Aim To develop and psychometrically test the distress thermometer for caregivers (DT-C) and document the distress level in primary caregivers of children and adolescents diagnosed with schizophrenia. Design A validation diagnostic accuracy study and descriptive cross-sectional survey. Methods DT-C was adopted based on Harverman's distress thermometer for parents. The cut-off score was detected by using receiver operating characteristic analysis with the Depression Anxiety Stress Scale-21 as a reference standard in a sample of 324 caregivers of children and adolescents diagnosed with schizophrenia in China collected between Jan 2017 and Feb 2018. Results One-item DT of DT-C indicated a good retest reliability (r = 0.86) and one-item DT and the Problem List (PL) indicated good convergent validity (r = 0.67-0.88). Overall and individual PL domains showed good internal consistency (KR 20 values ranged from 0.70-0.90). Setting seven as the cut-off score, the values of sensitivity (0.72-0.81), specificity (0.86-0.90), Youden's index (0.61-0.70), positive predictive value (0.67-0.74), and negative predictive value (0.84-0.92) were most satisfactory and area under curve values showed significantly excellent discrimination (0.88-0.90). The average DT score for the 324 participants was 6.34 (SD 2.49), with 46.9% of the participants above the cut-off. Caregivers above the cut-off score faced significant multiple problems in practical, family/social, cognitive, emotional, and parenting domains. Conclusion The DT-C, with six domains containing 35 items in Problem List and with the cut-off score at seven, can be a rapid screening tool to measure distress in these caregivers. The level of distress in caregivers was relatively high. Psychoeducation on specific needs and a solid mutual support network are recommended for mitigating caregivers' distress. Impact This study adapted a reliable DT-C to measure distress of caregivers, which has the potential to be introduced to caregivers of other types of child and adolescent mental disorders in research, assessments and care planning for health professionals.
This paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice. We employed a scoping review methodology to rapidly map the field of ML in mental health. Eight health and information technology research databases were searched for papers covering this domain. Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type, and study results. Articles were then synthesised via narrative review. Three hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis (ii) prognosis, treatment and support (iii) public health, and (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's disease. ML techniques used included support vector machines, decision trees, neural networks, latent Dirichlet allocation, and clustering. Overall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration. With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to other areas of psychology and mental health. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field.