Exploring offending characteristics of young people with foetal alcohol spectrum disorder in Western Australia.

Neurodevelopmental impairments resulting from Foetal Alcohol Spectrum Disorder (FASD) can increase the likelihood of justice system involvement. This study compared offence characteristics in young people with FASD to demographically matched controls (n = 500) in Western Australia. A novel approach (i.e. association rule mining) was adopted to uncover relationships between personal attributes and offence characteristics. For FASD participants (n = 100), file records were reviewed retrospectively. Mean age of the total sample was 15.60 years (range = 10-24), with 82% males and 88% Australian Aboriginal. After controlling for demographic factors, regression analyses showed FASD participants were more likely than controls to be charged with reckless driving (odds ratio, OR = 4.20), breach of bail/community orders (OR = 3.19), property damage (OR = 1.84), and disorderly behaviour (OR = 1.54). Overall, our findings suggest justice-involved individuals with FASD have unique offending profiles. These results have implications for sentencing, diversionary/crime prevention programs and interventions.

Adverse childhood experiences, associated stressors and comorbidities in children and youth with fetal alcohol spectrum disorder across the justice and child protection settings in Western Australia.

BACKGROUND: Individuals with Fetal Alcohol Spectrum Disorder (FASD) are at risk of having adverse childhood experiences (ACEs), especially those with child protection and/or justice system involvement. The complex relationship between FASD and psychosocial vulnerabilities in the affected individual is an important clinical risk factor for comorbidity. This study (1) explored the ACEs and associated stressors in individuals with FASD; (2) investigated the association between ACEs and negative outcomes, i.e., justice/child protection system involvement; and (3) examined the relationship between ACEs and comorbid conditions such as mood and neurodevelopmental disorders. METHODS: Data were collected retrospectively via file review from diagnostic clinics in Western Australia. Life adversity was coded using a standardised ACEs questionnaire. A total of 211 participants (72% males) with FASD with a mean age of 11 years (range = 2-21) were included in the final sample. 70% of the total sample had been involved with the child protection system and 40% had trouble with the law. RESULTS: Exposure to drinking/substance misuse at home (70%) and domestic violence (52%) were the two most common ACEs across the total sample. In the entire cohort, 39% had four or more ACEs, indicating higher risks of poor health outcomes. Additional stressors recorded were disengagement from school (43%), transiency (19%), victims of bullying (12%), traumatic brain injury (9%) and homelessness (5%). ACEs such as drinking/substance misuse at home, emotional neglect and physical neglect were positively associated with child protection system involvement. Additionally, exposure to domestic violence was positively correlated with justice system involvement. Higher rates of life adversity in this clinical population were associated with an increased number of comorbidities. Specifically, those with FASD who had comorbidities such as attachment disorder, substance use disorder, and PTSD also reported higher ACEs scores. CONCLUSION: ACEs were common in this clinical population. Increased ACEs in this sample were associated with increased comorbidities and involvement with the child protection and/or justice system. This highlights that prevention, intervention and early diagnosis of FASD are important for at risk children to reduce the negative effects of ACEs.

The provision of alcohol and breastfeeding information by maternal health practitioners in the Australian setting.

BACKGROUND: In the 2009 National Health and Medical Research Council (NHMRC) Australian Guidelines to Reduce Health Risks from Drinking, a guideline specific to lactating women was included. For the first time the effect of alcohol at this important developmental stage was nationally and internationally acknowledged. AIMS: To determine the degree to which maternal health practitioners adopted an Australian national policy guideline (Guideline 4B) on alcohol and breastfeeding into their everyday health practice and the factors associated with adoption. MATERIALS AND METHODS: A convenience sample of participants completed an online survey based on the Nursing Practice Questionnaire (NPQ) to elicit measures of knowledge, awareness and practice implementation. RESULTS: In total, 240 maternal health practitioners completed the online survey. All statistical analyses clearly indicated a higher adoption of Guideline 4B by the child health nurses, midwives and general practitioners (GPs) than was the case for paediatricians and obstetricians. A mean adoption score (range 0-4) indicative of 'some' practice implementation of 3.13, 3.04 and 2.73 was obtained by child health nurses, midwives and GPs, respectively. Obstetricians and paediatricians scored a mean of 2.0, indicating they remain to be 'persuaded about the practice' of incorporating discussions around alcohol and breastfeeding into their practice. CONCLUSION: Despite the existence of a national alcohol guideline for breastfeeding women, maternal health practitioners are not incorporating this advice into their everyday practice with lactating women. Opportunities exist for all maternal practitioners along the reproductive continuum to protect long-term breastfeeding duration using an evidence-based harm minimisation approach to alcohol consumption.

A systematic review of prevention interventions to reduce prenatal alcohol exposure and fetal alcohol spectrum disorder in indigenous communities.

BACKGROUND: Fetal alcohol spectrum disorder (FASD) is a preventable, lifelong neurodevelopmental disorder caused by prenatal alcohol exposure. FASD negatively impacts individual Indigenous communities around the world. Although many prevention interventions have been developed and implemented, they have not been adequately evaluated. This systematic review updates the evidence for the effectiveness of FASD prevention interventions in Indigenous/Aboriginal populations internationally, and in specific populations in North America and New Zealand, and offers recommendations for future work. METHOD: The MEDLINE, Embase, CINAHL Plus, Web of Science, PsycINFO, SocINDEX, and Informit databases were searched from inception to 22/08/2017 for all prevention and intervention papers published in peer-reviewed scientific journals, with results, targeting prenatal alcohol exposure and FASD in Indigenous populations. This review was limited to studies published in English and excluded interventions focusing on the workforce. All steps were completed independently by two reviewers with discrepancies resolved via consensus with the senior author. RESULTS: There was significant heterogeneity in the ten included studies. Populations targeted included non-pregnant women of child-bearing age, pregnant women, school children and the general public. Study designs included one randomised controlled trial, five cohort studies with pre-post design, one cross-sectional study with different pre- and post-intervention groups, and four studies collected post-intervention data. Studies assessed changes in knowledge, and/or changes in risk for prenatal alcohol exposure including self-reported alcohol consumption, use of birth control or a combination of both. One study was conducted in Australia and nine in the US. The methodological quality of all studies was rated as 'Poor' using the systematic review assessment tools developed by The National Heart, Lung and Blood Institute. Studies were subject to substantial bias due to issues such as high loss to follow-up, lack of control groups and the reliance on self-report measures to assess the main outcome. CONCLUSION: Overall, there is little evidence that previous interventions aiming to reduce the risk of prenatal alcohol exposure or FASD in Indigenous populations have been effective. Future intervention studies should address the cultural factors and historical context that are fundamental to successful work with Indigenous populations, and be designed, implemented and evaluated using rigorous methods. This systematic review was registered with PROSPERO, CRD42018086212.

The development of a culturally appropriate school based intervention for Australian Aboriginal children living in remote communities: A formative evaluation of the Alert Program® intervention.

BACKGROUND/AIM: Although previous research has demonstrated the benefits of targeting self-regulation in non-Aboriginal children, it is unclear whether such programs would be effective for Aboriginal children attending school in remote communities. Some of these children have been diagnosed with a fetal alcohol spectrum disorder (FASD) impairing their ability to self-regulate. The aim of this article is to describe a three phase formative process to develop and pilot a curriculum version of the Alert Program® , a promising intervention for improving self-regulation that could be used in remote community schools. This modified version of the program will be subsequently tested in a cluster randomised controlled trial. METHODS: A mixed methods approach was used. RESULTS: Modifications to the Alert Program® , its delivery and evaluation were made after community and stakeholder consultation facilitated by a senior Aboriginal community researcher. Changes to lesson plans and program resources were made to reflect the remote community context, classroom environment and the challenging behaviours of children. Standardised study outcome measures were modified by removing several questions that had little relevance to the lives of children in remote communities. Program training for school staff was reduced in length to reduce staff burden. CONCLUSIONS: This study identified aspects of the Alert Program® training, delivery and measures for evaluation that need modification before their use in assessing the efficacy of the Alert Program® in remote Aboriginal community primary schools.

Nurturing families: One year pilot outcomes for a modified Parent Child Assistance Program in Australia.

Alcohol and Other Drug (AOD) exposure during pregnancy is linked to serious adverse child outcomes, including Fetal Alcohol Spectrum Disorder (FASD). The Parent-Child Assistance Program (PCAP) supports women with problematic AOD use, who are pregnant or have young children, and are not effectively engaging with services. PCAP has been shown to reduce alcohol exposed pregnancies, promote AOD abstinence, increase employment and family planning and improve child outcomes. This manuscript reports the first pilot evaluation of the PCAP program delivered in Australia. A pre-post-intervention repeated measures design was used. Eleven women receiving PCAP from a not-for-profit organisation were invited to take part in the study, with eight providing complete pre-post data. Home visitation case management was provided by trained and experienced case-managers. Clients were assisted to engage with existing services effectively to meet their own goals via a combination of relational theory, motivational interviewing and harm reduction concepts. The PCAP Modified Addiction Severity Index 5th Edition was adapted for use in Australia and was used to measure domains of addiction severity related problems as the primary outcome. Secondary outcomes included client satisfaction and program fidelity. There were significant changes in composite addiction severity scores from baseline to one year. 80% of participants had periods of abstinence of longer than four months. All clients had better connection to services, no subsequent AOD exposed pregnancies, and were highly satisfied with the program. Four had children returned to their care. Implementation was similar to the original PCAP program with major differences including case-managers relying on training manuals only without undertaking in-person training; being more experienced; providing more direct AOD counselling; and having less supervision. The findings will inform future program delivery and methodology for a larger longitudinal study assessing outcomes at program exit.

Association between Bar Closing Time, Alcohol Use Disorders and Blood Alcohol Concentration: A Cross-Sectional Observational Study of Nightlife-Goers in Perth, Australia.

Introduction and aims: Associations between bar trading hours, a government lever for controlling alcohol availability, nightlife-goer intoxication levels and their likelihood of alcohol use disorder (AUD) have not been explored. We investigated whether: (i) participant AUD was associated with blood alcohol concentration (BAC); and, (ii) any association between AUD and BAC was moderated by participant preferred bar (i.e., venue spent most time at) closing time. Design and methods: A cross-sectional observational study using a sample of nightlife-goers who went out drinking in Perth, Western Australia, on weekends in 2015-16. Participants who reported alcohol use that night and spent most time in a bar (n = 667) completed street intercept surveys including AUDIT-C (n = 459) and provided a breath sample to estimate BAC (n = 651). We used gender-specific multinomial logistic regression models to explore associations between participant AUDIT-C score (1−4, lower risk; 5−7, hazardous; 8−12, active AUD), preferred bar type (standard vs. late closing time based on absence or presence of an extended trading permit) and BAC (male: 0−0.049, 0.05−0.099, ≥0.1 g/100 mL; female: 0−0.049, 0.05−0.079, ≥0.08 g/100 mL). Results: Males with active AUD (RR = 3.31; 95% CI 1.30−8.42; p = 0.01) and females with hazardous/active AUD (RR = 9.75; 95% CI 2.78−34.21; p < 0.001) were both more likely to have high-range BAC than their counterparts typically drinking at lower risk. We also found preferred bar type moderated the association between AUDIT-C score and BAC for some males but no females. Males with active AUD and high-range BAC were less likely to prefer late closing bars than males usually drinking at lower risk and high-range BAC (RR = 0.12; 95% CI 0.02−0.96; p = 0.046). Discussion and conclusions: Our study provides evidence of positive associations between AUD and acute intoxication among nightlife-goers and on the moderating effect of bar closing times among males.

Correction: Gilmore et al. Association between Nightlife Goers' Likelihood of an Alcohol Use Disorder and Their Preferred Bar's Closing Time: A Cross-Sectional Observational Study in Perth, Australia. Int. J. Environ. Res. Public Health 2021, 18, 13040.

In the original publication [...].

Association of prenatal alcohol exposure with offspring DNA methylation in mammals: a systematic review of the evidence.

BACKGROUND: Prenatal alcohol exposure (PAE) is associated with a range of adverse offspring neurodevelopmental outcomes. Several studies suggest that PAE modifies DNA methylation in offspring cells and tissues, providing evidence for a potential mechanistic link to Fetal Alcohol Spectrum Disorder (FASD). We systematically reviewed existing evidence on the extent to which maternal alcohol use during pregnancy is associated with offspring DNA methylation. METHODS: A systematic literature search was conducted across five online databases according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. PubMed, Web of Science, EMBASE, Google Scholar and CINAHL Databases were searched for articles relating to PAE in placental mammals. Data were extracted from each study and the Risk of Bias in Non-Randomized Studies of Interventions (ROBINS-I) was used to assess the potential for bias in human studies. RESULTS: Forty-three articles were identified for inclusion. Twenty-six animal studies and 16 human studies measured offspring DNA methylation in various tissues using candidate gene analysis, methylome-wide association studies (MWAS), or total nuclear DNA methylation content. PAE dose and timing varied between studies. Risk of bias was deemed high in nearly all human studies. There was insufficient evidence in human and animal studies to support global disruption of DNA methylation from PAE. Inconclusive evidence was found for hypomethylation at IGF2/H19 regions within somatic tissues. MWAS assessing PAE effects on offspring DNA methylation showed inconsistent evidence. There was some consistency in the relatively small number of MWAS conducted in populations with FASD. Meta-analyses could not be conducted due to significant heterogeneity between studies. CONCLUSION: Considering heterogeneity in study design and potential for bias, evidence for an association between PAE and offspring DNA methylation was inconclusive. Some reproducible associations were observed in populations with FASD although the limited number of these studies warrants further research. Trail Registration: This review is registered with PROSPERO (registration number: CRD42020167686).

A systematic review of the biological, social, and environmental determinants of intellectual disability in children and adolescents.

Aim: This systematic review aimed to identify the most important social, environmental, biological, and/or genetic risk factors for intellectual disability (ID). Methods: Eligible were published prospective or retrospective comparative studies investigating risk factors for ID in children 4-18 years. Exclusions were single group studies with no comparator without ID and a sample size <100. Electronic databases (Medline, Cochrane Library, EMBASE, PsycInfo, Campbell Collaboration, and CINAHL) were searched for eligible publications from 1980 to 2020. Joanna Briggs Institute critical appraisal instruments, appropriate for study type, were used to assess study quality and risk of bias. Descriptive characteristics and individual study results were presented followed by the synthesis for individual risk factors, also assessed using GRADE. Results: Fifty-eight individual eligible studies were grouped into six exposure topics: sociodemographic; antenatal and perinatal; maternal physical health; maternal mental health; environmental; genetic or biological studies. There were few eligible genetic studies. For half the topics, the certainty of evidence (GRADE) was moderate or high. Conclusion: Multiple studies have examined individual potential determinants of ID, but few have investigated holistically to identify those populations most at risk. Our review would indicate that there are vulnerable groups where risk factors we identified, such as low socioeconomic status, minority ethnicity, teenage motherhood, maternal mental illness, and alcohol abuse, may cluster, highlighting a target for preventive strategies. At-risk populations need to be identified and monitored so that interventions can be implemented when appropriate, at preconception, during pregnancy, or after birth. This could reduce the likelihood of ID and provide optimal opportunities for vulnerable infants. Systematic review registration: [https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=120032], identifier [CRD42019120032].

Identifying how the principles of self-determination could be applied to create effective alcohol policy for First Nations Australians: Synthesising the lessons from the development of general public policy.

BACKGROUND: Harmful alcohol consumption contributes to poorer health for all people. For Indigenous Peoples of Australia, Canada, and New Zealand alcohol impacts their wellbeing significantly, this is partially explained by both their experiences of colonisation and the resulting impact on structural and social determinants of health. Indigenous Peoples have a recognised right to self-determination, which includes their right to contribute to policy decisions that affect them. This right is based on international recognition and principles, and acknowledgement of historical culture and law. The aim of this narrative review is to examine the processes of inclusion of Indigenous Peoples in policy development processes for evidence of self-determination to inform alcohol policy development. METHODS: Ninety-eight peer-reviewed journal articles were identified through four databases. Twenty papers describing the inclusion of Indigenous Peoples in policy development processes were included; one focusing on alcohol. Two authors reviewed and coded the papers by four domains of Indigenous inclusion in policy processes: Indigenous representation; method of inclusion; reasons for inclusion; and stage of inclusion. RESULTS: There is no single model for the integration of self-determination into policy. However, the nature of participation is key in ensuring that Indigenous Peoples' self-determination is recognised. While all the papers reported Indigenous Peoples being included in processes, there was little evidence of self-determination. CONCLUSIONS: Self-determination is a right, and critical to effective policy and action. The inclusion of Indigenous Peoples in policy development alone is not self-determination; however, creating the conditions that ensures Indigenous Peoples have influence throughout policy processes is one integral component of self-determination.

Association between Nightlife Goers' Likelihood of an Alcohol Use Disorder and Their Preferred Bar's Closing Time: A Cross-Sectional Observational Study in Perth, Australia.

INTRODUCTION AND AIMS: Associations between longer-term alcohol-related conditions and licensed outlet trading hours are not well understood. We investigated the association between nightlife-goers' likelihood of an alcohol use disorder (AUD) and their preference for bars with special permits to remain open 'late' (i.e., spent more time there compared to any other venue) until 2 a.m. or 3 a.m. (Friday; Saturday) or midnight (Sunday) compared to bars with 'standard' closing times of midnight (Friday; Saturday) or 10 p.m. (Sunday). DESIGN AND METHODS: A cross-sectional observational study was conducted in four major nightlife areas of Perth, Australia, in 2015-2016. We conducted weekend street intercept surveys outside bars between 8 p.m. and 3 a.m. and screened participants who reported alcohol use prior to the survey and spent more time in a bar than any other venue type (n = 667) regarding their past year drinking pattern using AUDIT-C (n = 459). We used gender-specific logistic regression models to estimate associations between AUDIT-C categories (1-4, low risk; 5-7, hazardous; 8-12, active AUD) and preference for bars with different closing times (late vs. standard). RESULTS: A large proportion of participants were hazardous drinkers or had active AUD (83% males; 65% females), and over half preferred a late to a standard closing bar. We found evidence of a positive association between preference for late closing bars and hazardous drinking females (OR = 3.48; 95% CI 1.47-8.23; p = 0.01), but not for females with active AUD, male hazardous drinkers, nor males with active AUD. DISCUSSION AND CONCLUSIONS: Our study adds new evidence on associations between likelihood of AUD among nightlife-goers and trading hours. With increasing international relaxation of trading hours, evidence that late closing bars may be preferred by hazardous drinking females will be of concern to policymakers wanting to curb alcohol-related harms in the community.

It takes a village: Influencing policy and practice to prevent alcohol use in pregnancy and promote better outcomes for individuals living with Fetal Alcohol Spectrum Disorder.

Fetal Alcohol Spectrum Disorder (FASD) is a neurodevelopmental disorder caused by exposure to alcohol in utero. It has pervasive, lifelong impacts and is recognised as a major public health concern in many countries where alcohol is used. The FASD Research Australia Centre of Research Excellence (CRE) was funded by the National Health and Medical Research Council to generate and translate evidence to address prevention, diagnosis, and management of FASD in Australia. The current paper describes the approach to policy and practice impact taken by our CRE, including our stakeholder engagement processes and the key principles that underlie our approach. We provide examples of policy and practice influence in FASD prevention, diagnosis and management that have been achieved over the past five years and discuss challenges that are routinely faced in the translation of our work.

A reduction in reported alcohol use in pregnancy in Australian Aboriginal communities: a prevention campaign showing promise.

OBJECTIVE: Aboriginal leaders in remote Western Australian communities with high rates of prenatal alcohol exposure invited researchers to evaluate the community-led Marulu foetal alcohol spectrum disorder (FASD) Prevention Strategy initiated in 2010. METHODS: The proportion of women reporting alcohol use during pregnancy to midwives was compared between 2008, 2010 and 2015. Initial midwife appointments were calculated by weeks of gestation. The proportions of women reporting alcohol use by age at birth were compared. RESULTS: Alcohol use reduced significantly from 2010 (61.0%) to 2015 (31.9%) with first-trimester use reducing significantly from 2008 (45.1%) to 2015 (21.6%). Across all years, 40.8% reported alcohol use during pregnancy and 14.8% reported use in both first and third trimesters. Most women attended the midwife in the first trimester. There was a significant relationship between increased maternal age and third-trimester alcohol use. CONCLUSIONS: The reduction in reported prenatal alcohol exposure in an Aboriginal community setting during a period of prevention activities provides initial evidence for a community-led strategy that might be applicable to similar communities. Implications for public health: The reductions in alcohol use reduce the risk of children being born with FASD in an area with high prevalence, with possible resultant reductions in associated health, economic and societal costs.

Predicting alcohol dependence treatment outcomes: a prospective comparative study of clinical psychologists versus 'trained' machine learning models.

BACKGROUND AND AIMS: Clinical staff are typically poor at predicting alcohol dependence treatment outcomes. Machine learning (ML) offers the potential to model complex clinical data more effectively. This study tested the predictive accuracy of ML algorithms demonstrated to be effective in predicting alcohol dependence outcomes, compared with clinical judgement and traditional linear regression. DESIGN: Prospective study. ML models were trained on 1016 previously treated patients (training-set) who attended a hospital-based alcohol and drug clinic. ML models (n = 27), clinical psychologists (n = 10) and a 'traditional' logistic regression model (n = 1) predicted treatment outcome during the initial treatment session of an alcohol dependence programme. SETTING: A 12-week cognitive behavioural therapy (CBT)-based abstinence programme for alcohol dependence in a hospital-based alcohol and drug clinic in Australia. PARTICIPANTS: Prospective predictions were made for 220 new patients (test-set; 70.91% male, mean age = 35.78 years, standard deviation = 9.19). Sixty-nine (31.36%) patients successfully completed treatment. MEASUREMENTS: Treatment success was the primary outcome variable. The cross-validated training-set accuracy of ML models was used to determine optimal parameters for selecting models for prospective prediction. Accuracy, sensitivity, specificity, area under the receiver operator curve (AUC), Brier score and calibration curves were calculated and compared across predictions. FINDINGS: The mean aggregate accuracy of the ML models (63.06%) was higher than the mean accuracy of psychologist predictions (56.36%). The most accurate ML model achieved 70% accuracy, as did logistic regression. Both were more accurate than psychologists (P < 0.05) and had superior calibration. The high specificity for the selected ML (79%) and logistic regression (90%) meant they were significantly (P < 0.001) more effective than psychologists (50%) at correctly identifying patients whose treatment was unsuccessful. For ML and logistic regression, high specificity came at the expense of sensitivity (26 and 31%, respectively), resulting in poor prediction of successful patients. CONCLUSIONS: Machine learning models and logistic regression appear to be more accurate than psychologists at predicting treatment outcomes in an abstinence programme for alcohol dependence, but sensitivity is low.

A preliminary investigation of the effects of prenatal alcohol exposure on facial morphology in children with Autism Spectrum Disorder.

Alcohol exposure during pregnancy has been associated with altered brain development and facial dysmorphology. While Autism Spectrum Disorder (ASD) is not specifically related to distinct facial phenotypes, recent studies have suggested certain facial characteristics such as increased facial masculinity and asymmetry may be associated with ASD and its clinical presentations. In the present study, we conducted a preliminary investigation to examine facial morphology in autistic children with (n = 37; mean age = 8.21 years, SD = 2.72) and without (n = 100; mean age = 8.37 years, SD = 2.47) prenatal alcohol exposure. Using three-dimensional facial scans and principal component analysis, we identified a facial shape associated with prenatal alcohol exposure in autistic children. However, variations in the alcohol-related facial shape were generally not associated with behavioral and cognitive outcomes. These findings suggest that while early exposure to alcohol may influence the development of facial structures, it does not appear to be associated with ASD phenotypic variability. Importantly, although these findings do not implicate a role for prenatal alcohol exposure in the etiology of ASD, further research is warranted to investigate the link between prenatal alcohol exposure and facial morphology differences among neurodevelopmental conditions.

School-based intervention to address self-regulation and executive functioning in children attending primary schools in remote Australian Aboriginal communities.

Executive functioning and self-regulation influence a range of outcomes across the life course including physical and mental health, educational success, and employment. Children prenatally exposed to alcohol or early life trauma (ELT) are at higher risk of impairment of these skills and may require intervention to address self-regulation deficits. Researchers partnered with the local Aboriginal health organization and schools to develop and pilot a manualized version of the Alert Program® in the Fitzroy Valley, north Western Australia, a region with documented high rates of fetal alcohol spectrum disorder and ELT. This self-controlled cluster randomized trial evaluated the effect of an 8-week Alert Program® intervention on children's executive functioning and self-regulation skills. Following parent or caregiver consent (referred to hereafter as parent), 271 students were enrolled in the study. This reflects a 75% participation rate and indicates the strong community support that exists for the study. Teachers from 26 primary school classrooms across eight Fitzroy Valley schools received training to deliver eight, one-hour Alert Program® lessons over eight-weeks to students. Student outcomes were measured by parent and teacher ratings of children's behavioral, emotional, and cognitive regulation. The mean number of lessons attended by children was 4.2. Although no significant improvements to children's executive functioning skills or behavior were detected via the teacher-rated measures as hypothesized, statistically significant improvements were noted on parent-rated measures of executive functioning and behavior. The effectiveness of future self-regulation programs may be enhanced through multimodal delivery through home, school and community based settings to maximize children's exposure to the intervention. Despite mixed findings of effect, this study was an important first step in adapting and evaluating the Alert Program® for use in remote Australian Aboriginal community schools, where access to self-regulation interventions is limited.

Machine learning vs addiction therapists: A pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication.

BACKGROUND AND OBJECTIVES: Clinical staff providing addiction treatment predict patient outcome poorly. Prognoses based on linear statistics are rarely replicated. Addiction is a complex non-linear behavior. Incorporating non-linear models, Machine Learning (ML) has successfully predicted treatment outcome when applied in other areas of medicine. Using identical assessment data across the two groups, this study compares the accuracy of ML models versus clinical staff to predict alcohol dependence treatment outcome in behavior therapy using patient data only. METHODS: Machine learning models (n = 28) were constructed ('trained') using demographic and psychometric assessment data from 780 previously treated patients who had undertaken a 12 week, abstinence-based Cognitive Behavioral Therapy program for alcohol dependence. Independent predictions applying assessment data for an additional 50 consecutive patients were obtained from 10 experienced addiction therapists and the 28 trained ML models. The predictive accuracy of the ML models and the addiction therapists was then compared with further investigation of the 10 best models selected by cross-validated accuracy on the training-set. Variables selected as important for prediction by staff and the most accurate ML model were examined. RESULTS: The most accurate ML model (Fuzzy Unordered Rule Induction Algorithm, 74%) was significantly more accurate than the four least accurate clinical staff (51%-40%). However, the robustness of this finding may be limited by the moderate area under the receiver operator curve (AUC = 0.49). There was no significant difference in mean aggregate predictive accuracy between 10 clinical staff (56.1%) and the 28 best models (58.57%). Addiction therapists favoured demographic and consumption variables compared with the ML model using more questionnaire subscales. CONCLUSIONS: The majority of staff and ML models were not more accurate than suggested by chance. However, the best performing prediction models may provide useful adjunctive information to standard clinically available prognostic data to more effectively target treatment approaches in clinical settings.

Predicting Language Difficulties in Middle Childhood From Early Developmental Milestones: A Comparison of Traditional Regression and Machine Learning Techniques.

Purpose: The current study aimed to compare traditional logistic regression models with machine learning algorithms to investigate the predictive ability of (a) communication performance at 3 years old on language outcomes at 10 years old and (b) broader developmental skills (motor, social, and adaptive) at 3 years old on language outcomes at 10 years old. Method: Participants (N = 1,322) were drawn from the Western Australian Pregnancy Cohort (Raine) Study (Straker et al., 2017). A general developmental screener, the Infant Monitoring Questionnaire (Squires, Bricker, & Potter, 1990), was completed by caregivers at the 3-year follow-up. Language ability at 10 years old was assessed using the Clinical Evaluation of Language Fundamentals-Third Edition (Semel, Wiig, & Secord, 1995). Logistic regression models and interpretable machine learning algorithms were used to assess predictive abilities of early developmental milestones for later language outcomes. Results: Overall, the findings showed that prediction accuracies were comparable between logistic regression and machine learning models using communication-only performance as well as performance on communication and broader developmental domains to predict language performance at 10 years old. Decision trees are incorporated to visually present these findings but must be interpreted with caution because of the poor accuracy of the models overall. Conclusions: The current study provides preliminary evidence that machine learning algorithms provide equivalent predictive accuracy to traditional methods. Furthermore, the inclusion of broader developmental skills did not improve predictive capability. Assessment of language at more than 1 time point is necessary to ensure children whose language delays emerge later are identified and supported. Supplemental Material: https://doi.org/10.23641/asha.6879719.

Study protocol for a self-controlled cluster randomised trial of the Alert Program to improve self-regulation and executive function in Australian Aboriginal children with fetal alcohol spectrum disorder.

INTRODUCTION: While research highlights the benefits of early diagnosis and intervention for children with fetal alcohol spectrum disorders (FASD), there are limited data documenting effective interventions for Australian children living in remote communities. METHODS AND ANALYSIS: This self-controlled cluster randomised trial is evaluating the effectiveness of an 8-week Alert Program school curriculum for improving self-regulation and executive function in children living in remote Australian Aboriginal communities. Children in grades 1-6 attending any of the eight participating schools across the Fitzroy Valley in remote North-West Australia (N ≈ 363) were invited to participate. Each school was assigned to one of four clusters with clusters randomly assigned to receive the intervention at one of four time points. Clusters two, three and four had extended control conditions where students received regular schooling before later receiving the intervention. Trained classroom teachers delivered the Alert Program to students in discrete, weekly, 1-hour lessons. Student outcomes were assessed at three time points. For the intervention condition, data collection occurred 2 weeks immediately before and after the intervention, with a follow-up 8 weeks later. For control conditions in clusters two to four, the control data collection matched that of the data collection for the intervention condition in the preceding cluster. The primary outcome is change in self-regulation. FASD diagnoses will be determined via medical record review after the completion of data collection. The results will be analysed using generalised linear mixed modelling and reported in accordance with Consolidated Standards of Reporting Trials (CONSORT) guidelines. ETHICS AND DISSEMINATION: Ethical approval was obtained from the University of Western Australia (WA) (RA/4/1/7234), WA Aboriginal Health Ethics Committee (601) and WA Country Health Service (2015:04). The Kimberley Aboriginal Health Planning Forum Research Sub-Committee and WA Department of Education also provided approval. The results will be disseminated through peer-reviewed journals, conference presentations, the media and at forums. TRIAL REGISTRATION NUMBER: ACTRN12615000733572; Pre-results.