Personalized Aggression Risk Prediction: Comparison
View Latest Version
Please note this is a comparison between Version 2 by Camila Xu and Version 1 by Jing Ling Tay.

Aggression is defined as a range of hostile behaviors intended to cause harm. Aggression risk assessments are vital to prevent injuries and morbidities amongst patients and staff in psychiatric settings.

  • aggression risk
  • artificial intelligence
  • inpatient
  • prediction

1. Introduction

Patients with psychiatric disorders, including schizophrenia, affective conditions, and substance use disorders, have been associated with a greater risk of aggression [1]. Aggression is defined as a range of hostile behaviors intended to cause harm [2]. Specifically, patients with psychiatric disorders were three to four times more likely than their siblings without psychiatric disorders to be either subjected to aggression or perpetrate aggression [1]. A meta-analysis also found that one in five psychiatric inpatients was assaultive during their hospitalization [3]. Such aggressive episodes can potentially result in physical injuries, prolonged hospitalization and feelings of fear and trauma in victims [4]. Of note, healthcare workers can be victims of such aggression. Ninety-one percent of all healthcare workers, including psychiatrists, psychologists, nurses, social workers and allied health workers, had previously reported experiencing verbal abuse, 45% experienced physical aggression and 23.8% sustained injuries [5]. More than a quarter (26%) of psychiatric nurses suffered serious injuries such as fractures, permanent disabilities or eye injuries during their work dealing with restraints of patients under their care [6]. Consequently, such injuries can aggravate burnout, emotional and psychiatric issues, and affect morale and job satisfaction amongst healthcare workers [7,8][7][8]. Being able to predict the occurrence of such aggressive episodes prior to their onset would allow for better preparation to prevent or mitigate the onset and manage the aggressive episode if it occurs.
There are risk assessment tools that have been utilized widely to predict aggression in patients with psychiatric conditions [9]. However, some of these aggression risk assessment tools face limitations in terms of sensitivity and specificity, generalizability to other populations, limited sample size, clinical parameters or data points [9,10,11,12][9][10][11][12]. Less-valid and reliable aggression risk assessments potentially predispose patients to unfair stigma and discrimination. False positive assessment scores render lower-risk patients to unjustifiable restrictions and higher risk patients to possibly less-warranted medical attention [13].
With the advances in harnessing artificial intelligence (AI) methods to evaluate big data, it is hoped that this may help to address existing limitations and allow for more accurate aggression risk prediction amongst patients seen clinically. Initially used in other areas of medicine, artificial intelligence algorithms, including machine learning methods, have been increasingly evaluated in psychiatry for their feasibility in the: (1) classification of patients from healthy individuals based on composite data in psychotic disorders [14,15][14][15] and affective disorders [16]; (2) prediction of depressive disorders [17] and anxiety disorders [18]; and even (3) drug repurposing for potential new treatments in substance use disorders [19]. In aggression risk assessment, predictive analysis can be used to evaluate specific contributory and dynamic factors related to aggression, including personalized data from physiological, movement sensors and electronic health records [20].

2. Personalized Aggression Risk Prediction

Overall, there are few findings from this research. First, whilst the prediction accuracy across tried models and studies had observed an acceptable to excellent range for specific algorithms (AUC range 0.75–0.87), no single machine learning model outperformed the others consistently across the studies (AUC range 0.61–0.87). Second, factors associated with the risk of aggression related to the demographic and social profile, history of aggression, forensic history, other psychiatric histories, mental status and challenging behaviours during admission and management domains. In terms of accuracy in the prediction of aggression risk based on AUC values, most studies had acceptable to excellent accuracies, but there was no single model that outperformed consistently across the studies. OuResearchers' findings were comparable (AUC in the acceptable to excellent range) with that of recent studies which employed machine learning models in clinical predictions within inpatient settings related to suicide (AUC 0.77) [35][21], readmissions (AUC 0.75–0.76), and length of hospital stay (AUC 0.85–0.86) [36][22]. In ourthis reviewsearch, only two studies examined the newer supervised deep-learning models [24,27][23][24]. The newer supervised machine learning models have incorporated text sequence into their algorithms, and one study found that the deep learning model, especially when coupled with document embedding, achieved slightly better ROC [27][24] when compared with earlier machine learning algorithms. However, the optimization and balance of data point inclusion and fit of relevant included variables within a specific AI model need further evaluation. In terms of predictors of aggression, patients with certain demographic and social characteristics were more prone to aggression. The findings in this revisewarch were congruent with previous findings which included younger age [37,38,39,40[25][26][27][28][29][30],41,42], older age [43][31], being unmarried [38[26][32][33][34],44,45,46], being childless [47][35], lower education [44][32], unemployment [44,48,49[32][36][37][38],50], lower intelligence [38][26], financial issues [51,52][39][40] and homelessness [53][41]. Of note, an earlier study found an association between homelessness and crimes, but not specifically aggressive crimes [54][42]. Being subjected to physical neglect was also a predictor of aggression in this revisewarch. In contrast, existing literature highlighted other related factors such as physical abuse [55[43][44],56], separation from caregivers during growing up years [49][37], parental abuse and antisocial behaviors towards family members, family illnesses and conflicts [50][38] as pertinent predictors of aggression. A common clinical predictor was having prior assaultive history, including aggressive threats, witnessed and perpetrated abuse [24[23][38][45],29,50], which is consistent with extant findings [57,58,59][46][47][48]. OuResearchers' findings of other aspects in the psychiatric history were also reported in earlier studies, such as depression [40][28], insomnia [60][49], suicidal ideations [61,62][50][51] and frequent admissions [43][31]. Like findings from this revisewarch, earlier studies had also found that high total PANSS scores predicted aggression [29[38][45],50], especially for items such as poor impulse control [63,64][52][53], irritability [65][54], uncooperativeness [66][55], hostility [41,64][29][53] and tension [29,30][45][56]. This revisewarch found that forensic history and having a poor legal prognosis were predictive of aggression. Likewise, a meta-analysis of 110 studies found that forensic history was the strongest static factor for predicting aggression [64][53]. In contrast to findings from this revisewarch, other studies also observed positive psychotic symptoms [40[28][38],50], negative symptoms [50][38] and poorer insight [40,66][28][55] as predictive of aggression. In terms of the management domain, the usage of haloperidol and high antipsychotic dosage were associated with aggression. The use of haloperidol and high antipsychotic dosage [39][27] were probably an effect, rather than a cause for aggression [67][57]. In addition, it was thought that poor compliance with pharmacological and non-pharmacological therapies were correlated with aggression [64][53], as well as the discontinuation of pharmacological treatment in patients with psychotic disorders such as schizophrenia [50][38]. In contrast with the current revisewarch, other studies also identified additional predictors of aggression, including involuntary admission [68][58] and off-hour admission [43][31]. There are several possible inter-relationships between the factors mentioned. For example, homelessness may interact with mental illness, unemployment, need for financial aid and aggression. People with mental illnesses were more likely to be unemployed, aggravating their financial difficulties, which can be associated with homelessness and vice versa [69,70][59][60]; homelessness has been independently linked to aggression [71,72][61][62]. In addition, the relationship between poorly controlled mental illnesses such as psychotic disorders, level of psychopathology based on PANSS score ratings, and aggression is also plausible. People with poorly controlled psychotic disorders can have more severe psychotic psychopathology and aggression, with higher PANSS total and subdomain scores, and may require involuntary admissions for management of the psychiatric illness and a higher psychotropic dose at the beginning for stabilization [73][63]. There are several ethical considerations surrounding the use of AI in aggression risk prediction. First is the issue of privacy and surveillance related to principles of respect for persons and non-maleficence. The possibility of such data collection for aggression prediction can potentially translate to blanket surveillance of all patients. Hence, setting certain limits to data access, for example, only on a “need to know and predict basis” for on-duty staff may be useful to protect patients’ privacy [74][64]. Second, to benefit practical interventions in the clinical settings, evolving clinical context and factors need to be considered when interpreting findings derived from AI platforms and algorithms [74][64]. Third, any clinical management plan that incorporates data using AI methods to predict and prevent aggression needs to be reviewed over time to ensure that patients are not subjected to unnecessary or unfair seclusion measures. There are several limitations within this revisewarch. First, there were few studies examining the use of AI methods in aggression risk prediction. Second, the heterogeneity of the included studies with the small number of studies to date limited further quantitative analyses, including parcellation of subtypes of aggression. Third, most studies were conducted cross-sectionally and longer-term effects of AI methods in aggression risk prediction were not examined. Fourth, there was also a paucity of data on how AI helps in mitigating and managing aggression in psychiatric inpatient settings over time. There are several possible future research directions. First, as aggression risk prediction is dynamic; an area where artificial intelligence can be harnessed is its ability to provide iterative and relevant predictions with continual input of current and new data from health records. The dynamic data can potentially shed light on the changing unique clinical profiles of patients related to aggression over time. Second, different machine learning algorithms and models can be combined to better identify longitudinal predictive variables for personalized prevention of aggressive behaviors in inpatient psychiatric treatment settings. Third, incorporating relevant clinical and biological information such as data from clinical assessments, laboratory tests, neuroimaging and neurocognitive assessments can proffer insights into underlying biological factors associated with aggression. It is hoped that the stigma against patients with aggressive tendencies in inpatient settings can be further reduced as we better understand personalized etiological and predictive markers for aggression and reformulate preventive efforts.

References

  1. Sariaslan, A.; Arseneault, L.; Larsson, H.; Lichtenstein, P.; Fazel, S. Risk of subjection to violence and perpetration of violence in persons with psychiatric disorders in Sweden. JAMA Psychiatry 2020, 77, 359–367.
  2. Anderson, C.A.; Bushman, B.J. Human aggression. Annu. Rev. Psychol. 2002, 53, 27–51.
  3. di Giacomo, E.; Iozzino, L.; Ferrari, C.; Strozza, C.; Large, M.; Nielssen, O.; de Girolamo, G. Prevalence and risk factors of violence by psychiatric acute inpatients: Systematic review and meta-analysis—A 2019 update. Violence Ment. Disord. 2020, 181–202.
  4. Richter, D.; Berger, K. Post-traumatic stress disorder following patient assaults among staff members of mental health hospitals: A prospective longitudinal study. BMC Psychiatry 2006, 6, 15.
  5. Bizzarri, J.V.; Piacentino, D.; Kotzalidis, G.D.; Moser, S.; Cappelletti, S.; Weissenberger, G.; Pompili, M.; Conca, A. Aggression and violence toward healthcare workers in a psychiatric service in Italy: A retrospective questionnaire-based survey. J. Nerv. Ment. Dis. 2020, 208, 299–305.
  6. Moylan, L.; Cullinan, M. Frequency of assault and severity of injury of psychiatric nurses in relation to the nurses’ decision to restrain. J. Psychiatr. Ment. Health Nurs. 2011, 18, 526–534.
  7. Kader, N.; Elhusein, B.; Elhassan, N.M.; Alabdulla, M.; Hammoudeh, S.; Hussein, N.-R. Burnout and job satisfaction among psychiatrists in the Mental Health Service, Hamad Medical Corporation, Qatar. Asian J. Psychiatry 2021, 58, 102619.
  8. Seun-Fadipe, C.T.; Akinsulore, A.A.; Oginni, O.A. Workplace violence and risk for psychiatric morbidity among health workers in a tertiary health care setting in Nigeria: Prevalence and correlates. Psychiatry Res. 2019, 272, 730–736.
  9. Ghosh, M.; Twigg, D.; Kutzer, Y.; Towell-Barnard, A.; De Jong, G.; Dodds, M. The validity and utility of violence risk assessment tools to predict patient violence in acute care settings: An integrative literature review. Int. J. Ment. Health Nurs. 2019, 28, 1248–1267.
  10. Lorettu, L.; Nivoli, A.M.; Milia, P.; Nivoli, G. Violence risk assessment in mental health. In Violence and Mental Disorders; Springer: Berlin/Heidelberg, Germany, 2020; pp. 231–252.
  11. Scurich, N.; Monahan, J.; John, R.S. Innumeracy and unpacking: Bridging the nomothetic/idiographic divide in violence risk assessment. Law Hum. Behav. 2012, 36, 548.
  12. Ramesh, T.; Igoumenou, A.; Montes, M.V.; Fazel, S. Use of risk assessment instruments to predict violence in forensic psychiatric hospitals: A systematic review and meta-analysis. Eur. Psychiatry 2018, 52, 47–53.
  13. Ryan, C.; Nielssen, O.; Paton, M.; Large, M. Clinical decisions in psychiatry should not be based on risk assessment. Australas. Psychiatry 2010, 18, 398–403.
  14. Chilla, G.S.; Yeow, L.Y.; Chew, Q.H.; Sim, K.; Prakash, K. Machine learning classification of schizophrenia patients and healthy controls using diverse neuroanatomical markers and Ensemble methods. Sci. Rep. 2022, 12, 2755.
  15. Hu, M.; Qian, X.; Liu, S.; Koh, A.J.; Sim, K.; Jiang, X.; Guan, C.; Zhou, J.H. Structural and diffusion MRI based schizophrenia classification using 2D pretrained and 3D naive Convolutional Neural Networks. Schizophr. Res. 2021, 243, 330–341.
  16. Saeedi, A.; Saeedi, M.; Maghsoudi, A.; Shalbaf, A. Major depressive disorder diagnosis based on effective connectivity in EEG signals: A convolutional neural network and long short-term memory approach. Cogn. Neurodyn. 2021, 15, 239–252.
  17. Andersson, S.; Bathula, D.R.; Iliadis, S.I.; Walter, M.; Skalkidou, A. Predicting women with depressive symptoms postpartum with machine learning methods. Sci. Rep. 2021, 11, 7877.
  18. Eder, S.J.; Steyrl, D.; Stefanczyk, M.M.; Pieniak, M.; Martínez Molina, J.; Pešout, O.; Binter, J.; Smela, P.; Scharnowski, F.; Nicholson, A.A. Predicting fear and perceived health during the COVID-19 pandemic using machine learning: A cross-national longitudinal study. PLoS ONE 2021, 16, e0247997.
  19. Zhou, M.; Wang, Q.; Zheng, C.; John Rush, A.; Volkow, N.D.; Xu, R. Drug repurposing for opioid use disorders: Integration of computational prediction, clinical corroboration, and mechanism of action analyses. Mol. Psychiatry 2021, 26, 5286–5296.
  20. Large, M.; Nielssen, O. The limitations and future of violence risk assessment. World Psychiatry 2017, 16, 25.
  21. Passos, I.C.; Mwangi, B.; Cao, B.; Hamilton, J.E.; Wu, M.-J.; Zhang, X.Y.; Zunta-Soares, G.B.; Quevedo, J.; Kauer-Sant’Anna, M.; Kapczinski, F. Identifying a clinical signature of suicidality among patients with mood disorders: A pilot study using a machine learning approach. Journal of affective disorders 2016, 193, 109–116.
  22. Rajkomar, A.; Oren, E.; Chen, K.; Dai, A.M.; Hajaj, N.; Hardt, M.; Liu, P.J.; Liu, X.; Marcus, J.; Sun, M. Scalable and accurate deep learning with electronic health records. NPJ Digit. Med. 2018, 1, 18.
  23. Suchting, R.; Green, C.E.; Glazier, S.M.; Lane, S.D. A data science approach to predicting patient aggressive events in a psychiatric hospital. Psychiatry Res. 2018, 268, 217–222.
  24. Menger, V.; Scheepers, F.; Spruit, M. Comparing deep learning and classical machine learning approaches for predicting inpatient violence incidents from clinical text. Appl. Sci. 2018, 8, 981.
  25. Micciolo, R.; Bianconi, G.; Canal, L.; Clerici, M.; Ferla, M.T.; Giugni, C.; Iozzino, L.; Sbravati, G.; Tura, G.B.; Vita, A.; et al. Young age and the risk of violent behaviour in people with severe mental disorders: Prospective, multicentre study. BJPsych Open 2021, 8, e1.
  26. Rueve, M.E.; Welton, R.S. Violence and mental illness. Psychiatry 2008, 5, 34–48.
  27. Tasmim, S.; Kolla, N.J.; Dada, O.; Bani-Fatemi, A.; De Luca, V. Correlation between violence and antipsychotic dosage in schizophrenia: A secondary analysis of the clinical antipsychotic trials for intervention effectiveness (CATIE) dataset. Pharmacopsychiatry 2019, 52, 217–221.
  28. Swanson, J.W.; Swartz, M.S.; Van Dorn, R.A.; Elbogen, E.B.; Wagner, H.R.; Rosenheck, R.A.; Stroup, T.S.; McEvoy, J.P.; Lieberman, J.A. A national study of violent behavior in persons with schizophrenia. Arch. Gen. Psychiatry 2006, 63, 490–499.
  29. d’Ettorre, G.; Pellicani, V. Workplace violence toward mental healthcare workers employed in psychiatric wards. Saf. Health Work. 2017, 8, 337–342.
  30. Nielssen, O.; Large, M. Rates of homicide during the first episode of psychosis and after treatment: A systematic review and meta-analysis. Schizophr. Bull. 2010, 36, 702–712.
  31. Odawara, T.; Narita, H.; Yamada, Y.; Fujita, J.; Yamada, T.; Hirayasu, Y. Use of restraint in a general hospital psychiatric unit in Japan. Psychiatry Clin. Neurosci. 2005, 59, 605–609.
  32. Draine, J.; Salzer, M.S.; Culhane, D.P.; Hadley, T.R. Role of social disadvantage in crime, joblessness, and homelessness among persons with serious mental illness. Psychiatric Serv. 2002, 53, 565–573.
  33. Klassen, D.; O’Connor, W.A. A prospective study of predictors of violence in adult male mental health admissions. Law Hum. Behav. 1988, 12, 143–158.
  34. Spidel, A.; Lecomte, T.; Greaves, C.; Sahlstrom, K.; Yuille, J.C. Early psychosis and aggression: Predictors and prevalence of violent behaviour amongst individuals with early onset psychosis. Int. J. Law Psychiatry 2010, 33, 171–176.
  35. Jovanovic, N.; Kudumija Slijepcevic, M.; Podlesek, A. Personality traits in suicidal and homicidal subjects with schizophrenia. J. Forensic Psychiatry Psychol. 2019, 30, 76–88.
  36. Stanton, B.; Baldwin, R.M.; Rachuba, L. A quarter century of violence in the United States: An epidemiologic assessment. Psychiatr. Clin. North Am. 1997, 20, 269–282.
  37. Kirchebner, J.; Sonnweber, M.; Nater, U.M.; Günther, M.; Lau, S. Stress, Schizophrenia, and Violence: A Machine Learning Approach. J. Interpers. Violence 2022, 37, 602–622.
  38. Ntounas, P.; Katsouli, A.; Efstathiou, V.; Pappas, D.; Chatzimanolis, P.; Touloumis, C.; Papageorgiou, C.; Douzenis, A. Comparative study of aggression–dangerousness on patients with paranoid schizophrenia: Focus on demographic data, PANSS, drug use and aggressiveness. Int. J. Law Psychiatry 2018, 60, 1–11.
  39. Fisher, H.L.; Craig, T.K.; Fearon, P.; Morgan, K.; Dazzan, P.; Lappin, J.; Hutchinson, G.; Doody, G.A.; Jones, P.B.; McGuffin, P. Reliability and comparability of psychosis patients’ retrospective reports of childhood abuse. Schizophr. Bull. 2011, 37, 546–553.
  40. Heinrichs, R.W.; Sam, E.P. Schizophrenia and crime: How predictable are charges, convictions and violence? Int. J. Ment. Health Addict. 2012, 10, 122–131.
  41. Bartels, S.J.; Drake, R.E.; Wallach, M.A.; Freeman, D.H. Characteristic hostility in schizophrenic outpatients. Schizophr. Bull. 1991, 17, 163–171.
  42. Fischer, S.N.; Shinn, M.; Shrout, P.; Tsemberis, S. Homelessness, mental illness, and criminal activity: Examining patterns over time. Am. J. Community Psychol. 2008, 42, 251–265.
  43. Fryer, M.A.; Beech, M.; Byrne, G.J. Seclusion use with children and adolescents: An Australian experience. Aust. New Zealand J. Psychiatry 2004, 38, 26–33.
  44. Green, K.; Browne, K.; Chou, S. The relationship between childhood maltreatment and violence to others in individuals with psychosis: A systematic review and meta-analysis. Trauma Violence Abus. 2019, 20, 358–373.
  45. Günther, M.P.; Kirchebner, J.; Lau, S. Identifying direct coercion in a high risk subgroup of offender patients with schizophrenia via machine learning algorithms. Front. Psychiatry 2020, 11, 415.
  46. Mossman, D. Assessing predictions of violence: Being accurate about accuracy. J. Consult. Clin. Psychol. 1994, 62, 783.
  47. Elbogen, E.B.; Johnson, S.C. The intricate link between violence and mental disorder: Results from the National Epidemiologic Survey on Alcohol and Related Conditions. Arch. Gen. Psychiatry 2009, 66, 152–161.
  48. Elbogen, E.B.; Swanson, J.W.; Swartz, M.S.; Van Dorn, R. Family representative payeeship and violence risk in severe mental illness. Law Hum. Behav. 2005, 29, 563–574.
  49. Kamphuis, J.; Dijk, D.-J.; Spreen, M.; Lancel, M. The relation between poor sleep, impulsivity and aggression in forensic psychiatric patients. Physiol. Behav. 2014, 123, 168–173.
  50. Witt, K.; Hawton, K.; Fazel, S. The relationship between suicide and violence in schizophrenia: Analysis of the Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) dataset. Schizophr. Res. 2014, 154, 61–67.
  51. Ben-Zeev, D.; Scherer, E.A.; Brian, R.M.; Mistler, L.A.; Campbell, A.T.; Wang, R. Use of multimodal technology to identify digital correlates of violence among inpatients with serious mental illness: A pilot study. Psychiatr. Serv. 2017, 68, 1088–1092.
  52. Gordon, V.; Egan, V. What self-report impulsivity measure best postdicts criminal convictions and prison breaches of discipline? Psychol. Crime Law 2011, 17, 305–318.
  53. Witt, K.; Van Dorn, R.; Fazel, S. Risk factors for violence in psychosis: Systematic review and meta-regression analysis of 110 studies. PLoS ONE 2013, 8, e55942.
  54. Sun, L.; Han, X.; Wang, K.; Xu, C.; Song, Z.; Zhang, J.; Cao, D.; Tan, L.; Chen, F.; Wu, S. Candidate symptomatic markers for predicting violence in schizophrenia: A cross-sectional study of 7711 patients in a Chinese population. Asian J. Psychiatry 2021, 59, 102645.
  55. Arango, C.; Barba, A.C.; González-Salvador, T.; Ordonez, A.C. Violence in inpatients with schizophrenia: A prospective study. Schizophr. Bull. 1999, 25, 493–503.
  56. Hofmann, L.A.; Lau, S.; Kirchebner, J. Advantages of Machine Learning in Forensic Psychiatric Research—Uncovering the Complexities of Aggressive Behavior in Schizophrenia. Appl. Sci. 2022, 12, 819.
  57. Dib, J.E.; Yaacoub, H.E.; Ikdais, W.H.; Atallah, E.; Merheb, T.J.; Ajaltouni, J.; Akkari, M.; Mourad, M.; Nasr, M.E.; Hachem, D. Rapid tranquillisation in a psychiatric emergency hospital in Lebanon: TREC-Lebanon–a pragmatic randomised controlled trial of intramuscular haloperidol and promethazine v. intramuscular haloperidol, promethazine and chlorpromazine. Psychol. Med. 2021, 1–9.
  58. Danielsen, A.; Fenger, M.; Østergaard, S.; Nielbo, K.; Mors, O. Predicting mechanical restraint of psychiatric inpatients by applying machine learning on electronic health data. Acta Psychiatr. Scand. 2019, 140, 147–157.
  59. Susser, E.; Lovell, A.; Conover, S. Unravelling the causes of homelessness–and of its association with mental illness. In Epidemiology and the Prevention of Mental Disorders; Routledge: London, UK, 2021; pp. 228–239.
  60. Varshney, M.; Mahapatra, A.; Krishnan, V.; Gupta, R.; Deb, K.S. Violence and mental illness: What is the true story? J. Epidemiol. Community Health 2016, 70, 223–225.
  61. Choe, J.Y.; Teplin, L.A.; Abram, K.M. Perpetration of violence, violent victimization, and severe mental illness: Balancing public health concerns. Psychiatr. Serv. 2008, 59, 153–164.
  62. Swanson, J.W.; Swartz, M.S.; Essock, S.M.; Osher, F.C.; Wagner, H.R.; Goodman, L.A.; Rosenberg, S.D.; Meador, K.G. The social–environmental context of violent behavior in persons treated for severe mental illness. Am. J. Public Health 2002, 92, 1523–1531.
  63. Chandra, I.S.; Kumar, K.L.; Reddy, M.P.; Reddy, C.M.P.K. Attitudes toward medication and reasons for non-compliance in patients with schizophrenia. Indian J. Psychol. Med. 2014, 36, 294–298.
  64. Müller, V.C. Ethics of Artificial Intelligence and Robotics. Available online: https://plato.stanford.edu/archives/sum2021/entries/ethics-ai (accessed on 31 July 2022).
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)
ScholarVision Creations
Feedback