A Mathematical Model of Suicidal-Intent-Estimation in Adults

Retrospective assessment of suicidal intent is important to prevent future attempts. The objective of the study is to mathematically model the method of suicidal intent estimation. Real-life data of 200 suicide attempters has been collected according to Beck’s suicide intent scale (BSIS), which is composed of three constructs and 20 indicators to assess the suicidal intent as ‘low’, ‘medium’ or ‘high’. Each indicator possesses three preconditions for intent scoring. For conventional scoring first 15 indicators are used. The collected data has been analysed to note its distribution, reliability and mining significant indicators. Three Multilayer Feed Forward Neural Net (MLFFNN) classifiers have been developed. MLFFNN-1 is developed with first fifteen indicators to mimic the conventional way of scoring. MLFFNN-2 has been designed with all twenty indicators to note whether the network could better classify with more information. Significant (or quality) indicators, obtained through Multiple Linear Regressions and the Principal component analysis (PCA) are finally used to construct the MLFFNN-3. It is to see whether high quality information better influence the classification task. Performances of the neural nets are then compared and validated with the scorings performed by a group of psychiatrists (who are the human experts) and the regressions analysis. The paper observes that MLFFNNs have outperformed the human experts and regressions in terms of both speed and accuracy. MLFFNN-1 is found to be the best of the lot. It concludes that BSIS could efficiently be mapped onto neural networks.