This prognostic study evaluates whether psychosis transition can be predicted in patients with clinical high-risk syndromes or recent-onset depression by multimodal machine learning that optimally integrates clinical and neurocognitive data, structural magnetic resonance imaging, and polygenic risk scores for schizophrenia.
The goal of this study was to prevent rehospitalizations and thus to optimize satisfaction with treatment and quality of life in patients suffering by schizophrenia or schizoaffective disorder. A complex intervention with improved cooperation between in- and outpatient services was applied to 46 "high utilizing" patients after discharge from inpatient care during an intervention phase of 6 months. The study was controlled by a matched group of 47 patients receiving treatment as usual. The intervention was based on a computerized decision support module. Eight psychiatrists in private practices were supplied with this software to obtain guideline-based recommendations according to current psychopathology and clinical state. Suggested complex interventions by the software included psychoeducation, social competence group therapy, integrated psychological therapy, computer-based cognitive training, coping skills training, sociotherapy, nursing care, home visits, social-worker care, assistance to family members, and the use of an emergency call-in line. A local hospital project team arranged specifically suggested interventions. We intended to accomplish a reduction of rehospitalization rates by 50% in the intervention group within a 12-month follow-up phase. Satisfaction with treatment, subjective quality of life, and treatment costs in terms of daily inpatient costs were compared between both groups. Moderator variables such as socio-demographical aspects or influences of certain interventions to rehospitalization rate were analyzed. The sample included patients more seriously ill than originally expected. Subjects in the control group (CG) were older (46 years) than those subjects in the intervention group (IG) (40 years). Other sociodemographical aspects (sex, family status, level of education, and number of former hospitalizations) showed no differences between both groups. The rehospitalization rate and the mean length of inpatient treatment were reduced to nearly 50% in the intervention group. The rate of readmissions increased in the control group, leading to a difference of 23% between both groups. The most important factor to favorably influence rehospitalization rates was the participation in coping skills training. There was an increase in patient satisfaction with treatment, while the subjective quality of life remained constant. Since these improvements were accomplished with lower costs (in terms of inpatient care), cost effectiveness was higher in the IG than in the CG. The most important single factor to favorably influence rehospitalization rates was the participation in coping skills training. Only the guideline consistent complex therapies as common intervention caused the significant overall result. Thereby, satisfaction with treatment increased considerably during the 6 months of intervention and remained constant during 12 months of follow up. The model project described is an important step to gain evidence and experience with integrated care for patients with schizophrenia.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.