Correction of: Using New and Emerging Technologies to Identify and Respond to Suicidality Among Help-Seeking Young People: A Cross-Sectional Study

Predicting self-harm within six months after initial presentation to youth mental health services: A machine learning study

BACKGROUND

A priority for health services is to reduce self-harm in young people. Predicting self-harm is challenging due to their rarity and complexity, however this does not preclude the utility of prediction models to improve decision-making regarding a service response in terms of more detailed assessments and/or intervention. The aim of this study was to predict self-harm within six-months after initial presentation.

METHOD

The study included 1962 young people (12-30 years) presenting to youth mental health services in Australia. Six machine learning algorithms were trained and tested with ten repeats of ten-fold cross-validation. The net benefit of these models were evaluated using decision curve analysis.

RESULTS

Out of 1962 young people, 320 (16%) engaged in self-harm in the six months after first assessment and 1642 (84%) did not. The top 25% of young people as ranked by mean predicted probability accounted for 51.6% - 56.2% of all who engaged in self-harm. By the top 50%, this increased to 82.1%-84.4%. Models demonstrated fair overall prediction (AUROCs; 0.744-0.755) and calibration which indicates that predicted probabilities were close to the true probabilities (brier scores; 0.185-0.196). The net benefit of these models were positive and superior to the 'treat everyone' strategy. The strongest predictors were (in ranked order); a history of self-harm, age, social and occupational functioning, sex, bipolar disorder, psychosis-like experiences, treatment with antipsychotics, and a history of suicide ideation.

CONCLUSION

Prediction models for self-harm may have utility to identify a large sub population who would benefit from further assessment and targeted (low intensity) interventions. Such models could enhance health service approaches to identify and reduce self-harm, a considerable source of distress, morbidity, ongoing health care utilisation and mortality.

Project Synergy: co-designing technology-enabled solutions for Australian mental health services reform

Project Synergy aims to test the potential of new and emerging technologies to enhance the quality of mental health care provided by traditional face-to-face services. Specifically, it seeks to ensure that consumers get the right care, first time (delivery of effective mental health care early in the course of illness). Using co-design with affected individuals, Project Synergy has built, implemented and evaluated an online platform to assist the assessment, feedback, management and monitoring of people with mental disorders. It also promotes the maintenance of wellbeing by collating health and social information from consumers, their supportive others and health professionals. This information is reported back openly to consumers and their service providers to promote genuine collaborative care. The online platform does not provide stand-alone medical or health advice, risk assessment, clinical diagnosis or treatment; instead, it supports users to decide what may be suitable care options. Using an iterative cycle of research and development, the first four studies of Project Synergy (2014-2016) involved the development of different types of online prototypes for young people (i) attending university; (ii) in three disadvantaged communities in New South Wales; (iii) at risk of suicide; and (iv) attending five headspace centres. These contributed valuable information concerning the co-design, build, user testing and evaluation of prototypes, as well as staff experiences during development and service quality improvements following implementation. Through ongoing research and development (2017-2020), these prototypes underpin one online platform that aims to support better multidimensional mental health outcomes for consumers; more efficient, effective and appropriate use of health professional knowledge and clinical skills; and quality improvements in mental health service delivery.

A Digital Platform Designed for Youth Mental Health Services to Deliver Personalized and Measurement-Based Care

Mental disorders that commonly emerge during adolescence and young adulthood are associated with substantial immediate burden and risks, as well as potentially imparting lifetime morbidity and premature mortality. While the development of health services that are youth focused and prioritize early intervention has been a critical step forward, an ongoing challenge is the heterogeneous nature of symptom profiles and illness trajectories. Consequently, it is often difficult to provide quality mental health care, at scale, that addresses the broad range of health, social, and functional needs of young people. Here, we describe a new digital platform designed to deliver personalized and measurement-based care. It provides health services and clinicians with the tools to directly address the multidimensional needs of young people. The term "personalized" describes the notion that the assessment of, and the sequence of interventions for, mental disorders are tailored to the young person-and their changing needs over time, while "measurement-based" describes the use of systematic and continuing assessment of a young person's outcomes over the entire course of clinical care. Together, these concepts support a framework for care that transcends a narrow focus on symptom reduction or risk reduction. Instead, it prioritizes a broader focus on enhancing social, health, and physical outcomes for young people and a commitment to tracking these outcomes throughout this key developmental period. Now, with twenty-first century technologies, it is possible to provide health services with the tools needed to deliver quality mental health care.