Prediction of physical violence in schizophrenia with machine learning algorithms

Prediction of physical violence in schizophrenia with machine learning algorithms. Wang, K. Z., Bani-Fatemi, A., Adanty, C., Harripaul, R., Griffiths, J., Kolla, N., Gerretsen, P., Graff, A., & De Luca, V. Psychiatry Research, 289:11296, 2020.

Paper doi abstract bibtex

Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence.

@article{wbahgkggd20,
abstract = {Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence.},
author = {Wang, Kevin Z. and Bani-Fatemi, Ali and Adanty, Christopher and Harripaul, Ricardo and Griffiths, John and Kolla, Nathan and Gerretsen, Philip and Graff, Ariel and {De Luca}, Vincenzo},
doi = {10.1016/j.psychres.2020.112960},
issn = {18727123},
journal = {Psychiatry Research},
keywords = {Childhood trauma,Machine learning,Personality,Schizophrenia,Violence},
pages = {11296},
pmid = {32361562},
title = {{Prediction of physical violence in schizophrenia with machine learning algorithms}},
url = {https://doi.org/10.1016/j.psychres.2020.112960},
volume = {289},
year = {2020}
}

Downloads: 0

{"_id":"2FHFEbpKNrKyGMFSh","bibbaseid":"wang-banifatemi-adanty-harripaul-griffiths-kolla-gerretsen-graff-etal-predictionofphysicalviolenceinschizophreniawithmachinelearningalgorithms-2020","author_short":["Wang, K. Z.","Bani-Fatemi, A.","Adanty, C.","Harripaul, R.","Griffiths, J.","Kolla, N.","Gerretsen, P.","Graff, A.","De Luca, V."],"bibdata":{"bibtype":"article","type":"article","abstract":"Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence.","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Kevin","Z."],"suffixes":[]},{"propositions":[],"lastnames":["Bani-Fatemi"],"firstnames":["Ali"],"suffixes":[]},{"propositions":[],"lastnames":["Adanty"],"firstnames":["Christopher"],"suffixes":[]},{"propositions":[],"lastnames":["Harripaul"],"firstnames":["Ricardo"],"suffixes":[]},{"propositions":[],"lastnames":["Griffiths"],"firstnames":["John"],"suffixes":[]},{"propositions":[],"lastnames":["Kolla"],"firstnames":["Nathan"],"suffixes":[]},{"propositions":[],"lastnames":["Gerretsen"],"firstnames":["Philip"],"suffixes":[]},{"propositions":[],"lastnames":["Graff"],"firstnames":["Ariel"],"suffixes":[]},{"propositions":[],"lastnames":["De Luca"],"firstnames":["Vincenzo"],"suffixes":[]}],"doi":"10.1016/j.psychres.2020.112960","issn":"18727123","journal":"Psychiatry Research","keywords":"Childhood trauma,Machine learning,Personality,Schizophrenia,Violence","pages":"11296","pmid":"32361562","title":"Prediction of physical violence in schizophrenia with machine learning algorithms","url":"https://doi.org/10.1016/j.psychres.2020.112960","volume":"289","year":"2020","bibtex":"@article{wbahgkggd20,\nabstract = {Patients with schizophrenia have been shown to have an increased risk for physical violence. While certain features have been identified as risk factors, it has been difficult to integrate these variables to identify violent patients. The present study thus attempts to develop a clinically-relevant predictive tool. In a population of 275 schizophrenia patients, we identified 103 participants as violent and 172 as non-violent through electronic medical documentation, and conducted cross-sectional assessments to identify demographic, clinical, and sociocultural variables. Using these predictors, we utilized seven machine learning classification algorithms to predict for past instances of physical violence. Our classification algorithms predicted with significant accuracy compared to random discrimination alone, and had varying degrees of predictive power, as described by various performance measures. We determined that the random forest model performed marginally better than other algorithms, with an accuracy of 62% and an area under the receiver operator characteristic curve (AUROC) of 0.63. To summarize, machine learning classification algorithms are becoming increasingly valuable, though, optimization of these models is needed to better complement diagnostic decisions regarding early interventional measures to predict instances of physical violence.},\nauthor = {Wang, Kevin Z. and Bani-Fatemi, Ali and Adanty, Christopher and Harripaul, Ricardo and Griffiths, John and Kolla, Nathan and Gerretsen, Philip and Graff, Ariel and {De Luca}, Vincenzo},\ndoi = {10.1016/j.psychres.2020.112960},\nissn = {18727123},\njournal = {Psychiatry Research},\nkeywords = {Childhood trauma,Machine learning,Personality,Schizophrenia,Violence},\npages = {11296},\npmid = {32361562},\ntitle = {{Prediction of physical violence in schizophrenia with machine learning algorithms}},\nurl = {https://doi.org/10.1016/j.psychres.2020.112960},\nvolume = {289},\nyear = {2020}\n}\n","author_short":["Wang, K. Z.","Bani-Fatemi, A.","Adanty, C.","Harripaul, R.","Griffiths, J.","Kolla, N.","Gerretsen, P.","Graff, A.","De Luca, V."],"key":"wbahgkggd20","id":"wbahgkggd20","bibbaseid":"wang-banifatemi-adanty-harripaul-griffiths-kolla-gerretsen-graff-etal-predictionofphysicalviolenceinschizophreniawithmachinelearningalgorithms-2020","role":"author","urls":{"Paper":"https://doi.org/10.1016/j.psychres.2020.112960"},"keyword":["Childhood trauma","Machine learning","Personality","Schizophrenia","Violence"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://leandrosweb.com/library.bib","dataSources":["vRJd4wNg9HpoZSMHD"],"keywords":["childhood trauma","machine learning","personality","schizophrenia","violence"],"search_terms":["prediction","physical","violence","schizophrenia","machine","learning","algorithms","wang","bani-fatemi","adanty","harripaul","griffiths","kolla","gerretsen","graff","de luca"],"title":"Prediction of physical violence in schizophrenia with machine learning algorithms","year":2020}