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

"The reasons you believe …": An exploratory study of text driven evidence gathering and prediction from first responder records justifying state authorised intervention for mental health episodes

Objective First responders' mandatory reports of mental health episodes requiring emergency hospital care contain rich information about patients and their needs. In Queensland (Australia) much of the information contained in Emergency Examination Authorities (EEAs) remains unused. We propose and demonstrate a methodology to extract and translate vital information embedded in reports like EEAs and to use it to investigate the extreme propensity of incidence of serious mental health episodes. Methods The proposed method integrates clinical, demographic, spatial and free text information into a single data collection. The data is subjected to exploratory analysis for spatial pattern recognition leading to an observational epidemiology model for the association of maximum spatial recurrence of EEA episodes. Results Sentiment analysis revealed that among EEA presentations hospital and health service (HHS) region #4 had the lowest proportion of positive sentiments (18 %) compared to 33 % for HHS region #1 pointing to spatial differentiation of sentiments immanent in mandated free text which required more detailed analysis. At the postcode geographical level, we found that variation in maximum spatial recurrence of EEAs was significantly positively associated with spatial range of sentiments (0.29, p < 0.001) and the postcode-referenced sex ratio (0.45, p = 0.01). The volatility of sentiments significantly correlated with extremes of recurrence of EEA episodes. The predicted (probabilistic) incidence rate when mapped reflected this correlation. Conclusions The paper demonstrates the efficacy of integrating, machine extracted, human sentiments (as potential surrogates) with conventional exposure variables for evidence-based methods for mental health spatial epidemiology. Such insights from informatics-driven epidemiological observations may inform the strategic allocation of health system resources to address the highest levels of need and to improve the standard of care for mental patients while also enhancing their safe and humane treatment and management.

Characteristics of domestic violence perpetrators with dementia from police records using text mining

Aim

Few studies have examined the characteristics of domestic violence (DV) committed by people with dementia. We provide an overview of DV perpetrated by people with dementia in the community based on police reports of attendances at DV events.

Method

A text mining method was used on 416,441 New South Wales (NSW) police narratives of DV events from January 2005 to December 2016 to extract information for Persons of Interest (POIs) with mentions of dementia.

Results

Events involving those with dementia accounted for a relatively low proportion of total DV events (<1%). Of the 260 DV events with a dementia mention for the POI, the most common abuse types were assault (49.7%) and verbal abuse (31.6%). Spouses were the largest group of victims (50.8%) followed by children (8.8%). Physical abuse was common, occurring in 82.4% of events, but injuries were relatively mild. Although weapons were infrequently used, they were involved in 5% of events, mostly by POIs aged 75 years and older. Similarly, the POIs were mainly aged 75+ years (60%), however the proportion of those aged <65 was relatively high (20.8%) compared to the reported prevalence of dementia in that age group.

Conclusions

This study demonstrates that some cases of DV perpetrated by people with reported dementia are significant enough to warrant police involvement. This highlights the need to proactively discuss the potential for violence as part of the holistic management and support family members, particularly those caring for people with young-onset dementias.

Detecting mental and physical disorders using multi-task learning equipped with knowledge graph attention network

Mental and physical disorders (MPD) are inextricably linked in many medical cases; psychosomatic diseases can be induced by mental concerns and psychological discomfort can ensue from physiological diseases. However, existing medical informatics studies focus on identifying mental or physical disorders from a unilateral perspective. Consequently, no existing domain knowledge base, corpus, or detection modeling approach considers mental as well as physical aspects concurrently. This paper proposes a joint modeling approach to detect MPD. First, we crawl through online medical consultation records of patients from websites and build an MPD knowledge ontology by extracting the core conceptual features of the text. Based on the ontology, an MPD knowledge graph containing 12,673 nodes and 82,195 relations is obtained using term matching with a domain thesaurus of each concept. Subsequently, an MPD corpus with fine-grained severities (None, Mild, Moderate, Severe, Dangerous) and 8909 records is constructed by formulating MPD classification criteria and a data annotation process under the guidance of domain experts. Taking the knowledge graph and corpus as the dataset, we design a multi-task learning model to detect the MPD severity, in which a knowledge graph attention network (KGAT) is embedded to better extract knowledge features. Experiments are performed to demonstrate the effectiveness of our model. Furthermore, we employ ontology-based and centrality-based methods to discover additional potential inferred knowledge, which can be captured by KGAT so as to improve the prediction performance and interpretability of our model. Our dataset has been made publicly available, so it can be further used as a medical informatics reference in the fields of psychosomatic medicine, psychiatrics, physical co-morbidity, and so on.

Mental illness concordance between hospital clinical records and mentions in domestic violence police narratives: Data linkage study (Preprint)

Background

To better understand domestic violence, data sources from multiple sectors such as police, justice, health, and welfare are needed. Linking police data to data collections from other agencies could provide unique insights and promote an all-of-government response to domestic violence. The New South Wales Police Force attends domestic violence events and records information in the form of both structured data and a free-text narrative, with the latter shown to be a rich source of information on the mental health status of persons of interest (POIs) and victims, abuse types, and sustained injuries.

Objective

This study aims to examine the concordance (ie, matching) between mental illness mentions extracted from the police’s event narratives and mental health diagnoses from hospital and emergency department records.

Methods

We applied a rule-based text mining method on 416,441 domestic violence police event narratives between December 2005 and January 2016 to identify mental illness mentions for POIs and victims. Using different window periods (1, 3, 6, and 12 months) before and after a domestic violence event, we linked the extracted mental illness mentions of victims and POIs to clinical records from the Emergency Department Data Collection and the Admitted Patient Data Collection in New South Wales, Australia using a unique identifier for each individual in the same cohort.

Results

Using a 2-year window period (ie, 12 months before and after the domestic violence event), less than 1% (3020/416,441, 0.73%) of events had a mental illness mention and also a corresponding hospital record. About 16% of domestic violence events for both POIs (382/2395, 15.95%) and victims (101/631, 16.01%) had an agreement between hospital records and police narrative mentions of mental illness. A total of 51,025/416,441 (12.25%) events for POIs and 14,802/416,441 (3.55%) events for victims had mental illness mentions in their narratives but no hospital record. Only 841 events for POIs and 919 events for victims had a documented hospital record within 48 hours of the domestic violence event.

Conclusions

Our findings suggest that current surveillance systems used to report on domestic violence may be enhanced by accessing rich information (ie, mental illness) contained in police text narratives, made available for both POIs and victims through the application of text mining. Additional insights can be gained by linkage to other health and welfare data collections.

Listening to Mental Health Crisis Needs at Scale: Using Natural Language Processing to Understand and Evaluate a Mental Health Crisis Text Messaging Service

The current mental health crisis is a growing public health issue requiring a large-scale response that cannot be met with traditional services alone. Digital support tools are proliferating, yet most are not systematically evaluated, and we know little about their users and their needs. Shout is a free mental health text messaging service run by the charity Mental Health Innovations, which provides support for individuals in the UK experiencing mental or emotional distress and seeking help. Here we study a large data set of anonymised text message conversations and post-conversation surveys compiled through Shout. This data provides an opportunity to hear at scale from those experiencing distress; to better understand mental health needs for people not using traditional mental health services; and to evaluate the impact of a novel form of crisis support. We use natural language processing (NLP) to assess the adherence of volunteers to conversation techniques and formats, and to gain insight into demographic user groups and their behavioural expressions of distress. Our textual analyses achieve accurate classification of conversation stages (weighted accuracy = 88%), behaviours (1-hamming loss = 95%) and texter demographics (weighted accuracy = 96%), exemplifying how the application of NLP to frontline mental health data sets can aid with post-hoc analysis and evaluation of quality of service provision in digital mental health services.

Utilizing Text Mining, Data Linkage and Deep Learning in Police and Health Records to Predict Future Offenses in Family and Domestic Violence

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.

Nonfatal Strangulation During Domestic Violence Events in New South Wales: Prevalence and Characteristics Using Text Mining Study of Police Narratives

Nonfatal strangulation (NFS) is a common form of domestic violence (DV) that frequently leaves no visible signs of injury and can be a portent for future fatality. A validated text mining approach was used to analyze a police dataset of 182,949 DV events for the presence of NFS. Results confirmed NFS within intimate partner relationships is a gendered form of violence. The presence of injury and/or other (non-NFS) forms of physical abuse, emotional/verbal/social abuse, and the perpetrator threatening to kill the victim, were associated with significantly higher odds of NFS perpetration. Police data contain rich information that can be accessed using automated methodologies such as text mining to add to our understanding of this pressing public health issue.

Domestic Violence in Residential Care Facilities in New South Wales, Australia: A Text Mining Study

BACKGROUND AND OBJECTIVES

The police are often the first to attend domestic violence events in New South Wales (NSW), Australia, recording related details as structured information (e.g., date of the event, type of incident, premises type) and as text narratives which contain important information (e.g., mental health status, abuse types) for victims and perpetrators. This study examined the characteristics of victims and persons of interest (POIs) suspected and/or charged with perpetrating a domestic violence related crime in residential care facilities.

RESEARCH DESIGN AND METHODS

The study employed a text mining method that extracted key information from 700 police recorded domestic violence events in NSW residential care facilities.

RESULTS

Victims were mostly female (65.4%) and older adults (median age 80.3). POIs were predominantly male (67.0%) and were younger than the victims (median age 57.0). While low rates of mental illnesses were recorded (29.1% in victims; 17.4% in POIs), 'dementia' was the most common condition among POIs (55.7%) and victims (73.0%). 'Physical abuse' was the most common abuse type (80.2%) with 'bruising' the most common injury (36.8%). The most common relationship between perpetrator and victim was 'carer' (76.6%).

DISCUSSION AND IMPLICATIONS

These findings highlight the opportunity provided by police text-based data to provide insights into elder abuse within residential care facilities.

Surveillance of Domestic Violence Using Text Mining Outputs From Australian Police Records

In Australia, domestic violence reports are mostly based on data from the police, courts, hospitals, and ad hoc surveys. However, gaps exist in reporting information such as victim injuries, mental health status and abuse types. The police record details of domestic violence events as structured information (e.g., gender, postcode, ethnicity), but also in text narratives describing other details such as injuries, substance use, and mental health status. However, the voluminous nature of the narratives has prevented their use for surveillance purposes. We used a validated text mining methodology on 492,393 police-attended domestic violence event narratives from 2005 to 2016 to extract mental health mentions on persons of interest (POIs) (individuals suspected/charged with a domestic violence offense) and victims, abuse types, and victim injuries. A significant increase was observed in events that recorded an injury type (28.3% in 2005 to 35.6% in 2016). The pattern of injury and abuse types differed between male and female victims with male victims more likely to be punched and to experience cuts and bleeding and female victims more likely to be grabbed and pushed and have bruises. The four most common mental illnesses (alcohol abuse, bipolar disorder, depression schizophrenia) were the same in male and female POIs. An increase from 5.0% in 2005 to 24.3% in 2016 was observed in the proportion of events with a reported mental illness with an increase between 2005 and 2016 in depression among female victims. These findings demonstrate that extracting information from police narratives can provide novel insights into domestic violence patterns including confounding factors (e.g., mental illness) and thus enable policy responses to address this significant public health problem.

Prevalence of Mental Illnesses in Domestic Violence Police Records: Text Mining Study

Background

The New South Wales Police Force (NSWPF) records details of significant numbers of domestic violence (DV) events they attend each year as both structured quantitative data and unstructured free text. Accessing information contained in the free text such as the victim’s and persons of interest (POI's) mental health status could be useful in the better management of DV events attended by the police and thus improve health, justice, and social outcomes.

Objective

The aim of this study is to present the prevalence of extracted mental illness mentions for POIs and victims in police-recorded DV events.

Methods

We applied a knowledge-driven text mining method to recognize mental illness mentions for victims and POIs from police-recorded DV events.

Results

In 416,441 police-recorded DV events with single POIs and single victims, we identified 64,587 events (15.51%) with at least one mental illness mention versus 4295 (1.03%) recorded in the structured fixed fields. Two-thirds (67,582/85,880, 78.69%) of mental illnesses were associated with POIs versus 21.30% (18,298/85,880) with victims; depression was the most common condition in both victims (2822/12,589, 22.42%) and POIs (7496/39,269, 19.01%). Mental illnesses were most common among POIs aged 0-14 years (623/1612, 38.65%) and in victims aged over 65 years (1227/22,873, 5.36%).

Conclusions

A wealth of mental illness information exists within police-recorded DV events that can be extracted using text mining. The results showed mood-related illnesses were the most common in both victims and POIs. Further investigation is required to determine the reliability of the mental illness mentions against sources of diagnostic information.

Development and Validation of a Machine Learning Individualized Treatment Rule in First-Episode Schizophrenia

Importance

Little guidance exists to date on how to select antipsychotic medications for patients with first-episode schizophrenia.

Objective

To develop a preliminary individualized treatment rule (ITR) for patients with first-episode schizophrenia.

Design, Setting, and Participants

This prognostic study obtained data from Taiwan's National Health Insurance Research Database on patients with prescribed antipsychotic medications, ambulatory claims, or discharge diagnoses of a schizophrenic disorder between January 1, 2005, and December 31, 2011. An ITR was developed by applying a targeted minimum loss-based ensemble machine learning method to predict treatment success from baseline clinical and demographic data in a 70% training sample. The model was validated in the remaining 30% of the sample. The probability of treatment success was estimated for each medication for each patient under the model. The analysis was conducted between July 16, 2018, and July 15, 2019.

Exposures

Fifteen different antipsychotic medications.

Main Outcomes and Measures

Treatment success was defined as not switching medication and not being hospitalized for 12 months.

Results

Among the 32 277 patients in the analysis, the mean (SD) age was 36.7 (14.3) years, and 15 752 (48.8%) were male. In the validation sample, the treatment success rate (SE) was 51.7% (1.0%) under the ITR and was 44.5% (0.5%) in the observed population (Z = 7.1; P < .001). The estimated treatment success if all patients were given a prescription for 1 medication was significantly lower for each of the 13 medications than under the ITR (Z = 4.2-16.8; all P < .001). Aripiprazole (3088 [31.9%]) and amisulpride (2920 [30.2%]) were the medications most often recommended by the ITR. Only 1054 patients (10.9%) received ITR-recommended medications. Observed treatment success, although lower than the success under the ITR, was nonetheless significantly higher than if medications had been randomized (44.5% [SE, 0.55%] vs 41.3% [SE, 0.4%]; Z = 6.9; P < .001), although only marginally higher than if medications had been randomized in their observed population proportions (44.5% [SE, 0.5%] vs 43.5% [SE, 0.4%]; Z = 2.2; P = .03]).

Conclusions and Relevance

These results suggest that an ITR may be associatded with an increase in the treatment success rate among patients with first-episode schizophrenia, but experimental evaluation is needed to confirm this possibility. If confirmed, model refinement that investigates biomarkers, clinical observations, and patient reports as additional predictors in iterative pragmatic trials would be needed before clinical implementation.

Automated Analysis of Domestic Violence Police Reports to Explore Abuse Types and Victim Injuries: Text Mining Study

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.