Human–AI collaboration for dysphagia rehabilitation from effectiveness to implementation complexity: a systematic review

npj | digital medicine Article Published in partnership with Seoul National University Bundang Hospital https://doi.org/10.1038/s41746-026-02729-9 Human–AI collaboration for dysphagia rehabilitation from effectiveness to implementation complexity: a systematic review Check for updates 1234567890():,; 1234567890():,; Wenwen Yang, Sufang Li, Yifei Du, Mengran Chen, Funa Yang, Fan Zhang, Ji Zhao, Yanqing Li Xiaoxia Xu & Oropharyngeal dysphagia affects over half of neurological and oncological populations, yet rehabilitation is constrained by a global therapist shortage that human–AI collaboration has not demonstrably addressed. Here we report a systematic review of 31 studies (1012 participants; PROSPERO: CRD420251115997) evaluating AI-augmented swallowing rehabilitation in adults with oropharyngeal dysphagia, or in healthy volunteers testing systems designed for clinical application. We synthesised findings by aetiology and collaboration mode, assessing risk of bias and certainty of evidence (Grading of Recommendations, Assessment, Development and Evaluation, GRADE). AIaugmented interventions produce short-term gains in functional oral intake and physiological measures (GRADE moderate/low certainty), but these effects attenuate within weeks of cessation, and adherence declines sharply once clinician supervision is withdrawn. NASSS framework analysis reveals a central paradox: the adopter domain—digital literacy, cognitive impairment, interface usability—is the dominant implementation barrier (61.3% rated high), meaning the populations with the greatest need face the steepest barriers to adoption. AI algorithm performance is rated at very low certainty, with validation largely confined to healthy volunteers. These findings support advancement to pragmatic trials for supervised post-stroke rehabilitation but underscore that evidence for other aetiologies, unsupervised settings, and sustained outcomes remains insufficient. Safe swallowing requires sub-second coordination of over thirty craniocervical muscle pairs1,2—yet its rehabilitation remains critically underresourced worldwide. Oropharyngeal dysphagia affects up to 30% of community-dwelling older adults and exceeds 50% in most neurological and oncological populations studied, including stroke, Parkinson’s disease, age-related frailty and head and neck cancer (HNC)3–8. Regardless of aetiology, dysphagia independently raises the risk of aspiration pneumonia, malnutrition, and death—post-stroke dysphagia alone confers a more than fourfold increase in pneumonia risk9,10, and aspiration pneumonia remains the leading cause of death in advanced Parkinson’s disease11,12. Because swallowing dysfunction frequently persists or progresses beyond the acute phase13,14, rehabilitation needs are chronic and escalating—accounting for an estimated US$4.3–7.1 billion in excess dysphagia-related inpatient costs per year in the United States15,16, a burden set to intensify as the global population aged 60 and older approaches 2.1 billion by 205017. Intensive swallowing rehabilitation promotes neuroplastic recovery and functional improvement18,19, but delivering it at adequate intensity hinges on a specialist workforce whose numbers fall far short of global need—and the deficit is widening. In the United States, speech-language pathologist employment is projected to grow by 15% between 2024 and 2034—well above the occupational average—yet still fall short of demand20. In low- and middleincome countries the deficit is orders of magnitude larger: the WHO estimates fewer than ten skilled rehabilitation practitioners per million population, and only 17% of low-income countries have even one speech–language therapist per million21,22. The consequence is that a large proportion of patients worldwide cannot access swallowing rehabilitation at sufficient intensity. Technology may help close this gap—but only if it augments, rather than supplants, the clinical expertise on which safe practice depends. The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China. npj Digital Medicine | (2026)9:404 e-mail: ; 1 https://doi.org/10.1038/s41746-026-02729-9 Article Fig. 1 | NASSS framework-based complexity assessment of implementation barriers to human–AI collaborative dysphagia intervention. Barriers are mapped onto seven NASSS domains: D1 (Condition), D2 (Technology), D3 (Value Proposition), D4a (Adopters: Patients), D4b (Adopters: Therapists), and D5–7 (Organisation, Wider System, and Embedding). Surrounding panels detail domain-specific barriers synthesised from the included studies. Directional annotations between domains indicate cross-domain cascading interactions. Solid arrows denote primary influence pathways; dashed curved arrows denote cross-domain interactions; the dashed boundary at the bottom indicates additional complexity amplification in low- and middle-income country contexts. Human–AI collaboration in rehabilitation embodies this principle, positioning AI not as an autonomous decision-maker but as computational support—real-time physiological monitoring, pattern recognition across multiple signal streams, and individualised dosage adaptation—while clinicians retain contextual judgement, oversight of aspiration risk, and the therapeutic relationship23–25. We define a human–AI collaborative rehabilitation system as one integrating: at least one AI-enhanced component, such as adaptive parameter adjustment, multi-parameter pattern recognition, personalised protocol generation, or algorithm-driven real-time feedback and risk alerting; and at least one form of human clinical involvement, such as treatment plan formulation or approval, intervention supervision, parameter adjustment, or exception management. This definition spans a spectrum of collaboration intensity, from continuous clinician oversight with AI-augmented assessment to semi-autonomous AI operation under periodic clinical review. Swallowing lends itself to such collaboration: it generates multimodal physiological signals—electromyographic activity, lingual pressure, laryngeal excursion, deglutition acoustics26–28—that encode the rapid biomechanical sequences governing airway protection and bolus transit. These sequences unfold on millisecond timescales, beyond the reach of unaided clinical observation2 but amenable to computational analysis. Preliminary validation indicates that systems built on these signals achieve acceptable detection accuracy in specific populations and improve training precision in controlled settings29–31. Whether these early capabilities translate into real-world clinical benefit remains unclear. Systematic reviews show that specific swallowing interventions yield favourable group-level effects on impairment4,32–34, yet a Cochrane review—assessing functional endpoints—found no demonstrable reduction in mortality or long-term disability, with substantial interindividual response heterogeneity that conventional clinic (...truncated)