Dataset Information

Development and internal validation of a diagnostic prediction model for psoriasis severity.

ABSTRACT:

Background

While administrative health records such as national registries may be useful data sources to study the epidemiology of psoriasis, they do not generally contain information on disease severity.

Objectives

To develop a diagnostic model to distinguish psoriasis severity based on administrative register data.

Method

We conducted a retrospective registry-based cohort study using the Danish Skin Cohort linked with the Danish national registries. We developed a diagnostic model using a gradient boosting machine learning technique to predict moderate-to-severe psoriasis. We performed an internal validation of the model by bootstrapping to account for any optimism.

Results

Among 4016 adult psoriasis patients (55.8% women, mean age 59 years) included in this study, 1212 (30.2%) patients were identified as having moderate-to-severe psoriasis. The diagnostic prediction model yielded a bootstrap-corrected discrimination performance: c-statistic equal to 0.73 [95% CI: 0.71-0.74]. The internal validation by bootstrap correction showed no substantial optimism in the results with a c-statistic of 0.72 [95% CI: 0.70-0.74]. A bootstrap-corrected slope of 1.10 [95% CI: 1.07-1.13] indicated a slight under-fitting.

Conclusion

Based on register data, we developed a gradient boosting diagnostic model returning acceptable prediction of patients with moderate-to-severe psoriasis.

SUBMITTER: Liljendahl MS

PROVIDER: S-EPMC9903561 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and internal validation of a diagnostic prediction model for psoriasis severity.

Liljendahl Mie Sylow MS Loft Nikolai N Egeberg Alexander A Skov Lone L Nguyen Tri-Long TL

Diagnostic and prognostic research 20230207 1

<h4>Background</h4>While administrative health records such as national registries may be useful data sources to study the epidemiology of psoriasis, they do not generally contain information on disease severity.<h4>Objectives</h4>To develop a diagnostic model to distinguish psoriasis severity based on administrative register data.<h4>Method</h4>We conducted a retrospective registry-based cohort study using the Danish Skin Cohort linked with the Danish national registries. We developed a diagnos ...[more]

PMID: 36747306

Similar Datasets

Project description:BackgroundPsoriasis is a chronic immune-mediated inflammatory disease. N6-methyladenosine (m6A) is involved in numerous biological processes in both normal and diseased states. Herein, we aimed to explore the potential role of m6A regulators in the diagnosis of psoriasis and predict molecular mechanisms by which m6A regulators impact psoriasis.MethodsGSE30999 (170 human skin tissue samples) and GSE13355 (180 human skin tissue samples) were downloaded as the training analysis dataset and validation dataset respectively. M6A-related genes were obtained from the literature and their expression levels in GSE30999 samples were measured to identify M6A-related DEGs between psoriasis lesions (LS) and non-lesional lesions (NL). We identified m6A-related DEGs using differential expression analysis and assessed their interactions through correlation analysis and network construction. A logistic regression analysis followed by LASSO optimization was employed to select m6A-related DEGs for the construction of a diagnostic model. The performance of the model was validated using support vector machine (SVM) methodology with sigmoid kernel function and extensive cross-validation. Additionally, the correlation between m6A-related DEGs and immune cell infiltration was analyzed, as well as the association of these DEGs with psoriasis subtypes. Functional analysis of the m6A-related DEGs included the construction of regulatory networks involving miRNAs, transcription factors (TFs), and small-molecule drugs. The m6A modification patterns were also explored by examining the gene expression differences between psoriasis subtypes and their enriched biological pathways. Finally, the expression of significant m6A regulators involved in the diagnostic model was examined by RT-qPCR.ResultsIn this study, ten optimal m6A-related DEGs were identified, including FTO, IGF2BP2, METTL3, YTHDC1, ZC3H13, HNRNPC, IGF2BP3, LRPPRC, YTHDC2, and HNRNPA2B1. A diagnostic model based on these m6A-related DEGs was constructed, demonstrating high diagnostic accuracy with an area under the curve (AUC) in GSE30999 and GSE13355 of 0.974 and 0.730, respectively. Meanwhile, the expression level of m6A regulators verified by RT-qPCR was consistent with the results in GSE30999. The infiltration of activated mast cells and NK cells was significantly associated with all ten m6A-related DEGs in psoriasis. Among them, YTHDC1, HNRNPC, and FTO were targeted by most miRNAs and were regulated by nine related TFs. Therefore, patients may benefit from dorsomorphin and cyclosporine therapy. Between the two subgroups, 1,592 DEGs were identified, including LRPPRC and METTL3. These DEGs were predicted to be involved in neutrophil activation, cytokine-cytokine receptor interactions, and chemokine signaling pathways.ConclusionsA diagnostic model based on ten m6A-related DEGs in patients with psoriasis was constructed, which may provide early diagnostic biomarkers and therapeutic targets for psoriasis.

Project description:BackgroundLow-dose computed tomography screening has been proved to reduce lung cancer mortality, however, the issues of high false-positive rate and overdiagnosis remain unsolved. Risk prediction models for lung cancer that could accurately identify high-risk populations may help to increase efficiency. We thus sought to develop a risk prediction model for lung cancer incorporating epidemiological and metabolic markers in a Chinese population.MethodsDuring 2006 and 2015, a total of 122 497 people were observed prospectively for lung cancer incidence with the total person-years of 976 663. Stepwise multivariable-adjusted logistic regressions with Pentry = .15 and Pstay = .20 were conducted to select the candidate variables including demographics and metabolic markers such as high-sensitivity C-reactive protein (hsCRP) and low-density lipoprotein cholesterol (LDL-C) into the prediction model. We used the C-statistic to evaluate discrimination, and Hosmer-Lemeshow tests for calibration. Tenfold cross-validation was conducted for internal validation to assess the model's stability.ResultsA total of 984 lung cancer cases were identified during the follow-up. The epidemiological model including age, gender, smoking status, alcohol intake status, coal dust exposure status, and body mass index generated a C-statistic of 0.731. The full model additionally included hsCRP and LDL-C showed significantly better discrimination (C-statistic = 0.735, P = .033). In stratified analysis, the full model showed better predictive power in terms of C-statistic in younger participants (<50 years, 0.709), females (0.726), and former or current smokers (0.742). The model calibrated well across the deciles of predicted risk in both the overall population (PHL = .689) and all subgroups.ConclusionsWe developed and internally validated an easy-to-use risk prediction model for lung cancer among the Chinese population that could provide guidance for screening and surveillance.

Dataset Information

Development and internal validation of a diagnostic prediction model for psoriasis severity.

Background

Objectives

Method

Results

Conclusion

Publications

Development and internal validation of a diagnostic prediction model for psoriasis severity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets