Risk factors for readmission in schizophrenia patients following involuntary admission

Hung, Yu-Yuan; Chan, Hung‐Yu; Pan, Yi‐Ju

doi:10.1371/journal.pone.0186768

Cited by 41 publications

(42 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings from this study have highlighted the highest proportion of readmission and disease experience on patients who were single, age range between 31 and 40 years old, homebody, had primary or basic education and unemployed. The findings were parallel with previous study in Taiwan that determined younger age and unmarried patients were a significant risk factor of readmission (Hung, Chan, & Pan, 2017). Interestingly, highest proportion of readmission and disease experience was found on external factors such as intact family marital status and patients who live in urban area.…”

Section: Discussionsupporting

confidence: 89%

Socio-demography and psychosis symptom severity among male schizophrenia – Diagnosed patients of MOH Mental Health Facilities, Kingdom of Saudi Arabia; a correlational study

Parentela

Alharbi

Alahmadi³

et al. 2019

Archives of Psychiatric Nursing

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 89%

Socio-demography and psychosis symptom severity among male schizophrenia – Diagnosed patients of MOH Mental Health Facilities, Kingdom of Saudi Arabia; a correlational study

Parentela

Alharbi

Alahmadi³

et al. 2019

Archives of Psychiatric Nursing

View full text Add to dashboard Cite

“…Results show that previous (involuntary) admissions and the amount of previous psychiatric service use are reliable predictors of readmission [ 10 – 12 ]. Homelessness at admission discharge [ 11 , 13 ], being on benefits [ 14 ], being unmarried, living alone or having a small social network [ 11 , 15 ] and being of African and/or Caribbean origin [ 14 ] also are known predictors of psychiatric admission. Something these studies [ 6 – 15 ] have in common is that they used generalized linear modelling (GLM/logistic regression) for their prognostic models.…”

Section: Introductionmentioning

confidence: 99%

Predicting hospitalization following psychiatric crisis care using machine learning

Blankers

Post

Dekker

2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Accurate prediction models for whether patients on the verge of a psychiatric criseis need hospitalization are lacking and machine learning methods may help improve the accuracy of psychiatric hospitalization prediction models. In this paper we evaluate the accuracy of ten machine learning algorithms, including the generalized linear model (GLM/logistic regression) to predict psychiatric hospitalization in the first 12 months after a psychiatric crisis care contact. We also evaluate an ensemble model to optimize the accuracy and we explore individual predictors of hospitalization. Methods Data from 2084 patients included in the longitudinal Amsterdam Study of Acute Psychiatry with at least one reported psychiatric crisis care contact were included. Target variable for the prediction models was whether the patient was hospitalized in the 12 months following inclusion. The predictive power of 39 variables related to patients’ socio-demographics, clinical characteristics and previous mental health care contacts was evaluated. The accuracy and area under the receiver operating characteristic curve (AUC) of the machine learning algorithms were compared and we also estimated the relative importance of each predictor variable. The best and least performing algorithms were compared with GLM/logistic regression using net reclassification improvement analysis and the five best performing algorithms were combined in an ensemble model using stacking. Results All models performed above chance level. We found Gradient Boosting to be the best performing algorithm (AUC = 0.774) and K-Nearest Neighbors to be the least performing (AUC = 0.702). The performance of GLM/logistic regression (AUC = 0.76) was slightly above average among the tested algorithms. In a Net Reclassification Improvement analysis Gradient Boosting outperformed GLM/logistic regression by 2.9% and K-Nearest Neighbors by 11.3%. GLM/logistic regression outperformed K-Nearest Neighbors by 8.7%. Nine of the top-10 most important predictor variables were related to previous mental health care use. Conclusions Gradient Boosting led to the highest predictive accuracy and AUC while GLM/logistic regression performed average among the tested algorithms. Although statistically significant, the magnitude of the differences between the machine learning algorithms was in most cases modest. The results show that a predictive accuracy similar to the best performing model can be achieved when combining multiple algorithms in an ensemble model.

show abstract

“…- Many analyses focused on specific patient groups, as e.g., (first admitted) subjects with psychosis (25, 26), narrow age categories (25, 27) (adolescents; <50 years old), specific service settings, as e.g., compulsory community treatment (28) or selected countries or areas (14, 26, 29).…”

Section: Introductionmentioning

confidence: 99%

Predictors of Compulsory Re-admission to Psychiatric Inpatient Care

2019

View full text Add to dashboard Cite

Objective: This prospective study addresses risk factors of compulsory re-admission focusing on the role of the patient's subjective symptom distress and perceived social support, based on comprehensive patient and external (clinicians, study staff) assessments. Methods: Of the baseline sample, 168 (71%) patients with serious mental disorders, who had been compulsorily admitted to psychiatric inpatient care, were followed over 24 months after discharge within the framework of a RCT. Results: During this time 36% had compulsory re-admissions; risk was highest immediately after discharge. Regression models identified a history of previous compulsory hospitalisations and compulsory admission due to endangerment of others as the predictors most strongly associated with the outcome. Patients diagnosed with a psychotic disorder or an emotionally instable or combined personality disorder were most likely to experience compulsory re-hospitalisation, with poor response to treatment further significantly increasing the risk. The patient ratings of subjective symptom distress or perceived social support had no predictive value for compulsory re-admission, and this study did not provide evidence for a significant prognostic relevance of sociodemographic background factors. Conclusions: The present findings suggest that within individual-level variables disease-related factors are essentially the strongest predictors, but including the patients' subjective perspective does not enhance the prediction of compulsory re-hospitalisation. The psychiatric treatment of patients with recurrent and often challenging behavioural problems, at the more severe end of the spectrum of mental disorders, deserves closer attention if the use of compulsory hospitalisation is to be reduced.

show abstract

Risk factors for readmission in schizophrenia patients following involuntary admission

Cited by 41 publications

References 37 publications

Socio-demography and psychosis symptom severity among male schizophrenia – Diagnosed patients of MOH Mental Health Facilities, Kingdom of Saudi Arabia; a correlational study

Socio-demography and psychosis symptom severity among male schizophrenia – Diagnosed patients of MOH Mental Health Facilities, Kingdom of Saudi Arabia; a correlational study

Predicting hospitalization following psychiatric crisis care using machine learning

Predictors of Compulsory Re-admission to Psychiatric Inpatient Care

Contact Info

Product

Resources

About