects of the metaPRS were assessed in the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial (N=108,665).Findings: The metaPRS was associated with lung cancer risk with a hazard ratio of 1·37 (95% confidence interval: 1·33-1·42) per standard deviation increased. The metaPRS showed the highest C-index (0·590) compared with the previous nine PRSs (C-index: 0·531-0·565) in the UK Biobank. Similarly, the metaPRS increased the C-index by 0·016-0·067 over the previous PRSs (C-index: 0·580 vs 0·513-0·564) in the PLCO. Higher metaPRS was associated with younger age at lung cancer diagnosis. Besides, individuals at intermediate predicted risk by clinical risk model (1·34%-1·51%) with the intermediate-high genetic risk had a six-year average absolute lung cancer risk exceeded the threshold clinical risk model risk≥1·51%. The addition of metaPRS to the clinical risk model showed continuous net reclassification improvement (continuous NRI=6·50%) in the PLCO cohort.Interpretation: The metaPRS improves the predictive efficiency of lung cancer compared with the previous PRSs, and refines risk stratification for lung cancer.Funding: National Natural Science Foundation of China; Excellent Youth Foundation of Jiangsu Province; Research Unit of Prospective Cohort of Cardiovascular Diseases and Cancer, Chinese Academy of Medical Sciences.Declaration of Interest: The authors have no conflicts of interest to declare.Ethical Approval: All participants provided written informed consent, and ethical approval for the UKB was obtained from the NHS National Research Ethics Service. 

Meta Polygenic Risk Score and Lung Cancer Risk Prediction: Two Prospective Cohort Studies

Background In addition to age and sex, also smoking history and levels of blood pressure, cholesterol, lipoproteins and inflammation are established biomarkers for coronary heart disease (CHD). As standard polygenic risk scores (PRS) have recently proven successful for CHD prediction, it remains of high interest to determine how a combined PRS of biomarkers (BioPRS) constructed from statistically relevant biomarkers can further improve genetic prediction of CHD. Methods We developed CHDBioPRS, which combines BioPRS with PRS of CHD, via regularized regression in UK Biobank (UKB) training data (n = 208,010). The resulting CHDBioPRS was tested on an independent UK Biobank subset (n = 25,765) and on the FinnGen study (n = 306,287). Results We observed a consistent pattern across all data sets where BioPRS was clearly predictive of CHD and improved standard PRS for CHD when the two were combined. In UKB test data, CHDPRS had a hazard ratio (HR) of 1.78 (95% confidence interval 1.67-1.91, area under the curve (AUC) 0.808) and CHDBioPRS had a HR of 1.88 (1.75-2.01, AUC 0.811) per one standard deviation of PRS. In FinnGen data, HR of CHDPRS was 1.57 (1.55-1.60, AUC 0.752) and HR of CHDBioPRS was 1.60 (1.58-1.62, AUC 0.755). We observed larger effects of CHDBioPRS in subsets of early onset cases with HR of 2.07 (1.85-2.32, AUC 0.790) in UKB test data and of 2.10 (2.04-2.16, AUC 0.791) in FinnGen. Results were similar when stratified by sex. Conclusions Integration of biomarker based BioPRS improved on the standard PRS for CHD and the gain was largest with early onset CHD cases. These findings highlight the benefit of enriching polygenic risk prediction of CHD with the genetics of associated biomarkers.

Integration of biomarker polygenic risk score improves prediction of coronary heart disease in UK Biobank and FinnGen

Objective: To investigate the association between chronic lung diseases and the risk of lung cancer. Methods: Using UK Biobank (UKB) survey data, 472 397 participants who had not previously been diagnosed with cancer and whose self-reported sex was consistent with their genetic sex were studied. Information on the prevalence of previous chronic lung diseases, general demographic characteristics and the prevalence of lung cancer was collected using baseline questionnaires and national health system data. The multivariate Cox proportional risk regression model was used to analyze the association between four previous chronic lung diseases (asthma, chronic obstructive pulmonary disease, idiopathic pulmonary fibrosis and interstitial pulmonary disease) and the risk of lung cancer. A total of 458 526 participants with genotype data in the observational study were selected as research objects, and the closely related and independent genetic loci with four chronic lung diseases were selected as instrumental variables, and the association between four chronic lung diseases and the risk of lung cancer was analyzed by Mendelian randomization (MR). The dose-response relationship between genetic risk score and the risk of lung cancer in different chronic lung diseases was evaluated using a restricted cubic spline function. Results: The age [M (Q1, Q3)] of the subjects was 57 (50, 63) years old, and there were 3 516 new cases of lung cancer (0.74%) during follow-up. The multivariate Cox proportional hazard regression model analysis showed that previous chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis were associated with the risk of lung cancer, about 1.61 (1.49-1.75) and 2.61 (1.24-5.49), respectively. MR Studies showed that genetically predicted chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis were associated with the risk of lung cancer, with HR (95%CI) of 1.10 (1.03-1.19) and 1.04 (1.01-1.08), respectively. The results of restricted cubic spline function analysis showed that the risk of lung cancer increased linearly with the increase of genetic risk scores for chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis (P<0.05). Neither observational studies nor Mendelian randomization analysis found an association between previous asthma or interstitial lung disease and the risk of lung cancer (both P values>0.05). Conclusion: Chronic obstructive pulmonary disease and idiopathic pulmonary fibrosis are potential risk factors for lung cancer.目的： 探讨既往患有慢性肺部疾病与肺癌发病风险的关联情况。 方法： 采用英国生物银行（UKB）调查数据，以既往未被诊断为癌症且自报性别与遗传性别一致的472 397名参与者为研究对象。采用基线问卷和国家健康系统数据收集既往慢性肺部疾病患病情况、一般人口学特征以及肺癌患病情况等信息。采用多因素Cox比例风险回归模型分析哮喘、慢性阻塞性肺病、特发性肺纤维化、间质性肺病等4种既往慢性肺部疾病与肺癌发病风险的关联。以观察性研究中具有基因型数据的458 526名参与者为研究对象，选择与4种慢性肺部疾病密切相关且相互独立的遗传位点作为工具变量，采用孟德尔随机化（MR）分析4种慢性肺部疾病与肺癌发病风险的关联情况。采用限制性立方样条函数评估不同慢性肺部疾病GRS与肺癌发病风险的剂量反应关系。 结果： 研究对象年龄的M（Q1，Q3）为57（50，63）岁，随访期间新发肺癌3 516例（0.74%）。多因素Cox比例风险回归模型分析结果显示：既往患有慢性阻塞性肺病和特发性肺纤维化与肺癌发病风险存在关联，分别为1.61（1.49~1.75）和2.61（1.24~5.49）。MR研究结果显示：遗传预测的慢性阻塞性肺病和特发性肺纤维化与肺癌发病风险存在关联，HR（95%CI）分别为1.10（1.03~1.19）和1.04（1.01~1.08）。限制性立方样条函数分析结果显示：肺癌发病风险随慢性阻塞性肺病和特发性肺纤维化遗传风险评分增加而升高且呈线性关系（P<0.05）。观察性研究和孟德尔随机化分析均未发现既往患有哮喘或间质性肺病与肺癌发病风险存在关联（均P>0.05）。 结论： 既往患有慢性阻塞性肺病和特发性肺纤维化是肺癌发生的潜在危险因素。. 

[Association between chronic lung diseases and the risk of lung cancer in UK Biobank: observational and Mendelian randomization analyses].

Introduction The COVID-19 pandemic has caused disruptions to mental health services, forcing the rapid implementation of alternative ways of delivering services alongside a greater immediate, and continuously growing, demand across those services. The care and level of mental health service provided are felt to be inadequate to respond to the increasing demand for mental health conditions in the time of the pandemic, leading to an urgent need to learn from service change and consequences to inform solutions and plans to support the NHS post-pandemic plan in the UK. This rapid review aims to understand the changes in mental health services during the pandemic and summarise the impact of these changes on the health outcomes of people with mental health conditions. Methods and analysis Cochrane CENTRAL, MEDLINE, EMBASE, and PsycInfowill be searched for eligible studies with key terms indicating mental health AND COVID-19 AND health services. Studies will be included if objective and subjective effects of changes to mental health services in response to COVID-19 are reported on adults with mental health conditions, peer-reviewed and published in the English language. Study selection and data extraction will be undertaken dependently by two reviewers. Evidence will be summarised narratively and in a logic model. Ethics and dissemination Ethics approval is not required for this review. A list of interventions/services/models of care delivered to people with mental health conditions will be grouped as "Do", "Don't" and "Don't know" based on the evidence on effectiveness and acceptability. The results will be written for publication in an open-access peer-reviewed journal and disseminated to the public and patients, clinicians, commissioners, funders, and academic conferences. PROSPERO registration number CRD42022306923

The impact of changes in mental health services in response to COVID-19 on people with mental health conditions: protocol for a rapid review

Metabolic syndrome (MetS) is a complex metabolic disorder with a global prevalence of 20-25%. Early identification and intervention would help minimize the global burden on healthcare systems. Here, we measured over 400 proteins from ~20,000 proteomes using data-independent acquisition mass spectrometry for 7890 serum samples from a longitudinal cohort of 3840 participants with two follow-up time points over ten years. We then built a machine learning model for predicting the risk of developing MetS within ten years. Our model, composed of 11 proteins and the age of the individuals, achieved an area under the curve of 0.784 in the discovery cohort (n=855) and 0.774 in the validation cohort (n=242). Using linear mixed models, we found that apolipoproteins, immune-related proteins, and coagulation-related proteins best correlated with MetS development. This population-scale proteomics study broadens our understanding of MetS, and may guide the development of prevention and targeted therapies for MetS.

Population serum proteomics uncovers prognostic protein classifier and molecular mechanisms for metabolic syndrome

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Y. Fu

Author Tools

Chat about Author

Papers

Integration of biomarker polygenic risk score improves prediction of coronary heart disease in UK Biobank and FinnGen

[Association between chronic lung diseases and the risk of lung cancer in UK Biobank: observational and Mendelian randomization analyses].

The impact of changes in mental health services in response to COVID-19 on people with mental health conditions: protocol for a rapid review

Population serum proteomics uncovers prognostic protein classifier and molecular mechanisms for metabolic syndrome