Multimodel inference for biomarker development: an application to schizophrenia

Download

s41398-019-0419-4.pdf

Date

2019-02-11

Author

Cooper, Jason D.
Han, Sung Yeon Sarah
Tomasik, Jakub
Özcan Kabasakal, Süreyya
Rustogi, Nitin
van Beveren, Nico J. M.
Leweke, F. Markus
Bahn, Sabine

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

142
views

75
downloads

In the present study, to improve the predictive performance of a model and its reproducibility when applied to an independent data set, we investigated the use of multimodel inference to predict the probability of having a complex psychiatric disorder. We formed training and test sets using proteomic data (147 peptides from 77 proteins) from two-independent collections of first-onset drug-naive schizophrenia patients and controls. A set of prediction models was produced by applying lasso regression with repeated tenfold cross-validation to the training set. We used feature extraction and model averaging across the set of models to form two prediction models. The resulting models clearly demonstrated the utility of a multimodel based approach to make good (training set AUC > 0.80) and reproducible predictions (test set AUC > 0.80) for the probability of having schizophrenia. Moreover, we identified four proteins (five peptides) whose effect on the probability of having schizophrenia was modified by sex, one of which was a novel potential biomarker of schizophrenia, foetal haemoglobin. The evidence of effect modification suggests that future schizophrenia studies should be conducted in males and females separately. Future biomarker studies should consider adopting a multimodel approach and going beyond the main effects of features.

Subject Keywords

Biological Psychiatry, Cellular and Molecular Neuroscience, Psychiatry and Mental health

URI

https://hdl.handle.net/11511/49069

Journal

TRANSLATIONAL PSYCHIATRY

DOI

https://doi.org/10.1038/s41398-019-0419-4

Collections

Department of Chemistry, Article

Suggestions

OpenMETU
Core

Perceived Partner Responsiveness, Daily Negative Affect Reactivity, and All-Cause Mortality: A 20-Year Longitudinal Study Stanton, Sarah C. E.; Selçuk, Emre; Farrell, Allison K.; Slatcher, Richard B.; Ong, Anthony D. (Ovid Technologies (Wolters Kluwer Health), 2019-01-01) Objective This study tested longitudinal associations between absolute levels of perceived partner responsiveness (PPR; how much people perceive that their romantic partners understand, care for, and appreciate them), daily negative affect reactivity and positive affect reactivity, and all-cause mortality in a sample of 1,208 adults for three waves of data collection spanning 20 years. We also tested whether longitudinal changes in PPR predicted mortality via affect reactivity. Methods Data were taken from ...
Patterns of Depression in Medical Patients and Their Relationship with Causal Attrihutions for Illness Karanci, Nuray A. (S. Karger AG, 1988) he present study investigated the factor structure of the Beck Depression Inventory (BDI), and causal attributions for the development of illness in a sample of 102 inpatients of a thoracic surgery department, with the main objective of examining the power of causal attributions and functional support in predicting different factors derived from the BDI. The results revealed that the BDI clusters into affective/motivational, somatic/vegetative, self-blame and self-punitiveness dimensions. Causal attribution...
A new fuzzy-chaotic modelling proposal for medical diagnostic processes Beyan, Timur; Baykal, Nazife; Department of Information Systems (2005) Main reason of this study is to set forth the internal paradox of the basic approach of the artificial intelligence in the medical field to by discussing on the theoretical and application levels and to suggest solutions in theory and practice against that. In order to rule out the internal paradox in the medical decision support systematic, a new medical model is suggested and based on this, concepts such as disease, health, etiology, diagnosis and treatment are questioned. Meanwhile, with the current scie...
HOW DYSFUNCTIONAL ARE THE DYSFUNCTIONAL ATTITUDES IN ANOTHER CULTURE SAHIN, NH; SAHIN, N (Wiley, 1992-03-01) The Dysfunctional Attitude Scale (DAS-A) has been used in many studies to measure depressogenic attitudes, vulnerability to depression and to assess the effectiveness of cognitive therapy. Despite its frequent use in research, no data have yet been reported on its item validity. The purpose of the present study was to investigate the item validity and psychometric properties of the DAS-A in the Turkish cultural context. The subjects were 345 university students. The locally adapted versions of the Beck ...
Influence of Emotional Distress among Supporters on the Outcome of Psychogeriatric Day Care GILLEARD, C. J. (Royal College of Psychiatrists, 1987-2) <jats:p>From a sample of consecutive referrals for psychogeriatric day care, the influence of the supporters' emotional distress and self-reported strain, together with the number of problems presented by the patient, was examined in relation to outcome, 6–7 months after initial attendance. A higher level of problems and the failure to achieve any reduction in reported distress were both found to contribute to the breakdown of community care and to the subsequent institutionalisation of the patient. Day hos...

Citation Formats

J. D. Cooper et al., “Multimodel inference for biomarker development: an application to schizophrenia,” TRANSLATIONAL PSYCHIATRY, pp. 0–0, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/49069.