Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning
Abstract Cognitive impairments are generally observed in patients with schizophrenia. However, it is unclear whether neurocognitive dysfunction can predict the efficacy of antipsychotics for first-episode schizophrenia (FES). Machine learning methods provide a relatively unbiased approach when evalu...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Schizophrenia |
| Online Access: | https://doi.org/10.1038/s41537-025-00640-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234992897458176 |
|---|---|
| author | Xianghe Wang Tianqi Gao Xiaodong Guo Bingjie Huang Yunfei Ji Wanheng Hu Xiaolin Yin Yue Zheng Chengcheng Pu Xin Yu |
| author_facet | Xianghe Wang Tianqi Gao Xiaodong Guo Bingjie Huang Yunfei Ji Wanheng Hu Xiaolin Yin Yue Zheng Chengcheng Pu Xin Yu |
| author_sort | Xianghe Wang |
| collection | DOAJ |
| description | Abstract Cognitive impairments are generally observed in patients with schizophrenia. However, it is unclear whether neurocognitive dysfunction can predict the efficacy of antipsychotics for first-episode schizophrenia (FES). Machine learning methods provide a relatively unbiased approach when evaluating heterogeneous data, especially when building multifactor prediction models. This study conducted a secondary analysis based on the Chinese FES Trial (CNFEST), which was a 1-year study involving a randomized controlled trial for the first eight weeks followed by a 48-week open-label observation. The current study aimed to build a prediction model of eight-week antipsychotic response based on baseline clinical and demographic features. Six machine learning algorithms, including random forest, eXtreme gradient boosting (XGBoost), logistic regression, linear support vector machine (SVM), radial basis function SVM and poly SVM were applied and compared to draw the prediction model. The predictive effects were evaluated by balanced accuracy, sensitivity and specificity. The predictive factors were compared with F scores. A total of 450 qualified subjects contributed to the model. The prediction model constructed via XGBoost algorithm had the highest accuracy (68.8%) and prognostic certainty (44.3%) among all the algorithms. The baseline neurocognitive tests with strong predictive significance were the Grooved Pegboard Test, Trail Making Test Part A, Paced Auditory Serial Addition Test, Brief Visuospatial Learning Test, Hopkins Verbal Learning Test and Color Trails Test. This study emphasizes the importance of fine motor skills, verbal learning, visual learning, working memory and attention for the response of drug-naïve FES patients to antipsychotics. The model generated by XGBoost, which shows preferable accuracy, provides psychiatric practitioners with a possible way to predict efficacy for FES patients. |
| format | Article |
| id | doaj-art-3b666bd901b44bcdac9cd5bf0076d73a |
| institution | Kabale University |
| issn | 2754-6993 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Schizophrenia |
| spelling | doaj-art-3b666bd901b44bcdac9cd5bf0076d73a2025-08-20T04:02:56ZengNature PortfolioSchizophrenia2754-69932025-07-011111910.1038/s41537-025-00640-yNeurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learningXianghe Wang0Tianqi Gao1Xiaodong Guo2Bingjie Huang3Yunfei Ji4Wanheng Hu5Xiaolin Yin6Yue Zheng7Chengcheng Pu8Xin Yu9Peking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalPeking University Sixth HospitalAbstract Cognitive impairments are generally observed in patients with schizophrenia. However, it is unclear whether neurocognitive dysfunction can predict the efficacy of antipsychotics for first-episode schizophrenia (FES). Machine learning methods provide a relatively unbiased approach when evaluating heterogeneous data, especially when building multifactor prediction models. This study conducted a secondary analysis based on the Chinese FES Trial (CNFEST), which was a 1-year study involving a randomized controlled trial for the first eight weeks followed by a 48-week open-label observation. The current study aimed to build a prediction model of eight-week antipsychotic response based on baseline clinical and demographic features. Six machine learning algorithms, including random forest, eXtreme gradient boosting (XGBoost), logistic regression, linear support vector machine (SVM), radial basis function SVM and poly SVM were applied and compared to draw the prediction model. The predictive effects were evaluated by balanced accuracy, sensitivity and specificity. The predictive factors were compared with F scores. A total of 450 qualified subjects contributed to the model. The prediction model constructed via XGBoost algorithm had the highest accuracy (68.8%) and prognostic certainty (44.3%) among all the algorithms. The baseline neurocognitive tests with strong predictive significance were the Grooved Pegboard Test, Trail Making Test Part A, Paced Auditory Serial Addition Test, Brief Visuospatial Learning Test, Hopkins Verbal Learning Test and Color Trails Test. This study emphasizes the importance of fine motor skills, verbal learning, visual learning, working memory and attention for the response of drug-naïve FES patients to antipsychotics. The model generated by XGBoost, which shows preferable accuracy, provides psychiatric practitioners with a possible way to predict efficacy for FES patients.https://doi.org/10.1038/s41537-025-00640-y |
| spellingShingle | Xianghe Wang Tianqi Gao Xiaodong Guo Bingjie Huang Yunfei Ji Wanheng Hu Xiaolin Yin Yue Zheng Chengcheng Pu Xin Yu Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning Schizophrenia |
| title | Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning |
| title_full | Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning |
| title_fullStr | Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning |
| title_full_unstemmed | Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning |
| title_short | Neurocognition as a major predictor of 8-week response to antipsychotics for drug-naïve first-episode schizophrenia using machine learning |
| title_sort | neurocognition as a major predictor of 8 week response to antipsychotics for drug naive first episode schizophrenia using machine learning |
| url | https://doi.org/10.1038/s41537-025-00640-y |
| work_keys_str_mv | AT xianghewang neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT tianqigao neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT xiaodongguo neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT bingjiehuang neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT yunfeiji neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT wanhenghu neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT xiaolinyin neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT yuezheng neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT chengchengpu neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning AT xinyu neurocognitionasamajorpredictorof8weekresponsetoantipsychoticsfordrugnaivefirstepisodeschizophreniausingmachinelearning |