Dataset Information

Multivariable Predictive Models to Identify the Optimal Biologic Therapy for Treatment of Patients With Psoriasis at the Individual Level.

ABSTRACT:

Importance

Identifying the optimal long-term biologic therapy for patients with psoriasis is often done through trial and error.

Objective

To identify the optimal biologic therapy for individual patients with psoriasis using predictive statistical and machine learning models.

Design, setting, and participants

This population-based cohort study used data from Danish nationwide registries, primarily DERMBIO, and included adult patients treated for moderate-to-severe psoriasis with biologics. Data were processed and analyzed between spring 2021 and spring 2022.

Main outcomes and measures

Patient clusters of clinical relevance were identified and their success rates estimated for each drug. Furthermore, predictive prognostic models to identify optimal biologic treatment at the individual level based on data from nationwide registries were evaluated.

Results

Assuming a success criterion of 3 years of sustained treatment, this study included 2034 patients with a total of 3452 treatment series. Most treatment series involved male patients (2147 [62.2%]) originating from Denmark (3190 [92.4%]), and 2414 (69.9%) had finished an education longer than primary school. The average ages were 24.9 years at psoriasis diagnosis and 45.5 years at initiation of biologic therapy. Gradient-boosted decision trees and logistic regression were able to predict a specific cytokine target (eg, interleukin-17 inhibition) associated with a successful treatment with accuracies of 63.6% and 59.2%, and top 2 accuracies of 95.9% and 93.9%. When predicting specific drugs resulting in success, gradient boost and logistic regression had accuracies of 48.5% and 44.4%, top 2 accuracies of 77.6% and 75.9%, and top 3 accuracies of 89.9% and 89.0%.

Conclusions and relevance

Of the treatment prediction models used in this cohort study of patients with psoriasis, gradient-boosted decision trees performed significantly better than logistic regression when predicting specific biologic therapy (by drug as well as target) leading to a treatment duration of at least 3 years without discontinuation. Predicting the optimal biologic could benefit patients and clinicians by minimizing the number of failed treatment attempts.

SUBMITTER: Nielsen ML

PROVIDER: S-EPMC9386602 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multivariable Predictive Models to Identify the Optimal Biologic Therapy for Treatment of Patients With Psoriasis at the Individual Level.

Nielsen Mia-Louise ML Petersen Troels Christian TC Maul Julia-Tatjana JT Wu Jashin J JJ Rasmussen Mads Kirchheiner MK Bertelsen Trine T Ajgeiy Kawa Khaled KK Skov Lone L Thomsen Simon Francis SF Thyssen Jacob P JP Egeberg Alexander A

JAMA dermatology 20221001 10

<h4>Importance</h4>Identifying the optimal long-term biologic therapy for patients with psoriasis is often done through trial and error.<h4>Objective</h4>To identify the optimal biologic therapy for individual patients with psoriasis using predictive statistical and machine learning models.<h4>Design, setting, and participants</h4>This population-based cohort study used data from Danish nationwide registries, primarily DERMBIO, and included adult patients treated for moderate-to-severe psoriasis ...[more]

PMID: 35976663

Similar Datasets

Project description:IntroductionBiologic agents are used in patients with severe psoriasis who have not adequately responded to existing conventional systemic therapies. However, only a limited number of medical institutions in Japan are approved to use them, and their relatively high cost represents a substantial burden to patients. Apremilast is an oral phosphodiesterase-4 inhibitor approved in Japan for the treatment of psoriasis vulgaris in adult patients with an inadequate response to topical therapies and psoriatic arthritis in adult patients with active disease. To date, a large-scale real-world study of treatment patterns and costs associated with apremilast in Japan has not been conducted. The objective of this study was to assess whether apremilast can prolong time to first biologic therapy use and decrease total medical cost.MethodsUsing the Medical Data Vision hospital-based claims database, 506 psoriasis patients were propensity score matched and analyzed (apremilast: n = 253; non-apremilast: n = 253).ResultsThe incidence rate of first biologic therapy use per 1000 patient-years was significantly lower in the apremilast group than in the non-apremilast group (30.3 vs. 107.6; P < 0.001), and the total medical costs per month were significantly lower in the apremilast group than in the non-apremilast group (76,594 yen/month vs. 102,411 yen/month, P < 0.001). In a sensitivity analysis of a propensity-score-matched subset of eligible patients prescribed biologics during the follow-up period (apremilast: n = 14; non-apremilast: n = 14), the incidence of first biologic therapy use was 2,797.6 per 1000 patient-years (95% CI: 1,656.9, 4,723.6) in the non-apremilast group and 856.1 per 1000 patient-years (95% CI: 507.0, 1,445.5) in the apremilast group.ConclusionThese results suggest that apremilast prolongs the time to first biologic therapy use in patients with psoriasis, thereby reducing the total medical cost and decreasing the economic burden on patients.

Project description:Biologic therapies are increasingly used to treat chronic inflammatory skin diseases such as psoriasis and atopic dermatitis. In clinical practice, scores based on evaluation of objective and subjective symptoms are used to assess disease severity, leading to evaluation of treatment goals with clinical decisions on treatment initiation, switch to another treatment modality or to discontinue current treatment. However, this visual-based scoring is relatively subjective and inaccurate due to inter- and intraobserver reliability. Optical coherence tomography (OCT) is a fast, high-resolution, in vivo imaging modality that enables the visualization of skin structure and vasculature. We evaluated the use of OCT for quantification and monitoring of skin inflammation to improve objective assessment of disease activity in patients with psoriasis and atopic dermatitis. We assessed the following imaging parameters including epidermal thickness, vascular density, plexus depth, vessel diameter, and vessel count. A total of four patients with psoriasis or atopic dermatitis were treated with biologic agents according to current treatment guidelines. OCT was used to monitor their individual treatment response in a target lesion representing disease activity for 52 weeks. Psoriatic and eczema lesions exhibited higher epidermal thickness, increased vascular density, and higher vessel count compared to uninvolved skin. An upward shift of the superficial vascular plexus accompanied by smaller vessel diameters was seen in psoriasis in contrast to atopic dermatitis, where larger vessels were observed. A response to biologic therapy was characterized by normalization of the imaging parameters in the target lesions in comparison to uninvolved skin during the observation period of 52 weeks. Optical coherence tomography potentially serves as an instrument to monitor biologic therapy in inflammatory skin diseases. Imaging parameters may enable objective quantification of inflammation in psoriasis or atopic dermatitis in selected representative skin areas. OCT may reveal persistent subclinical inflammation in atopic dermatitis beyond clinical remission.

Project description:ObjectivesWhile off-label dosing of biologic treatments may be necessary in selected psoriasis patients, no systematic review exists to date that synthesizes the efficacy and safety of these off-label dosing regimens. The aim of this systematic review is to evaluate efficacy and safety of off-label dosing regimens (dose escalation, dose reduction, and interrupted treatment) with etanercept, adalimumab, infliximab, ustekinumab, and alefacept for psoriasis treatment.Data sources and study selectionWe searched OVID Medline from January 1, 1990 through August 1, 2011 for prospective clinical trials that studied biologic therapy for psoriasis treatment in adults. Individual articles were screened for studies that examined escalated, reduced, or interrupted therapy with etanercept, adalimumab, infliximab, ustekinumab, or alefacept.Data synthesisA total of 23 articles with 12,617 patients matched the inclusion and exclusion criteria for the systematic review. Data were examined for primary and secondary efficacy outcomes and adverse events including infections, malignancies, cardiovascular events, and anti-drug antibodies. The preponderance of data suggests that continuous treatment with anti-TNF agents and anti-IL12/23 agent was necessary for maintenance of disease control. Among non-responders, dose escalation with etanercept, adalimumab, ustekinumab, and alefacept typically resulted in greater efficacy than standard dosing. Dose reduction with etanercept and alefacept resulted in reduced efficacy. Withdrawal of the examined biologics led to an increase in disease activity; efficacy from retreatment did not result in equivalent initial response rates for most biologics. Safety data on off-label dosing regimens are limited.ConclusionDose escalation in non-responders generally resulted in increased efficacy in the examined biologics used to treat moderate-to-severe psoriasis. Continuous treatment with anti-TNF agents and anti-IL12/23 agent results in superior efficacy over interrupted therapy. The decision to use off-label dosing needs to account for both benefits and risks and be individualized to patients' disease severity, quality of life, and existence of comorbidities.

Dataset Information

Multivariable Predictive Models to Identify the Optimal Biologic Therapy for Treatment of Patients With Psoriasis at the Individual Level.

Importance

Objective

Design, setting, and participants

Main outcomes and measures

Results

Conclusions and relevance

Publications

Multivariable Predictive Models to Identify the Optimal Biologic Therapy for Treatment of Patients With Psoriasis at the Individual Level.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets