Timely initiation of effective therapy is crucial for preventing disability in multiple sclerosis; however, treatment response varies greatly among patients. Comprehensive predictive models of individual treatment response are lacking. Our aims were: (i) to develop predictive algorithms for individual treatment response using demographic, clinical and paraclinical predictors in patients with multiple sclerosis; and (ii) to evaluate accuracy, and internal and external validity of these algorithms. This study evaluated 27 demographic, clinical and paraclinical predictors of individual response to seven disease-modifying therapies in MSBase, a large global cohort study. Treatment response was analysed separately for disability progression, disability regression, relapse frequency, conversion to secondary progressive disease, change in the cumulative disease burden, and the probability of treatment discontinuation. Multivariable survival and generalized linear models were used, together with the principal component analysis to reduce model dimensionality and prevent overparameterization. Accuracy of the individual prediction was tested and its internal validity was evaluated in a separate, non-overlapping cohort. External validity was evaluated in a geographically distinct cohort, the Swedish Multiple Sclerosis Registry. In the training cohort (n = 8513), the most prominent modifiers of treatment response comprised age, disease duration, disease course, previous relapse activity, disability, predominant relapse phenotype and previous therapy. Importantly, the magnitude and direction of the associations varied among therapies and disease outcomes. Higher probability of disability progression during treatment with injectable therapies was predominantly associated with a greater disability at treatment start and the previous therapy. For fingolimod, natalizumab or mitoxantrone, it was mainly associated with lower pretreatment relapse activity. The probability of disability regression was predominantly associated with pre-baseline disability, therapy and relapse activity. Relapse incidence was associated with pretreatment relapse activity, age and relapsing disease course, with the strength of these associations varying among therapies. Accuracy and internal validity (n = 1196) of the resulting predictive models was high (>80%) for relapse incidence during the first year and for disability outcomes, moderate for relapse incidence in Years 2-4 and for the change in the cumulative disease burden, and low for conversion to secondary progressive disease and treatment discontinuation. External validation showed similar results, demonstrating high external validity for disability and relapse outcomes, moderate external validity for cumulative disease burden and low external validity for conversion to secondary progressive disease and treatment discontinuation. We conclude that demographic, clinical and paraclinical information helps predict individual response to disease-modifying therapies at the time of their commencement.

Amiri Hospital P O Box 1661 Qurtoba Kuwait 73767 Kuwait

Assaf Harofeh Medical Center Zerifin Beer Yaakov 70100 Israel

Azienda Ospedaliera di Rilievo Nazionale San Giuseppe Moscati Avellino Contrada Amoretta Avellino 83100 Italy

Azienda Sanitaria Unica Regionale Marche AV3 Via Santa Lucia 2 Macerata 62100 Italy

Brain and Mind Centre University of Sydney 100 Mallett Camperdown 2050 Australia

C Mondino National Neurological Institute via Mondino 2 Pavia 27100 Italy

Centre de réadaptation déficience physique Chaudière Appalache 9500 blvd Centre Hospitalier Levis G6X 0A1 Canada

Cliniques Universitaires Saint Luc avenue Hippocrate 10 UCL10 80 Brussels 1200 BXL Belgium

CORe Department of Medicine University of Melbourne 300 Grattan St Melbourne 3050 Australia

Department of Biomedical and Neuromotor Sciences University of Bologna Via dei Vestini Bologna 66100 Italy

Department of Clinical Neuroscience Karolinska Institutet Stockholm SE 17177 Sweden

Department of Medicine University of Melbourne 300 Grattan St Melbourne 3050 Australia

Department of Neurology and Center of Clinical Neuroscience General University Hospital and Charles University Prague Katerinska 30 Prague 12808 Czech Republic

Department of Neurology Box Hill Hospital Monash University Melbourne Australia

Department of Neurology Royal Melbourne Hospital 300 Grattan St Melbourne 3050 Australia

Department of Neuroscience Imaging and Clinical Sciences University 'G d'Annunzio' Via dei Vestini Chieti 66100 Italy

Department of Statistics and Probability University of Economics Prague Winston Churchill Sq 1938 4 Prague 13067 Czech Republic

Flinders Medical Centre Flinders Drive Adelaide 5042 Australia

Groene Hart ziekenhuis bleulandweg 10 Gouda 2800 BB The Netherlands

Hopital Notre Dame 1560 Sherbrooke East Montreal H2L 4M1 Canada; CHUM and Universite de Montreal Montreal Canada

Hospital de Galdakao Usansolo Barrio Labeaga s n Galdakao 48660 Spain

Hospital Donostia Paseo de Begiristain San Sebastián 20014 Spain

Hospital Germans Trias i Pujol Crtra de Canyet s n Badalona 8916 Spain

Hospital Italiano Guise 1870 Buenos Aires 1425 Argentina

Hospital Universitario La Paz Paseo de la Castellana 261 Madrid 28050 Spain

Hospital Universitario Virgen Macarena Amador de los Rios 48 50 4a Sevilla 41003 Spain

INEBA Institute of Neuroscience Buenos Aires Guardia Vieja 4435 Buenos Aires C1192AAW Argentina

Isfahan University of Medical Sciences Soffeh St Isfahan 81744 Iran

Jahn Ferenc Teaching Hospital Köves u 1 Budapest 1101 Hungary

Jewish General Hospital 3755 Cote Sainte Catherine Montreal J7A 4T8 Canada

KTU Medical Faculty Farabi Hospital Karadeniz Technical University Trabzon 61080 Turkey

Liverpool Hospital Elizabeth St Liverpool 21 Australia

Nemocnice Jihlava Vrchlickeho 59 Jihlava 58633 Czech Republic

Neuro Rive Sud 4896 boul Taschereau suite 250 Greenfield Park J4V 2J2 Canada

Nuovo Ospedale Civile Sant'Agostino Estense via giardini 1355 Modena 41100 Italy

Ondokuz Mayis University Medical Faculty Kurupelit Samsun 55160 Turkey

Ospedali Riuniti di Salerno Via s Leonardo Salerno 84100 Italy

Royal Brisbane and Women's Hospital 33 North Street Spring Hill QLD 4000 Australia

University of Bari Via Calefati 53 Bari 70122 Italy

University of Florence Viale Morgagni 85 Florence 50134 Italy

University of Newcastle Lookout Road Newcastle 2305 Australia

University of Parma Via Gramsci 14 Parma 43100 Italy

Westmead Hospital Hawkesbury Rd Sydney 2145 Australia

Zuyderland Ziekenhuis Walramstraat 23 Sittard 6131 BK The Netherlands

Komentář v

Brain. 2018 May 1;141(5):e39. doi: 10.1093/brain/awy056. PubMed

Komentář v

Brain. 2018 May 1;141(5):e38. doi: 10.1093/brain/awy055. PubMed

Citace poskytuje Crossref.org

A future of AI-driven personalized care for people with multiple sclerosis

Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study

Predictors of treatment switching in the Big Multiple Sclerosis Data Network

Using personalized prognosis in the treatment of relapsing multiple sclerosis: A practical guide

Treatment Response Score to Glatiramer Acetate or Interferon Beta-1a