Multidimensional subtypes and treatment outcome in first-time DWI offenders

AI-based disease category prediction model using symptoms from low-resource Ethiopian language: Afaan Oromo text

Automated disease diagnosis and prediction, powered by AI, play a crucial role in enabling medical professionals to deliver effective care to patients. While such predictive tools have been extensively explored in resource-rich languages like English, this manuscript focuses on predicting disease categories automatically from symptoms documented in the Afaan Oromo language, employing various classification algorithms. This study encompasses machine learning techniques such as support vector machines, random forests, logistic regression, and Naïve Bayes, as well as deep learning approaches including LSTM, GRU, and Bi-LSTM. Due to the unavailability of a standard corpus, we prepared three data sets with different numbers of patient symptoms arranged into 10 categories. The two feature representations, TF-IDF and word embedding, were employed. The performance of the proposed methodology has been evaluated using accuracy, recall, precision, and F1 score. The experimental results show that, among machine learning models, the SVM model using TF-IDF had the highest accuracy and F1 score of 94.7%, while the LSTM model using word2vec embedding showed an accuracy rate of 95.7% and F1 score of 96.0% from deep learning models. To enhance the optimal performance of each model, several hyper-parameter tuning settings were used. This study shows that the LSTM model verifies to be the best of all the other models over the entire dataset.

Applicability of Type A/B alcohol dependence in the general population

BACKGROUND

This study examined the concurrent and predictive validity of Type A/B alcohol dependence in the general population-a typology developed in clinical populations to gauge severity of dependence.

METHODS

Data were drawn from Waves 1 and 2 of the National Epidemiologic Survey on Alcohol and Related Conditions (NESARC). The sample included 1,172 alcohol-dependent drinkers at baseline who were reinterviewed three years later. Latent class analysis was used to derive Type A/B classification using variables replicating the original Type A/B typology. Predictive validity of the Type A/B classification was assessed by multivariable linear and logistic regressions.

RESULTS

A two-class solution consistent with Babor's original Type A/B typology adequately fit the data. Type B alcoholics in the general population, compared to Type As, had higher alcohol severity and more co-occurring drug, mental, and physical health problems. In the absence of treatment services utilization, Type B drinkers had two times the odds of being alcohol dependent three years later. Among those who utilized alcohol treatment services, Type B membership was predictive of heavy drinking and drug dependence, but not alcohol dependence, three years later.

CONCLUSIONS

Findings suggest that Type A/B classification is both generalizable to, and valid within, the US general population of alcohol dependent drinkers. Results highlight the value of treatment for mitigating the persistence of dependence among Type B alcoholics in the general population. Screening for markers of vulnerability to Type B dependence could be of clinical value for health care providers to determine appropriate intervention.

Relative mortality among criminals in Norway and the relation to drug and alcohol related offenses

BACKGROUND

Registered offenders are known to have a higher mortality rate, but given the high proportion of offenders with drug-addiction, particularly among offenders with a custodial sentence, higher mortality is expected. While the level of overall mortality compared to the non-criminal population is of interest in itself, we also estimate the risk of death by criminal records related to substance abuse and other types of criminal acts, and separate between those who receive a prison sentence or not.

METHODS

Age-adjusted relative risks of death for 2000-2008 were studied in a population based dataset. Our dataset comprise the total Norwegian population of 2.9 million individuals aged 15-69 years old in 1999, of whom 10% had a criminal record in the 1992-1999 period.

RESULTS

Individuals with a criminal record have twice the relative risk (RR) of death of the control group (non-offenders). Males with a record of use/possession of drugs and a prison record have an 11.9 RR (females, 15.6); males with a drug record but no prison record have a 6.9 RR (females 10.5). Males imprisoned for driving under the influence of substances have a 4.4 RR (females 5.6); males with a record of driving under the influence but no prison sentence have a 3.2 RR (females 6.5). Other male offenders with a prison record have a 2.8 RR (females 3.7); other male offenders with no prison record have a 1.7 RR (females 2.3).

CONCLUSION

Significantly higher mortality was found for people with a criminal record, also for those without any record of drug use. Mortality is much higher for those convicted of substance-related crimes: more so for drug- than for alcohol-related crimes and for women.

Decision-making capacities and affective reward anticipation in DWI recidivists compared to non-offenders: a preliminary study

OBJECTIVES

Impaired decision making is seen in several problem behaviours including alcoholism and problem gambling. Decision-making style may contribute to driving while impaired with alcohol (DWI) in some offenders as well. The Somatic Marker Framework theorizes that decision making is the product of two interacting affective neural systems, an impulsive, rapid, amygdala-dependent process for emotionally signalling the immediate negative or positive consequences of an option, and a reflective, longer-lasting, ventral medial prefrontal cortex dependent system for emotionally signalling the future negative or positive prospects of an option. This study tested the hypothesis that offenders who showed disadvantageous decision-making would be at higher risk for recidivism than those who showed more advantageous decision-making. In addition, in line with the Somatic Marker Hypothesis, offenders who showed disadvantageous decision-making would exhibit a distinct pattern of somatic activation compared to offenders who showed more advantageous decision-making.

METHODS

A sample of 21 DWI offenders with from 2 to 7 past DWI convictions and a reference group consisting of 19 non-offender (N-O) drivers were recruited and administered the Iowa Gambling Task (IGT), as well as evaluated on sociodemographic, driving and alcohol use dimensions. In addition, anticipatory skin conductance response (aSCR) was measured in the 5s prior to each of a 100 card draws on the IGT.

RESULTS

Median split of the DWI offender sample based upon overall performance on the IGT yielded two subgroups (IGT-R Hi and IGT-R Lo). Hypothesis 1 was supported, as the IGT-R Lo group possessed significantly greater frequency of past DWI convictions and severity of past drinking. Descriptive analyses revealed that on the IGT, IGT-R Hi group performed similarly to the N-O reference group while the IGT-R Lo group performed significantly worse. Hypothesis 2 was not supported.

CONCLUSIONS

Decision making is a plausible explanatory neurocognitive pathway to severer forms of DWI. The role of emotional processing in DWI risk is uncertain. Subtyping DWI offenders using neurocognitive criteria seems a promising avenue for improving clinically meaningful methods of DWI risk assessment and intervention.

A descriptive analysis of the social context of drinking among first-time DUI offenders

OBJECTIVE

To understand the role of social context in contributing to the incidence of alcohol-impaired driving.

METHODS

Telephone interviews were conducted with 161 individuals who received a first-time DUI citation. They were predominantly white (70%), male (62%) and 21 to 45 years of age (62%). They were paid $25 for their participation. Questions were asked about their social network, the social context in which they typically drink, the specific location and circumstances where they were drinking at the time of their citation, risky driving behaviors, in the last month as well as the number of traffic tickets they received and crashes they have been involved in since they started to drive.

RESULTS

Two reliable social contexts of drinking were identified through principle components factors analysis: emotional pain and social facilitation. Analyses of variance showed that drinking in a context of emotional pain (eg, to deal with depression, stress) was related to drinking alone at this location and driving when they know they have had too much to drink. Drinking in a context of social facilitation (eg, with friends, to be sociable) was related to drinking more frequently and with others (versus alone) at this location. Social facilitation was also positively related to driving over the speed limit and running a red light/stop sign.

CONCLUSIONS

The social context of drinking is important for understanding the social network of drinking drivers, because most (86%) said that someone from their social network was with them at this drinking location. The need to understand how significant others influence the context of drinking as well as the likelihood of impaired driving is critical for program development. These results suggest that different types of interventions are needed for offenders depending on their social context of drinking.

Unraveling the complexity of driving while intoxicated: a study into the prevalence of psychiatric and substance abuse comorbidity

OBJECTIVE

Research is beginning to provide an indication of the co-occurring substance abuse and mental health needs for the driving under the influence (DUI) population. This study aimed to examine the extent of such psychiatric problems among a large sample size of DUI offenders entering treatment in Texas.

METHODS

This is a study of 36,373 past year DUI clients and 308,714 non-past year DUI clients admitted to Texas treatment programs between 2005 and 2008. Data were obtained from the State's administrative dataset.

RESULTS

Analysis indicated that non-past year DUI clients were more likely to present with more severe illicit substance use problems, while past year DUI clients were more likely to have a primary problem with alcohol. Nevertheless, a cannabis use problem was also found to be significantly associated with DUI recidivism in the last year. In regards to mental health status, a major finding was that depression was the most common psychiatric condition reported by DUI clients, including those with more than one DUI offence in the past year. This cohort also reported elevated levels of Bipolar Disorder compared to the general population, and such a diagnosis was also associated with an increased likelihood of not completing treatment. Additionally, female clients were more likely to be diagnosed with mental health problems than males, as well as more likely to be placed on medications at admission and more likely to have problems with methamphetamine, cocaine, and opiates.

CONCLUSIONS

DUI offenders are at an increased risk of experiencing comorbid psychiatric disorders, and thus, corresponding treatment programs need to cater for a range of mental health concerns that are likely to affect recidivism rates.

Personality traits and mental health of severe drunk drivers in Sweden

The present study was intended to investigate personality characteristics and mental health of severe driving under influence (DUI) offenders in a Swedish cohort. More specifically the aim was to investigate the personality traits as assessed by The NEO personality inventory (NEO-PI-R) and aspects of mental health as assessed by the symptom checklist (SCL-90) as compared to the general population. The subjects were 162 severe DUI offenders (with the BAC >0.099%) with an age range of 18-88 years, 143 males and 19 females. It was found that the openness to experience and conscientiousness scales of NEO-PI-R differentiated Swedish DUI offenders from Swedish norm population. The differences between the DUI group and the general population on the on SCL-90 scales were all significant except on the Hostility scale. Two main subtypes of DUI offenders identified were roughly comparable to types I and II alcoholics, as in Cloninger's typology. Among all the scales used (personality traits, psychiatric comorbidity and alcohol use), the only factor that was predictive for future relapses to drunk driving was the factor of depression.

Drivers' Understanding of Adaptive Cruise Control Limitations

Adaptive cruise control (ACC) is one system that is changing the driver-vehicle relationship. However, not all drivers are aware of the systems' capabilities or limitations. In this study, a cluster analysis was used to classify drivers based on how aware they were of the limitations associated with ACC. Three cluster groups emerged: those who are aware, unaware, and unsure of ACC limitations. Further examination revealed that drivers who were unaware or unsure exhibited potentially hazardous behavior when compared to the aware group. These two groups were more willing to use ACC when tired or on curvy roads. The unaware and unsure groups were also more likely to use conventional cruise control (CCC) in the absence of ACC. All three cluster groups reported high levels of trust in ACC. This may be problematic for the unaware and unsure groups since they may trust the system based on inappropriate expectations which can impact driver safety. Lower levels of awareness coupled with high levels of trust in ACC may correspond to potential misuse of the system. However, the findings suggest that this could be potentially mitigated through extended use of ACC.

Depressive symptoms, drinking consequences, and motivation to change in first time DWI offenders

BACKGROUND

Psychological disorders are common among driving-while-intoxicated (DWI) offenders; thus, a DWI arrest may serve as an important opportunity for further screening and subsequent treatment.

OBJECTIVES

The current study examined the extent to which mild to moderate pretreatment depressive symptoms, as measured by the Beck Depression Inventory (BDI), could predict intervention outcomes in 284 first-time DWI offenders.

METHODS

Participants were given drinking-related and psychosocial assessments at the beginning and end of a 10-week intervention and at 6- and 12-month follow-ups.

RESULTS

After the intervention and at both follow-ups, all participants reported declines in depressive symptoms, alcohol consumption, and negative drinking consequences and higher self-efficacy to avoid high-risk drinking. It was notable, however, that offenders with depressive symptoms reported more drinking-related consequences and lower self-efficacy at all time points, but greater motivation to change their drinking behavior.

CONCLUSIONS

The findings suggest that offenders with depressive symptoms have more severe symptomatology than nondepressed offenders but may be more amenable to changing their drinking.

SCIENTIFIC SIGNIFICANCE

The BDI may be a useful screening tool for determining which offenders are in need of an intervention following a DWI arrest.

A double-blind, placebo-controlled pilot trial of quetiapine for the treatment of Type A and Type B alcoholism

BACKGROUND

Atypical antipsychotics may be useful in the treatment of alcohol dependence. Human trials suggest that atypical antipsychotics may reduce alcohol craving and consumption, especially among patients with comorbid psychopathology. Therefore, these medications may be more useful for treating more severely affected alcoholics, such as patients with Type B alcoholism. Type B alcoholics are characterized by an early age of onset of problem drinking, high severity of alcohol dependence, increased psychopathology, and treatment-resistance. Quetiapine is an atypical antipsychotic with a favorable side effect profile, and may be a promising medication for the treatment of alcohol dependence, particularly Type B alcoholism.

METHODS

Male and female alcoholics (33 Type A and 28 Type B) were included in a 12-week, double-blind, placebo-controlled trial. After detoxification, patients were randomized to receive quetiapine (n = 29), 400 mg/d at bedtime, or placebo (n = 32). The primary outcome measure was the quantity and frequency of alcohol consumption, measured by the timeline follow back.

RESULTS

Forty-seven patients (77%) completed the trial, with no significant between-group differences in treatment retention. Nine quetiapine-treated patients (31%) maintained complete abstinence compared with 2 placebo-treated patients (6%) (chi(2) = 6.3, P = 0.012). There was a significant interaction between quetiapine and alcoholic subtype. As predicted, quetiapine- versus placebo-treated Type B alcoholics had significantly fewer days of drinking and fewer days of heavy drinking. Alcohol craving was also significantly reduced in quetiapine-treated compared with placebo-treated Type B alcoholics. Among Type A alcoholics, quetiapine provided no advantage over placebo in improving drinking outcomes.

CONCLUSIONS

Quetiapine may be effective for the treatment of alcohol dependence, particularly in the more complicated Type B, early-onset alcoholics.

Typologies of alcohol use disorders among men with schizophrenic disorders

Alcohol use disorders are common among persons with schizophrenia and are associated with a vast array of negative consequences: criminality, poor compliance with treatment, and reoccurrence of acute episodes of psychosis. In samples of non-mentally disordered individuals, typologies of alcohol use disorders have been shown to be useful in furthering understanding of etiology and of effective treatments. Such typologies, however, have not previously been examined in individuals with schizophrenia. The main objective of the study was to validate four uni-dimensional typologies and the multi-dimensional Type I/II-Type A/B typology in a sample of men with schizophrenic disorders and alcohol use disorders. All uni-dimensional typologies showed at least some degree of concurrent validity. The Type I/II-Type A/B typology was successfully replicated with fair concurrent validity across the domains of pre-morbid risk factors and drug use, but not for the domains of criminality, illness, or personality. The predictive validity was poor for all typologies. The results provide evidence for the heterogeneity of alcohol use disorders among men with schizophrenia.

Concurrent and predictive validity of drug use and psychiatric diagnosis among first-time DWI offenders

BACKGROUND

Previous studies have found that driving while intoxicated (DWI) offenders report high rates of substance dependence and other psychiatric disorders.

METHOD

The current study evaluated the prevalence, clinical correlates at program admission, and prognostic significance over a 1-year follow-up of 2 diagnostic subgroup variables (drug abuse or dependence; mood or anxiety disorder) among 290 first-time DWI offenders receiving group counseling interventions.

RESULTS

A lifetime diagnosis of drug abuse or dependence (42% of sample) was associated with higher levels of alcohol consumption, lower coping confidence, greater readiness to change, increased alcohol, drug, and legal problems, and more alcohol-related negative consequences at the initiation of DWI intervention. Significant decreases in drinking were noted at intervention termination for the drug diagnoses subgroup, but were not sustained at 1-year follow-up. The presence of a lifetime diagnosis of anxiety or mood disorder (30% of sample) was associated with lower coping confidence, greater readiness to change, and with greater and more enduring negative consequences of drinking during the DWI intervention and 1-year follow-up period.

CONCLUSIONS

Results suggest that a psychiatric diagnosis might guide the intervention and aftercare planning for DWI offenders to reduce recidivism and drinking.

The Type A-Type B classification in a community sample of problem drinkers: structural and predictive validity

OBJECTIVE

The Type A-Type B multidimensional classification model has been useful for identifying a subgroup of alcohol dependent drinkers with more severe psychosocial problems and a poor prognosis. Evidence suggests its dimensions may be useful for identifying problem drinkers in the general population at risk for developing alcohol dependence. To date, the model has not yet been investigated for this purpose. The present study investigated the Type A/Type B distinction in a community sample of problem drinkers as well as its predictive validity among problem drinkers with no history of alcohol dependence.

METHOD

Households from a geographically delimited area in the United States were designated via random digit dialing and randomly designated members were screened for eligibility. A total of 876 participants met eligibility criteria and completed a structured interview (AUDADIS) on alcohol and other health related behaviors at baseline and at 1-year follow-up. A k-means cluster analysis was performed to identify subgroups of problem drinkers.

RESULTS

A two-cluster solution adequately fit the data and identified two main subgroups of problem drinkers consistent with a Type A-Type B distinction. The group differences held among those with and without a history of alcohol dependence and the subset of Type B drinkers with no history of alcohol dependence were approximately five times (beta = 1.56, p< or =0.01) more likely to have an initial onset of dependence than Type A drinkers at 1-year follow-up. In contrast, a DSM-IV alcohol abuse diagnosis at baseline did not predict 1-year onset of dependence.

CONCLUSIONS

The Type A-Type B model is useful for identifying untreated problem drinkers at risk for developing alcohol dependence. This model may facilitate the development of more targeted prevention efforts.

Typologies of drug dependence: comparative validity of a multivariate and four univariate models

Data from a longitudinal cohort study were used to directly compare the concurrent and predictive validity of four univariate typologic approaches with a multivariate approach in subtyping drug dependence. The four univariate typologies were based upon: (a) age-of-onset of drug abuse/dependence, (b) presence of drug abuse in first-degree relatives, (c) presence of antisocial personality disorder, and (d) sex. The multivariate typologic approach was based on indices of vulnerability, chronicity, consequences, and psychopathology, yielding the Type A/B dichotomy first demonstrated in alcohol dependence. Subtypes generated from the univariate typologies were then each compared with the multivariate typology on measures of concurrent and predictive validity, and the strength of association was compared statistically. There was evidence of significantly greater concurrent validity of the Type A/B typology compared with the univariate typologies across all the domains of validation (risk, substance use, psychopathology, personality, and overall functioning). The multivariate typology also fared better than the univariate ones in all three domains on which predictive validity was evaluated: substance use, psychopathology, and overall functioning, as well as the degree of change in several composite scores (drug, medical, legal, and psychiatric) and the global psychiatric symptom index. This direct method of comparison seemed to demonstrate the superior validity of the multivariate cluster-analytic approach over the univariate approaches to classifying subjects with drug dependence.