Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation
IntroductionPsychiatric comorbidities have a significant impact on the course of illness in patients with schizophrenia spectrum disorders. To accurately predict outcomes for individual patients using computerized prognostic models, it is essential to consider these comorbidities and their influence...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-10-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1237490/full |
| _version_ | 1797660937613737984 |
|---|---|
| author | Violet van Dee Seyed Mostafa Kia Seyed Mostafa Kia Seyed Mostafa Kia Inge Winter-van Rossum Inge Winter-van Rossum René S. Kahn Wiepke Cahn Wiepke Cahn Hugo G. Schnack |
| author_facet | Violet van Dee Seyed Mostafa Kia Seyed Mostafa Kia Seyed Mostafa Kia Inge Winter-van Rossum Inge Winter-van Rossum René S. Kahn Wiepke Cahn Wiepke Cahn Hugo G. Schnack |
| author_sort | Violet van Dee |
| collection | DOAJ |
| description | IntroductionPsychiatric comorbidities have a significant impact on the course of illness in patients with schizophrenia spectrum disorders. To accurately predict outcomes for individual patients using computerized prognostic models, it is essential to consider these comorbidities and their influence.MethodsIn our study, we utilized a multi-modal deep learning architecture to forecast symptomatic remission, focusing on a multicenter sample of patients with first-episode psychosis from the OPTiMiSE study. Additionally, we introduced a counterfactual model explanation technique to examine how scores on the Mini International Neuropsychiatric Interview (MINI) affected the likelihood of remission, both at the group level and for individual patients.ResultsOur findings at the group level revealed that most comorbidities had a negative association with remission. Among them, current and recurrent depressive disorders consistently exerted the greatest negative impact on the probability of remission across patients. However, we made an interesting observation: current suicidality within the past month and substance abuse within the past 12 months were associated with an increased chance of remission in patients. We found a high degree of variability among patients at the individual level. Through hierarchical clustering analysis, we identified two subgroups: one in which comorbidities had a relatively limited effect on remission (approximately 45% of patients), and another in which comorbidities more strongly influenced remission. By incorporating comorbidities into individualized prognostic prediction models, we determined which specific comorbidities had the greatest impact on remission at both the group level and for individual patients.DiscussionThese results highlight the importance of identifying and including relevant comorbidities in prediction models, providing valuable insights for improving the treatment and prognosis of patients with psychotic disorders. Furthermore, they open avenues for further research into the efficacy of treating these comorbidities to enhance overall patient outcomes. |
| first_indexed | 2024-03-11T18:37:07Z |
| format | Article |
| id | doaj.art-aaaef5dd2ba946609dc8b18937e1a9f3 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-03-11T18:37:07Z |
| publishDate | 2023-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-aaaef5dd2ba946609dc8b18937e1a9f32023-10-12T16:57:43ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402023-10-011410.3389/fpsyt.2023.12374901237490Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanationViolet van Dee0Seyed Mostafa Kia1Seyed Mostafa Kia2Seyed Mostafa Kia3Inge Winter-van Rossum4Inge Winter-van Rossum5René S. Kahn6Wiepke Cahn7Wiepke Cahn8Hugo G. Schnack9Department of Psychiatry, Brain Center, University Medical Center Utrecht, Utrecht University, Utrecht, NetherlandsDepartment of Psychiatry, Brain Center, University Medical Center Utrecht, Utrecht University, Utrecht, NetherlandsDonders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, NetherlandsDepartment of Cognitive Science and Artificial Intelligence, Tilburg University, Tilburg, NetherlandsDepartment of Psychiatry, Brain Center, University Medical Center Utrecht, Utrecht University, Utrecht, NetherlandsIcahn School of Medicine at Mount Sinai, New York City, NY, United StatesIcahn School of Medicine at Mount Sinai, New York City, NY, United StatesDepartment of Psychiatry, Brain Center, University Medical Center Utrecht, Utrecht University, Utrecht, NetherlandsAltrecht Science, Altrecht Mental Health Institute, Utrecht, NetherlandsDepartment of Psychiatry, Brain Center, University Medical Center Utrecht, Utrecht University, Utrecht, NetherlandsIntroductionPsychiatric comorbidities have a significant impact on the course of illness in patients with schizophrenia spectrum disorders. To accurately predict outcomes for individual patients using computerized prognostic models, it is essential to consider these comorbidities and their influence.MethodsIn our study, we utilized a multi-modal deep learning architecture to forecast symptomatic remission, focusing on a multicenter sample of patients with first-episode psychosis from the OPTiMiSE study. Additionally, we introduced a counterfactual model explanation technique to examine how scores on the Mini International Neuropsychiatric Interview (MINI) affected the likelihood of remission, both at the group level and for individual patients.ResultsOur findings at the group level revealed that most comorbidities had a negative association with remission. Among them, current and recurrent depressive disorders consistently exerted the greatest negative impact on the probability of remission across patients. However, we made an interesting observation: current suicidality within the past month and substance abuse within the past 12 months were associated with an increased chance of remission in patients. We found a high degree of variability among patients at the individual level. Through hierarchical clustering analysis, we identified two subgroups: one in which comorbidities had a relatively limited effect on remission (approximately 45% of patients), and another in which comorbidities more strongly influenced remission. By incorporating comorbidities into individualized prognostic prediction models, we determined which specific comorbidities had the greatest impact on remission at both the group level and for individual patients.DiscussionThese results highlight the importance of identifying and including relevant comorbidities in prediction models, providing valuable insights for improving the treatment and prognosis of patients with psychotic disorders. Furthermore, they open avenues for further research into the efficacy of treating these comorbidities to enhance overall patient outcomes.https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1237490/fullpsychosiscomorbidityprecision psychiatrymachine learningcounterfactual explanation |
| spellingShingle | Violet van Dee Seyed Mostafa Kia Seyed Mostafa Kia Seyed Mostafa Kia Inge Winter-van Rossum Inge Winter-van Rossum René S. Kahn Wiepke Cahn Wiepke Cahn Hugo G. Schnack Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation Frontiers in Psychiatry psychosis comorbidity precision psychiatry machine learning counterfactual explanation |
| title | Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| title_full | Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| title_fullStr | Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| title_full_unstemmed | Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| title_short | Revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| title_sort | revealing the impact of psychiatric comorbidities on treatment outcome in early psychosis using counterfactual model explanation |
| topic | psychosis comorbidity precision psychiatry machine learning counterfactual explanation |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2023.1237490/full |
| work_keys_str_mv | AT violetvandee revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT seyedmostafakia revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT seyedmostafakia revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT seyedmostafakia revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT ingewintervanrossum revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT ingewintervanrossum revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT reneskahn revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT wiepkecahn revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT wiepkecahn revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation AT hugogschnack revealingtheimpactofpsychiatriccomorbiditiesontreatmentoutcomeinearlypsychosisusingcounterfactualmodelexplanation |