Download This Paper
Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.
Predicting Effective Treatment Selections for Depressive Patients to Achieve Early Improvement According to Their Subtype Affiliations
47 Pages Posted: 26 Jun 2019
More...Abstract
Background: The treatment outcomes of the depression remain unsatisfactory. The timely selection of the optimal treatment at early-stage is a critical issue. Despite of significant findings in neuroimaging biomarkers, few studies included neuroimaging assessments in early-phases of treatment and a single biomarker is hard to guide personal treatment selection. Thus, a data-driven approach combined with functional circuits and clinical symptom was applied to predict effective treatment selection by identifying treatment-related subgroups.
Methods: Our study was a naturalistic study and 489 participants were enrolled from three sites. We identified symptom-guided brain connectome subgroups and built an early-stage treatment prediction model in the discovery dataset (n=228). Subgroups were compared in the aspects of effective intervention, symptomatic improvement, demographics, brain connectomes and clinical symptoms. Notably, we employed two independent datasets (n=89) to externally validate model. New patients' effective intervention was then expected to be consistent with the pre-defined subgroup.
Results: Three subgroups with distinct treatment recommendations emerged: (1) an SSRIs-oriented subgroup with more symptomatic improvements of apathy. (2) a physiotherapy-oriented subgroup with high improvement of suicide symptom. (3) an SNRI-oriented subgroup, unique decreased interactions within salience network (SN), between SN and cognition control network, together with the high baseline depressive severity. Specially, our model had a high sensitivity of 83.6% in improvement prediction, with an overall accuracy of 69.7%. Furthermore, our model was more effective for SSRIs prediction with 87.5% accuracy.
Conclusion: Our study offers guidance of multiple treatment strategies in early-stage treatment and extrapolates neuroimaging findings to 'real-world' practice.
Funding Statement: The work was supported by the National Natural Science Foundation of China [grant numbers: 81871066，81571639]; Jiangsu Provincial Medical Innovation Team of the Project of Invigorating Health Care through Science, Technology and Education [grant number: CXTDC2016004]; Jiangsu Provincial key research and development program [grant number: BE2018609].
Declaration of Interests: The authors state that they have no conflict of interest with the content of this article.
Ethics Approval Statement: A complete description of the study was informed to all subjects and written informed consents were obtained from all participants as approved by the Research Ethics Review Board of the Affiliated Brain Hospital of Nanjing Medical University, Nanjing Drum Tower Hospital and Peking University Sixth Hospital.
Keywords: Precision Psychiatry; Major depressive disorder; Effective treatment selection; Early improvement; Multi-sites
Suggested Citation: Suggested Citation