Machine learning for predicting psychotic relapse at 2 years in schizophrenia in the national FACE-SZ cohort

被引：30

作者：

Fond, G. ^{[1
,4
,14
]}

Bulzacka, E. ^{[1
,2
,3
,6
]}

Boucekine, M. ^{[4
]}

Schurhoff, F. ^{[1
,2
,3
,6
]}

Berna, F. ^{[1
,4
,6
]}

Godin, O. ^{[1
,2
,3
]}

Aouizerate, B. ^{[1
,2
,3
,5
,14
]}

Capdevielle, D. ^{[1
,7
]}

Chereau, I ^{[1
,8
]}

D'Amato, T. ^{[1
,8
,9
]}

Dubertret, C. ^{[1
,10
,11
]}

Dubreucq, J. ^{[1
,10
,11
]}

Faget, C. ^{[1
,12
]}

Leignier, S. ^{[1
,11
]}

Lancon, C. ^{[1
,12
]}

Mallet, J. ^{[1
,10
,11
]}

Misdrahi, D. ^{[1
,5
,14
,15
]}

Passerieux, C. ^{[1
,13
]}

Rey, R. ^{[1
,8
,9
]}

Schandrin, A. ^{[1
,7
,14
]}

Urbach, M. ^{[1
,13
]}

Vidailhet, P. ^{[1
,4
,6
]}

Leboyer, M. ^{[1
,2
,3
,6
]}

Boyer, L. ^{[1
,4
,14
]}

Llorca, P. M. ^{[1
,8
]}

Andrianarisoa, M. ^{[1
,6
]}

Bazin, N. ^{[1
]}

Blanc, O. ^{[1
,5
]}

Brunel, L. ^{[1
,6
]}

Chereau-Boudet, I ^{[1
,5
]}

Chesnoy-Servanin, G. ^{[1
,8
]}

Coulon, N.

Jm, Danion ^{[1
,4
]}

Deloge, A. ^{[1
,9
]}

Delorme, C. ^{[1
,10
]}

Denizot, H. ^{[1
,5
]}

Dorey, J. M. ^{[1
,8
]}

Fluttaz, C. ^{[1
,10
]}

Fonteneau, S. ^{[1
,13
]}

Gabayet, F. ^{[1
,10
]}

Giraud-Baro, E. ^{[1
,10
]}

Lacelle, D. ^{[1
,5
]}

Laouamri, H. ^{[1
]}

Le Gloahec, T. ^{[1
,6
]}

Le Strat, Y. ^{[1
,11
]}

Llorca ^{[1
,5
]}

Metairie, E. ^{[1
,12
]}

Offerlin-Meyer, I ^{[1
,4
]}

Peri, P. ^{[1
,12
]}

Pires, S. ^{[1
,5
]}

机构：

[1] Fondat FondaMental, Creteil, France

[2] INSERM U955, Equipe Psychiat Translat, Creteil, France

[3] Univ Paris Est Creteil, DHU Pe PSY, Pole Psychiat Hop Univ H Mondor, Creteil, France

[4] Aix Marseille Univ, Fac Med, Etud & Rech Serv Sante & Qualite Vie, Secteur Timone, 27 Blvd Jean Moulin, F-13005 Marseille, France

[5] Univ Bordeaux, Ctr Hosp Charles Perrens, F-33076 Bordeaux, France

[6] Univ Strasbourg, Hop Univ Strasbourg, INSERM U1114, Federat Med Translat Strasbourg, Strasbourg, France

[7] Univ Montpellier I, Hop Colombiere, CHRU Montpellier, Serv Univ Psychiat Adulte, F-1061 Montpellier, France

[8] Univ Auvergne, Fac Med, CMP B, CHU, EA 7280, F-63003 Clermont Ferrand 69, France

[9] Univ Claude Bernard Lyon, Ctr Rech Neurosci Lyon, Equipe PSYR2, Ctr Hosp Le Vinatier,Pole Est, 95 Bd Pinel, F-69678 Bron, France

[10] Univ Paris Diderot, Louis Mourier Hosp, AP HP, Dept Psychiat,Fac Med,Colombes U894, Paris, France

[11] Ctr Referent Rehabil Psychosociale, Grenoble, France

[12] Pole Univ Psychiat, AP HM, Marseille, France

[13] Univ Versailles St Quentin Yvelines, Ctr Hosp Versailles, Serv Psychiat Adulte, UFR Sci Sante Simone Veil, Versailles, France

[14] Univ Bordeaux, INRA, NutriNeuro, U1286, F-33076 Bordeaux, France

[15] CNRS UMR 5287 INCIA, Paris, France

来源：

PROGRESS IN NEURO-PSYCHOPHARMACOLOGY & BIOLOGICAL PSYCHIATRY | 2019年 / 92卷

关键词：

Schizophrenia; Aggressiveness; Relapse; Prediction; Machine learning; PREMORBID INTELLIGENCE LEVELS; RATING-SCALE; MEDICATION ADHERENCE; PRODROMAL SYMPTOMS; SELF-REPORT; RELIABILITY; VALIDITY; INSIGHT; DURATION; VERSION;

D O I：

10.1016/j.pnpbp.2018.12.005

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

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 < 2 years, low Buss& Perry hostility score, high CTQ score, low premorbid IQ and low medication adherence (BARS) score were found to be the best predictors of follow-up withdrawal with a percentage of correct prediction of 52.4%, sensitivity 62%, specificity 38.7%. Conclusion: Machine learning can help constructing predictive score. In the present sample, aggressivenessappears to be a good early warning sign of psychotic relapse and follow-up withdrawal and should be systematically assessed in SZ subjects. The other above-mentioned clinical variables may help clinicians to improve the prediction of psychotic relapse at 2 years.

引用

页码：8 / 18

页数：11

共 59 条

[1] RELIABILITY AND VALIDITY OF A DEPRESSION RATING-SCALE FOR SCHIZOPHRENICS [J].

ADDINGTON, D ;

ADDINGTON, J ;

MATICKATYNDALE, E ;

JOYCE, J .

SCHIZOPHRENIA RESEARCH, 1992, 6 (03) :201-208

[2] International Diabetes Federation: a consensus on Type 2 diabetes prevention [J].

Alberti, K. G. M. M. ;

Zimmet, P. ;

Shaw, J. .

DIABETIC MEDICINE, 2007, 24 (05) :451-463

[3] Attributable risk of co-morbid substance use disorder in poor Observance to pharmacological treatment and the occurrence of relapse in schizophrenia [J].

Ameller, A. ;

Gorwood, P. .

ENCEPHALE-REVUE DE PSYCHIATRIE CLINIQUE BIOLOGIQUE ET THERAPEUTIQUE, 2015, 41 (02) :174-183

[4]

[Anonymous], J STAT SOFTW, V61, P1

[5]

[Anonymous], 1983, CLASSIFICATION REGRE

[6]

[Anonymous], 2008, ECHELLE INTELLIGENCE

[7] The cost of relapse and the predictors of relapse in the treatment of schizophrenia [J].

Ascher-Svanum, Haya ;

Zhu, Baojin ;

Faries, Douglas E. ;

Salkever, David ;

Slade, Eric P. ;

Peng, Xiaomei ;

Conley, Robert R. .

BMC PSYCHIATRY, 2010, 10

[8] The burden of schizophrenia on caregivers - A review [J].

Awad, A. George ;

Voruganti, Lakshmi N. P. .

PHARMACOECONOMICS, 2008, 26 (02) :149-162

[9]

Baddeley A. D., 1994, Doors and people: A test of visual and verbal recall and recognition

[10] A RATING-SCALE FOR DRUG-INDUCED AKATHISIA [J].

BARNES, TRE .

BRITISH JOURNAL OF PSYCHIATRY, 1989, 154 :672-676

← 1 2 3 4 5 6 →