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."/>
Skip to main content

Table 2 Performance of IGT across all groups

From: Can cognition help predict suicide risk in patients with major depressive disorder? A machine learning study

  Group Group comparisons  
HC* (N = 98) DNS* (N = 61) DSA* (N = 52) HC* vs DNS* vs DSA* DNS* + DSA* vs HC*
Mean(SD) Mean(SD) Mean(SD) F d.f p-value HC* vs DNS* HC* vs DSA* DNS* vs DSA* t p-value
p-value p-value p-value
IGT* performance
 Block1(Trials 1–20) -5.27 (6.725) -3.8 (7.269) -3 (6.669) 2.056 2 0.131 0.195 0.056 0.54 1.935 0.054
 Block2(Trials 21–40) -4.08 (7.896) -2.47 (8.848) -1.54 (7.868) 1.818 2 0.165 0.229 0.071 0.549 1.813 0.071
 Block3(Trials 41–60) -1.55 (9.079) -4.07 (9.072) -2.38 (7.118) 1.583 2 0.208 0.077 0.574 0.305 -1.452 0.148
 Block4(Trials 61–80) -0.51 (9.465) -3.67 (8.471) -3.94 (7.092) 3.782 2 0.024 0.027 0.022 0.867 -2.751 0.006
 Block5(Trials 81–100) 1.33 (9.877) -2.34 (9.345) -2.85 (9.712) 4.261 2 0.015 0.023 0.013 0.783 -2.913 0.004
 Net total score -10.06 (34.148) -16.53 (33.422) -13.73 (28.883) 0.755 2 0.471 0.229 0.514 0.652 -1.145 0.254
 PartA(Trails 1–40) -9.35 (12.315) -6.27 (13.956) -4.54 (12.221) 2.666 2 0.072 0.143 0.029 0.476 2.199 0.029
 PartB(Trails 41–100) -0.735 (25.015) -10.03 (20.881) -9.17 (19.571) 3.838 2 0.023 0.018 0.031 0.916 -2.775 0.006
  1. *DSA Depressed suicide attempter, DNS Depressed non-suicide attempter, HC Healthy control, IGT Iowa Gambling Task