Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria

Background: Omalizumab is the best treatment for patients with chronic spontaneous urticaria (CSU). Machine learning (ML) approaches can be used to predict response to therapy and the effectiveness of a treatment. No studies are available on the use of ML techniques to predict the response to Omaliz...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Davide Stefano Sardina, Giuseppe Valenti, Francesco Papia, Carina Gabriela Uasuf
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	chronic spontaneous urticaria omalizumab machine learning technique biomarkers anti-IgE Medicine (General) R5-920
Acceso en línea:	https://doaj.org/article/68bf52e54d32483f949bae14eb2ff421
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:68bf52e54d32483f949bae14eb2ff421
record_format	dspace
spelling	oai:doaj.org-article:68bf52e54d32483f949bae14eb2ff4212021-11-25T17:22:04ZExploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria10.3390/diagnostics111121502075-4418https://doaj.org/article/68bf52e54d32483f949bae14eb2ff4212021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/2150https://doaj.org/toc/2075-4418Background: Omalizumab is the best treatment for patients with chronic spontaneous urticaria (CSU). Machine learning (ML) approaches can be used to predict response to therapy and the effectiveness of a treatment. No studies are available on the use of ML techniques to predict the response to Omalizumab in CSU. Methods: Data from 132 CSU outpatients were analyzed. Urticaria Activity Score over 7 days (UAS7) and treatment efficacy were assessed. Clinical and demographic characteristics were used for training and validating ML models to predict the response to treatment. Two methodologies were used to label the data based on the response to treatment (UAS7 ≥ 6): (A) at 1, 3 and 5 months; (B) classifying the patients as early responders (ER), late responders (LR) or non-responders (NR) (ER: UAS 7 ≥ 6 at first month, LR: UAS 7 ≥ 6 at third month, NR: if none of the previous conditions occurred). Results: ER were predominantly characterized by hypertension, while LR mainly suffered from asthma and hypothyroidism. A slight positive correlation (R<sup>2</sup> = 0.21) was found between total IgE levels and UAS7 at 1 month. Variable Importance Analysis (VIA) reported D-dimer and C-reactive proteins as the key blood tests for the performance of learning techniques. Using methodology (A), SVM (specificity of 0.81) and k-NN (sensitivity of 0.8) are the best models to predict LR at the third month. Conclusion: k-NN plus the SVM model could be used to identify the response to treatment. D-dimer and C-reactive proteins have greater predictive power in training ML models.Davide Stefano SardinaGiuseppe ValentiFrancesco PapiaCarina Gabriela UasufMDPI AGarticlechronic spontaneous urticariaomalizumabmachine learning techniquebiomarkersanti-IgEMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 2150, p 2150 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	chronic spontaneous urticaria omalizumab machine learning technique biomarkers anti-IgE Medicine (General) R5-920
spellingShingle	chronic spontaneous urticaria omalizumab machine learning technique biomarkers anti-IgE Medicine (General) R5-920 Davide Stefano Sardina Giuseppe Valenti Francesco Papia Carina Gabriela Uasuf Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
description	Background: Omalizumab is the best treatment for patients with chronic spontaneous urticaria (CSU). Machine learning (ML) approaches can be used to predict response to therapy and the effectiveness of a treatment. No studies are available on the use of ML techniques to predict the response to Omalizumab in CSU. Methods: Data from 132 CSU outpatients were analyzed. Urticaria Activity Score over 7 days (UAS7) and treatment efficacy were assessed. Clinical and demographic characteristics were used for training and validating ML models to predict the response to treatment. Two methodologies were used to label the data based on the response to treatment (UAS7 ≥ 6): (A) at 1, 3 and 5 months; (B) classifying the patients as early responders (ER), late responders (LR) or non-responders (NR) (ER: UAS 7 ≥ 6 at first month, LR: UAS 7 ≥ 6 at third month, NR: if none of the previous conditions occurred). Results: ER were predominantly characterized by hypertension, while LR mainly suffered from asthma and hypothyroidism. A slight positive correlation (R<sup>2</sup> = 0.21) was found between total IgE levels and UAS7 at 1 month. Variable Importance Analysis (VIA) reported D-dimer and C-reactive proteins as the key blood tests for the performance of learning techniques. Using methodology (A), SVM (specificity of 0.81) and k-NN (sensitivity of 0.8) are the best models to predict LR at the third month. Conclusion: k-NN plus the SVM model could be used to identify the response to treatment. D-dimer and C-reactive proteins have greater predictive power in training ML models.
format	article
author	Davide Stefano Sardina Giuseppe Valenti Francesco Papia Carina Gabriela Uasuf
author_facet	Davide Stefano Sardina Giuseppe Valenti Francesco Papia Carina Gabriela Uasuf
author_sort	Davide Stefano Sardina
title	Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
title_short	Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
title_full	Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
title_fullStr	Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
title_full_unstemmed	Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria
title_sort	exploring machine learning techniques to predict the response to omalizumab in chronic spontaneous urticaria
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/68bf52e54d32483f949bae14eb2ff421
work_keys_str_mv	AT davidestefanosardina exploringmachinelearningtechniquestopredicttheresponsetoomalizumabinchronicspontaneousurticaria AT giuseppevalenti exploringmachinelearningtechniquestopredicttheresponsetoomalizumabinchronicspontaneousurticaria AT francescopapia exploringmachinelearningtechniquestopredicttheresponsetoomalizumabinchronicspontaneousurticaria AT carinagabrielauasuf exploringmachinelearningtechniquestopredicttheresponsetoomalizumabinchronicspontaneousurticaria
_version_	1718412475218526208

Exploring Machine Learning Techniques to Predict the Response to Omalizumab in Chronic Spontaneous Urticaria

Ejemplares similares