An accumulation of research evidence has pointed to parent-implemented communication intervention as effective in reducing the severity of social communication deficits in autistic preschoolers. Despite even high-quality evidence, real-world translation to clinical practice remains challenging, especially for children from lower-income families, for two reasons. First, the intervention outcome is highly variable despite study-level efficacy data, most likely due to unique child and parent factors that make intervention response uneven across individual children. Second, the cost of intervention with the largest effect sizes remains high due to its one-on-one format. With the overarching goal to reduce cost and to increase intervention effectiveness at the individual-child level, this project will conduct a randomized controlled trial (RCT) to compare the effectiveness of two options for intervention to address two specific objectives. The investigators will first ascertain whether parent-implemented communication intervention taught by a speech therapist in a Group format (up to 8 families learning together) is more effective than intervention learnt by the parents themselves (learning the same materials without the guidance of a therapist) at the study level. The investigators will then evaluate what combinations of parent and child behavioral factors determine which format of intervention is likely to be more effective at the individual-child level. It is likely that not all families require the more costly Group format of intervention. Machine learning analytics with cross-validation will be used in constructing predictive models of intervention response, which will increase the likelihood of these models being generalizable to new patients.

This study will be among the first examples of fulfilling the promise of Precision Medicine in providing guidance to patients and families with developmental disorders not about whether to receive intervention but which option for intervention to receive in the context of multiple options. This predict-to prescribe approach of autism intervention will likely lead to a paradigm shift in clinical practice and ultimately result in lowering the overall cost and increasing the effectiveness of intervention for autistic children as individuals.

For parents of autistic children, the primary concern is to minimize the impact of the condition, likely through evidence-based intervention. The secondary concern is whether any intervention prescribed is affordable and the logistics of completion feasible. This project will obtain evidence for autism intervention options that have different costs and intervention delivery formats (group vs. self-study) to evaluate whether a more costly option is more effective at the study level. The investigators will then develop a predict to-prescribe approach that informs parents which intervention option would likely be most cost-effective in light of each family's unique characteristics (i.e., effectiveness at the individual-child level). [We use the term "parents" to mean caregivers throughout this protocol.]

Autism affects 14 per 10,000 (0.14%) children in Hong Kong and 39.23 per 10,000 in Mainland China. Social communication is a challenging domain in autism, and about 29% of autistic preschoolers have severe verbal deficits. Intervention through pharmaceutical means remains elusive, leaving behavioral interventions the most realistic and immediate avenue of intervention. This project will focus on enhancing the cost-effectiveness of behavioral intervention that targets language and communication. The investigators will do so in the context of precision medicine, in which the investigators aim to identify the most cost effective intervention for the individual autistic child.

AIM OF STUDY:

Objective 1: The investigators will first ascertain whether parent-implemented communication intervention taught by a speech therapist in a Group format (up to 8 families learning together) is more effective than intervention learnt by the parents themselves (learning the same materials without the guidance of a therapist) at the study level.

Objective 2: The investigators will examine pre-intervention child and parent variables simultaneously and construct predictive models of response to the two intervention options (group, more costly vs. self-study, less costly) at the individual-child level.

Inclusion Criteria:

• Have a confirmed diagnosis of autism spectrum disorder or was evaluated to have elevated likelihood ("at-risk" or "suspected") by a Clinical Psychologist, Psychiatrist or Pediatrician who recommended continuous surveillance.
• Meet ADOS-2 criteria for autism or autism spectrum.
• Limited spontaneous expressive language, defined as producing two-to-three-word phrases or fewer, i.e., Autism Diagnostic Observation Schedule, Second Edition (ADOS-2) Module 2, Item A1 > 0.

Exclusion Criteria:

• Mullen Scale of Early Learning non-verbal age at or less than 12 months
• Parent who has severe psychological or neurological conditions prohibiting them from conducting the intervention program at home (restricted to only the parent in the program)
• Children with any other severe developmental problems beyond autism spectrum disorder