Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • News
  • Published:

Machine learning-guided intervention trials to predict treatment response at an individual patient level: an important second step following randomized clinical trials

Molecular Psychiatry volume 25, pages 701–702 (2020)Cite this article

Subjects

Cao et al. [1] reported a clinical tool able to predict response to risperidone treatment in first-episode drug-naive schizophrenia patients with a balanced accuracy of 82.5%. This work made a significant contribution to the field of personalized psychiatric treatment by using powerful machine learning techniques to analyze resting-state functional magnetic resonance imaging (fMRI) data as compared to a prior study that also reported a treatment response predictive tool in patients with schizophrenia [2].

Prediction of treatment response at an individual patient level remains an elusive goal in mental disorders. In particular, selecting an antipsychotic medication for schizophrenia remains a trial-and-error process, with no specific biomarkers to lend decision support. Randomized clinical trials and meta-analyses, the pillars of evidence-based medicine, have helped us identify effective treatment for specific disorders by leveraging traditional statistical methods. Traditional statistical methods primarily provide average group-level results within a population. On the one hand, this approach allows us to make broad generalizations about a specific population. On the other hand, it fails at detecting nuances related to an individual subject and therefore significant results may not represent a real benefit for some. Indeed, subjects included in clinical trials may not always reflect patients from the real-world clinical scenarios. In the latter, patients frequently have different multimorbidity profile, symptoms severity, degree of functional impairment, and even cultural backgrounds compared to the former [3]—and all these factors may play a role in treatment response. Consequently, machine learning-guided intervention trials may help evidence-based medicine by (a) using these nuances to make predictions of treatment response (and side effects) at an individual level; (b) handling large amount of data from multiple biological levels to develop treatment response signatures; (c) finding non-linear biological data patterns associated with response to treatment. Below we explore these points and factors that the field should take into consideration moving forward.

This is a preview of subscription content, access via your institution

Relevant articles

Open Access articles citing this article.

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

References

  1. Cao B, Cho RY, Chen D, Xiu M, Wang L, Soares JC, et al. Treatment response prediction and individualized identification of first-episode drug-naïve schizophrenia using brain functional connectivity. Mol Psychiatry. 2018. https://doi.org/10.1038/s41380-018-0106-5.

  2. Sarpal DK, Argyelan M, Robinson DG, Szeszko PR, Karlsgodt KH, John M, et al. Baseline striatal functional connectivity as a predictor of response to antipsychotic drug treatment. Am J Psychiatry. 2016;173:69–77.

    Article  Google Scholar 

  3. Greenhalgh T, Howick J, Maskrey N. Evidence based medicine: a movement in crisis? BMJ. 2014;348:g3725–g3725.

    Article  Google Scholar 

  4. Kessler RC, Stein MB, Petukhova MV, Bliese P, Bossarte RM, Bromet EJ, et al. Predicting suicides after outpatient mental health visits in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS). Mol Psychiatry. 2017;22:544–51.

    Article  CAS  Google Scholar 

  5. Cole JH, Ritchie SJ, Bastin ME, Valdés Hernández MC, Muñoz Maniega S, Royle N, et al. Brain age predicts mortality. Mol Psychiatry. 2018;23:1385–92.

    Article  CAS  Google Scholar 

  6. Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;375:1216–9.

    Article  Google Scholar 

  7. Chekroud AM, Zotti RJ, Shehzad Z, Gueorguieva R, Johnson MK, Trivedi MH, et al. Cross-trial prediction of treatment outcome in depression: a machine learning approach. Lancet Psychiatry. 2016;3:243–50.

    Article  Google Scholar 

  8. van Waarde JA, Scholte HS, van Oudheusden LJB, Verwey B, Denys D, van Wingen GA. A functional MRI marker may predict the outcome of electroconvulsive therapy in severe and treatment-resistant depression. Mol Psychiatry. 2015;20:609–14.

    Article  Google Scholar 

  9. Månsson KNT, Frick A, Boraxbekk C-J, Marquand AF, Williams SCR, Carlbring P, et al. Predicting long-term outcome of Internet-delivered cognitive behavior therapy for social anxiety disorder using fMRI and support vector machine learning. Transl Psychiatry. 2015;5:e530.

    Article  Google Scholar 

  10. Leucht S, Cipriani A, Spineli L, Mavridis D, Örey D, Richter F, et al. Comparative efficacy and tolerability of 15 antipsychotic drugs in schizophrenia: a multiple-treatments meta-analysis. Lancet. 2013;382:951–62.

    Article  CAS  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Programa de Pós-Graduação em Psiquiatria e Ciências do Comportamento, Laboratory of Molecular Psychiatry and Bipolar Disorder Program, Hospital de Clínicas de Porto Alegre, Universidade Federal do Rio Grande do Sul, Porto Alegre, RS, Brazil

    Ives Cavalcante Passos

  2. UT Center of Excellence on Mood Disorders, Department of Psychiatry and Behavioral Sciences, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, TX, USA

    Benson Mwangi

Authors
  1. Ives Cavalcante Passos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Benson Mwangi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ives Cavalcante Passos.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Passos, I.C., Mwangi, B. Machine learning-guided intervention trials to predict treatment response at an individual patient level: an important second step following randomized clinical trials. Mol Psychiatry 25, 701–702 (2020). https://doi.org/10.1038/s41380-018-0250-y

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41380-018-0250-y

This article is cited by

Search

Advanced search

Quick links