Detail
Článek
Článek online
FT
Medvik - BMČ
  • Je něco špatně v tomto záznamu ?

Prediction of lithium response using clinical data

A. Nunes, R. Ardau, A. Berghöfer, A. Bocchetta, C. Chillotti, V. Deiana, J. Garnham, E. Grof, T. Hajek, M. Manchia, B. Müller-Oerlinghausen, M. Pinna, C. Pisanu, C. O'Donovan, G. Severino, C. Slaney, A. Suwalska, P. Zvolsky, P. Cervantes, M. Del...

. 2020 ; 141 (2) : 131-141. [pub] 20191122

Jazyk angličtina Země Spojené státy americké

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc21012874

Grantová podpora
Genome Canada - International
Dalhousie Department of Psychiatry Research Fund - International
64410 CIHR - Canada
Nova Scotia Health Research Foundation Scotia Scholars Graduate Scholarship - International
Killam Postgraduate Scholarship - International
64410 CIHR - Canada

OBJECTIVE: Promptly establishing maintenance therapy could reduce morbidity and mortality in patients with bipolar disorder. Using a machine learning approach, we sought to evaluate whether lithium responsiveness (LR) is predictable using clinical markers. METHOD: Our data are the largest existing sample of direct interview-based clinical data from lithium-treated patients (n = 1266, 34.7% responders), collected across seven sites, internationally. We trained a random forest model to classify LR-as defined by the previously validated Alda scale-against 180 clinical predictors. RESULTS: Under appropriate cross-validation procedures, LR was predictable in the pooled sample with an area under the receiver operating characteristic curve of 0.80 (95% CI 0.78-0.82) and a Cohen kappa of 0.46 (0.4-0.51). The model demonstrated a particularly low false-positive rate (specificity 0.91 [0.88-0.92]). Features related to clinical course and the absence of rapid cycling appeared consistently informative. CONCLUSION: Clinical data can inform out-of-sample LR prediction to a potentially clinically relevant degree. Despite the relevance of clinical course and the absence of rapid cycling, there was substantial between-site heterogeneity with respect to feature importance. Future work must focus on improving classification of true positives, better characterizing between- and within-site heterogeneity, and further testing such models on new external datasets.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc21012874
003      
CZ-PrNML
005      
20210507101536.0
007      
ta
008      
210420s2020 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1111/acps.13122 $2 doi
035    __
$a (PubMed)31667829
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Nunes, A $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada $u Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada
245    10
$a Prediction of lithium response using clinical data / $c A. Nunes, R. Ardau, A. Berghöfer, A. Bocchetta, C. Chillotti, V. Deiana, J. Garnham, E. Grof, T. Hajek, M. Manchia, B. Müller-Oerlinghausen, M. Pinna, C. Pisanu, C. O'Donovan, G. Severino, C. Slaney, A. Suwalska, P. Zvolsky, P. Cervantes, M. Del Zompo, P. Grof, J. Rybakowski, L. Tondo, T. Trappenberg, M. Alda
520    9_
$a OBJECTIVE: Promptly establishing maintenance therapy could reduce morbidity and mortality in patients with bipolar disorder. Using a machine learning approach, we sought to evaluate whether lithium responsiveness (LR) is predictable using clinical markers. METHOD: Our data are the largest existing sample of direct interview-based clinical data from lithium-treated patients (n = 1266, 34.7% responders), collected across seven sites, internationally. We trained a random forest model to classify LR-as defined by the previously validated Alda scale-against 180 clinical predictors. RESULTS: Under appropriate cross-validation procedures, LR was predictable in the pooled sample with an area under the receiver operating characteristic curve of 0.80 (95% CI 0.78-0.82) and a Cohen kappa of 0.46 (0.4-0.51). The model demonstrated a particularly low false-positive rate (specificity 0.91 [0.88-0.92]). Features related to clinical course and the absence of rapid cycling appeared consistently informative. CONCLUSION: Clinical data can inform out-of-sample LR prediction to a potentially clinically relevant degree. Despite the relevance of clinical course and the absence of rapid cycling, there was substantial between-site heterogeneity with respect to feature importance. Future work must focus on improving classification of true positives, better characterizing between- and within-site heterogeneity, and further testing such models on new external datasets.
650    _2
$a dospělí $7 D000328
650    _2
$a věk při počátku nemoci $7 D017668
650    _2
$a antimanika $x terapeutické užití $7 D018692
650    _2
$a plocha pod křivkou $7 D019540
650    _2
$a bipolární porucha $x farmakoterapie $x epidemiologie $7 D001714
650    12
$a pravidla klinického rozhodování $7 D000081415
650    _2
$a progrese nemoci $7 D018450
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a lidé $7 D006801
650    _2
$a sloučeniny lithia $x terapeutické užití $7 D018020
650    12
$a strojové učení $7 D000069550
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a lidé středního věku $7 D008875
650    _2
$a ROC křivka $7 D012372
650    _2
$a rizikové faktory $7 D012307
650    _2
$a poruchy iniciace a udržování spánku $x epidemiologie $7 D007319
650    _2
$a výsledek terapie $7 D016896
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Ardau, R $u Unit of Clinical Pharmacology, San Giovanni di Dio Hospital, University Hospital of Cagliari, Cagliari, Italy
700    1_
$a Berghöfer, A $u Charité University Medical Center, Institute for Social Medicine, Epidemiology and Health Economics, Berlin, Germany
700    1_
$a Bocchetta, A $u Unit of Clinical Pharmacology, San Giovanni di Dio Hospital, University Hospital of Cagliari, Cagliari, Italy
700    1_
$a Chillotti, C $u Unit of Clinical Pharmacology, San Giovanni di Dio Hospital, University Hospital of Cagliari, Cagliari, Italy
700    1_
$a Deiana, V $u Section of Neuroscience and Clinical Pharmacology, Department of Biomedical Sciences, University of Cagliari, Cagliari, Italy
700    1_
$a Garnham, J $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada
700    1_
$a Grof, E $u Mood Disorders Center of Ottawa, Ottawa, ON, Canada $u Department of Psychiatry, University of Toronto, Toronto, ON, Canada
700    1_
$a Hajek, T $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada
700    1_
$a Manchia, M $u Section of Psychiatry, Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy $u Department of Pharmacology, Dalhousie University, Halifax, NS, Canada
700    1_
$a Müller-Oerlinghausen, B $u Charité Universitätsmedizin-Berlin, Berlin, Germany
700    1_
$a Pinna, M $u Centro Lucio Bini, Cagliari e Roma, Italy
700    1_
$a Pisanu, C $u Section of Neuroscience and Clinical Pharmacology, Department of Biomedical Sciences, University of Cagliari, Cagliari, Italy
700    1_
$a O'Donovan, C $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada
700    1_
$a Severino, G $u Section of Neuroscience and Clinical Pharmacology, Department of Biomedical Sciences, University of Cagliari, Cagliari, Italy
700    1_
$a Slaney, C $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada
700    1_
$a Suwalska, A $u Department of Adult Psychiatry, Poznan University of Medical Sciences, Poznan, Poland $u Department of Mental Health, Poznan University of Medical Sciences, Poznan, Poland
700    1_
$a Zvolsky, P $u Department of Psychiatry, Charles University, Prague, Czech Republic
700    1_
$a Cervantes, P $u Department of Psychiatry, McGill University Health Centre, Montreal, QC, Canada
700    1_
$a Del Zompo, M $u Section of Neuroscience and Clinical Pharmacology, Department of Biomedical Sciences, University of Cagliari, Cagliari, Italy
700    1_
$a Grof, P $u Mood Disorders Center of Ottawa, Ottawa, ON, Canada $u Department of Psychiatry, University of Toronto, Toronto, ON, Canada
700    1_
$a Rybakowski, J $u Department of Adult Psychiatry, Poznan University of Medical Sciences, Poznan, Poland $u Department of Psychiatric Nursing, Poznan University of Medical Sciences, Poznan, Poland
700    1_
$a Tondo, L $u Centro Lucio Bini, Cagliari e Roma, Italy $u Harvard Medical School and McLean Hospital, Boston, MA, USA
700    1_
$a Trappenberg, T $u Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada
700    1_
$a Alda, M $u Department of Psychiatry, Dalhousie University, Halifax, NS, Canada
773    0_
$w MED00009053 $t Acta psychiatrica Scandinavica $x 1600-0447 $g Roč. 141, č. 2 (2020), s. 131-141
856    41
$u https://pubmed.ncbi.nlm.nih.gov/31667829 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20210420 $b ABA008
991    __
$a 20210507101536 $b ABA008
999    __
$a ok $b bmc $g 1651115 $s 1133253
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2020 $b 141 $c 2 $d 131-141 $e 20191122 $i 1600-0447 $m Acta psychiatrica Scandinavica $n Acta Psychiatr Scand $x MED00009053
GRA    __
$p Genome Canada $2 International
GRA    __
$p Dalhousie Department of Psychiatry Research Fund $2 International
GRA    __
$a 64410 $p CIHR $2 Canada
GRA    __
$p Nova Scotia Health Research Foundation Scotia Scholars Graduate Scholarship $2 International
GRA    __
$p Killam Postgraduate Scholarship $2 International
GRA    __
$a 64410 $p CIHR $2 Canada
LZP    __
$a Pubmed-20210420

Najít záznam

Citační ukazatele

Možnosti archivace