Dataset Information

Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study.

ABSTRACT: BACKGROUND:Vast numbers of domestic violence (DV) incidents are attended by the New South Wales Police Force each year in New South Wales and recorded as both structured quantitative data and unstructured free text in the WebCOPS (Web-based interface for the Computerised Operational Policing System) database regarding the details of the incident, the victim, and person of interest (POI). Although the structured data are used for reporting purposes, the free text remains untapped for DV reporting and surveillance purposes. OBJECTIVE:In this paper, we explore whether text mining can automatically identify mental health disorders from this unstructured text. METHODS:We used a training set of 200 DV recorded events to design a knowledge-driven approach based on lexical patterns in text suggesting mental health disorders for POIs and victims. RESULTS:The precision returned from an evaluation set of 100 DV events was 97.5% and 87.1% for mental health disorders related to POIs and victims, respectively. After applying our approach to a large-scale corpus of almost a half million DV events, we identified 77,995 events (15.83%) that mentioned mental health disorders, with 76.96% (60,032/77,995) of those linked to POIs versus 16.47% (12,852/77,995) for the victims and 6.55% (5111/77,995) for both. Depression was the most common mental health disorder mentioned in both victims (22.25%, 3269) and POIs (18.70%, 8944), followed by alcohol abuse for POIs (12.19%, 5829) and various anxiety disorders (eg, panic disorder, generalized anxiety disorder) for victims (11.66%, 1714). CONCLUSIONS:The results suggest that text mining can automatically extract targeted information from police-recorded DV events to support further public health research into the nexus between mental health disorders and DV.

SUBMITTER: Karystianis G

PROVIDER: S-EPMC6231811 | biostudies-other | 2018 Sep

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study.

Karystianis George G Adily Armita A Schofield Peter P Schofield Peter P Knight Lee L Galdon Clara C Greenberg David D Jorm Louisa L Nenadic Goran G Butler Tony T

Journal of medical Internet research 20180913 9

<h4>Background</h4>Vast numbers of domestic violence (DV) incidents are attended by the New South Wales Police Force each year in New South Wales and recorded as both structured quantitative data and unstructured free text in the WebCOPS (Web-based interface for the Computerised Operational Policing System) database regarding the details of the incident, the victim, and person of interest (POI). Although the structured data are used for reporting purposes, the free text remains untapped for DV r ...[more]

PMID: 30213778

Similar Datasets

Project description:BACKGROUND:The police attend numerous domestic violence events each year, recording details of these events as both structured (coded) data and unstructured free-text narratives. Abuse types (including physical, psychological, emotional, and financial) conducted by persons of interest (POIs) along with any injuries sustained by victims are typically recorded in long descriptive narratives. OBJECTIVE:We aimed to determine if an automated text mining method could identify abuse types and any injuries sustained by domestic violence victims in narratives contained in a large police dataset from the New South Wales Police Force. METHODS:We used a training set of 200 recorded domestic violence events to design a knowledge-driven approach based on syntactical patterns in the text and then applied this approach to a large set of police reports. RESULTS:Testing our approach on an evaluation set of 100 domestic violence events provided precision values of 90.2% and 85.0% for abuse type and victim injuries, respectively. In a set of 492,393 domestic violence reports, we found 71.32% (351,178) of events with mentions of the abuse type(s) and more than one-third (177,117 events; 35.97%) contained victim injuries. "Emotional/verbal abuse" (33.46%; 117,488) was the most common abuse type, followed by "punching" (86,322 events; 24.58%) and "property damage" (22.27%; 78,203 events). "Bruising" was the most common form of injury sustained (51,455 events; 29.03%), with "cut/abrasion" (28.93%; 51,284 events) and "red marks/signs" (23.71%; 42,038 events) ranking second and third, respectively. CONCLUSIONS:The results suggest that text mining can automatically extract information from police-recorded domestic violence events that can support further public health research into domestic violence, such as examining the relationship of abuse types with victim injuries and of gender and abuse types with risk escalation for victims of domestic violence. Potential also exists for this extracted information to be linked to information on the mental health status.

Project description:Family and Domestic violence (FDV) is a global problem with significant social, economic, and health consequences for victims including increased health care costs, mental trauma, and social stigmatization. In Australia, the estimated annual cost of FDV is $22 billion, with one woman being murdered by a current or former partner every week. Despite this, tools that can predict future FDV based on the features of the person of interest (POI) and victim are lacking. The New South Wales Police Force attends thousands of FDV events each year and records details as fixed fields (e.g., demographic information for individuals involved in the event) and as text narratives which describe abuse types, victim injuries, threats, including the mental health status for POIs and victims. This information within the narratives is mostly untapped for research and reporting purposes. After applying a text mining methodology to extract information from 492,393 FDV event narratives (abuse types, victim injuries, mental illness mentions), we linked these characteristics with the respective fixed fields and with actual mental health diagnoses obtained from the NSW Ministry of Health for the same cohort to form a comprehensive FDV dataset. These data were input into five deep learning models (MLP, LSTM, Bi-LSTM, Bi-GRU, BERT) to predict three FDV offense types ("hands-on," "hands-off," "Apprehended Domestic Violence Order (ADVO) breach"). The transformer model with BERT embeddings returned the best performance (69.00% accuracy; 66.76% ROC) for "ADVO breach" in a multilabel classification setup while the binary classification setup generated similar results. "Hands-off" offenses proved the hardest offense type to predict (60.72% accuracy; 57.86% ROC using BERT) but showed potential to improve with fine-tuning of binary classification setups. "Hands-on" offenses benefitted least from the contextual information gained through BERT embeddings in which MLP with categorical embeddings outperformed it in three out of four metrics (65.95% accuracy; 78.03% F1-score; 70.00% precision). The encouraging results indicate that future FDV offenses can be predicted using deep learning on a large corpus of police and health data. Incorporating additional data sources will likely increase the performance which can assist those working on FDV and law enforcement to improve outcomes and better manage FDV events.

Project description:BackgroundFor ecological studies, it is crucial to count on adequate descriptions of the environments and samples being studied. Such a description must be done in terms of their physicochemical characteristics, allowing a direct comparison between different environments that would be difficult to do otherwise. Also the characterization must include the precise geographical location, to make possible the study of geographical distributions and biogeographical patterns. Currently, there is no schema for annotating these environmental features, and these data have to be extracted from textual sources (published articles). So far, this had to be performed by manual inspection of the corresponding documents. To facilitate this task, we have developed EnvMine, a set of text-mining tools devoted to retrieve contextual information (physicochemical variables and geographical locations) from textual sources of any kind.ResultsEnvMine is capable of retrieving the physicochemical variables cited in the text, by means of the accurate identification of their associated units of measurement. In this task, the system achieves a recall (percentage of items retrieved) of 92% with less than 1% error. Also a Bayesian classifier was tested for distinguishing parts of the text describing environmental characteristics from others dealing with, for instance, experimental settings.Regarding the identification of geographical locations, the system takes advantage of existing databases such as GeoNames to achieve 86% recall with 92% precision. The identification of a location includes also the determination of its exact coordinates (latitude and longitude), thus allowing the calculation of distance between the individual locations.ConclusionEnvMine is a very efficient method for extracting contextual information from different text sources, like published articles or web pages. This tool can help in determining the precise location and physicochemical variables of sampling sites, thus facilitating the performance of ecological analyses. EnvMine can also help in the development of standards for the annotation of environmental features.

Project description:Unstructured clinical narratives are continuously being recorded as part of delivery of care in electronic health records, and dedicated tagging staff spend considerable effort manually assigning clinical codes for billing purposes. Despite these efforts, however, label availability and accuracy are both suboptimal. In this retrospective study, we aimed to automate the assignment of top-level International Classification of Diseases version 9 (ICD-9) codes to clinical records from human and veterinary data stores using minimal manual labor and feature curation. Automating top-level annotations could in turn enable rapid cohort identification, especially in a veterinary setting. To this end, we trained long short-term memory (LSTM) recurrent neural networks (RNNs) on 52,722 human and 89,591 veterinary records. We investigated the accuracy of both separate-domain and combined-domain models and probed model portability. We established relevant baseline classification performances by training Decision Trees (DT) and Random Forests (RF). We also investigated whether transforming the data using MetaMap Lite, a clinical natural language processing tool, affected classification performance. We showed that the LSTM-RNNs accurately classify veterinary and human text narratives into top-level categories with an average weighted macro F1 score of 0.74 and 0.68 respectively. In the "neoplasia" category, the model trained on veterinary data had a high validation accuracy in veterinary data and moderate accuracy in human data, with F1 scores of 0.91 and 0.70 respectively. Our LSTM method scored slightly higher than that of the DT and RF models. The use of LSTM-RNN models represents a scalable structure that could prove useful in cohort identification for comparative oncology studies. Digitization of human and veterinary health information will continue to be a reality, particularly in the form of unstructured narratives. Our approach is a step forward for these two domains to learn from and inform one another.

Project description:BackgroundDomestic violence in the perinatal period is associated with adverse obstetric outcomes, but evidence is limited on its association with perinatal mental disorders. We aimed to estimate the prevalence and odds of having experienced domestic violence among women with antenatal and postnatal mental disorders (depression and anxiety disorders including post-traumatic stress disorder [PTSD], eating disorders, and psychoses).Methods and findingsWe conducted a systematic review and meta-analysis (PROSPERO reference CRD42012002048). Data sources included searches of electronic databases (to 15 February 2013), hand searches, citation tracking, update of a review on victimisation and mental disorder, and expert recommendations. Included studies were peer-reviewed experimental or observational studies that reported on women aged 16 y or older, that assessed the prevalence and/or odds of having experienced domestic violence, and that assessed symptoms of perinatal mental disorder using a validated instrument. Two reviewers screened 1,125 full-text papers, extracted data, and independently appraised study quality. Odds ratios were pooled using meta-analysis. Sixty-seven papers were included. Pooled estimates from longitudinal studies suggest a 3-fold increase in the odds of high levels of depressive symptoms in the postnatal period after having experienced partner violence during pregnancy (odds ratio 3.1, 95% CI 2.7-3.6). Increased odds of having experienced domestic violence among women with high levels of depressive, anxiety, and PTSD symptoms in the antenatal and postnatal periods were consistently reported in cross-sectional studies. No studies were identified on eating disorders or puerperal psychosis. Analyses were limited because of study heterogeneity and lack of data on baseline symptoms, preventing clear findings on causal directionality.ConclusionsHigh levels of symptoms of perinatal depression, anxiety, and PTSD are significantly associated with having experienced domestic violence. High-quality evidence is now needed on how maternity and mental health services should address domestic violence and improve health outcomes for women and their infants in the perinatal period.

Project description:BackgroundLittle is known about the extent to which being a victim of domestic violence is associated with different mental disorders in men and women. We aimed to estimate the prevalence and odds of being a victim of domestic violence by diagnostic category and sex.MethodsStudy designSystematic review and meta-analysis.Data sourcesEighteen biomedical and social sciences databases (including MEDLINE, EMBASE, PsycINFO); journal hand searches; scrutiny of references and citation tracking of included articles; expert recommendations, and an update of a systematic review on victimisation and mental disorder.Inclusion criteriaobservational and intervention studies reporting prevalence or odds of being a victim of domestic violence in men and women (aged ≥16 years), using validated diagnostic measures of mental disorder.ProcedureData were extracted and study quality independently appraised by two reviewers.AnalysisRandom effects meta-analyses were used to pool estimates of prevalence and odds.ResultsForty-one studies were included. There is a higher risk of experiencing adult lifetime partner violence among women with depressive disorders (OR 2.77 (95% CI 1.96-3.92), anxiety disorders (OR 4.08 (95% CI 2.39-6.97), and PTSD (OR 7.34 95% CI 4.50-11.98), compared to women without mental disorders. Insufficient data were available to calculate pooled odds for other mental disorders, family violence (i.e. violence perpetrated by a non-partner), or violence experienced by men. Individual studies reported increased odds for women and men for all diagnostic categories, including psychoses, with a higher prevalence reported for women. Few longitudinal studies were found so the direction of causality could not be investigated.ConclusionsThere is a high prevalence and increased likelihood of being a victim of domestic violence in men and women across all diagnostic categories, compared to people without disorders. Longitudinal studies are needed to identify pathways to being a victim of domestic violence to optimise healthcare responses.

Project description:BackgroundThe emerging field of epidemiological criminology studies the intersection between public health and justice systems. To increase the value of and reduce waste in research activities in this area, it is important to perform transparent research priority setting considering the needs of research beneficiaries and end users along with a systematic assessment of the existing research activities to address gaps and harness opportunities.ObjectiveIn this study, we aimed to examine published research outputs in epidemiological criminology to assess gaps between published outputs and current research priorities identified by prison stakeholders.MethodsA rule-based method was applied to 23,904 PubMed epidemiological criminology abstracts to extract the study determinants and outcomes (ie, "themes"). These were mapped against the research priorities identified by Australian prison stakeholders to assess the differences from research outputs. The income level of the affiliation country of the first authors was also identified to compare the ranking of research priorities in countries categorized by income levels.ResultsOn an evaluation set of 100 abstracts, the identification of themes returned an F1-score of 90%, indicating reliable performance. More than 53.3% (11,927/22,361) of the articles had at least 1 extracted theme; the most common was substance use (1533/11,814, 12.97%), followed by HIV (1493/11,814, 12.64%). The infectious disease category (2949/11,814, 24.96%) was the most common research priority category, followed by mental health (2840/11,814, 24.04%) and alcohol and other drug use (2433/11,814, 20.59%). A comparison between the extracted themes and the stakeholder priorities showed an alignment for mental health, infectious diseases, and alcohol and other drug use. Although behavior- and juvenile-related themes were common, they did not feature as prison priorities. Most studies were conducted in high-income countries (10,083/11,814, 85.35%), while countries with the lowest income status focused half of their research on infectious diseases (47/91, 52%).ConclusionsThe identification of research themes from PubMed epidemiological criminology research abstracts is possible through the application of a rule-based text mining method. The frequency of the investigated themes may reflect historical developments concerning disease prevalence, treatment advances, and the social understanding of illness and incarcerated populations. The differences between income status groups are likely to be explained by local health priorities and immediate health risks. Notable gaps between stakeholder research priorities and research outputs concerned themes that were more focused on social factors and systems and may reflect publication bias or self-publication selection, highlighting the need for further research on prison health services and the social determinants of health. Different jurisdictions, countries, and regions should undertake similar systematic and transparent research priority-setting processes.

Dataset Information

Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study.

Publications

Automatic Extraction of Mental Health Disorders From Domestic Violence Police Narratives: Text Mining Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets