Psychosocial Factors Predict the Level of Aggression of People with Drug Addiction: A Machine Learning Approach

Hong, Liu; Xie, Chuyin; Lian, Peican; Yu, Chengfu; Xie, Ying

doi:10.1080/13548506.2021.1910321

Cited by 4 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characteristics of the included studies and ML models are summarized in Tables 1 , 2 . One study was conducted in the United States ( 17 ), two in China ( 18 , 24 ), two in Canada ( 25 , 26 ), two in Netherlands ( 27 , 28 ), and one in Switzerland ( 29 ). We classified the studies in terms of the size of their samples into: small [<100 data entries, one study ( 18 )], medium [200–900, three studies ( 24 , 25 , 29 )], and large [≥1,000, four studies ( 17 , 26 – 28 )].…”

Section: Resultsmentioning

confidence: 99%

“…Three studies focused on the predictive model of aggression specifically in patients affected by schizophrenia spectrum disorders: two of them in a forensic setting ( 18 , 29 ), and one in a clinical setting ( 25 ). One study enrolled patients affected by drug addiction ( 24 ). Three studies used information of psychiatric patients from Electronic Health Records (EHR) ( 17 , 27 , 28 ), and one analyzed retrospective information of patients from 10 forensic psychiatry facilities ( 26 ).…”

Section: Resultsmentioning

confidence: 99%

“…Three studies used information of psychiatric patients from Electronic Health Records (EHR) ( 17 , 27 , 28 ), and one analyzed retrospective information of patients from 10 forensic psychiatry facilities ( 26 ). Only one study ( 28 ) used an independent cohort to validate the ML model, while the remaining ones used only internal cross-validation ( 17 , 18 , 24 – 27 , 29 ). Three studies out of eight reported ML algorithms with AUC above 0.80 ( 18 , 26 , 29 ), which is an indication of good discrimination ability.…”

Section: Resultsmentioning

confidence: 99%

“…Regarding RoB, seven out of eight studies scored high in RoB on participant selection for the following reasons: five used data from existing sources, such as EHR ( 17 , 25 – 28 ), or medical records ( 29 ) collected for different purposes and without a protocol; one did not perform a consecutive recruitment of patients ( 24 ). One study scored high in RoB on predictors, because assessment of predictors was not made without knowledge of outcome data ( 18 ), and one scored unclear in the predictors domain because it was not clear if assessment of predictors was made without knowledge of outcome data ( 24 ). One study scored unclear in the outcome session because authors did not clearly define when and how they measured the outcome ( 24 ).…”

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

The impact of machine learning in predicting risk of violence: A systematic review

et al. 2022

View full text Add to dashboard Cite

BackgroundInpatient violence in clinical and forensic settings is still an ongoing challenge to organizations and practitioners. Existing risk assessment instruments show only moderate benefits in clinical practice, are time consuming, and seem to scarcely generalize across different populations. In the last years, machine learning (ML) models have been applied in the study of risk factors for aggressive episodes. The objective of this systematic review is to investigate the potential of ML for identifying risk of violence in clinical and forensic populations.MethodsFollowing Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines, a systematic review on the use of ML techniques in predicting risk of violence of psychiatric patients in clinical and forensic settings was performed. A systematic search was conducted on Medline/Pubmed, CINAHL, PsycINFO, Web of Science, and Scopus. Risk of bias and applicability assessment was performed using Prediction model Risk Of Bias ASsessment Tool (PROBAST).ResultsWe identified 182 potentially eligible studies from 2,259 records, and 8 papers were included in this systematic review. A wide variability in the experimental settings and characteristics of the enrolled samples emerged across studies, which probably represented the major cause for the absence of shared common predictors of violence found by the models learned. Nonetheless, a general trend toward a better performance of ML methods compared to structured violence risk assessment instruments in predicting risk of violent episodes emerged, with three out of eight studies with an AUC above 0.80. However, because of the varied experimental protocols, and heterogeneity in study populations, caution is needed when trying to quantitatively compare (e.g., in terms of AUC) and derive general conclusions from these approaches. Another limitation is represented by the overall quality of the included studies that suffer from objective limitations, difficult to overcome, such as the common use of retrospective data.ConclusionDespite these limitations, ML models represent a promising approach in shedding light on predictive factors of violent episodes in clinical and forensic settings. Further research and more investments are required, preferably in large and prospective groups, to boost the application of ML models in clinical practice.Systematic review registration[www.crd.york.ac.uk/prospero/], identifier [CRD42022310410].

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

The impact of machine learning in predicting risk of violence: A systematic review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Substance uses reversible disorder causes social problems and asdistinguished by a range of physical, psychological, and social impacts. Substance uses disorders are related to different psychological and social factors [14]. Literature has demonstrated that individuals with substance use disorder have more psychosocial problems.…”

Section: Introductionmentioning

confidence: 99%

Psycho-Social and Morbidity of Substance Use Disorder in Women

Iftikhar

Riaz

2022

IJIST

View full text Add to dashboard Cite

Substance abuse disorder is a major and worldwide concern that cursed countries and mankind. Psychosocial factors influences differ across the person and may contribute to the development of physical and mental disorders. The research aimed to investigate the impact of psychological factors (Self-esteem, Depression, Anxiety, and Decision-Making Confidence) and social factors (Childhood Problems, Hostility, Risk-taking, and Social Conformity) that predictors of substance use disorder in women. en cross-sectional survey design was used in this study. Drug Abuse Screaming Test (DAST) and psychosocial functioning scale were used to collect data on women (N=200). The purposive sampling technique was employed for sample selection; moreover, the snowball technique was also used as the drug-addicted women recommended the other women. Results of the study ravels that psychosocial factors were a significant predictor of substance use disorder in women. The finding of the multiple regression analysis reveals that psychosocial factors were significant predictors of substance use disorder in women [R2 =.46, F (1,142)14.26, p<.01]. In conclusion, this study highlights some psychological (Self-esteem, Anxiety, Decision-making confidence) and social factors (Childhood problems, Risk-taking, and social conformity) that are valuable predictors of substance use disorder in women. These findings may help clinicians to develop treatment and policy guidelines for the prevention of drug addiction in women.

show abstract

Human addictive behavior prediction by using lime with ensemble model

Sabapathi,

Paul Peter Jacob,

Thirumaran Chembian

et al. 2024

IJEECS

View full text Add to dashboard Cite

<span>The data-driven techniques have utilized data mining and machine learning (ML) techniques in the biomedical and healthcare fields. The process of decision-making in uncertain contextual related to human addictions and emotions play an important role in the present research. The main aim of the research is to perform classification and generate a support system for uncertain addiction circumstances by proposing a technique for drug addiction treatment. The human behavior has majority shown challenges for the prediction of human behaviors that includes body poses estimation, movements and interaction with objects. This pose estimation has showed complexity with more pose aspects and the proposed research attempts to understand the human behaviors. The present research uses the local interpretable model-agnostic explanations (LIME) for finding the input features which are most important to generate a particular output based on decision service. LIME understands the model to perturb the data samples as an input and understands shows predictions change. Also, the ensemble classifier contains classifiers group that combines for performing the prediction of all unseen instances based on voting. The proposed LIME Feature-Ensemble classifier obtained 97.54% of accuracy when compared to the existing convolutional neural network (CNN) of 59.33% and Ensemble model of 93.33% accuracy.</span>

show abstract

Psychosocial Factors Predict the Level of Aggression of People with Drug Addiction: A Machine Learning Approach

Cited by 4 publications

References 20 publications

The impact of machine learning in predicting risk of violence: A systematic review

The impact of machine learning in predicting risk of violence: A systematic review

Psycho-Social and Morbidity of Substance Use Disorder in Women

Human addictive behavior prediction by using lime with ensemble model

Contact Info

Product

Resources

About