Machine learning in suicide science: Applications and ethics

For decades, our ability to predict suicide has remained at near‐chance levels. Machine learning has recently emerged as a promising tool for advancing suicide science, particularly in the domain of suicide prediction. The present review provides an introduction to machine learning and its potential application to open questions in suicide research. Although only a few studies have implemented machine learning for suicide prediction, results to date indicate considerable improvement in accuracy and positive predictive value. Potential barriers to algorithm integration into clinical practice are discussed, as well as attendant ethical issues. Overall, machine learning approaches hold promise for accurate, scalable, and effective suicide risk detection; however, many critical questions and issues remain unexplored.     

Adolescent suicidal behaviors as a function of depression,hopelessness, alcohol use,and social support: A longitudinal investigation

Surveyed two high school cohorts (ns=698 and 283) to study independent prospective predictors of adolescent suicidal behaviors (thoughts, communicatio to others, attempts). Within each cohort, there were two measurements conducted 6 months apart. Structural equation models were tested, with depressive symptoms, hopelessness, alcohol consumption, social support, and gender serving as predictors. In the larger cohort, depression predicted later levels of all three suicidal behaviors controlling for baseline suicidal behaviors. Also, suicidal thoughts predicted later communications, and suicide attempts predicted future thoughts. In the smaller cohort, alcohol consumption predicted all three suicidal behaviors at the later measurement, whereas depression was predictive only of later thoughts. Major issues regarding prevention, theories of suicide and negative affect, and methodological/analytical approaches were discussed.     

Social Rules: Origin; Character; Logic; Change (Book)

Although less observable than the overt actions of fighting and assault, covert antisocial behaviors such as stealing and property destruction comprise an important subclass of externalizing behavior patterns, displaying considerable predictive power toward delinquency in adolescence. I discuss a laboratory paradigm for objective observation of such behaviors in children that has shown impressive concurrent and predictive validity among samples of boys with and without attention deficit hyperactivity disorder. Addressed herein are crucial questions regarding the ethics of tempting children to steal objects and small amounts of money and to deface property as well as the types of informed consent and debriefing procedures utilized in research with this paradigm. Weighing ethical considerations alongside the ability to predict delinquent behavior presents provocative issues for those interested in understanding the development of antisocial behavior.     

Objective assessment of covert antisocial behavior: predictive validity and ethical considerations

Although less observable than the overt actions of fighting and assault, covert antisocial behaviors such as stealing and property destruction comprise an important subclass of externalizing behavior patterns, displaying considerable predictive power toward delinquency in adolescence. I discuss a laboratory paradigm for objective observation of such behaviors in children that has shown impressive concurrent and predictive validity among samples of boys with and without attention deficit hyperactivity disorder. Addressed herein are crucial questions regarding the ethics of tempting children to steal objects and small amounts of money and to deface property as well as the types of informed consent and debriefing procedures utilized in research with this paradigm. Weighing ethical considerations alongside the ability to predict delinquent behavior presents provocative issues for those interested in understanding the development of antisocial behavior.     

Ethical Considerations when Employing Fake Identities in Online Social Networks for Research

Online social networks (OSNs) have rapidly become a prominent and widely used service, offering a wealth of personal and sensitive information with significant security and privacy implications. Hence, OSNs are also an important—and popular—subject for research. To perform research based on real-life evidence, however, researchers may need to access OSN data, such as texts and files uploaded by users and connections among users. This raises significant ethical problems. Currently, there are no clear ethical guidelines, and researchers may end up (unintentionally) performing ethically questionable research, sometimes even when more ethical research alternatives exist. For example, several studies have employed “fake identities” to collect data from OSNs, but fake identities may be used for attacks and are considered a security issue. Is it legitimate to use fake identities for studying OSNs or for collecting OSN data for research? We present a taxonomy of the ethical challenges facing researchers of OSNs and compare different approaches. We demonstrate how ethical considerations have been taken into account in previous studies that used fake identities. In addition, several possible approaches are offered to reduce or avoid ethical misconducts. We hope this work will stimulate the development and use of ethical practices and methods in the research of online social networks.     

Suicide surveillance in the U.S. Military--reporting and classification biases in rate calculations

The military has a well-defined population with suicide prevention programs that have been recognized as possible models for civilian suicide prevention efforts. Monitoring prevention programs requires accurate reporting. In civilian settings, several studies have confirmed problems in the reporting and classification of suicides. This analysis evaluated whether suicides were underreported or misclassified under accident or undetermined manner of death in the military system. We reviewed all 1998 and 1999 military deaths using official death reports and compared these data with additional sources, most importantly the DoD Medical Mortality Registry. We assessed for evidence of expressed suicidal intent and past psychiatric history among deaths classified as undetermined and accidents due to gunshot, overdose, drowning, falls, or asphyxia. Using sources other than official records, we found 17% more suicides than were reported, and an additional 4% of deaths that were suspicious for suicide. This study suggests that reporting and classification errors may account for 21% additional suicides in the military. These findings are comparable to rates seen in civilian studies and add to the literature regarding the problems inherent in using administrative death classification data for medical surveillance purposes.     

The cultural theory and model of suicide

A growing body of research has demonstrated important variations in the prevalence, nature, and correlates of suicide across ethnic and sexual minority groups. Despite these developments, existing clinical and research approaches to suicide assessment and prevention have not incorporated cultural variations in any systematic way. In addition, theoretical models of suicide have been largely devoid of cultural influence. The current report presents a comprehensive analysis of literature describing the relationship between cultural factors and suicide in three major ethnic groups (African Americans, Asian Americans, and Latinos) and LGBTQ¹ sexual minority groups. We utilized an inductive approach to synthesize this variegated body of research into four factors that account for 95% of existing culturally specific risk data: cultural sanctions, idioms of distress, minority stress, and social discord. These four cultural factors are then integrated into a theoretical framework: the Cultural Model of Suicide. Three theoretical principles emerge: (1) culture affects the types of stressors that lead to suicide; (2) cultural meanings associated with stressors and suicide affect the development of suicidal tendencies, one's threshold of tolerance for psychological pain, and subsequent suicidal acts; and (3) culture affects how suicidal thoughts, intent, plans, and attempts are expressed. The Cultural Model of Suicide provides an empirically guided cohesive approach that can inform culturally competent suicide assessment and prevention efforts in future research and clinical practice. Including both ethnic and sexual minorities in our investigations ensures advancement along a multiple identities perspective.     

A cluster analysis of the circumstances of death in suicides in Hong Kong

Classification of suicides is essential for clinicians to better identify self-harm patients with future suicidal risks. This study examined potential subtypes of suicide in a psychological autopsy sample (N = 148) in Hong Kong. Hierarchical cluster analysis extracted two subgroups of subjects in terms of expressed deliberation assessed by the Beck Suicide Intent Scale (SIS). The first group was associated with charcoal burning suicide, no psychiatric illness, indebtedness, better problem-solving ability, chronic stress, and higher overall SIS scores. The second group was associated with jumping from a height, psychotic disorders, psychiatric treatment, acute stress, and lower overall SIS score. The existence of a substantial cluster of subjects with lower expressed intent and preparation has important implications for the performance of the SIS as a predictive tool. Suicide prevention strategy may have to target potential subgroups with specific approaches.     

A model for the description and interpretation of suicide prevention.

Views about suicide prevention are based on underlying beliefs about the origins of problems and basic concepts about humankind. These implicit theories have an effect on prevention practices. Making these views explicit is one of the keys for the further development of suicide prevention. In this study a paradigm for analyzing suicide prevention of means of a coding frame and interpreting findings by means of theoretical models of prevention was elaborated. The analysis was based on empirical data consisting of definitions of prevention given by psychologists (N = 34) participating in the national suicide prevention project in Finland. The study demonstrates that suicide prevention can be differentiated at the operational level by means of the analysis method generated. Moreover, the findings can be interpreted according to theoretical criteria. Views expressed by the psychologists seemed to correspond largely to central features of current prevention models. Furthermore, the data can be seen to serve as an empirical validation of these models. Suicide prevention proved to be a multifactorial concept manifesting mainly process theory and interactional explanations of suicidality, and prevention practices fell into a simple typology of four categories.     

Resolving Ethical Dilemmas in Suicide Prevention: The Case of Telephone Helpline Rescue Policies

The ethical basis of suicide prevention is illustrated by contrasting helpline emergency rescue policies of the Samaritans and the AAS and the U.S. National Suicide Prevention Lifeline network. We contrast moralist, relativist, and libertarian ethical premises and question whether suicide can be rational. Samaritans respect a caller's right to decide to die by suicide; U.S. helplines oblige emergency intervention during an attempt even against the caller's will. We analyze the effect of emergency rescue when there is high suicide risk but an attempt has not been initiated. We examine links between values and actions, needs for empirical evidence to guide practice, and propose vigorous dialogue about values in the gray zone of moral practice.     

Preferences for suicide prevention strategies among university students in Japan: a cross-sectional study using full-profile conjoint analysis

In Japan, implementation of suicide prevention policies is mainly supported by public funds. However, it is unclear what kinds of suicide prevention strategies people prefer. We conducted a survey to clarify people’s preferences regarding suicide prevention strategies adopted in Japan. This was a cross-sectional self-administered questionnaire survey. Participants were recruited through a lecture held by the first author at their university. We distributed questionnaires to 324 people present at the lecture; 249 completed questionnaires were included in the final analysis. We estimated suicide prevention strategy preferences using full profile conjoint analysis. For all six prevention strategies, the inclusion of each strategy in the policy profile was statistically significantly related to the positive evaluation of the overall policy profile. Marginal Willingness to Pay (MWTP) for restriction of access to means showed the highest value of the six suicide prevention strategies. MWTP was the lowest for public awareness activities. Preferred suicide prevention strategies in Japan are restriction of access to means and enhancement of psychiatric services. The results of this study indicate the strategies that are preferred have a high level of evidence of suicide prevention and do not directly intervene in a person’s free will to die by suicide.     

Toward a hermeneutic model of ethical decision making in clinical practice

Documented ethical violations and empirical research have demonstrated that, despite professional standards and formal training in ethical principles, some psychotherapists engage in unethical behaviors that compromise the welfare of clients. It appears that competing values and interests that emerge in the therapeutic endeavor can interfere with therapists' considerations of ethical standards and their willingness to act ethically. Expanding current models of ethical decision making, this article offers a hermeneutic model that recognizes that in addition to moral reasoning, the context of the therapeutic relationship and the therapist's subjective responses are fundamental considerations in the interpretation and application of ethical interventions. Implications for understanding and training of ethics in psychotherapy in this broader context are explored.     

Treating the Capability for Suicide: A Vital and Understudied Frontier in Suicide Prevention

Current efforts at suicide prevention center largely on reducing suicidal desire among individuals hospitalized for suicidality or being treated for related psychopathology. Such efforts have yielded evidence‐based treatments, and yet the national suicide rate has continued to climb. We propose that this disconnect is heavily influenced by an unmet need to consider population‐level interventions aimed at reducing the capability for suicide. Drawing on lessons learned from other public health phenomena that have seen drastic declines in frequency in recent decades (HIV, lung cancer, motor vehicle accidents), we propose that current suicidality treatment efforts trail current suicidality theories in their lack of focus on the extent to which individuals thinking about suicide are capable of transitioning from ideation to attempt. We summarize extant evidence for specific capability‐centered approaches (e.g., means safety) and propose other options for improving our ability to address this largely overlooked variable. We also note that population‐level approaches in this regard would represent an important opportunity to decrease risk in individuals who either lack access to evidence‐based care or underreport suicidal ideation, as a reduced capability for suicide would theoretically diminish the potency of suicidal desire and, in this sense, lower the odds of a transition from ideation to attempt.     

An Evidence-Based Approach to Managing Suicidal Patients in the Patient-Centered Medical Home

Primary care is a critical setting for suicide prevention because it is often the first and only source of mental health care for the U.S. general population. It is also important because suicidal patients report a greater number of somatic complaints and make more frequent medical visits compared to nonsuicidal patients. Models for managing suicide within primary care have recently arisen, yet no models have been proposed for use within the patient-centered medical home (PCMH), a primary care model that integrates behavioral health into its practice. The authors suggest a chronic disease model for the management of suicide risk in the PCMH along with collaborative strategies that may include suicide screening and targeted assessment, warm hand-offs, cognitive-behavioral interventions, routine collaborative medication management, and means restriction counseling. The current paper advises how those within the PCMH can adapt and implement evidence-based practices to manage suicide. Finally, the authors discuss a case example illustrating these evidence-based and collaborative methods.     

A Systematic Review of Mass Media Campaigns for Suicide Prevention: Understanding Their Efficacy and the Mechanisms Needed for Successful Behavioral and Literacy Change

Mass media campaigns are increasingly seen as an important part of suicide prevention; however, despite their popularity, their efficacy is not well understood. The current review aimed to address key knowledge gaps regarding how mass media campaigns can be optimized to prevent suicide, by looking at their global efficacy, and mechanisms related to successful outcomes. A systematic review of the international literature examined studies which evaluated mass media campaigns targeted at suicide prevention, where suicide behaviors (mortality, attempts) or suicide literacy (knowledge, attitudes, help‐seeking) was identified as a primary outcome. Thirteen articles describing 12 unique campaigns met eligibility criteria. For behavioral outcomes, mass media campaigns appear to be most effective when delivered as part of a multicomponent suicide prevention strategy, while “standalone campaigns” were modestly useful for increasing suicide literacy. Level of exposure, repeat exposure, and community engagement appeared to be fundamental to the success of these campaigns; however, these constructs were poorly adhered to in the development and implementation of campaigns. Overall, the mixed quality of the included studies highlights a need for increased quantity, consistency, and quality of evaluations to advance the evidence base.     

Psychological autopsies: methods and ethics

Essential knowledge on suicide is derived from studies that include interviews with survivors. In this paper, we discuss methodological and ethical issues pertaining to the interview method known as "psychological autopsy"; the discussion is based on our application of the method to three studies of suicides in Sweden and on a review of other investigations. Interviewing a survivor is a delicate matter, and the integrity of the deceased, the integrity and health of the informant, and the psychological strain on the interviewer must all be taken into consideration. The interviewer should have clinical experience in order to be prepared to deal with interviewees in grief. Contact by telephone, followed by an introductory letter, provides an opportunity to meet survivors in an empathic manner and has a low rejection rate. A 2- to 6-month interval between suicide and interview is recommended. The survivor's reactions to the interview should be evaluated in order to expand the empirical base for ethical considerations. Studies on the validity and reliability of the method are necessary.     

Reflexivity in Counterspaces Fieldwork

Reflexivity is an important tool for navigating ethically important moments in fieldwork. It may be particularly useful in situations where the researcher has the potential to undermine the conduct of the study and/or the well‐being‐enhancing role of counterspaces. In this article, I explore my use of reflexivity to traverse ethically important moments I encountered while investigating a counterspace for African‐American youth who had been incarcerated. The ethical challenge concerned whether and how to continue this study in light of realizing that I held implicit biases toward the research participants. I describe my process for arriving at a decision and propose key considerations for the use of reflexivity in supporting ethical fieldwork within counterspaces.     

Health Problems and Male Firearm Suicide

Drawing on constructs of masculinity as it relates to both gun ownership and men's health, we use a rich data set, the New Jersey Violent Death Reporting System as well as hospital discharge data, to analyze 3,413 completed male suicides between the years of 2003 and 2009. We test the hypotheses that the use of firearms is more common when physical health problems are cited as suicide circumstances, and that suicide decedents who use firearms have poorer physical health than those who used other methods. Results show that firearms are disproportionately used in male suicides when physical health is listed as a circumstance. Additionally, among suicide decedents with a hospitalization during the 3 years prior to death, those who used firearms were in poorer health than those who used other methods. These findings have implications for prevention efforts, because restricting access to lethal means is an important aspect of suicide prevention.     

Qualitative research in multicultural psychology: philosophical underpinnings, popular approaches, and ethical considerations

This article reviews the current and emerging status of qualitative research in psychology. The particular value of diverse philosophical paradigms and varied inquiry approaches to the advancement of psychology generally, and multicultural psychology specifically, is emphasized. Three specific qualitative inquiry approaches anchored in diverse philosophical research paradigms are highlighted: consensual qualitative research, grounded theory, and participatory action research. The article concludes by highlighting important ethical considerations in multicultural qualitative research.