A scientific assessment on prediction fashions for self-harm & suicide

Think about a affected person sitting in entrance of you, weary of life, urgently asking you for assist. As a therapist, you do what you do greatest on this scenario: you are taking a coin out of your pocket, toss it within the air, and see which aspect it lands on: Heads. “Nicely,” you say cautiously to the affected person, “it appears like you might be prone to suicide.” Based mostly on this end result, you classify the affected person as suicidal and provoke the usual suicide prevention methods.
Okay, let’s neglect that situation shortly: who would resolve a matter life-or-death by flipping a coin, proper?

It seems that assessing threat components for suicide (De Beurs, 2024) doesn’t work a lot better than a coin flip, as a long time of proof exhibits. In a complete meta-analysis of fifty years of analysis on threat components for suicidal ideas and behaviours, Franklin and colleagues (2017) concluded that “prediction was solely barely higher than likelihood for all outcomes.”

Transferring on from easy prediction fashions with particular person threat components (e.g., loneliness, a most cancers prognosis or home violence), the sector transitioned to establishing extra advanced prediction fashions together with multivariable predictors as within the ideation-to-action frameworks (Klonsky, Saffer & Bryan, 2018; Torino et al., 2026), and extra refined statistical approaches corresponding to machine studying (e.g., Boudreaux et al. 2021).

]Of their systematic assessment on statistical prediction fashions for self-harm and suicide, Seyedsalehi and colleagues (2025) have synthesised proof from 91 articles about 167 fashions and critically appraised their predictive efficiency. Do these fashions make extra correct predictions than earlier analysis has been capable of obtain? And what can we be taught from them for medical observe?

Strategies

The reviewers searched 5 databases (MEDLINE, EMBASE, PsycINFO, CINAHL and World Well being) from inception to 30 November 2021. An up to date search together with exterior validations was carried out on 25 October 2024. Inclusion standards have been the event and/or exterior validation of statistical prediction fashions for self-harm and/or suicide. Fashions predicting suicidal ideation have been excluded, as have been threat evaluation scales, checklists and research of unassisted medical judgement: solely multivariable fashions with statistically derived weights have been included. The Prediction mannequin Threat of Bias Evaluation Device (PROBAST) (Wolff et al., 2019) was used for risk-of-bias evaluation.

Outcomes

In complete, the systematic assessment recognized 91 research reporting on 167 statistical threat prediction fashions (self-harm: 76 fashions; suicide: 51 fashions; mixed: 40 fashions) and 29 exterior validations. A minority of the fashions have been externally validated (8%, 14/167) or described in sufficient element to allow validation (17%, 28/167). Over 60% of fashions and exterior validations used knowledge from the USA (n = 125, 64%), and most (72%) have been based mostly on routine knowledge corresponding to digital well being data or administrative databases. As an indicator of mannequin complexity, the variety of predictor parameters within the closing fashions ranged from 2 to eight,071 (median 13, IQR 6 to 29), and the variety of candidate parameters thought of ranged from 9 to over 89,000 (median 150).

One necessary discovering was about how properly the fashions discriminated between threat and no threat. To evaluate their discriminatory power, the so-called C-index was used as a statistical measure (additionally termed concordance index; Harrell et al. 1982). A worth of 0.5 is sort of a coin toss, whereas values nearer to 1 present that the mannequin is healthier at distinguishing between folks at larger or decrease threat of suicide/self-harm.

• Within the mannequin improvement research, C-indices various between 0.61 and 0.97 (median 0.82); which means that fashions predicted threat higher than likelihood.
• In exterior validation research, C-indices ranged from 0.60 to 0.86 (median 0.81), which is near the event determine and akin to prediction fashions in cardiovascular medication, respiratory medication and COVID-19. Discrimination did fall for self-harm fashions (0.85 to 0.73) and suicide fashions (0.82 to 0.76), however rose for fashions predicting the composite end result (0.79 to 0.85).
• Median C-indices for every mannequin sort are introduced in desk 1.

Desk 1. Median C index of prediction fashions.

Notice: the exterior validation column is predicated on 29 exterior validations, not on the mannequin numbers proven.

Predicting threat is one factor (i.e. somebody is prone to suicide); figuring out whether or not that predicted threat corresponds to the precise threat is one other (i.e. a suicide try). Calibration was assessed for less than 15 of 167 fashions (9%) in improvement research and in 9 of 29 exterior validations (31%), protecting six fashions in complete. Amongst these, two mannequin households confirmed sufficient discrimination and calibration in exterior validation: OxMIS and the Simon fashions, 5 fashions in complete. What precisely do they predict?

• OxMIS (Oxford Mental Illness and Suicide device) is a freely out there web-based 17-item mannequin predicting suicide at 1 12 months in folks with extreme psychological sickness, utilizing socio-demographic and medical threat components. The unique improvement paper (Fazel et al., 2019) reported sensitivity of 55% (95% confidence interval [CI] 47 to 63%), specificity of 75% (95% CI 74 to 75%), and optimistic and damaging predictive values of two% and 99%. On this assessment, OxMIS was the one mannequin whose exterior validations have been rated at low threat of bias.
• The 4 Simon fashions (Simon et al. 2018) predict 90-day threat of suicide try and suicide dying following psychological well being specialty and common medical visits, utilizing 313 demographic and medical traits from digital well being data. Throughout the 4 fashions, the unique paper reported sensitivity of seven.0% to 48.1%, specificity of 95.0% to 95.2%, optimistic predictive values of 0.26% to five.4% and damaging predictive values of 99.6% to 99.9%.

Threat of bias was excessive for all mannequin improvement research and all however two exterior validations (each of OxMIS). The primary causes have been incomplete or inappropriate analysis of predictive efficiency (92%), inadequate pattern sizes (77%), inappropriate dealing with of lacking knowledge (66%), and failure to account for overfitting and optimism in efficiency estimates (63%).

One discovering is straightforward to overlook. The difficult fashions did no higher than the straightforward ones. Excessive-dimensional fashions had a median C-index of 0.82, precisely the identical as low-dimensional fashions, and fashions constructed on routine knowledge (0.84) carried out very similar to these constructed on prospectively collected knowledge (0.81).

Conclusions

Although the coin-toss metaphor could not appear acceptable for such an necessary matter, precisely predicting suicide stays an actual problem. Thus, promising scientific outcomes ought to nonetheless be interpreted with sensible scepticism. On the one hand, the authors have recognized 5 fashions that demonstrated good predictive efficiency in exterior knowledge units (Seyedsalehi et al. 2025); thus, suggesting that:

“ […] blanket criticisms of the predictive efficiency of threat fashions for suicide outcomes should not evidence-based.”

Alternatively, the medical usefulness of those fashions stays questionable. This shall be mentioned additional within the medical implication part.

Strengths and limitations

Strengths

• The authors have addressed a number of limitations of earlier critiques and supply a complete overview of a posh proof base.
• Research protocols (TRIPOD-SRMA; PRISMA) have been adhered to.

Limitations

• No meta-analysis was performed, as defined by the authors, which limits the quantitative synthesis of the out there proof.
• One necessary limitation is that suicide makes an attempt and non-suicidal self-injury weren’t distinguished (p. 2). The authors comply with the NICE definition of self-harm, any act of intentional self-injury or self-poisoning no matter intent, however these stay two distinct constructs (e.g., Brausch & Gutierrez, 2010; Muehlenkamp & Kerr, 2010). A European Scoping Evaluation highlights heterogenous terminologies and recommends a global settlement for future analysis (Jakobsen et al., 2023).
• Many of the screening, knowledge extraction and threat of bias evaluation was carried out by a single reviewer, with solely 10% independently checked by a second.
• The assessment didn’t contain sufferers or medical specialists, which can clarify its predominantly scientific reasonably than practice-oriented focus.
• A limitation of the proof base is the methodological weak spot of current research, as criticised by the authors:

The event of so many suicide prediction fashions, typically utilizing sub-optimal strategies, and plenty of answering the identical analysis query, is a major supply of analysis waste.

Implications for observe

From a scientific perspective, this assessment is extremely fascinating, methodologically robust and customarily well-written. From a medical perspective, nevertheless, its quick sensible implications are much less clear. An necessary query due to this fact stays: How can these findings be translated into medical observe?

Notably, solely eleven of 167 fashions (7%) will be accessed by clinicians as a device to calculate suicide threat (for instance utilizing a choice tree). A ‘fast and simple’ resolution for on a regular basis medical observe sounds promising, however that doesn’t assure that it’s going to really be possible. Who supplies entry to the device? How does it work in observe? Is particular coaching mandatory?

The authors recommend their findings needs to be thought of in future updates to medical tips (p. 15), naming the NICE self-harm steering and NHS England suicide prevention steering, each of which presently advise towards threat prediction instruments. That deserves additional dialogue. Suicide threat evaluation presents a posh problem. People can’t be diminished to predefined classes or fashions, so no single mannequin is prone to be ample for precisely assessing suicide threat. As Teismann and colleagues (2026) summarise:

Latest meta-analyses reveal that neither particular person threat components, composite threat scores, medical judgment, nor adherence to theoretical fashions or synthetic intelligence allows sufficiently correct prediction of suicidal habits.

As an alternative of specializing in threat prediction, we might give attention to suicide prevention methods (Teismann et al., 2026). Actually, this will not require a lot, as a current systematic assessment by Homan and colleagues (2026) discovered that temporary interventions after suicide makes an attempt work (Hemming, 2026). Nonetheless, suicide prevention requires greater than interventions at a person stage; it additionally requires a public well being method (Lawson, 2024).

To bridge the hole between scientific findings and medical observe, shut collaboration amongst public well being professionals, clinicians and researchers is important. This assessment supplies an necessary scientific basis for such interdisciplinary efforts, in order that finally, prediction now not turns into a matter of a coin toss however will be guided by evidence-based approaches.

Assertion of pursuits

Laura Melzer has no conflicts of curiosity to reveal. AI was used for enhancing functions solely.

Editor

Edited by Laura Hemming.

Hyperlinks

Main paper

Aida Seyedsalehi, James Bailey, Maya Ogonah, Thomas Fanshawe, Seena Fazel (2025). Prediction fashions for self-harm and suicide: a scientific assessment and demanding appraisal. BMC medication, 23(1), 549. https://doi.org/10.1186/s12916-025-04367-6

Different references

Boudreaux, E. D., Rundensteiner, E., Liu, F., Wang, B., Larkin, C., Agu, E., Ghosh, S., Semeter, J., Simon, G., & Davis-Martin, R. E. (2021). Making use of Machine Studying Approaches to Suicide Prediction Utilizing Healthcare Information: Overview and Future Instructions. Frontiers in psychiatry, 12, 707916. https://doi.org/10.3389/fpsyt.2021.707916

Brausch, A.M., Gutierrez, P.M. Variations in Non-Suicidal Self-Damage and Suicide Makes an attempt in Adolescents. J Youth Adolescence 39, 233–242 (2010). https://doi.org/10.1007/s10964-009-9482-0

De Beurs, D. The nice unknown? Assessing suicide threat in trials of psychological interventions for melancholy. The Psychological Elf, August 2024.

Fazel, S., Wolf, A., Larsson, H. et al. The prediction of suicide in extreme psychological sickness: improvement and validation of a medical prediction rule (OxMIS). Transl Psychiatry 9, 98 (2019). https://doi.org/10.1038/s41398-019-0428-3

Franklin, J. C., Ribeiro, J. D., Fox, Ok. R., Bentley, Ok. H., Kleiman, E. M., Huang, X., Musacchio, Ok. M., Jaroszewski, A. C., Chang, B. P., & Nock, M. Ok. (2017). Threat components for suicidal ideas and behaviors: A meta-analysis of fifty years of analysis. Psychological Bulletin, 143(2), 187–232. https://doi.org/10.1037/bul0000084

Harrell, F. E., Jr, Califf, R. M., Pryor, D. B., Lee, Ok. L., & Rosati, R. A. (1982). Evaluating the yield of medical assessments. JAMA, 247(18), 2543–2546.

Hemming, L. Temporary interventions after suicide makes an attempt: does connection save lives? The Psychological Elf, June 2026.

Homan, S., Marciniak, M. A., Michel, S., Bertram, A. M., Rühlmann, C., Pethő, A., Kirchhofer, L., Biele, L., Segerer, R., Homan, P., Olbrich, S., O’Connor, R. C., & Kleim, B. (2026). Effectiveness of temporary interventions and contacts after suicide try: a scientific assessment and meta-analysis. EClinicalMedicine, 93, 103824. https://doi.org/10.1016/j.eclinm.2026.103824

Jakobsen, S. G., Nielsen, T., Larsen, C. P., Andersen, P. T., Lauritsen, J., Stenager, E., & Christiansen, E. (2023). Definitions and incidence charges of self-harm and suicide makes an attempt in Europe: A scoping assessment. Journal of psychiatric analysis, 164, 28–36. https://doi.org/10.1016/j.jpsychires.2023.05.06

Klonsky, E. D., Saffer, B. Y., & Bryan, C. J. (2018). Ideation-to-action theories of suicide: a conceptual and empirical replace. Present opinion in psychology, 22, 38–43. https://doi.org/10.1016/j.copsyc.2017.07.020

Lawson, Ok. Suicide prevention: increasing the narrative to stopping the disaster, not simply treating the disaster. The Psychological Elf, November 2024.

Marzecki, F. Home violence and suicide in girls: insights from a nationwide UK examine. The Psychological Elf, November 2025.

Matthews, D. A most cancers prognosis brings a suicide threat: The earlier after prognosis, and the extra aggressive the most cancers, the upper the chance. The Psychological Elf, November 2025.

Muehlenkamp, J. J., & Kerr, P. L. (2010). Untangling a posh net: how non-suicidal self-injury and suicide makes an attempt differ. Prevention researcher, 17(1), 8.

Pikett, L. Is focusing on loneliness the important thing to releasing folks from entrapment and stopping suicide? The Psychological Elf, November 2023.

Simon, G. E., Johnson, E., Lawrence, J. M., Rossom, R. C., Ahmedani, B., Lynch, F. L., Beck, A., Waitzfelder, B., Ziebell, R., Penfold, R. B., & Shortreed, S. M. (2018). Predicting Suicide Makes an attempt and Suicide Deaths Following Outpatient Visits Utilizing Digital Well being Information. The American journal of psychiatry, 175(10), 951–960. https://doi.org/10.1176/appi.ajp.2018.17101167

Teismann, T., Janssen, W. C., & Heering, H. D. (2026). Suicide threat evaluation: medical implications of the unpredictability of suicidal habits. Frontiers in psychiatry, 17, 1844322. https://doi.org/10.3389/fpsyt.2026.1844322

Torino, G., Calati, R., Brambilla, P., & Delvecchio, G. (2026). Ideation-to-action framework of suicide: a scientific assessment of the Built-in Motivational-Volitional mannequin and the Three-Step Principle. Journal of affective issues, 399, 121138. https://doi.org/10.1016/j.jad.2025.121138

Wolff, R. F., Moons, Ok. G., Riley, R. D., Whiting, P. F., Westwood, M., Collins, G. S., … & PROBAST Group†. (2019). PROBAST: a device to evaluate the chance of bias and applicability of prediction mannequin research. Annals of inside medication, 170(1), 51-58.

Photograph credit