Metten Somers
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Metten Somers has a total of 118 co-authors. Here are the top co-authors by number of shared publications:
- Marco Pm Boks
Department of Psychiatry, Amsterdam UMC, Amsterdam, The Netherlands
7 shared publications - Iris E. C. Sommer
Rudolf Magnus Institute of Neuroscience, University Medical Center Utrecht, Utrecht, The Netherlands
6 shared publications - Edwin van Dellen
UMC Utrecht, Utrecht. Julius Centrum voor Gezondheidswetenschappen
3 shared publications René S. Kahn
Brain Center Rudolf Magnus, Department of Psychiatry, University Medical Center Utrecht, 3508 GA Utrecht, The Netherlands
3 shared publications- Bart P. F. Rutten
Department of Psychiatry and Neuropsychology, Mental Health and Neuroscience Research Institute, Maastricht University Medical Centre, Maastricht, The Netherlands
2 shared publications - Bochao Danae Lin
Department of Psychiatry and Neuropsychology, School for Mental Health and Neuroscience, Maastricht University Medical Centre, Maastricht, the Netherlands
2 shared publications
Latest Publications
- Open Access
Prognostic predictions in psychosis: exploring the complementary role of machine learning models
BACKGROUND Predicting outcomes in schizophrenia spectrum disorders is challenging due to the variability of individual trajectories. While machine learning (ML) shows promise in outcome prediction, is has not yet been integrated into clinical practice. Understanding how ML models (MLMs) can complement psychiatrists’ predictions and bridge the gap between MLM capabilities and practical use is key. OBJECTIVE This study aims to compare the performance of psychiatrists and MLMs in predicting short-term symptomatic and functional remission in patients with first-episode psychosis and explore whether MLMs can improve psychiatrists’ prognostic accuracy. METHOD Twenty-four psychiatrists predicted symptomatic and functional remission probabilities based on written baseline information from 66 patients in the OPTiMiSE trial. ML-generated predictions were then shared with psychiatrists, allowing them to adjust their estimates. A questionnaire assessed trust in MLMs, perceived information gaps, and psychiatrists’ self-assessed predictive accuracy, which was compared to actual accuracy. FINDINGS The predictive accuracy of the MLM was comparable to that of psychiatrists for symptomatic remission (MLM: 0.50, psychiatrists: 0.52) and functional remission (MLM: 0.72, psychiatrists: 0.79). Interrater agreement was low but comparable for psychiatrists and the MLM. Although the MLM did not improve overall predictive accuracy, it showed potential in aiding psychiatrists with difficult-to-predict cases. However, psychiatrists struggled to recognize when to rely on the model’s output and we were unable to determine a clear pattern in these cases based on their characteristics. Psychiatrists could not reliably estimate their predictive accuracy. Psychiatrists expressed moderate to high trust in MLMs for prognostic prediction, but highlighted concerns about the lack of transparency and interpretability of model outputs. CONCLUSIONS MLMs are a promising tool for supporting psychiatric decision-making, particularly in challenging cases. However, their potential remains underutilized due to limitations in predictive accuracy and a lack of clarity in how predictions are generated. Addressing these issues is essential to build trust and foster integration into clinical practice. CLINICAL IMPLICATIONS MLMs are best suited as supplementary tools, providing a second opinion while psychiatrists retain decision-making autonomy. Integrating predictions from both sources may help reduce individual biases and improve accuracy. This approach leverages the strengths of MLMs without compromising clinical responsibility. What is already known on this topic While machine learning models (MLMs) show promise in predicting outcomes in psychotic disorders, they have yet to be integrated into clinical practice. Evidence on the predictive accuracy of psychiatrists for these disorders is limited, with only two small studies published before 1990 suggesting moderate accuracy. Comparisons of MLMs and psychiatrists in this context have not been previously conducted. What this study adds This is the first study to compare the predictive accuracy of psychiatrists with that of an MLM for psychotic disorders and to assess whether an MLM can enhance psychiatrists’ performance. It highlights that while MLMs do not improve overall accuracy, they may support psychiatrists in difficult cases. Insights into psychiatrists’ trust in MLMs and the challenges of implementing these models are also provided. How this study might affect research, practice, or policy The findings emphasize the need for advancements in MLM accuracy, interpretability, and strategies to identify cases where MLMs are most beneficial. These improvements could foster effective integration of MLMs as supplementary tools in clinical practice, aiding psychiatrists in decision-making while maintaining their autonomy.
Open AccessPrognostic predictions in psychosis: exploring the complementary role of machine learning models
BACKGROUND Predicting outcomes in schizophrenia spectrum disorders is challenging due to the variability of individual trajectories. While machine learning (ML) shows promise in outcome prediction, is has not yet been integrated into clinical practice. Understanding how ML models (MLMs) can complement psychiatrists’ predictions and bridge the gap between MLM capabilities and practical use is key. OBJECTIVE This study aims to compare the performance of psychiatrists and MLMs in predicting short-term symptomatic and functional remission in patients with first-episode psychosis and explore whether MLMs can improve psychiatrists’ prognostic accuracy. METHOD Twenty-four psychiatrists predicted symptomatic and functional remission probabilities based on written baseline information from 66 patients in the OPTiMiSE trial. ML-generated predictions were then shared with psychiatrists, allowing them to adjust their estimates. A questionnaire assessed trust in MLMs, perceived information gaps, and psychiatrists’ self-assessed predictive accuracy, which was compared to actual accuracy. FINDINGS The predictive accuracy of the MLM was comparable to that of psychiatrists for symptomatic remission (MLM: 0.50, psychiatrists: 0.52) and functional remission (MLM: 0.72, psychiatrists: 0.79). Interrater agreement was low but comparable for psychiatrists and the MLM. Although the MLM did not improve overall predictive accuracy, it showed potential in aiding psychiatrists with difficult-to-predict cases. However, psychiatrists struggled to recognize when to rely on the model’s output and we were unable to determine a clear pattern in these cases based on their characteristics. Psychiatrists could not reliably estimate their predictive accuracy. Psychiatrists expressed moderate to high trust in MLMs for prognostic prediction, but highlighted concerns about the lack of transparency and interpretability of model outputs. CONCLUSIONS MLMs are a promising tool for supporting psychiatric decision-making, particularly in challenging cases. However, their potential remains underutilized due to limitations in predictive accuracy and a lack of clarity in how predictions are generated. Addressing these issues is essential to build trust and foster integration into clinical practice. CLINICAL IMPLICATIONS MLMs are best suited as supplementary tools, providing a second opinion while psychiatrists retain decision-making autonomy. Integrating predictions from both sources may help reduce individual biases and improve accuracy. This approach leverages the strengths of MLMs without compromising clinical responsibility. What is already known on this topic While machine learning models (MLMs) show promise in predicting outcomes in psychotic disorders, they have yet to be integrated into clinical practice. Evidence on the predictive accuracy of psychiatrists for these disorders is limited, with only two small studies published before 1990 suggesting moderate accuracy. Comparisons of MLMs and psychiatrists in this context have not been previously conducted. What this study adds This is the first study to compare the predictive accuracy of psychiatrists with that of an MLM for psychotic disorders and to assess whether an MLM can enhance psychiatrists’ performance. It highlights that while MLMs do not improve overall accuracy, they may support psychiatrists in difficult cases. Insights into psychiatrists’ trust in MLMs and the challenges of implementing these models are also provided. How this study might affect research, practice, or policy The findings emphasize the need for advancements in MLM accuracy, interpretability, and strategies to identify cases where MLMs are most beneficial. These improvements could foster effective integration of MLMs as supplementary tools in clinical practice, aiding psychiatrists in decision-making while maintaining their autonomy.
- Open Access
- 2 July 2023
- Published by Elsevier in Psychiatry Research
- Vol. 326, 115328
Outcome prediction of electroconvulsive therapy for depression
- 2 July 2023
- Published by Elsevier in Psychiatry Research
- Vol. 326, 115328
Open AccessOutcome prediction of electroconvulsive therapy for depression
- Open Access
- 1 March 2022
- Published by Elsevier in Biological Psychiatry
- Vol. 91 (6) , 531-539
Interrogating Associations Between Polygenic Liabilities and Electroconvulsive Therapy Effectiveness
- 1 March 2022
- Published by Elsevier in Biological Psychiatry
- Vol. 91 (6) , 531-539
Open AccessInterrogating Associations Between Polygenic Liabilities and Electroconvulsive Therapy Effectiveness
- Open Access
- 14 February 2022
- Published by Elsevier in Biological Psychiatry
- Vol. 91 (6) , A3-A4
Table of Contents
- 14 February 2022
- Published by Elsevier in Biological Psychiatry
- Vol. 91 (6) , A3-A4
Open AccessTable of Contents
- Open Access
A Genetic Population Isolate in The Netherlands Showing Extensive Haplotype Sharing and Long Regions of Homozygosity
Genetic isolated populations have features that may facilitate genetic analyses and can be leveraged to improve power of mapping genes to complex traits. Our aim was to test the extent to which a population with a former history of geographic isolation and religious endogamy, and currently with one of the highest fertility rates in The Netherlands, shows signs of genetic isolation. For this purpose, genome-wide genotype data was collected of 72 unrelated individuals from this population as well as in a sample of 104 random control subjects from The Netherlands. Additional reference data from different populations and population isolates was available through HapMap and the Human Genome Diversity Project. We performed a number of analyses to compare the genetic structure between these populations: we calculated the pairwise genetic distance between populations, examined the extent of identical-by-descent (IBD) sharing and estimated the effective population size. Genetic analysis of this population showed consistent patterns of a population isolate at all levels tested. We confirmed that this population is most closely related to the Dutch control subjects, and detected high levels of IBD sharing and runs of homozygosity at equal or even higher levels than observed in previously described population isolates. The effective population size of this population was estimated to be several orders of magnitude smaller than that of the Dutch control sample. We conclude that the geographic isolation of this population combined with rapid population growth has resulted in a genetic isolate with great potential value for future genetic studies.
Open AccessA Genetic Population Isolate in The Netherlands Showing Extensive Haplotype Sharing and Long Regions of Homozygosity
Genetic isolated populations have features that may facilitate genetic analyses and can be leveraged to improve power of mapping genes to complex traits. Our aim was to test the extent to which a population with a former history of geographic isolation and religious endogamy, and currently with one of the highest fertility rates in The Netherlands, shows signs of genetic isolation. For this purpose, genome-wide genotype data was collected of 72 unrelated individuals from this population as well as in a sample of 104 random control subjects from The Netherlands. Additional reference data from different populations and population isolates was available through HapMap and the Human Genome Diversity Project. We performed a number of analyses to compare the genetic structure between these populations: we calculated the pairwise genetic distance between populations, examined the extent of identical-by-descent (IBD) sharing and estimated the effective population size. Genetic analysis of this population showed consistent patterns of a population isolate at all levels tested. We confirmed that this population is most closely related to the Dutch control subjects, and detected high levels of IBD sharing and runs of homozygosity at equal or even higher levels than observed in previously described population isolates. The effective population size of this population was estimated to be several orders of magnitude smaller than that of the Dutch control sample. We conclude that the geographic isolation of this population combined with rapid population growth has resulted in a genetic isolate with great potential value for future genetic studies.
- 10 June 2015
- Published by Society for Neuroscience in Journal of Neuroscience
- Vol. 35 (23) , 8730-8736
Linkage Analysis in a Dutch Population Isolate Shows No Major Gene for Left-Handedness or Atypical Language Lateralization
Cerebral dominance of language function and hand preference are suggested to be heritable traits with possible shared genetic background. However, joined genetic studies of these traits have never been conducted. We performed a genetic linkage study in 37 multigenerational human pedigrees of both sexes (consisting of 355 subjects) enriched with left-handedness in which we also measured language lateralization. Hand preference was measured with the Edinburgh Handedness Inventory, and language lateralization was measured with functional transcranial Doppler during language production. The estimated heritability of left-handedness and language lateralization in these pedigrees is 0.24 and 0.31, respectively. A parametric major gene model was tested for left-handedness. Nonparametric analyses were performed for left-handedness, atypical lateralization, and degree of language lateralization. We did not observe genome-wide evidence for linkage in the parametric or nonparametric analyses for any of the phenotypes tested. However, multiple regions showed suggestive evidence of linkage. The parametric model showed suggestive linkage for left-handedness in the 22q13 region [heterogeneity logarithm of odds (HLOD) = 2.18]. Nonparametric multipoint analysis of left-handedness showed suggestive linkage in the same region [logarithm of odds (LOD) = 2.80]. Atypical language lateralization showed suggestive linkage in the 7q34 region (LODMax = 2.35). For strength of language lateralization, we observed suggestive linkage in the 6p22 (LODMax = 2.54), 7q32 (LODMax = 1.93), and 9q33 (LODMax = 2.10) regions. We did not observe any overlap of suggestive genetic signal between handedness and the extent of language lateralization. The absence of significant linkage argues against the presence of a major gene coding for both traits; rather, our results are suggestive of these traits being two independent polygenic complex traits.
- 10 June 2015
- Published by Society for Neuroscience in Journal of Neuroscience
- Vol. 35 (23) , 8730-8736
Linkage Analysis in a Dutch Population Isolate Shows No Major Gene for Left-Handedness or Atypical Language Lateralization
Cerebral dominance of language function and hand preference are suggested to be heritable traits with possible shared genetic background. However, joined genetic studies of these traits have never been conducted. We performed a genetic linkage study in 37 multigenerational human pedigrees of both sexes (consisting of 355 subjects) enriched with left-handedness in which we also measured language lateralization. Hand preference was measured with the Edinburgh Handedness Inventory, and language lateralization was measured with functional transcranial Doppler during language production. The estimated heritability of left-handedness and language lateralization in these pedigrees is 0.24 and 0.31, respectively. A parametric major gene model was tested for left-handedness. Nonparametric analyses were performed for left-handedness, atypical lateralization, and degree of language lateralization. We did not observe genome-wide evidence for linkage in the parametric or nonparametric analyses for any of the phenotypes tested. However, multiple regions showed suggestive evidence of linkage. The parametric model showed suggestive linkage for left-handedness in the 22q13 region [heterogeneity logarithm of odds (HLOD) = 2.18]. Nonparametric multipoint analysis of left-handedness showed suggestive linkage in the same region [logarithm of odds (LOD) = 2.80]. Atypical language lateralization showed suggestive linkage in the 7q34 region (LODMax = 2.35). For strength of language lateralization, we observed suggestive linkage in the 6p22 (LODMax = 2.54), 7q32 (LODMax = 1.93), and 9q33 (LODMax = 2.10) regions. We did not observe any overlap of suggestive genetic signal between handedness and the extent of language lateralization. The absence of significant linkage argues against the presence of a major gene coding for both traits; rather, our results are suggestive of these traits being two independent polygenic complex traits.
- 1 May 2015
- Published by Elsevier in Brain and Language
- Vol. 144, 10-15
On the relationship between degree of hand-preference and degree of language lateralization
- 1 May 2015
- Published by Elsevier in Brain and Language
- Vol. 144, 10-15
On the relationship between degree of hand-preference and degree of language lateralization
- 1 April 2015
- Published by Elsevier in Neuroscience & Biobehavioral Reviews
- Vol. 51, 48-63
Cognitive benefits of right-handedness: A meta-analysis
- 1 April 2015
- Published by Elsevier in Neuroscience & Biobehavioral Reviews
- Vol. 51, 48-63
Cognitive benefits of right-handedness: A meta-analysis
- Open Access
- 1 January 2011
- Published by Frontiers Media SA in Frontiers in Human Neuroscience
- Vol. 5, 31
The Measurement of Language Lateralization with Functional Transcranial Doppler and Functional MRI: A Critical Evaluation
Cerebral language lateralization can be assessed in several ways. In healthy subjects, functional MRI (fMRI) during performance of a language task has evolved to be the most frequently applied method. Functional Transcranial Doppler (fTCD) may provide a valid alternative, but has been used rarely. Both techniques have their own strengths and weaknesses and as a result may be applied in different fields of research. Until now, only one relatively small study (n=13) investigated the correlation between lateralization indices measured by fTCD and fMRI and showed a remarkably high correlation. To further evaluate the correlation between lateralization indices measured with fTCD and fMRI, we compared lateralization indices of twenty-two healthy subjects (twelve left- and ten right-handed) using the same word generation paradigm for the fTCD as for the fMRI experiment. Lateralization indices measured with fTCD were highly but imperfectly correlated with lateralization indices measured with fMRI (Spearman’s rho=0.75, p<0.001). The imperfectness of the correlation can partially be explained by methodological restrictions of fMRI as well as fTCD. Our results suggest that fTCD can be a valid alternative for fMRI to measure lateralization, particularly when costs or mobility are important factors in the study design.
- 1 January 2011
- Published by Frontiers Media SA in Frontiers in Human Neuroscience
- Vol. 5, 31
Open AccessThe Measurement of Language Lateralization with Functional Transcranial Doppler and Functional MRI: A Critical Evaluation
Cerebral language lateralization can be assessed in several ways. In healthy subjects, functional MRI (fMRI) during performance of a language task has evolved to be the most frequently applied method. Functional Transcranial Doppler (fTCD) may provide a valid alternative, but has been used rarely. Both techniques have their own strengths and weaknesses and as a result may be applied in different fields of research. Until now, only one relatively small study (n=13) investigated the correlation between lateralization indices measured by fTCD and fMRI and showed a remarkably high correlation. To further evaluate the correlation between lateralization indices measured with fTCD and fMRI, we compared lateralization indices of twenty-two healthy subjects (twelve left- and ten right-handed) using the same word generation paradigm for the fTCD as for the fMRI experiment. Lateralization indices measured with fTCD were highly but imperfectly correlated with lateralization indices measured with fMRI (Spearman’s rho=0.75, p<0.001). The imperfectness of the correlation can partially be explained by methodological restrictions of fMRI as well as fTCD. Our results suggest that fTCD can be a valid alternative for fMRI to measure lateralization, particularly when costs or mobility are important factors in the study design.
- 1 March 2009
- Published by Elsevier in Schizophrenia Research
- Vol. 108 (1-3) , 25-32
Hand-preference and population schizotypy: A meta-analysis
- 1 March 2009
- Published by Elsevier in Schizophrenia Research
- Vol. 108 (1-3) , 25-32
Hand-preference and population schizotypy: A meta-analysis