Machine learning for predicting psychotic relapse at 2 years in schizophrenia in the national FACE-SZ cohort
Progress in Neuro-Psychopharmacology and Biological Psychiatry. 2019-06-01; 92: 8-18
DOI: 10.1016/j.pnpbp.2018.12.005
Read on PubMed
1. Prog Neuropsychopharmacol Biol Psychiatry. 2019 Jun 8;92:8-18. doi:
10.1016/j.pnpbp.2018.12.005. Epub 2018 Dec 12.
Machine learning for predicting psychotic relapse at 2 years in schizophrenia in
the national FACE-SZ cohort.
Fond G(1), Bulzacka E(2), Boucekine M(3), Schürhoff F(2), Berna F(4), Godin
O(2), Aouizerate B(5), Capdevielle D(6), Chereau I(7), D’Amato T(8), Dubertret
C(9), Dubreucq J(10), Faget C(11), Leignier S(10), Lançon C(11), Mallet J(9),
Misdrahi D(12), Passerieux C(13), Rey R(8), Schandrin A(6), Urbach M(13),
Vidailhet P(14), Leboyer M(2); FACE-SZ (FondaMental Academic Centers of
Expertise for Schizophrenia) group; Boyer L(15), Llorca PM(7).
Author information:
(1)Fondation FondaMental, Créteil, France; Faculté de Médecine – Secteur Timone,
Aix-Marseille Univ, d’Etude et de Recherche sur les Services de Santé et la
Qualité de vie, 27 Boulevard Jean Moulin, 13005 Marseille, France. Electronic
address: .
(2)Fondation FondaMental, Créteil, France; INSERM U955, équipe de psychiatrie
translationnelle, Créteil, France, Université Paris-Est Créteil, DHU Pe-PSY,
Pôle de Psychiatrie des Hôpitaux Universitaires H Mondor, Créteil, France.
(3)Faculté de Médecine – Secteur Timone, Aix-Marseille Univ, d’Etude et de
Recherche sur les Services de Santé et la Qualité de vie, 27 Boulevard Jean
Moulin, 13005 Marseille, France.
(4)Fondation FondaMental, Créteil, France; Hôpitaux Universitaires de
Strasbourg, Université de Strasbourg, INSERM U1114, Fédération de Médecine
Translationnelle de Strasbourg, Strasbourg, France.
(5)Fondation FondaMental, Créteil, France; Centre Hospitalier Charles Perrens,
Université de Bordeaux, Bordeaux F-33076, France; INRA, NutriNeuro, University
of Bordeaux, U1286, Bordeaux F-33076, France.
(6)Fondation FondaMental, Créteil, France; Hôpital la Colombière, CHRU
Montpellier, Service Universitaire de Psychiatrie Adulte, Université Montpellier
1, Montpellier 1061, France.
(7)Fondation FondaMental, Créteil, France; Faculté de Médecine, Université
d’Auvergne, CMP B, CHU, EA 7280, Clermont-Ferrand Cedex 69 63003, France.
(8)Fondation FondaMental, Créteil, France; Centre de Recherche en Neurosciences
de Lyon, Université Claude Bernard Lyon, Equipe PSYR2, Centre Hospitalier Le
Vinatier, Pole Est, 95 bd Pinel, Bron Cedex 69678, France.
(9)Fondation FondaMental, Créteil, France; AP-HP, Department of Psychiatry,
Faculté de médecine, Louis Mourier Hospital, Université Paris Diderot, Colombes
U894, France.
(10)Fondation FondaMental, Créteil, France; Centre Référent de Réhabilitation
Psychosociale, Alpes Isère, Grenoble, France.
(11)Fondation FondaMental, Créteil, France; Assistance Publique des Hôpitaux de
Marseille (AP-HM), pôle universitaire de psychiatrie, Marseille, France.
(12)Fondation FondaMental, Créteil, France; Centre Hospitalier Charles Perrens,
Université de Bordeaux, Bordeaux F-33076, France; CNRS UMR 5287-INCIA, France.
(13)Fondation FondaMental, Créteil, France; Service de psychiatrie d’adulte,
Centre Hospitalier de Versailles, UFR des Sciences de la Santé Simone Veil,
Université Versailles Saint-Quentin en Yvelines, Versailles, France.
(14)Hôpitaux Universitaires de Strasbourg, Université de Strasbourg, INSERM
U1114, Fédération de Médecine Translationnelle de Strasbourg, Strasbourg,
France.
(15)Fondation FondaMental, Créteil, France; Faculté de Médecine – Secteur
Timone, Aix-Marseille Univ, d’Etude et de Recherche sur les Services de Santé et
la Qualité de vie, 27 Boulevard Jean Moulin, 13005 Marseille, France.
BACKGROUND: Predicting psychotic relapse is one of the major challenges in the
daily care of schizophrenia.
OBJECTIVES: To determine the predictors of psychotic relapse and follow-up
withdrawal in a non-selected national sample of stabilized community-dwelling SZ
subjects with a machine learning approach.
METHODS: Participants were consecutively included in the network of the
FondaMental Expert Centers for Schizophrenia and received a thorough clinical
and cognitive assessment, including recording of current treatment. Relapse was
defined by at least one acute psychotic episode of at least 7 days, reported by
the patient, her/his relatives or by the treating psychiatrist, within the
2-year follow-up. A classification and regression tree (CART) was used to
construct a predictive decision tree of relapse and follow-up withdrawal.
RESULTS: Overall, 549 patients were evaluated in the expert centers at baseline
and 315 (57.4%) (mean age = 32.6 years, 24% female gender) were followed-up at
2 years. On the 315 patients who received a visit at 2 years, 125(39.7%)
patients had experienced psychotic relapse at least once within the 2 years of
follow-up. High anger (Buss&Perry subscore), high physical aggressiveness
(Buss&Perry scale subscore), high lifetime number of hospitalization in
psychiatry, low education level, and high positive symptomatology at baseline
(PANSS positive subscore) were found to be the best predictors of relapse at
2 years, with a percentage of correct prediction of 63.8%, sensitivity 71.0% and
specificity 44.8%. High PANSS excited score, illness duration