The research, led by M. Ø. Lindstad and colleagues at the Norwegian University of Science and Technology, Oslo Metropolitan University and Oslo University Hospital, tested the Perceive, Recall, Plan and Perform (PRPP) Intervention in three adults over the age of 67 who were receiving home-based rehabilitation after acquired brain injury. Rather than a traditional clinical trial, the team used single-case experimental designs with multiple baselines, a methodology well suited to rehabilitation research where participants are heterogeneous and recruiting large groups is difficult. Each participant acted as their own control, with repeated measurements taken during staggered baseline phases before the intervention was introduced, allowing the researchers to demonstrate a functional relationship between treatment and improvement.

The PRPP system is grounded in an information-processing model of cognition. It frames everyday task performance as a continuous loop of four processes: perceiving incoming sensory information, recalling stored knowledge, planning and evaluating responses, and monitoring performance as the task unfolds. The assessment stage catalogues how a person applies 35 observable cognitive strategies—called descriptors—during a chosen activity, rating each as efficient, questionable or ineffective. The intervention stage then works on those weak links directly. Therapists use a structured prompting sequence, ‘Stop, Attend, Sense, Think, Do’, deploying verbal, visual or physical cues calibrated to each client’s cognitive profile. As the client grows more proficient, the therapist deliberately withdraws support, transferring control of the strategies to the client so that they can be generalised across tasks and settings.

Crucially, the intervention took place where cognitive difficulties actually bite: in participants’ own homes. Three Norwegian municipal home-based rehabilitation teams delivered the programme, which consisted of nine sessions over three weeks. Each participant selected one personally meaningful task as the focus of treatment. For one participant, pseudonymised as Helge, the goal was to write and send an email independently—something that had become laborious and error-prone since his brain injury. For Georg, it was putting on a sweater, a task that had defeated him despite his physical capability, apparently due to insecurity and learned non-use of intact skills. For Frank, it was brewing coffee, a multi-step activity in which he would omit critical steps such as filling the water reservoir or inserting the filter.

The results were measured with the PRPP Assessment Stage 1, which scores percent task mastery from 0 to 100, with independence set at a cut-off above 85 percent. Visual analysis of graphed data across baseline, intervention, post-intervention and follow-up phases was complemented by Tau-U, a statistical technique that combines non-overlap between phases with trend analysis within the intervention phase. All three participants showed clear improvements in task mastery, with 70 to 100 percent of intervention and follow-up data points exceeding baseline levels. Individual Tau-U values ranged from 0.8 to 1.0, and the weighted average across participants reached 0.94 for task mastery when baseline was compared with post-intervention and follow-up phases—a magnitude classified as a very large effect.

Equally important, the gains held. Improvements persisted immediately after the intervention ended and again at follow-up four weeks later, even though the therapists had by then withdrawn all prompting. Georg achieved full independence in dressing and scored beyond his expected goal on Goal Attainment Scaling, a change with ripple effects: he could get out of bed and stay warm in his wheelchair without waiting for home care staff, easing pressure on an entire morning routine. Frank maintained performance above the independence threshold four weeks after his final session and managed untrained tasks, such as collecting post from a locker and pouring coffee into a thermos, using the strategies he had acquired. His Barthel Index score had already been at the maximum of 20, illustrating a limitation of broad functional measures in capturing task-specific change.

Not every outcome was uniform. Helge achieved 100 percent task mastery only intermittently during follow-up, fluctuating between complete independence and partial dependence on the email task. The authors suggest that intellectual familiarity with a cognitive strategy is not the same as internalising it, and that the meaningfulness of the task itself may have played a role. Helge was approaching retirement, and the email task was anchored to a working identity that was fading; his motivation, they note in light of prior rehabilitation research, may have shifted accordingly. His residual difficulties clustered in the planning quadrant, and errors in follow-up were mostly about time efficiency rather than accuracy—yet he still reported confidence in sending emails on his own.

The study addresses a well-documented gap. Recent Cochrane reviews concluded that evidence for occupational therapy in cognitive impairment after stroke, and for cognitive rehabilitation in adults with acquired brain injury, remains insufficient and of low quality—drawn mostly from hospital settings and often from computer-based remediation aimed at impairments rather than real-world function. Evidence-based guidelines instead favour performance-focused, strategy-based, compensatory approaches, precisely the category into which the PRPP Intervention falls. Meanwhile, community-based occupational therapists, particularly generalists in small municipalities, report lacking the specialised competencies and evidence-based tools they need to serve clients with cognitive challenges. A system designed to apply across diagnoses, ages, severities and contexts could fill that void, though the authors caution that adoption requires cultural change within services and funding for the specialised PRPP training.

The authors are candid about limitations. Data collection by the therapists who delivered the intervention introduces potential bias, although blinded inter-observer agreement checks on 20 percent of sessions mostly exceeded the 80 percent acceptability threshold. Frank completed only eight sessions and fewer follow-up measurements than planned, partly because of impatience once he considered himself independent, though his perfectly stable baseline and daily independent performance partially offset the missing data. Crucially, the generalisation of cognitive strategies to untrained tasks could not be conclusively established, because new tasks were measured at only a single point. The Barthel Index, moreover, proved too coarse an instrument for home-based contexts, hitting ceiling effects and missing the richer activities that matter in daily life.

Even so, the study’s ecological validity is its signature strength. By measuring outcomes on the very tasks participants needed and wanted to perform, in the environments where they live, the research captures the kind of functional change that laboratory-based cognitive training often fails to deliver—and that randomised trials with underpowered samples have struggled to demonstrate. Single-case experimental designs, the authors argue, can generate robust evidence close to ordinary clinical practice even with small numbers, and they call for systematic replication, including multiple-baseline designs across behaviours within participants, to test whether strategy use truly transfers to novel and more complex activities. If the very large effects observed here hold up across that replication series, a structured prompting method delivered in a client’s own kitchen or living room may become one of the most practical weapons yet against the hidden cognitive toll of brain injury.

Subject of Research: Effectiveness of the PRPP cognitive strategy intervention for task performance in home-based rehabilitation after acquired brain injury

Article Title: Effectiveness of the PRPP Intervention after brain injury in home-based rehabilitation: Single-case experimental designs with multiple baselines

Article References: Lindstad, M. Ø., Obstfelder, A., Sveen, U., & Stigen, L. (2025). Effectiveness of the PRPP Intervention after brain injury in home-based rehabilitation: Single-case experimental designs with multiple baselines. Scandinavian Journal of Occupational Therapy, 32(1), Article 2444591. https://doi.org/10.1080/11038128.2024.2444591

Image Credits: AI Generated

DOI: 10.1080/11038128.2024.2444591

Keywords: cognitive rehabilitation, PRPP Intervention, acquired brain injury, home-based rehabilitation, occupational therapy, cognitive strategy use, task mastery, single-case experimental design, stroke, Tau-U, evidence-based practice, Effectiveness

The research addresses a stubborn gap in early autism intervention. Decades of work have shown that parent-mediated interventions, in which parents learn to embed evidence-based communication strategies into everyday routines, can dramatically increase the intensity of intervention a child receives and help skills generalize across settings. But those interventions live or die on implementation fidelity, the degree to which parents actually deliver the strategies as intended. Traditional coaching models depend on scheduled sessions with specialists, and between those sessions parents are often left without feedback, performance monitoring, or support. The delays between a parent’s performance and a professional’s correction can blunt learning, and the demands of daily family life frequently erode strategy use over time. The research team, led by Yusuf Akemoglu, set out to test whether AI could close that feedback loop.

PaiCoach is built on the Parent-implemented Communication Strategies-Storybook program, an intervention with a strong empirical track record in which parents use three naturalistic strategies during shared reading. Modeling involves demonstrating target words or communicative responses for the child. Mand-model combines prompts or questions with language models to elicit a response. Time delay creates opportunities for children to initiate communication by intentionally pausing before offering help. In the PaiCoach architecture, parents record short videos of their reading interactions and upload them to the platform. A backend pipeline combining automatic speech recognition, multimodal video analysis, and large language model processing then identifies instances of each strategy, estimates fidelity scores, and drafts time-stamped feedback. Crucially, no AI output reaches a parent until trained human reviewers verify it, making PaiCoach a human-in-the-loop system rather than an autonomous one.

The underlying AI was trained on the ASD-HI benchmark dataset, which contains 478 expert-labeled parent strategy-use instances drawn from 48 real-world shared reading sessions. The dataset was partitioned into training, validation, and test sets for model development. For the version evaluated in this study, the researchers replaced the original Whisper speech recognition component with Qwen3 and upgraded the classification and feedback model from GPT-4o to GPT-5.1. Internal evaluation showed the strategy detection model achieved roughly 82 percent recall, while the multimodal fidelity assessment model reached 68.6 percent accuracy. Strategy classification relied on observable interaction sequences, such as recognizing a time delay when a parent created a communication opportunity and deliberately paused, rather than attempting to judge which strategy a parent should have chosen.

To test the system rigorously, the team used a concurrent multiple-baseline across participants single-case experimental design, a method that allows researchers to demonstrate functional relations at the individual level by staggering the start of intervention across participants. Four mother-child dyads took part, each with a minimally verbal autistic child between 45 and 56 months of age. After stable baselines of three to seven sessions in which parents read as they normally would, families completed a one-hour Zoom training on the three communication strategies and then began using PaiCoach for six to seven intervention sessions, followed by maintenance probes roughly three weeks later. All procedures were conducted remotely across approximately 10 to 12 weeks.

The results were striking. Visual analysis showed immediate and sustained increases in parent implementation fidelity for all four mothers following the introduction of PaiCoach. Parent 3, for example, went from 0 percent fidelity across every baseline session to 76.4 percent in her very first intervention session, eventually stabilizing between 74.3 and 88.2 percent. Tau-U effect sizes, which quantify nonoverlap between baseline and intervention data, reached 1.00 for parent fidelity across all four dyads, indicating complete separation between phases. Child communicative responsiveness, measured as the percentage of parent-provided opportunities that drew a verbal or nonverbal response, rose in parallel, with Tau-U values ranging from 0.72 to 1.00 and a mean of 0.84, representing large to very large effects. Gains generally held during maintenance, even after feedback features were switched off.

The human validation data offer a candid look at the current state of AI in this domain. Across 53 reviewed sessions and 879 coded instances, about 69 percent of AI-generated outputs were accepted without modification while 31.4 percent required expert editing. Error rates varied by task: time detection required editing most often, followed by strategy detection, fidelity scoring, and feedback generation. The system occasionally missed gesture-based child responses when a book obscured the camera view, and overlapping speech or natural variation in parental praise sometimes caused fidelity scores to be downgraded incorrectly. Even so, the efficiency gains were considerable. Manually coding a five-minute session typically takes an experienced coder 20 to 30 minutes and a newly trained coder up to an hour. PaiCoach produced transcripts, preliminary coding, scores, and draft feedback within minutes, letting reviewers verify and correct results in roughly 5 to 10 minutes per session.

Parents themselves responded enthusiastically. In semi-structured interviews, all four mothers described wanting their children to communicate more and to engage more deeply with books, and several noted that the AI’s constant availability and nonjudgmental nature made it easier to seek and absorb feedback. One parent described the system’s comments as instructive criticism, while another emphasized the flexibility of uploading videos late at night before bedtime, when traveling to appointments would have been impossible. Quantitative measures backed up the interviews: mean ratings for training clarity, procedure feasibility, and perceived usefulness hovered between 4.3 and 5.0 on a 5-point scale, and the System Usability Scale yielded a mean score of 77.5, indicating good usability. Parents did report friction with video upload navigation, a reminder that user interface design matters as much as the underlying models.

What distinguishes PaiCoach from most AI tools in autism research is its indirect pathway of influence. Rather than delivering therapy directly to children, the system improves the learning environment by sharpening the adults around them. That design choice aligns with human-centered AI frameworks, which hold that effective systems should augment human decision-making rather than supplant it. The authors are careful to frame their findings as preliminary evidence for the feasibility of AI-augmented coaching, not proof of an autonomous intervention, noting that child communication behaviors proved harder for the AI to classify reliably than parent strategies.

Future work, the researchers say, should focus on expanding training datasets to capture greater variability in real-world interactions, improving multimodal models that integrate visual, auditory, and linguistic data, and exploring confidence-based thresholds or hybrid review models that apply human oversight selectively. Larger and more diverse populations, additional daily routines, and head-to-head comparisons with traditional coaching models are all on the agenda. If those efforts succeed, systems like PaiCoach could help solve one of early autism intervention’s most persistent problems: making expert-quality coaching available to every family, at the moment it is needed, inside the routines of everyday life.

Shared book reading offers a particularly strategic setting for this kind of intervention. The routine is already familiar to most families, occurs naturally several times a week, and provides repeated, predictable opportunities for children to request, label, and respond within a low-pressure context. Embedding communication strategies into an activity parents already perform reduces the burden of adding new obligations to crowded family schedules, which has long been a barrier to sustained strategy use outside formal sessions.

The single-case methodology deserves note as well. Unlike group designs that average outcomes across many participants, a concurrent multiple-baseline design evaluates each dyad as its own control, staggering intervention onset while baselines remain stable. This approach is well suited to early-stage feasibility research because it documents individual change patterns and demonstrates that improvements track the introduction of the system rather than maturation or practice alone. Tau-U effect sizes complement visual inspection by quantifying the degree of nonoverlap between phases, with values approaching 1.0 indicating that intervention-phase data points consistently exceeded baseline performance.

The maintenance findings carry practical weight. When feedback features were disabled for follow-up probes, fidelity gains largely persisted, suggesting that the AI-supported coaching period was sufficient for parents to internalize the strategies rather than becoming dependent on continuous prompting. Whether such durability extends to longer intervals and to other routines remains an open question.

The study also illustrates a broader trend in assistive technology research: benchmark datasets of expert-labeled behavioral instances are becoming foundational infrastructure for building and evaluating multimodal models in autism intervention. Because these systems must interpret subtle, context-dependent human behavior, transparent reporting of detection accuracy, editing rates, and failure modes, as this study provides, will be essential for building trust among clinicians and families as AI-supported coaching matures.

Subject of Research: An AI-supported parent coaching system for improving communication outcomes in minimally verbal autistic children

Article Title: Parent’s AI Coach (PaiCoach): A Single-Case Experimental Study of an AI-Supported Parent Coaching System for Autistic Children

Article References: Akemoğlu, Y., Li, Z., Zheng, Q., Roberts, E. B., Singh, S. P., & Xiong, J. (2026). Parent’s AI Coach (PaiCoach): A Single-Case Experimental Study of an AI-Supported Parent Coaching System for Autistic Children. Journal of Autism and Developmental Disorders. https://doi.org/10.1007/s10803-026-07519-6

Image Credits: AI Generated

DOI: 10.1007/s10803-026-07519-6

Keywords: artificial intelligence, autism, parent-mediated intervention, PaiCoach, shared book reading, human-in-the-loop, single-case experimental design, large language models, early intervention, communication strategies, implementation fidelity, multimodal AI