Multi-level modeling with nonlinear movement metrics to classify self-injurious behaviors in autism spectrum disorder.

Self-injurious behavior (SIB) is among the most dangerous concerns in autism spectrum disorder (ASD), often requiring detailed and tedious management methods. Sensor-based behavioral monitoring could address the limitations of these methods, though the complex problem of classifying variable behavior should be addressed first. We aimed to address this need by developing a group-level model accounting for individual variability and potential nonlinear trends in SIB, as a secondary analysis of existing data. Ten participants with ASD and SIB engaged in free play while wearing accelerometers. Movement data were collected from > 200 episodes and 18 different types of SIB. Frequency domain and linear movement variability measures of acceleration signals were extracted to capture differences in behaviors, and metrics of nonlinear movement variability were used to quantify the complexity of SIB. The multi-level logistic regression model, comprising of 12 principal components, explained > 65% of the variance, and classified SIB with > 75% accuracy. Our findings imply that frequency-domain and movement variability metrics can effectively predict SIB. Our modeling approach yielded superior accuracy than commonly used classifiers (~ 75 vs. ~ 64% accuracy) and had superior performance compared to prior reports (~ 75 vs. ~ 69% accuracy) This work provides an approach to generating an accurate and interpretable group-level model for SIB identification, and further supports the feasibility of developing a real-time SIB monitoring system.

Detecting and Classifying Self-injurious Behavior in Autism Spectrum Disorder Using Machine Learning Techniques.

Traditional self-injurious behavior (SIB) management can place compliance demands on the caregiver and have low ecological validity and accuracy. To support an SIB monitoring system for autism spectrum disorder (ASD), we evaluated machine learning methods for detecting and distinguishing diverse SIB types. SIB episodes were captured with body-worn accelerometers from children with ASD and SIB. The highest detection accuracy was found with k-nearest neighbors and support vector machines (up to 99.1% for individuals and 94.6% for grouped participants), and classification efficiency was quite high (offline processing at ~ 0.1 ms/observation). Our results provide an initial step toward creating a continuous and objective smart SIB monitoring system, which could in turn facilitate the future care of a pervasive concern in ASD.

Suicidal and self-harm presentations to Emergency Departments: The challenges of identification through diagnostic codes and presenting complaints.

BACKGROUND: The accuracy of data on suicide-related presentations to Emergency Departments (EDs) has implications for the provision of care and policy development, yet research on its validity is scarce. OBJECTIVE: To test the reliability of allocation of ICD-10 codes assigned to suicide and self-related presentations to EDs in Queensland, Australia. METHOD: All presentations due to suicide attempts, non-suicidal self-injury (NSSI) and suicidal ideation between 1 July 2017 and 31 December 2017 were reviewed. The number of presentations identified through relevant ICD-10-AM codes and presenting complaints in the Emergency Department Information System were compared to those identified through an application of an evolutionary algorithm and medical record review (gold standard). RESULTS: A total of 2540 relevant presentations were identified through the gold standard methodology. Great heterogeneity of ICD-10-AM codes and presenting complaints was observed for suicide attempts (40 diagnostic codes and 27 presenting complaints), NSSI (27 and 16, respectively) and suicidal ideation (38 and 34, respectively). Relevant ICD codes applied as primary or secondary diagnosis had very low sensitivity in detecting cases of suicide attempts (18.7%), NSSI (38.5%) and suicidal ideation (42.3%). A combination of ICD-10-AM code and a relevant presenting complaint increased specificity, however substantially reduced specificity and positive predictive values for all types of presentations. ED data showed bias in detecting higher percentages of suicide attempts by Indigenous persons (10.1% vs. 6.9%) or by cutting (28.1% vs. 10.3%), and NSSI by female presenters (76.4% vs. 67.4%). CONCLUSION: Suicidal and self-harm presentations are grossly under-enumerated in ED datasets and should be used with caution until a more standardised approach to their formulation and recording is implemented.

Imputation and characterization of uncoded self-harm in major mental illness using machine learning.

OBJECTIVE: We aimed to impute uncoded self-harm in administrative claims data of individuals with major mental illness (MMI), characterize self-harm incidence, and identify factors associated with coding bias. MATERIALS AND METHODS: The IBM MarketScan database (2003-2016) was used to analyze visit-level self-harm in 10 120 030 patients with ≥2 MMI codes. Five machine learning (ML) classifiers were tested on a balanced data subset, with XGBoost selected for the full dataset. Classification performance was validated via random data mislabeling and comparison with a clinician-derived "gold standard." The incidence of coded and imputed self-harm was characterized by year, patient age, sex, U.S. state, and MMI diagnosis. RESULTS: Imputation identified 1 592 703 self-harm events vs 83 113 coded events, with areas under the curve >0.99 for the balanced and full datasets, and 83.5% agreement with the gold standard. The overall coded and imputed self-harm incidence were 0.28% and 5.34%, respectively, varied considerably by age and sex, and was highest in individuals with multiple MMI diagnoses. Self-harm undercoding was higher in male than in female individuals and increased with age. Substance abuse, injuries, poisoning, asphyxiation, brain disorders, harmful thoughts, and psychotherapy were the main features used by ML to classify visits. DISCUSSION: Only 1 of 19 self-harm events was coded for individuals with MMI. ML demonstrated excellent performance in recovering self-harm visits. Male individuals and seniors with MMI are particularly vulnerable to self-harm undercoding and may be at risk of not getting appropriate psychiatric care. CONCLUSIONS: ML can effectively recover unrecorded self-harm in claims data and inform psychiatric epidemiological and observational studies.

Contemporary Classifications of Suicidal Behaviors.

Background: The absence of agreed-upon terminology, definitions, and operational classifications has hampered research in the field of suicidology for many decades. Aims and Method: We systematically reviewed contemporary classifications of suicidal behavior using the scope of the classification (comprehensive vs. restricted or single behaviors), and the presence or absence of a classification scheme and an operational definition of intent as features to enable analysis and comparison. Results: A chronological perspective shows that classification systems tend to be more and more precise and operational for clinical and research field work. However, on an international level, the development of classifications appears to precede the establishment of agreed-upon definitions and terms to describe suicidal behavior. Limitations: The review was conducted in English only. Conclusion: Universal agreement on definitions and terms for suicidal behavior should precede the development of classifications.

Development and Factorial Validation of the Inventory of Deliberate Self-Harm Behaviours for Portuguese Adolescents.

Deliberate self-harm (DSH) is a public health problem that mainly affects adolescents and young adults. Evidence suggests that multiple methods are used with a self-aggressive intent. The present article focuses on the development and factorial validation of the Inventory of Deliberate Self-harm Behaviours for Portuguese adolescents. This instrument assesses the lifetime frequency of 13 DSH methods, with and without suicidal intent. Study 1 consisted of an exploratory factor analysis with a sample of 131 adolescents with a reported history of DSH. Results revealed a three-factor structure with acceptable internal consistency: High Severity DSH, Mild Severity DSH, and Substance Use DSH. After item reduction, this structure was tested in Study 2 through a confirmatory factor analysis with an independent sample of 109 adolescents also with a history of DSH. Results showed an acceptable model fit. This instrument presents a solid structure and acceptable psychometric properties, allowing its use in further research.

Reconsidering important outcomes of the nonsuicidal self-injury disorder diagnostic criterion A.

OBJECTIVE: The nonsuicidal self-injury (NSSI) disorder diagnostic criteria have been the focus of empirical study. However, Criterion A (i.e., required frequency and timeframe) has received relatively limited attention. The current study aimed to examine the relationship between past 12-month NSSI frequency and eight NSSI behavior features among individuals with past 12-month and 1-month NSSI. METHOD: Participants were 723 undergraduate students reporting at least 1 past 12-month NSSI act and completed online questionnaires. Decision trees and structural equation model trees were utilized to examine the relationship between NSSI frequency and behavior features. RESULTS: Results highlight several potential subgroups: high (i.e., greater than 49 acts), moderate-to-high (i.e., 19-48 acts), low-to-moderate (i.e., 7-18 acts), and low (i.e., fewer than 6 acts) frequency subgroups. CONCLUSIONS: Findings suggest that increasing the NSSI disorder criterion A frequency cutoff or requiring at least one past month NSSI act may better demarcate individuals with more severe NSSI behavior.

Deliberate Self-Harm in Psychiatric Outpatients Aged 14-35 Years in Singapore.

INTRODUCTION: The main aim of the study was to identify the prevalence of deliberate self-harm (DSH) in a sample of youth outpatients attending the state psychiatric hospital in Singapore and to identify the sociodemographic and psychological/clinical risk factors associated with DSH. The secondary aim of  the study was to examine if different forms of DSH had distinguishing risk factors. MATERIALS AND METHODS: A total of 400 outpatients at the Institute of Mental Health completed a self-report survey comprising sociodemographic questions, the Functional Assessment of  Self-Mutilation, Childhood Trauma Questionnaire, Parental Bonding Instrument and the Patient Health Questionnaire Depression Scale. Logistic regression models were used to test the associations. RESULTS: The overall prevalence of DSH in our clinical population was 58.8%. Cutting/carving (25.4%) and hitting (20.4%) were the most common forms of DSH in the past 12 months. DSH acts were performed primarily for emotion regulation purposes. The risk factors for DSH in general were younger age group, female gender, abuse history and higher depression scores. Gender and age group were the factors that were differentially associated with cutting and hitting one's self. CONCLUSION: There was a high prevalence of DSH in the psychiatric outpatient population. The risk factors identified in this study are consistent with those of international studies which point to their stability across cultures.

Classification of injuries observed in functional classes of self-injurious behaviour.

BACKGROUND: Limited research has examined how the functions of self-injurious behaviour (SIB) relate to the production of injuries and the location, type or severity of those injuries. METHODS: Clinical and medical records were coded for 64 individuals hospitalised for SIB. When injuries were present, the physical properties of SIB and injuries were assessed across groups of individuals with automatically and socially maintained SIB. RESULTS: Injuries were observed for 35 of the individuals who engaged in SIB. Individuals who engaged in a single form of SIB were more likely to have injuries (P < .05). Individuals with SIB maintained by automatic reinforcement had significantly more severe injuries to the head than those in the social group (q < .05, P = .0132, H = 12.54). CONCLUSION: Although results are preliminary, the results provide evidence that the function of SIB may influence the severity and location of injuries produced.

Issues in Developing a Surveillance Case Definition for Nonfatal Suicide Attempt and Intentional Self-harm Using International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) Coded Data.

Suicide and intentional self-harm are among the leading causes of death in the United States. To study this public health issue, epidemiologists and researchers often analyze data coded using the International Classification of Diseases (ICD). Prior to October 1, 2015, health care organizations and providers used the clinical modification of the Ninth Revision of ICD (ICD-9-CM) to report medical information in electronic claims data. The transition in October 2015 to use of the clinical modification of the Tenth Revision of ICD (ICD-10-CM) resulted in the need to update methods and selection criteria previously developed for ICD-9-CM coded data. This report provides guidance on the use of ICD-10-CM codes to identify cases of nonfatal suicide attempts and intentional self-harm in ICD-10-CM coded data sets. ICD-10-CM codes for nonfatal suicide attempts and intentional self-harm include: X71-X83, intentional self-harm due to drowning and submersion, firearms, explosive or thermal material, sharp or blunt objects, jumping from a high place, jumping or lying in front of a moving object, crashing of motor vehicle, and other specified means; T36-T50 with a 6th character of 2 (except for T36.9, T37.9, T39.9, T41.4, T42.7, T43.9, T45.9, T47.9, and T49.9, which are included if the 5th character is 2), intentional self-harm due to drug poisoning (overdose); T51-T65 with a 6th character of 2 (except for T51.9, T52.9, T53.9, T54.9, T56.9, T57.9, T58.0, T58.1, T58.9, T59.9, T60.9, T61.0, T61.1, T61.9, T62.9, T63.9, T64.0, T64.8, and T65.9, which are included if the 5th character is 2), intentional self-harm due to toxic effects of nonmedicinal substances; T71 with a 6th character of 2, intentional self-harm due to asphyxiation, suffocation, strangulation; and T14.91, Suicide attempt. Issues to consider when selecting records for nonfatal suicide attempts and intentional self-harm from ICD-10-CM coded administrative data sets are also discussed.

Autolesiones sin finalidad autolítica: una revisión sistemática en adolescentes de la comunidad / Non-suicidal self-injury: a systematic review

El objetivo de este artículo es presentar una revisión de la investigación existente sobre las autolesiones no suicidas (ANS) en población comunitaria adolescente. Las ANS son un fenómeno tan común entre los adolescentes que se han propuesto como potencial trastorno independiente. Los rangos prevalencia están entre el 4,8 y el 28 %, con una edad de inicio entre los 12 y los 15 años. Su presencia se acompaña de diversos trastornos además del Trastorno Límite de Personalidad (TLP). Las experiencias adversas en la infancia así como factores internos son potentes factores de riesgo

The aim of this article is to present a review of the existing research on Non-suicidal self-injury (NSSI) in adolescents. NSSI is such a common phenomenon among adolescents that it has been proposed to be treated as a potential independent disorder. The prevalence ranges are between 4.8 and 28%, with the age range between 12 and 15 years. It occurs together with Borderline Personality Disorder (BPD) and other types of disorders in addition to this. Both adverse experiences in childhood and internal factors are potent risk factors

L'objectiu d'aquest article és presentar una revisió de la investigació existent sobre les autolesions no suïcides (ANS) en població comunitària adolescent. Les ANS són un fenomen tan comú entre els adolescents que s'han proposat com a potencial trastorn independent. Els rangs de prevalença estan entre el 4,8 I el 28 %, amb una edat d'inici entre els 12 I els 15 anys. La seva preséncia s'acompanya de diversos trastorns, a banda del trastorn límit de la personalitat (TLP). Les experiències adverses en la infantesa, així com factors interns, són potents factors de risc

Method of self-harm in adolescents and young adults and risk of subsequent suicide.

BACKGROUND: Self-harm is common in youth and an important risk factor for suicide. Certain self-harm methods might indicate a higher risk of suicide. The main aim of this study was to determine whether some methods of self-harm in adolescents (10-17 years) and young adults (18-24 years) are associated with a particularly high risk of suicide. A secondary aim was to ascertain how different self-harm methods might affect the probability of psychiatric follow-up. METHOD: Five Swedish registers were linked in a national population-based cohort study. All nonfatal self-harm events recorded in specialist health care, excluding psychiatry and primary care services, among 10-24 year olds between 2000 and 2009 were included. Methods were classified as poisoning, cutting/piercing, violent method (gassing, hanging, strangulation/suffocation, drowning, jumping and firearms), other and multiple methods. Hazard Ratios (HR) for suicide were calculated in Cox regression models for each method with poisoning as the reference. Odds Ratios (OR) for psychiatric inpatient care were determined in logistic regression models. Analyses were adjusted for important covariates and stratified by age group and treatment setting (inpatient/outpatient). RESULTS: Among adolescents with initial medical hospitalisation, use of a violent method was associated with a near eightfold increase in HR for suicide compared to self-poisoning in the adjusted analysis [HR 7.8; 95% confidence interval (CI) 3.2-19.0]. Among hospitalised young adult women, adjusted HRs were elevated fourfold for both cutting [4.0 (1.9-8.8)] and violent methods [3.9 (1.5-10.6)]. Method of self-harm did not affect suicide risk in young adult men. Adolescents using violent methods had an increased probability of psychiatric inpatient care following initial treatment for self-harm. CONCLUSIONS: Violent self-harm requiring medical hospitalisation may signal particularly high risk of future suicide in adolescents (both sexes) and in young adult women. For the latter group this is the case for cutting requiring hospitalisation as well.

Indirect self-destructiveness in individuals with schizophrenia

Objective: To explore the indirect self-destructiveness syndrome in patients with schizophrenia. Methods: Two hundred individuals with paranoid schizophrenia (117 men and 83 women, mean age 37.15 years), all in remission, were examined using the Polish version of the Chronic Self-Destructiveness Scale. Two hundred well-matched healthy individuals served as a control group. Results: The intensity of indirect self-destructiveness was greater in the schizophrenia group than in controls. The intensity of each manifestation was as follows (in decreasing order): helplessness and passiveness in the face of difficulties (A5), personal and social neglects (A3), lack of planfulness (A4), poor health maintenance (A2), transgression and risk (A1). Conclusion: Patients with schizophrenia displayed more behaviors that were indirectly self-destructive than healthy controls; they scored better than healthy controls only on caring for their own health. The patients showed the lowest intensity of behaviors connected with the active form of indirect self-destructiveness, and the highest intensity of behaviors connected with the passive form. These findings may enable delivery of more effective forms of pharmacological and psychosocial help to patients with schizophrenia.

Blurred Boundaries - A Qualitative Study of How Acts of Self-Harm and Attempted Suicide Are Defined by Mental Health Practitioners.

BACKGROUND: There is no commonly accepted definition of the term self-harm, and there is an ongoing debate about whether or not it should include acts of attempted suicide. The use of this language in clinical practice has not previously been explored. AIMS: To investigate if, and how, practitioners distinguish between acts of self-harm and attempted suicide, and present any implications for practice. METHOD: We conducted semistructured interviews with a random sample of 18 frontline practitioners from 10 mental health wards and completed a thematic analysis of interview data. RESULTS: Most participants described self-harm and attempted suicide as distinct behaviors. Characteristics of the act, disclosures of intent, and the level of distress observed were commonly used to differentiate between self-harm and attempted suicide. Very few participants believed that people who self-harm may also feel suicidal. Practitioners confidently described two different behaviors, yet self-harm and attempted suicide were often conflated, revealing the challenges and complexities associated with the separation of these acts in clinical practice. LIMITATIONS: Clinicians working in other settings or disciplines may have different views. Participants' accounts may not be an accurate representation of what happens in practice. CONCLUSION: This study adds to a body of evidence which argues against the dichotomous separation of these behaviors into acts of suicidal and nonsuicidal self-harm.Our findings suggest there is no common understanding of the boundaries between self-harm and attempted suicide among frontline clinicians. The language currently used, and consequent practice, particularly with regard to risk assessment, is problematic. Efforts should be made to operationalize terms around suicidal behavior and to incorporate these into training for clinical staff.

Indirect self-destructiveness in individuals with schizophrenia.

OBJECTIVE: To explore the indirect self-destructiveness syndrome in patients with schizophrenia. METHODS: Two hundred individuals with paranoid schizophrenia (117 men and 83 women, mean age 37.15 years), all in remission, were examined using the Polish version of the Chronic Self-Destructiveness Scale. Two hundred well-matched healthy individuals served as a control group. RESULTS: The intensity of indirect self-destructiveness was greater in the schizophrenia group than in controls. The intensity of each manifestation was as follows (in decreasing order): helplessness and passiveness in the face of difficulties (A5), personal and social neglects (A3), lack of planfulness (A4), poor health maintenance (A2), transgression and risk (A1). CONCLUSION: Patients with schizophrenia displayed more behaviors that were indirectly self-destructive than healthy controls; they scored better than healthy controls only on caring for their own health. The patients showed the lowest intensity of behaviors connected with the active form of indirect self-destructiveness, and the highest intensity of behaviors connected with the passive form. These findings may enable delivery of more effective forms of pharmacological and psychosocial help to patients with schizophrenia.

Developmental Trajectories of Nonsuicidal Self-Injury in Adolescence and Intrapersonal/Interpersonal Risk Factors.

This 3-wave study investigated the developmental trajectories of nonsuicidal self-injury (NSSI) and intrapersonal/interpersonal risk factors among 3,381 Chinese adolescents (56.2% females) aged from 13 to 17 years during a 1-year period. Using an accelerated longitudinal design and latent class growth analysis, we identified four subgroups of NSSI trajectories: negligible (74.6%), experimental (12.8%), moderate decreasing (10.8%), and high fluctuating (1.9%). Adolescents reporting both intrapersonal (i.e., impulsive behaviors and depression) and interpersonal (i.e., unstable relationships and parental criticism) risk factors were significantly more likely to follow the latter three trajectories. The findings of this study suggest there is heterogeneity in NSSI development among adolescents and highlight the contributions of both intrapersonal and interpersonal risk factors in the engagement in NSSI.

Self-injury - placement in mental disorders classifications, risk factors and primary mechanisms. Review of the literature. / Samouszkodzenia ­ miejsce w klasyfikacjach zaburzen psychicznych, czynniki ryzyka i mechanizmy ksztaltujace. Przeglad badan.

Self-injury is a common phenomenon among adolescents and young adults, however its prevalence in clinical population is estimated at 40-80%, especially in regard to patients during puberty. Symptoms usually appear between 12th and 14th year of age, and their average duration is approx. 2 years. According to accepted sociocultural norms self-injury can be regarded as a normal behavior. Nevertheless, the prevalence of body art phenomenon in Western culture including professional tattooing, piercing, scarification, burning tattoos and other body modification typical for tribal cultures, has forced the need to redefine the boundaries for normative behavior. Introduction of a separate nosological unit of Non-Suicidal Self Injury in the fifth edition of DSM classification proves the validity of discussion, being hold for many years, regarding classification and understanding of the underlying mechanisms of self-harm. The aim of our study was to present the current state of knowledge regarding self-harm, with an emphasis on issues devoted to their placement in newest mental disorders classifications and mechanisms responsible for their development and maintenance. Databases such as: PubMed, EBSCO (medical and psychological resources) and WEB OF SCIENCE (years 1990-2016) have been screened for the following key words: self-injury, self-harm, self-mutilation, suicide, deliberate self-harm, affect regulation, NSSI, DSH, personality disorders, suicide attempt, neurobiology self-harm, DSM-5, adolescent, adults, stress coping styles, self-mutilation - children, adolescents and adults-prevalence. The analysis indicated 110 articles and 3 textbooks. We have used the following criteria: (1) for the articles presenting the latest research on risk factors for self-harm we have used the criterion of the study group number (>30 people) and meta-analyses have been included, (2) for theories explaining the mechanisms of self-harm criterion of empirical review of the assumptions and the number of the published studies that verify the theory has been applied.