Mortality and further suicidal behaviour after an index suicide attempt: a 10-year study

OBJECTIVE: To examine further suicide attempts and mortality in the 10 years after a suicide attempt requiring hospital admission. METHOD: Participants were a consecutive series of 3690 individuals admitted to Christchurch Hospital for attempted suicide during the 10-year period 1993-2002. Data were obtained on admissions to Christchurch Hospital for attempted suicide during the study period. Mortality subsequent to the index suicide attempt was established from the National Mortality Database. The influence of age, gender and method of index suicide attempt on mortality and further suicide attempts requiring hospitalization were examined. RESULTS: Within 10 years, 28.1% of those who had been admitted for an index suicide attempt were readmitted for a further non-fatal suicide attempt, and 4.6% died by suicide. Risks and rates of readmission were higher in: females; those under 55; and those whose index attempt involved a method of low lethality. Risks and rates of suicide were higher in: males; those aged 25 and over; and those using an index suicide attempt method of high lethality. Risks and rates of readmission and mortality from suicide were highest in the first 2 years after the index attempt, although deaths and readmissions occurred throughout the 10 years study period. CONCLUSIONS: Those making suicide attempts requiring hospital admission are at high risk of further hospitalization for suicide attempt and of death from suicide. These findings suggest a need for ongoing support and monitoring, and for enhanced treatment and management of all those making suicide attempts which require hospital admission in an effort to reduce risks of further suicidal behaviour.     

Attempted suicide in Hanoi, Vietnam

BACKGROUND: Attempted suicide is a key predictor of suicide, which is among the dominant causes of young people's deaths worldwide. Very little is known about the characteristics of suicide attempters in Asia, especially in Vietnam. METHODS: Medical records of 509 patients (515 attempted-suicide events) admitted to Bach Mai General Hospital in Hanoi, Vietnam from 1 January 1999 to 30 April 2001 were analysed according to the criteria of the WHO Multicentre Study of Attempted Suicide. RESULTS: The suicide attempters' mean age was 28.3+/-12.9 years. Nearly half (48.7%) were aged 15-24. The female-to-male ratio of patients living in urban areas (2.1:1) was higher than in rural areas (1.2:1). In urban areas, students (32 %) and homeworkers (28%) and, in rural areas, farmers (56 %) and students (17%) were the salient occupational categories. Acute life stressors were the main causes (73.8%) of suicide attempts. Only in some 6% of cases had a psychiatric illness been diagnosed before the suicide attempts. As a means of attempting suicide, intoxication with analgesics and antipyretics (e. g. paracetamol) with low medical lethality scores was a frequent method among the urban patients, the majority of whom (81%) consequently stayed in hospital less than 24 h. Pesticide and rat poison, more commonly (57.2%) used by attempters in rural areas, had higher medical lethality scores and also necessitated more prolonged hospital treatment. CONCLUSIONS: Some suicide-preventive strategies used in the West for young people may be applicable in Vietnam. Reducing access to pesticides and rat poison is comparable to western efforts to make paracetamol or firearms less freely available. Skills in resolving family and other conflicts can be taught in schools according to WHO's suicide-prevention resources for teachers.     

Clinical Characteristics and Precipitating Factors of Adolescent Suicide Attempters Admitted for Psychiatric Inpatient Care in South Korea

Objective

We aimed to examine the rates, correlates, methods, and precipitating factors of suicide attempts among adolescent patients admitted for psychiatric inpatient care from 1999 to 2010 in a university hospital in Korea.

Methods

The subjects consisted of 728 patients who were admitted for psychiatric inpatient care in a university hospital over a 12-year period and who were aged 10-19 years at the time of admission. We retrospectively investigated the information on suicidal behaviors and other clinical information by reviewing the subjects'' electronic medical records. Whether these patients had completed their suicide on 31 December 2010 was determined by a link to the database of the National Statistical Office.

Results

Among 728 subjects, 21.7% had suicidal ideation at admission, and 10.7% admitted for suicidal attempts. Female gender, divorced/widowed parents, and the presence of mood disorders were associated with a significantly increased likelihood of suicide attempts. Most common method of suicide attempts was cutting, and most common reason for suicide attempts was relationship problems within the primary support group. A diagnosis of schizophrenia was associated with increased risk of death by suicide after discharge.

Conclusion

These results highlight the role of specific psychosocial factor (e.g., relational problems) and psychiatric disorders (e.g., mood disorders) in the suicide attempts of Korean adolescents, and the need for effective prevention strategies for adolescents at risk for suicide.     

Tentatives de suicides violentes à l’hôpital général de Fès (Maroc) : évaluation et prise en charge en psychiatrie de liaison. Étude prospective sur six mois

Suicide attempt situations are not only encountered in psychiatric emergency departments, but also in the other medical and surgical units as well. They are often poorly evaluated after the end of physical care, and they rarely happen in facilities of psychiatric care.MethodsThrough a prospective study established over a period of six months, conducted within the university hospital center Hassan II in Fez, we attempted in the context of the activity of the liaison psychiatry to assess, the suicide attempters hospitalized in the medical and surgical units after a violent suicide attempt. The study was spread over a period of 24 months, from January 2010 to December 2011. The objectives of our study were to describe the clinical and epidemiological profile of the suicide attempters that are admitted to the physical units of the university hospital center, to identify the units that are most demanding of psychiatric consultations for suicide attempts, the methods used, the underlying psychiatric disorders, and to assess the risk factors. From 180 requests for psychiatric consultation, 31 cases of suicide attempts were included in our study. The psychiatric evaluation was performed based on a psychiatric interview. Data was collected using questionnaires including 24 items. After an initial psychiatric examination designed to assess the patient's psychiatric condition, follow up examinations were completed at 1, 3 and 6 months intervals.ResultsOf the 31 attempt survivors aged between 13 and 65 included in our work, 60% were male and 45% of the patients had a psychiatric history. Twenty-six percent of our patients were hospitalized in a resuscitation unit and 23% in visceral surgery. The most common means used by the patients was the ingestion of caustic substances and drug toxicity in 26%. Most psychiatric disorders – diagnosed according to DSM-IV – were depressive disorder in 52% of cases, and a psychotic disorder (paranoid schizophrenia, schizophreniform disorder, schizoaffective disorder and brief psychotic disorder) in 36% of cases. The outcome was favorable in 70% of our patients after 6 months.DiscussionLiaison psychiatry is a growing field; it plays a crucial role in the assessment and management of suicidal behavior requiring medical somatic management.ConclusionOur study allowed us to meet the suicide attempters hospitalized in the medical and surgical units, to initiate and continue their support, and to participate in the prevention of any recurrence.     

Activation of emergency medical services for acute stroke in a nonurban population: the T.L.L. Temple Foundation Stroke Project

BACKGROUND AND PURPOSE: Activating emergency medical services (EMS) is the most important factor in reducing delay times to hospital arrival for stroke patients. Determining who calls 911 for stroke would allow more efficient targeting of public health initiatives. METHODS: The T.L.L. Temple Foundation Stroke Project is an acute stroke surveillance and intervention project in nonurban East Texas. Prospective case ascertainment allowed chart abstraction and structured interviews for all hospitalized stroke patients to determine if EMS was activated, and if so, by whom. RESULTS: Of 429 validated strokes, 38.0% activated EMS by calling 911. Logistic regression analysis comparing those who called 911 with those who did not activate EMS found that individuals who were employed were 81% less likely to have EMS activated (OR 0.19, 95% CI 0.04 to 0.63). Of the 163 cases in which 911 was called, the person activating EMS was: self (patient), 4.3%; family member of significant other, 60. 1%; paid caregiver, 18.4%; and coworker or other, 12.9%. Significant associations between the variables age group (P=0.02), insurance status (P=0.007), and living alone (P=0.05) with who called 911 was found on chi(2) analysis. CONCLUSIONS: Educational efforts directed at patients themselves at risk for stroke may be of low yield. To increase the use of time dependent acute stroke therapy, interventions may wish to concentrate on family, caregivers, and coworkers of high-risk patients. Large employers may be good targets to increase utilization of EMS services for acute stroke.     

Suicide by burning in Korea

Of 2,143 admissions following suicide attempts over a seven year period (1980-1986) in Seoul, Korea, there were 38 cases (1.8%) of suicide by burning. These cases were matched by age and sex with a control group of suicide attempts in general and were investigated for psychosocial differences from other suicide attempters. No significant differences were found in social factors such as education, religion, marital status, seasonal change and occupation. The majority of suicide attempts by burning were in a public place (73.7%) and were eventually fatal despite intensive medical treatment (78.9%). Half (52.7%) suffered from significant mental disorders and marital disharmony.     

Electroconvulsive therapy and suicide among the mentally ill in England: a national clinical survey

We aimed to determine the number and characteristics of psychiatric patients receiving electroconvulsive therapy (ECT) who had subsequently died by suicide. Data were collected on an 8-year (1999-2006) sample of suicide cases in England who had been in recent contact with mental health services. Of 9752 suicides, 71 (1%) were being treated with ECT at the time of death. Although the number of patients who received ECT had fallen substantially over time, the rate of suicide in these individuals showed no clear decrease and averaged 9 deaths per year, or a rate of 10.8 per 10,000 patients treated. These suicide cases were typically older, with high rates of affective disorder and previous self-harm. They were more likely to be an in-patient at the time of death than other suicide cases. Nearly half of the community cases who had received ECT had died within 3 months of discharge. Our results demonstrated that the fall in the use of ECT has not affected suicide rates in patients receiving this treatment. Services appear to acknowledge the high risk of suicide in those receiving ECT. Improvements in care of these severely ill patients may include careful discharge planning and improved observation of in-patients in receipt of ECT.     

The accuracy of prevalence estimations for suicide attempts. how reliably do adolescents and young adults report their suicide attempts?

This study explores the accuracy of prevalence estimations for suicide attempts. Data came from the Early Developmental Stages of Psychopathology (EDSP) Study, a prospective community study (mean follow-up period was 42 months) of 3,021 respondents aged 14 to 24 years at the outset of the study. Suicide attempters are at least 1.6 times more likely to drop out than subjects with no suicide attempts and suicidal ideas. A total of 8% of all suicide attempters answered in the negative the depression-related gate questions of all surveys. One-third of all baseline suicide attempters did not report their suicide attempt again at the four years later assessment. In particular, 80% of all nonreporters were female, and almost 60% were aged 14-17 at baseline.     

Patterns of self-destructive behaviour in schizophrenia

Of 110 consecutive, young schizophrenic patients, 18 (16.4%) died during a follow-up period of 14-17 years from first admission. Fifteen of them met with a sudden death. Definite suicide was proven in 10 cases (9%). Suicide was associated with chronicity in course, social dependency, and lowered efficiency. Some type of warning was present in all suicide cases. The frequency of suicide thoughts and attempts was high in the whole material. Suicide attempts were associated with protracted non-regressive symptomatology, readmission to hospital, social intervention, and female sex. The disparity of characteristics between attempted suicide and definite suicide cases may partly be explained by the preponderance of women among the former and by the fact that only half of the suicidal deaths occurred when the frequency of attempts was at its peak. In attempted suicide in men their characteristics were compatible with those of the whole group, as well as with those of the suicide cases.     

Social environment factors associated with suicide attempt among low-income African Americans: The protective role of family relationships and social support

Abstract Background Suicide and suicide attempts are important public health concerns, and recent decades have witnessed a rising rate of suicide among African Americans. A history of prior attempts is a leading risk factor for completed suicide. Further research is needed into the social environment risk factors for suicide attempt among African Americans. This study focused on two important dimensions of the social environment, family relationships and social support, as well as an important person-level risk factor—depressive symptoms. Method Data were obtained from a case-control study of 200 African American men and women aged 18–64 years, who sought services at a large, urban, public hospital. Odds ratios adjusted for significant sociodemographic differences between groups (aORs) were calculated for environment risk factors for suicide attempt among the cases and controls. The role of depressive symptoms was also studied. Results Lower levels of family adaptability and family cohesion increased the relative rate of suicide attempt in the sample. The aOR associated with the lowest quartile of family adaptability was 3.90, and the aORs associated with the first and second quartiles of family cohesion were 8.91 and 5.51, respectively. Lower levels of social embeddedness and social support increased the relative rate of suicide attempt in our sample. The aOR associated with the first and second quartiles of social embeddedness were 5.67 and 4.93, respectively, and the aOR associated with the lowest quartile of social support was 6.29. A mediating role of depression was discovered when depressive symptoms were entered into the logistic regression models. Conclusions Our findings indicate that social environment factors including deficits in family functioning and social support are associated strongly with suicide attempts among low-income African American men and women seeking treatment in a large, urban hospital. Thus, better family functioning and social supports can be considered protective factors in this population. The presence of depressive symptoms, a well-known risk factor for suicide attempts and suicide, appears to mediate the association between social environment factors and suicide attempt.     

Gender and age differences among youth, in utilization of mental health services in the year preceding suicide in taiwan

The primary objective of this study was to explore gender and age differences in the use of medical services during the year preceding suicide. Data were obtained from the mortality dataset of Department of Health and National Health Insurance Database. Included in the sample were 862 persons aged 12-24?years who committed suicide in Taiwan between 2001 and 2004. We compared the records of medical service utilization of adolescents (ages 12-18?years) with young adults (ages 19-24?years). Persons in both age groups contacted general practitioners more often than other types of medical providers in the year preceding suicide, with the exception of the month before suicide. Females made greater use of medical services than males in both age groups. Suicide prevention strategies should increase the emphasis in training non-psychiatric medical practitioners to identify and treat young persons at suicide risk.     

The Accuracy of Prevalence Estimations for Suicide Attempts. How Reliably Do Adolescents and Young Adults Report Their Suicide Attempts?

This study explores the accuracy of prevalence estimations for suicide attempts. Data came from the Early Developmental Stages of Psychopathology (EDSP) Study, a prospective community study (mean follow-up period was 42 months) of 3,021 respondents aged 14 to 24 years at the outset of the study. Suicide attempters are at least 1.6 times more likely to drop out than subjects with no suicide attempts and suicidal ideas. A total of 8% of all suicide attempters answered in the negative the depression-related gate questions of all surveys. One-third of all baseline suicide attempters did not report their suicide attempt again at the four years later assessment. In particular, 80% of all nonreporters were female, and almost 60% were aged 14–17 at baseline.     

Antidepressant drug therapy and suicide in severely depressed children and adults: A case-control study

CONTEXT: The Food and Drug Administration has issued a boxed warning concerning increased suicidal ideation and behavior associated with antidepressant drug treatment in children and adolescents. It is unknown whether antidepressant agents increase the risk of suicide death in children or adults. OBJECTIVE: To estimate the relative risk of suicide attempt and suicide death in severely depressed children and adults treated with antidepressant drugs vs those not treated with antidepressant drugs. DESIGN: Matched case-control study. SETTING: Outpatient treatment settings in the United States. PARTICIPANTS: Medicaid beneficiaries from all 50 states who received inpatient treatment for depression, excluding patients treated for pregnancy, bipolar disorder, schizophrenia or other psychoses, mental retardation, dementia, or delirium. Controls were matched to cases for age, sex, race or ethnicity, state of residence, substance use disorder, recent suicide attempt, number of days since hospital discharge, and recent treatment with antipsychotic, anxiolytic/hypnotic, mood stabilizer, and stimulant medications. MAIN OUTCOME MEASURES: Suicide attempts and suicide deaths. RESULTS: In adults (aged 19-64 years), antidepressant drug treatment was not significantly associated with suicide attempts (odds ratio [OR], 1.10; 95% confidence interval [CI], 0.86-1.39 [521 cases and 2394 controls]) or suicide deaths (OR, 0.90; 95% CI, 0.52-1.55 [86 cases and 396 controls]). However, in children and adolescents (aged 6-18 years), antidepressant drug treatment was significantly associated with suicide attempts (OR, 1.52; 95% CI, 1.12-2.07 [263 cases and 1241 controls]) and suicide deaths (OR, 15.62; 95% CI, 1.65-infinity [8 cases and 39 controls]). CONCLUSIONS: In these high-risk patients, antidepressant drug treatment does not seem to be related to suicide attempts and death in adults but might be related in children and adolescents. These findings support careful clinical monitoring during antidepressant drug treatment of severely depressed young people.     

What is still missing in acute-phase treatment of stroke: a prospective observational study

Early recognition of stroke symptoms and activation of emergency medical service (EMS) positively affects prognosis after a stroke. To assess stroke awareness among stroke patients and medical personnel in the catchment area of Verona Hospital and how it affects stroke care, we prospectively studied timing of acute stroke care in relation to patients’ characteristics. Patients admitted to Medical Departments of Verona University Hospital between January 1st and December 31st 2009 with a diagnosis of TIA or stroke were enrolled. Outcome measures were: time between (i) symptoms onset and hospital arrival, (ii) hospital arrival and brain CT scan, blood examination, ECG and neurological evaluation. The following patient/event characteristics were also collected: means of hospital arrival, sex, age, degree of disability, type of event (first or recurrent) and acute-phase treatment. Of 578 patients providing complete information, 60 % arrived to the emergency department with the EMS (EMS+ group), while 40 % arrived on their own (EMS?). EMS+ group was older than EMS? (mean age 76.2, SD 13.2, vs. 72.3, SD 13, respectively), displayed more severe symptoms (mRS 4 vs. 2) and shorter time interval between symptoms onset and hospital arrival, hospital arrival and CT scan, ECG, laboratory tests and neurological evaluation (p < 0.0001); 22 % of the EMS+ patients were stroke recurrences versus 29 % of the EMS? (p = 0.058); 85 % of thrombolised patients were EMS+. We conclude that there is a lack of awareness of stroke symptoms and risks of recurrence even among patients who already had a stroke and among medical personnel.     

Chronic alcohol problems among suicide attempters--post-mortem findings of a 14-year follow-up

This study set out to describe the clinical characteristics of a subgroup of suicide attempters with clear post-mortem evidence of long-term alcohol misuse, and to investigate the risk factors predicting chronic alcohol misuse/dependence using survival analysis. Data were collected over 14 years on all unselected deliberate self-poisoning patients (n=1018) treated in the emergency unit of Helsinki University Central Hospital. Of the 222 (22.7%) who had died by the end of the follow-up period, 85 (38.5%) showed clear post-mortem evidence of long-term alcohol misuse. Seventy-four per cent of misusers were men. The risk factors for chronic alcohol misuse/dependence among deceased suicide attempters were: male sex, numerous previous suicide attempts, non-impulsive suicide attempts, certain intention to die and subjective motive of the index attempt other than "wish to die". The findings emphasize that more attention should be focused on evaluating alcohol use and the risk of alcohol dependence in suicide attempters encountered in the emergency room of general hospitals.     

Pattern and risk factors for intentional drug overdose in Saudi Arabia.

BACKGROUND: Attempted suicide by intentional drug overdose is an understudied subject in Saudi Arabia. Saudi Arabia is an Islamic country where suicide or attempted suicide is strictly prohibited. Despite the strong religious and constitutional sanctions against suicide, cases of intentional drug overdose occasionally occur. Our study represents the first attempt to better understand and characterize this sensitive topic. METHODS: Using a retrospective chart review of patients aged 12 years and over with a diagnosis of intentional drug overdose between 1997 and 1999, we studied the demographic characteristics, the risk factors, the most commonly used drugs, and the resulting morbidities and mortalities of study subjects. RESULTS: Most of the patients were young (mean age 22 years, SD 4.6, range 15 to 40 years), and most were Saudi nationals (n = 76; 96%). Eighty percent of the patients were women. The occurrence of intentional drug overdose peaked during the month of September (that is, 20% of total cases). Previous suicide attempts, family conflicts, and psychiatric disorders represented significant risk factors. Single-agent overdose occurred in 30% of the patients, and most of the drugs used were prescribed medications (53%). Acetaminophen represented the most common drug (30%). While some patients required prolonged hospital stay or admission to the intensive care unit, no mortalities occurred. CONCLUSIONS: Intentional drug overdose is a relatively uncommon reason for hospital admission in Saudi Arabia. This study identifies certain risk factors relevant to the Saudi community and raises awareness about intentional drug overdose.     

Le suicide de patients hospitalisés en psychiatrie : analyse qualitative de huit cas à l’hôpital Sainte-Anne à Paris et recommandations

Inpatient suicide rates are high at the psychiatric hospital. Improvement in detecting suicidal patients and preventing suicidal acts during hospitalization is essential. As part of a working group on the evaluation of professional practices on suicide risk at Sainte-Anne Hospital in Paris, we retrospectively studied eight cases of inpatient suicides that occurred between 2009 and 2018. We conducted a qualitative analysis of multidisciplinary morbidity and mortality reviews and medical records data. In our case series, all patients had a personal history of suicide attempts (notably using a violent means), and half of them previously attempted suicide during hospitalization. In most cases, suicide occurred during weekends or public holidays and inside care units. Suicide by hanging was the most prevalent method. Regarding our results and the literature, a past personal suicide attempt is the most frequent risk factor for inpatient suicide. However, prediction of suicide remains weak and all psychiatric inpatients should be considered at significant risk of suicide during hospitalization and just after discharge. Inpatient suicide prevention is primarily based on a safer hospital environment (inventory at entry, anti-suicidal furniture, no height access and windows opening, etc.). In addition, specific and repeated suicide training for care teams, continuity of care, enhanced management with assessment and monitoring protocols, good teamwork communication and better traceability of suicide risk in records appear to be organizational requirements for inpatient suicide prevention. At the individual level, quality of contacts with the patient, interactions with relatives and significant others, and active treatment of psychiatric disorders and comorbidities are fundamental. After a suicide or suicide attempt at the hospital, experience sharing should be systematically put into place to improve care practices. The implementation of postvention measures with the aim to support other patients and caregivers in the affected medical unit, as well as the victim's relatives, should complete the actions to lead.     

Psychiatric emergencies in preclinical emergency service; incidence, treatment and evaluation by emergency physicians and staff

Preclinical psychiatric emergency situations (PES) rank third in frequency of calls in the German emergency medical system (EMS). However, few data exist concerning relevance and treatment of PES. The aim of this study was to investigate this relevance in preclinical EMS and its appraisal by emergency physicians and paramedics. The protocols filled in by EMS physicians on emergency duty in a German district were evaluated concerning PES. In addition, the emergency physicians and paramedics of the district were asked to complete a validated questionnaire concerning the importance, their own understanding of PES, and interest in training programs. With 9.2%, preclinical PES ranked third in frequency of all EMS calls. The most frequent case was substance abuse disorder (70%), followed by suicide attempts or ideation (33%). Specific therapy for psychiatric disorders is hardly ever performed. Emergency physicians and paramedics estimated the importance of knowledge about PES as high but rated their own knowledge as poor. Assessing five typical PES, emergency physicians gave the correct diagnoses in 71% of cases (paramedics 39%) and the correct therapy in 32% (paramedics 14%). The interest in training programs was significantly higher in experienced EMS physicians. Preclinical PES is a relevant diagnosis within EMS and correct treatment is hampered by limited knowledge. Sufficient training is not yet available, although programs are necessary and the willingness to participate in them is high.     

Recommended care for young people (15–19 years) after suicide attempts in certain European countries

Data on recommended care for young people aged 15–19 years after attempted suicide from nine European research centres during the period 1989–1992 were analysed in terms of gender, history of previous suicide attempt and methods used. Altogether 438 suicide attempts made by 353 boys and 1,102 suicide attempts made by 941 girls were included. Analyses of the total data from all centres showed that young people with a history of previous suicide attempt and those using violent methods had significantly higher chance of being recommended aftercare than first-time attempters or those choosing self-poisoning. There were no significant differences of being recommended care between genders. Logistic regression analyses of the material were performed and the results were similar. Both having previous attempted suicide (odds ratio 2.0, 95% CI 1.53–2.61) and using “hard” methods (odds ratio 1.71, 95% CI 1.49–1.96) were significantly associated with increased possibility of being recommended aftercare. When individual centres were analysed, large disparities of recommended care after suicide attempts were found and there were no uniform criteria of recommending care for young suicide attempters in Europe. Accepted: 23 August 1999     

Use of emergency department electronic medical records for automated epidemiological surveillance of suicide attempts: a French pilot study

The aim of this study was to determine whether an expert system based on automated processing of electronic health records (EHRs) could provide a more accurate estimate of the annual rate of emergency department (ED) visits for suicide attempts in France, as compared to the current national surveillance system based on manual coding by emergency practitioners. A feasibility study was conducted at Lyon University Hospital, using data for all ED patient visits in 2012. After automatic data extraction and pre‐processing, including automatic coding of medical free‐text through use of the Unified Medical Language System, seven different machine‐learning methods were used to classify the reasons for ED visits into “suicide attempts“ versus “other reasons“. The performance of these different methods was compared by using the F‐measure. In a test sample of 444 patients admitted to the ED in 2012 (98 suicide attempts, 48 cases of suicidal ideation, and 292 controls with no recorded non‐fatal suicidal behaviour), the F‐measure for automatic detection of suicide attempts ranged from 70.4% to 95.3%. The random forest and naïve Bayes methods performed best. This study demonstrates that machine‐learning methods can improve the quality of epidemiological indicators as compared to current national surveillance of suicide attempts.