Table 2.
Investigations by study subset and ML parameters.
| Citation | Journal | Outcome | Precision | Quality Rating |
|---|---|---|---|---|
| Liakata et al. 2012 [117] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.60 | 3 |
| Nikfarjam et al. 2012 [118] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.60 | 3 |
| Yeh et al. 2012 [119] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.77 | 3 |
| Cherry et al. 2012 [120] | Biomed Inform Insights | Death/NLP of Suicide Notes | 1.00 | 3 |
| Wang et al. 2012 [121] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.67 | 3 |
| Desmet et al. 2012 [122] | Biomed Inform Insights | Death/NLP of Suicide Notes | NR | 3 |
| Kovacevic et al. 2012 [123] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.67 | 3 |
| Pak et al. 2012 [124] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.62 | 3 |
| Spasic, 2012 [125] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.55 | 3 |
| McCarthy et al. 2012 [126] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.57 | 3 |
| Wicentowski et al. 2012 [127] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.69 | 3 |
| Sohn, 2012 [128] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.61 | 3 |
| Yang, 2012 [129] | Biomed Inform Insights | Death/NLP of Suicide Notes | 0.58 | 3 |
Investigations (N = 13) by study subset and ML parameters. Outcome focused on sentiment detection of suicide decedent notes using NLP. Notes: Quality ratings were performed according to the Oxford Centre for Evidence-Based Medicine Protocol; ML = machine learning; NLP = natural language processing; Precision = positive predictive value (PPV); NR = not reported.