Elsevier

Schizophrenia Research

Volume 188, October 2017, Pages 182-184
Schizophrenia Research

Letter to the Editor
Peripheral biomarker signatures of bipolar disorder and schizophrenia: A machine learning approach

https://doi.org/10.1016/j.schres.2017.01.018Get rights and content

Section snippets

Conflict of interest

Dr. Pinto, Dr. Passos, Dr. Gomes, Dr. Reckziegel and Dr. Mwangi reported no biomedical financial interests or potential conflicts of interest. Dr. Kauer-Sant’Anna reports grants from CNPQ – UNIVERSAL (Edital Universal 14/2011), grants from SMRI (Grant ID: 07TGF-1148 (co-investigator)), personal fees from ELI-LILLY, personal fees from NOVARTIS, personal fees from SHIRE, grants from FIPE-HCPA, grants and personal fees from CNPQ Produtividade em Pesquisa (Bolsista de Produtividade em Pesquisa do

Contributors

Authors Pinto, Passos, Gomes, Mwangi and Kauer-Sant'Anna contributed to the study design. Authors Pinto, Passos, Gomes and Reckziegel were responsible for the data collection and managed the literature searches. Authors Pinto, Passos and Mwangi undertook the statistical and machine learning analysis. Authors Pinto, Passos, Gomes, Reckziegel, Kapczinski, Mwangi and Kauer-Sant'Anna were responsible for the interpretation of findings and contributed to the final manuscript.

Acknowledgement

We thank the Laboratory of Molecular Psychiatry team from Hospital de Clinicas de Porto Alegre.

References (17)

There are more references available in the full text version of this article.

Cited by (22)

  • Machine learning approaches for prediction of bipolar disorder based on biological, clinical and neuropsychological markers: A systematic review and meta-analysis

    2022, Neuroscience and Biobehavioral Reviews
    Citation Excerpt :

    The overall strength of the evidence was assessed according to the GRADE approach (Iorio et al., 2015). The systematic search identified 763 studies, 81 of which met the inclusion criteria (Fig. S2, Table 3) (Achalia et al., 2020; Almeida et al., 2013; Anticevic et al., 2014; Appaji et al., 2019; Arribas et al., 2010; Bansal et al., 2012; Besga et al., 2016; Besga et al., 2015; Besga et al., 2012; Burger et al., 2017; Chen et al., 2020; Chen et al., 2014; Chen et al., 2015; Chuang and Kuo, 2017; Costafreda et al., 2011; Doan et al., 2017; Du et al., 2020; Erguzel et al., 2016; Erguzel et al., 2015; Fernandes et al., 2020; Frangou et al., 2017; Fung et al., 2015; Grotegerd et al., 2014; Grotegerd et al., 2013; Haenisch et al., 2016; Hajek et al., 2015; He et al., 2017; Hess et al., 2020; Jiang et al., 2020; Jie et al., 2015; Karthik and Sudha, 2020; Kittel-Schneider et al., 2020; Koutsouleris et al., 2015; Lai et al., 2015; Li et al., 2014; Li et al., 2020; Li et al., 2017; Lin et al., 2018; Lithgow et al., 2019a; Lithgow et al., 2019b; Matsubara et al., 2019; Mourão-Miranda et al., 2012; Munkholm et al., 2015; Munkholm et al., 2019; Mwangi et al., 2016; Nunes et al., 2020; Palaniyappan et al., 2019; Perez Arribas et al., 2018; Pinto et al., 2017; Pirooznia et al., 2012; Poletti et al., 2020; Rashid et al., 2016; Redlich et al., 2014; Rive et al., 2016; Roberts et al., 2017; Rocha-Rego et al., 2014; Rokham et al., 2020; Rubin-Falcone et al., 2018; Salvador et al., 2017; Schnack et al., 2014; Schulz et al., 2017; Schwarz et al., 2019; Serpa et al., 2014; Shan et al., 2020; Shao et al., 2019; Squarcina et al., 2019; Struyf et al., 2008; Sutcubasi et al., 2019; Tasic et al., 2019; Vai et al., 2020; Vawter et al., 2018; Wang et al., 2020; Wollenhaupt-Aguiar et al., 2020; Wu et al., 2017a; Wu et al., 2017b; Wu et al., 2016; Xu et al., 2014; Yang et al., 2019; Yu et al., 2020; Zheng et al., 2013; Zheng et al., 2019). 16 studies included in the systematic review were excluded from the meta-analysis: 14 reported only AUC values without overall accuracy (Chen et al., 2020; Chuang and Kuo, 2017; Doan et al., 2017; Hess et al., 2020; Li et al., 2020; Munkholm et al., 2015; Munkholm et al., 2019; Pirooznia et al., 2012; Schulz et al., 2017; Schwarz et al., 2019; Struyf et al., 2008; Xu et al., 2014; Zheng et al., 2013; Zheng et al., 2019) and 2 did not report overall accuracy (Lai et al., 2015; Tasic et al., 2019) (Fig. S2).

  • Bipolar disorders

    2020, The Lancet
    Citation Excerpt :

    The neurobiological progression hypothesis is the notion that people with bipolar disorders might exhibit progressive neurobiological changes as a function of illness duration and the number of previous episodes. Neurobiological progression in bipolar disorders is suggested by longitudinal phenomenological, neurostructural, cognitive, neurochemical, and biochemical data.84,85 Moreover, waning treatment response to pharmacological agents, cognitive behavioural therapy, and psychoeducation in people with multi-episode bipolar disorders with time indirectly supports the neurobiological progression hypothesis.86–88

  • Decoding rumination: A machine learning approach to a transdiagnostic sample of outpatients with anxiety, mood and psychotic disorders

    2020, Journal of Psychiatric Research
    Citation Excerpt :

    These techniques have the potential to create a paradigm shift in prediction and stratification of clinical outcomes (Librenza-Garcia et al., 2017). Recent studies have reported high prediction accuracies in distinguishing patients with bipolar disorder from healthy individuals with neuroimaging (Mwangi et al., 2016), neurocognitive data (Wu et al., 2016, 2017a; 2017b) and serum biomarkers (Pinto et al., 2017). A recent work also predicted who will attempt suicide among patients with bipolar disorder (Passos et al., 2016b).

  • Biomarkers for bipolar disorder

    2020, Neurobiology of Bipolar Disorder: Road to Novel Therapeutics
  • Precision medicine in the assessment of suicide risk

    2019, Precision Medicine for Investigators, Practitioners and Providers
  • The impact of machine learning techniques in the study of bipolar disorder: A systematic review

    2017, Neuroscience and Biobehavioral Reviews
    Citation Excerpt :

    Using a SVM algorithm, the model could distinguish schizophrenia patients from HC with 72.5% accuracy (p < 0.05) and bipolar disorder from HC with 77.5% accuracy (p < 0.05). The model, however, failed to differentiate bipolar disorder from schizophrenia subjects, with an accuracy of 49% (Pinto et al., 2017). We hypothesize that the inability to separate bipolar disorder from schizophrenia in the model may be due to shared characteristics among the disorders, such as cytokines profiles and immune-inflammatory related pathways (Goldsmith et al., 2016; Goodkind et al., 2015).

View all citing articles on Scopus
View full text