Refining Prediction in Treatment-Resistant Depression: Results of Machine Learning Analyses in the TRD III Sample

被引:57
|
作者
Kautzky, Alexander [1 ]
Dold, Markus [1 ]
Bartova, Lucie [1 ]
Spies, Marie [1 ]
Vanicek, Thomas [1 ]
Souery, Daniel [2 ,3 ]
Montgomery, Stuart [4 ]
Mendlewicz, Julien [5 ]
Zohar, Joseph [6 ]
Fabbri, Chiara [7 ]
Serretti, Alessandro [7 ]
Lanzenberger, Rupert [1 ]
Kasper, Siegfried [1 ]
机构
[1] Med Univ Vienna, Dept Psychiat & Psychotherapy, Wahringer Gurtel 18-20, A-1090 Vienna, Austria
[2] Univ Libre Bruxelles, Brussels, Belgium
[3] Psy Pluriel Ctr Europeen Psychol Med, Brussels, Belgium
[4] Univ London, Imperial Coll, London, England
[5] Free Univ Brussels, Sch Med, Brussels, Belgium
[6] Chaim Sheba Med Ctr, Div Psychiat, Ramat Gan, Israel
[7] Univ Bologna, Dept Biomed & Neuromotor Sci, Bologna, Italy
关键词
SUBSTANCE USE DISORDERS; MAJOR DEPRESSION; EUROPEAN MULTICENTER; RATING-SCALE; OPEN-LABEL; STRATEGIES; SYMPTOMS; NONRESPONDERS; IMPROVEMENT; DULOXETINE;
D O I
10.4088/JCP.16m11385
中图分类号
B849 [应用心理学];
学科分类号
040203 ;
摘要
Objective: The study objective was to generate a prediction model for treatment-resistant depression (TRD) using machine learning featuring a large set of 47 clinical and sociodemographic predictors of treatment outcome. Method: 552 Patients diagnosed with major depressive disorder (MDD) according to DSM-IV criteria were enrolled between 2011 and 2016. TRD was defined as failure to reach response to antidepressant treatment, characterized by a Montgomery-Asberg Depression Rating Scale (MADRS) score below 22 after at least 2 antidepressant trials of adequate length and dosage were administered. RandomForest (RF) was used for predicting treatment outcome phenotypes in a 10-fold cross-validation. Results: The full model with 47 predictors yielded an accuracy of 75.0%. When the number of predictors was reduced to 15, accuracies between 67.6% and 71.0% were attained for different test sets. The most informative predictors of treatment outcome were baseline MADRS score for the current episode; impairment of family, social, and work life; the timespan between first and last depressive episode; severity; suicidal risk; age; body mass index; and the number of lifetime depressive episodes as well as lifetime duration of hospitalization. Conclusions: With the application of the machine learning algorithm RF, an efficient prediction model with an accuracy of 75.0% for forecasting treatment outcome could be generated, thus surpassing the predictive capabilities of clinical evaluation. We also supply a simplified algorithm of 15 easily collected clinical and sociodemographic predictors that can be obtained within approximately 10 minutes, which reached an accuracy of 70.6%. Thus, we are confident that our model will be validated within other samples to advance an accurate prediction model fit for clinical usage in TRD.
引用
收藏
页数:9
相关论文
共 50 条
  • [41] Altered peripheral immune profiles in treatment-resistant depression: response to ketamine and prediction of treatment outcome
    D D Kiraly
    S R Horn
    N T Van Dam
    S Costi
    J Schwartz
    S Kim-Schulze
    M Patel
    G E Hodes
    S J Russo
    M Merad
    D V Iosifescu
    D S Charney
    J W Murrough
    Translational Psychiatry, 2017, 7 : e1065 - e1065
  • [42] Altered peripheral immune profiles in treatment-resistant depression: response to ketamine and prediction of treatment outcome
    Kiraly, D. D.
    Horn, S. R.
    Van Dam, N. T.
    Costi, S.
    Schwartz, J.
    Kim-Schulze, S.
    Patel, M.
    Hodes, G. E.
    Russo, S. J.
    Merad, M.
    Iosifescu, D. V.
    Charney, D. S.
    Murrough, J. W.
    TRANSLATIONAL PSYCHIATRY, 2017, 7 : e1065 - e1065
  • [43] Identification of treatment-resistant major depressive disorder using a machine learning algorithm
    Semeniuta, Daniel
    Marci, Carl
    Bandaria, Jigar
    Zabinski, Joseph W.
    Paulus, Jessica K.
    Orsini, Lucinda
    Boussios, Costas
    PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2023, 32 : 447 - 447
  • [44] Treatment-Resistant Schizophrenia: Insights From Genetic Studies and Machine Learning Approaches
    Pisanu, Claudia
    Squassina, Alessio
    FRONTIERS IN PHARMACOLOGY, 2019, 10
  • [45] PREDICTION OF TREATMENT-RESISTANT DEPRESSION USING EXOME SEQUENCE AND GENOME-WIDE DATA
    Fabbri, Chiara
    Kasper, Siegfried
    Kautzky, Alexander
    Zohar, Joseph
    Souery, Daniel
    Montgomery, Stuart
    Albani, Diego
    Ferentinos, Panagiotis
    Rujescu, Dan
    Mendlewicz, Julien
    Lewis, Cathryn
    Serretti, Alessandro
    EUROPEAN NEUROPSYCHOPHARMACOLOGY, 2019, 29 : S92 - S92
  • [46] Results of the First Randomized Controlled Trial of Deep Brain Stimulation in Treatment-Resistant Depression
    Richardson, R. Mark
    Ghuman, Avniel S.
    Karp, Jordan F.
    NEUROSURGERY, 2015, 77 (02) : N23 - N24
  • [47] Clinical efficacy of trauma-focused psychotherapies in treatment-resistant depression (TRD) in-patients: A randomized, controlled pilot-study
    Minelli, Alessandra
    Zampieri, Elisa
    Sacco, Chiara
    Bazzanella, Roberta
    Mezzetti, Nicoletta
    Tessari, Elisabetta
    Barlati, Stefano
    Bortolomasi, Marco
    PSYCHIATRY RESEARCH, 2019, 273 : 567 - 574
  • [48] The LILA-study: An observational study comparing the efficacy of lithium vs. lamotrigine as an augmentation strategy for treatment-resistant depression (TRD)
    Schindler, F
    Anghelescu, I
    BIOLOGICAL PSYCHIATRY, 2004, 55 : 40S - 41S
  • [49] A New Trick of Old Dogs: Can Kappa Opioid Receptor Antagonist Properties of Antidepressants Assist in Treating Treatment-Resistant Depression (TRD)?
    Schreiber, Shaul
    Keidan, Lee
    Pick, Chaim G.
    PHARMACEUTICALS, 2025, 18 (02)
  • [50] Modulating neuroplasticity through synergistic ketamine and accelerated sequential theta burst stimulation (TBS) for treatment-resistant depression (TRD) - A case report
    Ramesh, Veena
    Shamanna, Varsha
    Pathak, Harsh
    Nayok, Swarna Buddha
    Bose, Anushree
    Sreeraj, Vanteemar S.
    ASIAN JOURNAL OF PSYCHIATRY, 2024, 102