Predicting Secukinumab Fast-Responder Profile in Psoriatic Patients: Advanced Application of Artificial-Neural-Networks (ANNs)
December 2020 | Volume 19 | Issue 12 | Editorials | 1241 | Copyright © December 2020
Published online November 4, 2020
Giovanni Damiani MD,a,b,c,d,e Rosalynn R.Z. Conic MD PhD,a Paolo D.M. Pigatto Prof MD,d,e Carlo G. Carrera MD,c Chiara Franchi MD,d Angelo Cattaneo MD,c Piergiorgio Malagoli MD,f Radhakrishna Uppala Prof MD PhD,g Dennis Linder Prof MD,h Nicola L. Bragazzi MD PhD,i Enzo Grossi Prof MDj
aDepartment of Dermatology, Case Western Reserve University, Cleveland, OH
bYoung Dermatologists Italian Network
cUOC Dermatologia, Dipartimento di Fisiopatologia Medico-Chirurgica e dei Trapianti, Università degli Studi di Milano, UOC Dermatology, IRCCS Fondazione Ca’ Granda, Ospedale Maggiore Policlinico, Milan, Italy
dClinical Dermatology, IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
eDepartment of Biomedical, Surgical and Dental Sciences, University of Milan, Milan, Italy
fDermatology Unit,Azienda Ospedaliera San Donato Milanese, Milan, Italy
gDepartment of Obstetrics and Gynecology, Oakland University William Beaumont School of Medicine, Royal Oak, MI
hUnit of Dermatology, Ben Gurion University of the Negev, Beer-Sheva, Israel
iSchool of Public Health, Department of Health Sciences (DISSAL), University of Genoa, Italy
jFondazioneVilla Santa Maria,Tavernerio, Como, Italy
Abstract
Background: Drug resistance to biologics in psoriasis therapy can occur – it may be acquired during a treatment or else present itself from the beginning. To date, no biomarkers are known that may reliably guide clinicians in predicting responsiveness to biologics. Biologics may pose a substantial economic burden. Secukinumab efficiently targets IL-17 in the treatment of psoriasis.
Objective: To assess the “fast responder” patient profile, predicting it from the preliminary complete blood count (CBC) and clinical examination.
Materials and Methods: From November 2016 to May 2017 we performed a multicenter prospective open label pilot study in three Italian reference centers enrolling bio-naive plaque psoriasis patients, undergoing the initiation phase secukinumab treatment (300mg subcutaneous at week 0,1,2,3,4). We define fast responders as patients having achieved at least PASI 75 at the end of secukinumab induction phase. Clinical and CBC data at week 0 and at week 4 were analyzed with linear statistics, principal component analysis, and artificial neural networks (ANNs), also known as deep learning. Two different ANNs were employed: Auto Contractive Map (Auto-CM), an unsupervised ANNs, to study how this variables cluster and a supervised ANNs, Training with Input Selection and Testing (TWIST), to build the predictive model.
Results: We enrolled 23 plaque psoriasis patients: 19 patients were responders and 4 were non-responders. 30 attributes were examined by Auto-CM, creating a semantic map for three main profiles: responders, non-responders and an intermediate profile. The algorithm yielded 5 of the 30 attributes to describe the 3 profiles. This allowed us to set up the predictive model. It displayed after training testing protocol an overall accuracy of 91.88% (90% for responders and 93,75% for non-responders).
Conclusions: The present study is possibly the first approach employing ANNs to predict drug efficacy in dermatology; a wider use of ANNs may be conducive to useful both theoretical and clinical insight.
J Drugs Dermatol. 2020;19(12):1241-1246. doi:10.36849/JDD.2020.5006
INTRODUCTION
The anti–IL 17 biologic secukinumab has been recently shown to be fast and effective not only in clearing psoriasis skin lesions and preventing the associated cardiovascular damage but also for improving quality of life.1-4
Despite the large amount of data from randomized control trials (RCTs) now available on secukinumab, “real-life data†remain scarce, yet play a key role in clinicians’ daily practice.5,6 In fact, switching therapies due to lack of efficacy at 16 weeks7,8 or because of patients experiencing exacerbated side effects
