Shuqiong Zheng1,2, Weixiong Zeng3, Qianqian Xin1,2, Youran Ye1,2, Xiang Xue1,2, Enze Li1,2, Ting Liu1,2, Na Yan1,2, Weiguo Chen4, Honglei Yin5,6. 1. Department of Psychiatry, Nanfang Hospital, Southern Medical University, Guangzhou, China. 2. Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence, Guangzhou, China. 3. Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, China. 4. Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou, China. chen1999@smu.edu.cn. 5. Department of Psychiatry, Nanfang Hospital, Southern Medical University, Guangzhou, China. yinhonglei1981@163.com. 6. Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence, Guangzhou, China. yinhonglei1981@163.com.
Abstract
BACKGROUND: Previous studies suggest that deficits in cognition may increase the risk of suicide. Our study aims to develop a machine learning (ML) algorithm-based suicide risk prediction model using cognition in patients with major depressive disorder (MDD). METHODS: Participants comprised 52 depressed suicide attempters (DSA) and 61 depressed non-suicide attempters (DNS), and 98 healthy controls (HC). All participants were required to complete a series of questionnaires, the Suicide Stroop Task (SST) and the Iowa Gambling Task (IGT). The performance in IGT was analyzed using repeated measures ANOVA. ML with extreme gradient boosting (XGBoost) classification algorithm and locally explanatory techniques assessed performance and relative importance of characteristics for predicting suicide attempts. Prediction performances were compared with the area under the curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI). RESULTS: DSA and DNS preferred to select the card from disadvantageous decks (decks "A" + "B") under risky situation (p = 0.023) and showed a significantly poorer learning effect during the IGT (F = 2.331, p = 0.019) compared with HC. Performance of XGBoost model based on demographic and clinical characteristics was compared with that of the model created after adding cognition data (AUC, 0.779 vs. 0.819, p > 0.05). The net benefit of model was improved and cognition resulted in continuous reclassification improvement with NRI of 5.3%. Several clinical dimensions were significant predictors in the XGBoost classification algorithm. LIMITATIONS: A limited sample size and failure to include sufficient suicide risk factors in the predictive model. CONCLUSION: This study demonstrate that cognitive deficits may serve as an important risk factor to predict suicide attempts in patients with MDD. Combined with other demographic characteristics and attributes drawn from clinical questionnaires, cognitive function can improve the predictive effectiveness of the ML model. Additionally, explanatory ML models can help clinicians detect specific risk factors for each suicide attempter within MDD patients. These findings may be helpful for clinicians to detect those at high risk of suicide attempts quickly and accurately, and help them make proactive treatment decisions.
BACKGROUND: Previous studies suggest that deficits in cognition may increase the risk of suicide. Our study aims to develop a machine learning (ML) algorithm-based suicide risk prediction model using cognition in patients with major depressive disorder (MDD). METHODS: Participants comprised 52 depressed suicide attempters (DSA) and 61 depressed non-suicide attempters (DNS), and 98 healthy controls (HC). All participants were required to complete a series of questionnaires, the Suicide Stroop Task (SST) and the Iowa Gambling Task (IGT). The performance in IGT was analyzed using repeated measures ANOVA. ML with extreme gradient boosting (XGBoost) classification algorithm and locally explanatory techniques assessed performance and relative importance of characteristics for predicting suicide attempts. Prediction performances were compared with the area under the curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI). RESULTS: DSA and DNS preferred to select the card from disadvantageous decks (decks "A" + "B") under risky situation (p = 0.023) and showed a significantly poorer learning effect during the IGT (F = 2.331, p = 0.019) compared with HC. Performance of XGBoost model based on demographic and clinical characteristics was compared with that of the model created after adding cognition data (AUC, 0.779 vs. 0.819, p > 0.05). The net benefit of model was improved and cognition resulted in continuous reclassification improvement with NRI of 5.3%. Several clinical dimensions were significant predictors in the XGBoost classification algorithm. LIMITATIONS: A limited sample size and failure to include sufficient suicide risk factors in the predictive model. CONCLUSION: This study demonstrate that cognitive deficits may serve as an important risk factor to predict suicide attempts in patients with MDD. Combined with other demographic characteristics and attributes drawn from clinical questionnaires, cognitive function can improve the predictive effectiveness of the ML model. Additionally, explanatory ML models can help clinicians detect specific risk factors for each suicide attempter within MDD patients. These findings may be helpful for clinicians to detect those at high risk of suicide attempts quickly and accurately, and help them make proactive treatment decisions.
Authors: Gustavo Turecki; David A Brent; David Gunnell; Rory C O'Connor; Maria A Oquendo; Jane Pirkis; Barbara H Stanley Journal: Nat Rev Dis Primers Date: 2019-10-24 Impact factor: 52.329
Authors: Nadine M Melhem; Giovanna Porta; Maria A Oquendo; Jamie Zelazny; John G Keilp; Satish Iyengar; Ainsley Burke; Boris Birmaher; Barbara Stanley; J John Mann; David A Brent Journal: JAMA Psychiatry Date: 2019-06-01 Impact factor: 21.596
Authors: Bradley E Belsher; Derek J Smolenski; Larry D Pruitt; Nigel E Bush; Erin H Beech; Don E Workman; Rebecca L Morgan; Daniel P Evatt; Jennifer Tucker; Nancy A Skopp Journal: JAMA Psychiatry Date: 2019-06-01 Impact factor: 21.596