Background and Objectives
In recent years, prolonged inpatient treatment in psychiatry in general and forensic psychiatry in particular has faced more and more criticism and scientific scrutiny: Especially within involuntary treatment settings, inappropriately long stays have been viewed as potentially unethical (1–6). In addition, doubts have been raised about the benefits of prolonged inpatient treatment for patients’ rehabilitation (3, 7). Prolonged duration of inpatient treatment has been discussed as an indicator of economic inefficiency - particularly for forensic inpatient treatment, which constitutes a low-volume high-cost sector (3, 8–14). The internationally observed prolongation of forensic hospitalizations in the past years (1, 3, 7, 15–17), as well as the ever-growing demand for forensic services (18–21), have become a subject of socio-political debate with urgent need for more research on avenues to reduce the duration of inpatient treatments in order to reduce exploding costs whenever possible (2, 4). A recent review of 38 studies in eleven countries summarized a rich set of patient characteristics contributing to length of stay in psychiatric inpatient treatment (6), but concluded that just ten studies were useful in identifying clinically useful predictive factors, since "more rigorous multivariate statistical techniques" are required in order to eliminate confounding factors. Its authors also conducted an extensive qualitative and quantitative exploratory inquiry of the topic drawing on information from all stakeholders (patients, treatment professionals, experts) and mentioned not conducting file reviews on long-stay versus non-long-stay patients in forensic psychiatry (using adequate sophisticated statistical tools) as a key limitation to their comprehensive work. The present study aims to fill this gap using machine learning – a statistical approach novel to the field of psychiatry, which has recently been identified as superior to contemporary statistical approaches such as binary regression analysis in its sensitivity, specificity, accuracy and predictive validity (AUC: area under the curve) in direct comparison to contemporary statistical approaches (22). Machine learning, a form of artificial intelligence, relies on patterns and inference in a set of data in order to find an algorithm best predicting an outcome (such as length of stay in the present study). In exploratory data analysis it is thus superior to contemporary statistical methods in revealing previously "unseen" non-linear interdependencies between variables often also resulting in better predictive power (23, 24).
Findings and Inconsistencies of Relevant Prior Research
By for the first time (to our knowledge) applying machine learning to the study of predictors of length of stay in forensic psychiatry in order to better meet the statistical needs of this complexly (non-linearly) interrelated set of data (6), the current study aims to help provide more clarity on prior inconsistencies. These will be summarized in the remainder of this section along with frequently confirmed prior findings since they have informed the primary set of variables explored in the present study (also see Table 1 for a summary).
Past researchers studied patients from different security settings (25–27) or regardless of their moving (or not moving) from one level of security to another (1, 15, 16, 28, 29). In some research, factors which were found to be relevant to patients’ transfer from a medium to a minimum security setting were set equal to those relevant to patients’ discharge into the community, and vice versa (27). Furthermore, studies usually did not limit their sample to patients of a specific legal status (3, 14, 30, 31). Since different requirements for discharge apply due to different legal verdicts, it may well be that factors associated with duration of inpatient treatment also differ accordingly.
Studies revealed considerable differences in duration of forensic hospitalization between countries, and even between different regions within countries, suggesting substantial geographical variation in treatment standards, structural conditions of forensic care, as well as legal procedures (11, 16, 29, 32). Switzerland, the setting of the present study, is not among the 11 countries in which length of stay has been explored so far (6), thus providing new information on geographical inconsistencies.
With regard to socio-demographic factors, factors correlating with prolonged inpatient treatment included male gender (3, 33, 34), white skin colour (25, 30, 34), advanced age at the time of admission (15, 28), being unmarried (34, 35), low educational qualifications (16, 28, 34–36), low IQ (35), adjustment, socialisation, and partnership issues (36), no discharge address (15), unemployment before admission (16, 28, 35–37), and having lived with ones parents before admission (16). There is also some evidence that emotional neglect during childhood has a prolonging effect (7). Socio-demographic variables associated with a reduction of time spent in inpatient treatment included being a parent (1), good contact with one’s family or good social support (26–28), and living in a close relationship (16). While some studies reported prolonged inpatient treatment for certain religious minorities (28) and patients having migrated (7), others reported shorter length of stay for immigrants (16) and ethnic minorities (17).
Regarding patients’ criminal histories, empirical research indicated patients being forensically hospitalized for a prolonged period of time to be more likely to have engaged in past criminal and violent behaviours (3, 26, 35) and to be of younger age at their first delinquency or violent incident (3, 16, 35). Patients who had been admitted to a (forensic) psychiatric institution before or had been younger at their first psychiatric contact also tended to hospitalized longer (1, 7, 16, 17, 31, 34, 38). By contradiction, other studies (15, 39) reported patients who had previously been admitted to a forensic psychiatric hospital to have shorter hospitalizations.
With respect to the index offence leading to forensic hospitalisation, researchers recurrently reported the severity of the offence to be an important factor and predictor for inpatient treatment duration. The more serious the index offence, the longer the patient’s hospitalisation (15, 16, 25, 28–31, 33–36, 38–41). Additionally, studies suggested factors such as having committed a violent index offence (1, 17, 39), having been young at the time of the index offence (37), having offended against multiple victims (34), and having committed the offence against someone known to the patient (35) also extend forensic hospitalisation.
In terms of clinical assessment tools, lower “Global Assessment of Functioning” scores (1, 42), lower “Positive and Negative Syndrome Scale” scores (28), psychotic symptoms (27, 43), psychotic vulnerability, being in need of psychiatric medication (7), and having no insight into the mental illness (27) correlated with prolonged forensic inpatient treatment. Other studies, limiting their studied sample to offender patients with a schizophrenia spectrum disorder, suggested the presence of positive symptoms may have a protective effect against long hospitalization times (15, 37). A history of substance abuse (3, 7, 15, 44), a comorbid medical illnesses (28), and a learning disability (15) correlated with the duration of forensic hospitalisations.
In terms of forensic treatment variables, adverse behaviours and events such as violence, substance abuse, absconding, non-compliance, requirement of seclusion, physical restraints, forced medication, or conditional release failure significantly delayed discharge (1, 3, 16, 26, 27, 31, 33, 35, 38, 42). Patients who stayed hospitalised for a shorter period of time were more likely to make good therapeutic progress (15, 26), participate in more therapy programmes (26), work in the hospital (28), reside in open wards, had higher levels of ground privileges, were involved in community, educational, or vocational activities (42), participated in activities in general (27), were more likely to be cooperative (29), expressed remorse for their crime(s), and had positive references (35).
Table 1:Variables explored in this and prior research on length of stay
variable in current study
|
categorization in current study
|
prior research with similar variable
|
Sociodemographic variables
|
|
|
age at admission
|
numerical
|
(1, 6, 14, 16, 17, 26-30)
|
gender
|
dichotomous (female, male)
|
(1, 5, 6, 15, 16, 26, 27, 30, 34, 42)
|
marital status at time of index offence
|
dichotomous (married, single)
|
(5, 6, 15, 16, 26-28, 31, 35)
|
level of education
|
dichotomous (graduation from mandatory schooling/ no graduation from mandatory schooling)
|
(1, 6, 14, 16, 28, 34, 35)
|
employment at time of index offence
|
unemployed/ employed/ other (retired,…)
|
(5, 6, 16, 26, 27, 35)
|
country of birth Switzerland
|
dichotomous (yes/ no)
|
(5-7, 14, 16, 17, 26-28, 30, 34)
|
religion
|
catholic/islam/other
|
(6, 28)
|
homelessness at index offence
|
dichotomous (yes/ no)
|
(1, 15, 16)
|
Childhood variables
|
|
|
childhood history physical abuse
|
dichotomous (yes/ no)
|
(5)
|
childhood history of sexual abuse
|
dichotomous (yes/ no)
|
(7)
|
relationship instability in childhood
|
dichotomous (yes/ no)
|
(5, 7, 17)
|
parental psychiatric history
|
dichotomous (yes/ no)
|
(5, 7)
|
sexual deviation in childhood
|
dichotomous (yes/ no)
|
(7)
|
psychiatric admission in childhood
|
dichotomous (yes/ no)
|
(5, 6)
|
alcohol abuse in childhood
|
dichotomous (yes/ no)
|
(5, 35)
|
school maladjustment
|
dichotomous (yes/ no)
|
(5, 35)
|
poor family socioeconomic status (according to the definition of poverty by the Swiss Federal Statistical Office 2016 (45) )
|
dichotomous (yes/ no)
|
(35)
|
childhood aggression
|
dichotomous (yes/ no)
|
(5, 35)
|
separation from caregiver
|
dichotomous (yes/ no)
|
(5, 35)
|
Offence related variables
|
|
|
index offence leading to admission
|
homicide, including attempted/assault/threat, coercion/sexual abuse of children/rape, sexual assault/other sexual offence/ property crime without violence/property crime with violence/arson/criminal damage/traffic offences/offences against the controlled substances act/offences against the weapons act/other offences
|
(1, 5-7, 14-17, 27-31, 34, 35)
|
age at index offence
|
numeric
|
(1, 5-7, 35)
|
number of index offences
|
numeric
|
(6, 35)
|
any previous conviction
|
dichotomous (yes/ no)
|
(5-7, 14-17, 28, 30, 31)
|
age at first conviction
|
numeric
|
(5-7, 16, 17, 30)
|
victim injured deadly/severely
|
dichotomous (yes/ no)
|
(34, 35)
|
number of victims
|
numeric
|
(34)
|
victim known to offender
|
dichotomous (yes/ no)
|
(34, 35)
|
alcohol involved at offence
|
dichotomous (yes/ no)
|
(42)
|
previous forensic psychiatric admissions
|
dichotomous (yes/ no)
|
(15-17)
|
withdrawal of conditional release
|
dichotomous (yes/ no)
|
(16)
|
residual criminal responsibility
|
dichotomous (yes/ no)
|
(6, 16)
|
Psychiatric variables
|
|
|
number of previous psychiatric admissions
|
numeric
|
(5, 6, 14-17, 30, 31, 35)
|
age at first admission
|
numeric
|
(14, 16, 30)
|
specific schizophrenic spectrum disorder
|
schizophrenia/schiziotypic disorder/acute psychotic disorder/schizoaffective disorder
|
(1, 5-7, 14-17, 27, 28, 30, 31, 35, 42)
|
personality disorder lifetime
|
dichotomous (yes/ no)
|
(1, 5, 6, 14-17, 27, 30, 31, 35)
|
mood disorder lifetime
|
dichotomous (yes/ no)
|
(1, 5, 6, 14-16, 27, 28, 42)
|
alcohol abuse lifetime
|
dichotomous (yes/ no)
|
(6, 15, 17, 31, 35)
|
substance abuse lifetime
|
dichotomous (yes/ no)
|
(5-7, 15-17, 27, 28, 31)
|
sexual deviation
|
dichotomous (yes/ no)
|
(5, 7)
|
level of intelligence
|
high/average/low
|
(6, 7, 16, 35)
|
history of self-harming
|
dichotomous (yes/ no)
|
(6)
|
history of suicide attempt(s)
|
dichotomous (yes/ no)
|
(6)
|
delusions prior to admission
|
dichotomous (yes/ no)
|
(5, 27)
|
hallucinations prior to admission
|
dichotomous (yes/ no)
|
(5, 27)
|
cognitive impairment prior to admission
|
dichotomous (yes/ no)
|
(6)
|
Current forensic hospitalization
|
|
|
violent incidents
|
dichotomous (yes/ no)
|
(1, 5, 6, 16, 31, 42)
|
self-harming
|
dichotomous (yes/ no)
|
(6)
|
suicide attempt(s)
|
dichotomous (yes/ no)
|
(6, 16, 42)
|
attempts to substance use
|
dichotomous (yes/ no)
|
(1)
|
escape attempt(s)
|
dichotomous (yes/ no)
|
(1, 6, 16)
|
performance in occupational work
|
good/average/low
|
(6, 26)
|
difficulties during psychological therapy
|
dichotomous (yes/ no)
|
(6)
|
pharmacological treatment
|
dichotomous (yes/ no)
|
(6, 7, 15)
|
contact with family/friends
|
dichotomous (yes/ no)
|
(6)
|
changes in diagnosis during current treatment
|
Dichotomous (yes/ no)
|
(6)
|
admission source into current hospitalization
|
none/supervised living facility/prison/other forensic hospital/psychiatry
|
(6, 30)
|
involuntary medication
|
dichotomous (yes/ no)
|
(31)
|
insight into falseness of offence
|
dichotomous (yes/ no)
|
(35)
|
adherence (insight into illness and need of therapy)
|
dichotomous (yes/ no)
|
(26)
|
PANSS at admission
|
numeric
|
(28, 29)
|
PANSS at discharge
|
numeric
|
(28, 29)
|