Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders
BackgroundChild sexual abuse (CSA) has become a focal point for lawmakers, law enforcement, and mental health professionals. With high prevalence rates around the world and far-reaching, often chronic, individual, and societal implications, CSA and its leading risk factor, pedophilia, have been well...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1001085/full |
| _version_ | 1797843768705024000 |
|---|---|
| author | David Popovic David Popovic David Popovic David Popovic Maximilian Wertz Maximilian Wertz Carolin Geisler Joern Kaufmann Markku Lähteenvuo Markku Lähteenvuo Johannes Lieslehto Joachim Witzel Bernhard Bogerts Bernhard Bogerts Martin Walter Peter Falkai Peter Falkai Peter Falkai Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Kolja Schiltz Kolja Schiltz |
| author_facet | David Popovic David Popovic David Popovic David Popovic Maximilian Wertz Maximilian Wertz Carolin Geisler Joern Kaufmann Markku Lähteenvuo Markku Lähteenvuo Johannes Lieslehto Joachim Witzel Bernhard Bogerts Bernhard Bogerts Martin Walter Peter Falkai Peter Falkai Peter Falkai Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Kolja Schiltz Kolja Schiltz |
| author_sort | David Popovic |
| collection | DOAJ |
| description | BackgroundChild sexual abuse (CSA) has become a focal point for lawmakers, law enforcement, and mental health professionals. With high prevalence rates around the world and far-reaching, often chronic, individual, and societal implications, CSA and its leading risk factor, pedophilia, have been well investigated. This has led to a wide range of clinical tools and actuarial instruments for diagnosis and risk assessment regarding CSA. However, the neurobiological underpinnings of pedosexual behavior, specifically regarding hands-on pedophilic offenders (PO), remain elusive. Such biomarkers for PO individuals could potentially improve the early detection of high-risk PO individuals and enhance efforts to prevent future CSA.AimTo use machine learning and MRI data to identify PO individuals.MethodsFrom a single-center male cohort of 14 PO individuals and 15 matched healthy control (HC) individuals, we acquired diffusion tensor imaging data (anisotropy, diffusivity, and fiber tracking) in literature-based regions of interest (prefrontal cortex, anterior cingulate cortex, amygdala, and corpus callosum). We trained a linear support vector machine to discriminate between PO and HC individuals using these WM microstructure data. Post hoc, we investigated the PO model decision scores with respect to sociodemographic (age, education, and IQ) and forensic characteristics (psychopathy, sexual deviance, and future risk of sexual violence) in the PO subpopulation. We assessed model specificity in an external cohort of 53 HC individuals.ResultsThe classifier discriminated PO from HC individuals with a balanced accuracy of 75.5% (sensitivity = 64.3%, specificity = 86.7%, P5000 = 0.018) and an out-of-sample specificity to correctly identify HC individuals of 94.3%. The predictive brain pattern contained bilateral fractional anisotropy in the anterior cingulate cortex, diffusivity in the left amygdala, and structural prefrontal cortex-amygdala connectivity in both hemispheres. This brain pattern was associated with the number of previous child victims, the current stance on sexuality, and the professionally assessed risk of future sexual violent reoffending.ConclusionAberrant white matter microstructure in the prefronto-temporo-limbic circuit could be a potential neurobiological correlate for PO individuals at high-risk of reoffending with CSA. Although preliminary and exploratory at this point, our findings highlight the general potential of MRI-based biomarkers and particularly WM microstructure patterns for future CSA risk assessment and preventive efforts. |
| first_indexed | 2024-04-09T17:11:17Z |
| format | Article |
| id | doaj.art-3edb6e69e4444b2f933753478f5b1ac7 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-04-09T17:11:17Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-3edb6e69e4444b2f933753478f5b1ac72023-04-20T05:53:17ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-04-011410.3389/fpsyt.2023.10010851001085Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offendersDavid Popovic0David Popovic1David Popovic2David Popovic3Maximilian Wertz4Maximilian Wertz5Carolin Geisler6Joern Kaufmann7Markku Lähteenvuo8Markku Lähteenvuo9Johannes Lieslehto10Joachim Witzel11Bernhard Bogerts12Bernhard Bogerts13Martin Walter14Peter Falkai15Peter Falkai16Peter Falkai17Nikolaos Koutsouleris18Nikolaos Koutsouleris19Nikolaos Koutsouleris20Nikolaos Koutsouleris21Kolja Schiltz22Kolja Schiltz23Department of Psychiatry and Psychotherapy, Ludwig-Maximilians-University Munich, Munich, GermanyDepartment of Forensic Psychiatry, Ludwig-Maximilians-University Munich, Munich, GermanyInternational Max Planck Research School for Translational Psychiatry (IMPRS-TP), Munich, GermanyMax Planck Institute of Psychiatry, Munich, GermanyDepartment of Psychiatry and Psychotherapy, Ludwig-Maximilians-University Munich, Munich, GermanyDepartment of Forensic Psychiatry, Ludwig-Maximilians-University Munich, Munich, GermanyDepartment of Dermatology, Venereology, and Allergology, Charité - Universitätsmedizin Berlin, Berlin, GermanyDepartment of Neurology, Otto-von-Guericke-University, Magdeburg, GermanyDepartment of Forensic Psychiatry, University of Eastern Finland, Niuvanniemi Hospital, Kuopio, FinlandInstitute for Molecular Medicine FIMM, University of Helsinki, Helsinki, FinlandDepartment of Forensic Psychiatry, University of Eastern Finland, Niuvanniemi Hospital, Kuopio, FinlandCentral State Forensic Psychiatric Hospital of Saxony-Anhalt, Uchtspringe, Germany0Salus Institut, Salus gGmbH, Magdeburg, Germany1Department of Psychiatry and Psychotherapy, Otto-von-Guericke-University, Magdeburg, Germany2Department of Psychiatry and Psychotherapy, Jena University Hospital, Jena, GermanyDepartment of Psychiatry and Psychotherapy, Ludwig-Maximilians-University Munich, Munich, GermanyInternational Max Planck Research School for Translational Psychiatry (IMPRS-TP), Munich, GermanyMax Planck Institute of Psychiatry, Munich, GermanyDepartment of Psychiatry and Psychotherapy, Ludwig-Maximilians-University Munich, Munich, GermanyInternational Max Planck Research School for Translational Psychiatry (IMPRS-TP), Munich, GermanyMax Planck Institute of Psychiatry, Munich, Germany3Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London, United KingdomDepartment of Psychiatry and Psychotherapy, Ludwig-Maximilians-University Munich, Munich, GermanyDepartment of Forensic Psychiatry, Ludwig-Maximilians-University Munich, Munich, GermanyBackgroundChild sexual abuse (CSA) has become a focal point for lawmakers, law enforcement, and mental health professionals. With high prevalence rates around the world and far-reaching, often chronic, individual, and societal implications, CSA and its leading risk factor, pedophilia, have been well investigated. This has led to a wide range of clinical tools and actuarial instruments for diagnosis and risk assessment regarding CSA. However, the neurobiological underpinnings of pedosexual behavior, specifically regarding hands-on pedophilic offenders (PO), remain elusive. Such biomarkers for PO individuals could potentially improve the early detection of high-risk PO individuals and enhance efforts to prevent future CSA.AimTo use machine learning and MRI data to identify PO individuals.MethodsFrom a single-center male cohort of 14 PO individuals and 15 matched healthy control (HC) individuals, we acquired diffusion tensor imaging data (anisotropy, diffusivity, and fiber tracking) in literature-based regions of interest (prefrontal cortex, anterior cingulate cortex, amygdala, and corpus callosum). We trained a linear support vector machine to discriminate between PO and HC individuals using these WM microstructure data. Post hoc, we investigated the PO model decision scores with respect to sociodemographic (age, education, and IQ) and forensic characteristics (psychopathy, sexual deviance, and future risk of sexual violence) in the PO subpopulation. We assessed model specificity in an external cohort of 53 HC individuals.ResultsThe classifier discriminated PO from HC individuals with a balanced accuracy of 75.5% (sensitivity = 64.3%, specificity = 86.7%, P5000 = 0.018) and an out-of-sample specificity to correctly identify HC individuals of 94.3%. The predictive brain pattern contained bilateral fractional anisotropy in the anterior cingulate cortex, diffusivity in the left amygdala, and structural prefrontal cortex-amygdala connectivity in both hemispheres. This brain pattern was associated with the number of previous child victims, the current stance on sexuality, and the professionally assessed risk of future sexual violent reoffending.ConclusionAberrant white matter microstructure in the prefronto-temporo-limbic circuit could be a potential neurobiological correlate for PO individuals at high-risk of reoffending with CSA. Although preliminary and exploratory at this point, our findings highlight the general potential of MRI-based biomarkers and particularly WM microstructure patterns for future CSA risk assessment and preventive efforts.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1001085/fullpedophiliaMRIchild sexual abuse (CSA)support vector machinesmachine learningforensic psychiatry |
| spellingShingle | David Popovic David Popovic David Popovic David Popovic Maximilian Wertz Maximilian Wertz Carolin Geisler Joern Kaufmann Markku Lähteenvuo Markku Lähteenvuo Johannes Lieslehto Joachim Witzel Bernhard Bogerts Bernhard Bogerts Martin Walter Peter Falkai Peter Falkai Peter Falkai Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Nikolaos Koutsouleris Kolja Schiltz Kolja Schiltz Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders Frontiers in Psychiatry pedophilia MRI child sexual abuse (CSA) support vector machines machine learning forensic psychiatry |
| title | Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders |
| title_full | Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders |
| title_fullStr | Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders |
| title_full_unstemmed | Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders |
| title_short | Patterns of risk—Using machine learning and structural neuroimaging to identify pedophilic offenders |
| title_sort | patterns of risk using machine learning and structural neuroimaging to identify pedophilic offenders |
| topic | pedophilia MRI child sexual abuse (CSA) support vector machines machine learning forensic psychiatry |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1001085/full |
| work_keys_str_mv | AT davidpopovic patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT davidpopovic patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT davidpopovic patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT davidpopovic patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT maximilianwertz patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT maximilianwertz patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT carolingeisler patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT joernkaufmann patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT markkulahteenvuo patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT markkulahteenvuo patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT johanneslieslehto patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT joachimwitzel patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT bernhardbogerts patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT bernhardbogerts patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT martinwalter patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT peterfalkai patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT peterfalkai patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT peterfalkai patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT nikolaoskoutsouleris patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT nikolaoskoutsouleris patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT nikolaoskoutsouleris patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT nikolaoskoutsouleris patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT koljaschiltz patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders AT koljaschiltz patternsofriskusingmachinelearningandstructuralneuroimagingtoidentifypedophilicoffenders |