1. Procedures. From December 2022 to May 2024, the research team completed the collection and follow-up of 900 cases of language disorder and 1,200 cases of ADHD, and included them in the language disorder and ADHD cohort case collection database.From June 2024 to November 2024, 900 children with language disorders and 1,200 children with ADHD will be followed; blood samples will be collected from 600 children with language disorders and 800 children with ADHD; 800 children with ADHD will be completed using the fNIRS task test. From December 2024 to November 2025, complete the follow-up of 900 cases of language disorder and 1,200 cases of ADHD, complete the development of an early assessment tool set suitable for the Chinese children with language disorders and ADHD, complete the formulation of intervention plans, establish a unified standard, and extended the results to 50 hospitals.
2. Sample size. This study is an intervention study. The language disorder group and the ADHD group had to complete a two-year follow-up and intervention. collect blood samples from 900 cases of language disorder and 1,200 cases of ADHD, and complete an fNIRS task test from 800 ADHD patients. The primary endpoints were language disorder and ADHD.An electronic data acquisition system with a follow-up management module, multi-level authority management and automatic SMS notification function is adopted to build an integrated and standardized multi-center queue data storage and sharing platform. Based on the modularization of "core ability improvement", "specific ability improvement and ability strategy acquisition", "learning problems and interpersonal relationships", "social adaptation"; and other programs, sometimes combined with computer-aided cognitive training, parenting behavior management training and/or mindfulness training, aerobic exercise and other intervention forms can achieve personalized functional training intervention for children. Use brain near-infrared imaging technology to capture multimodal neuroimaging features of young children; use high-precision repetitive transcranial direct current stimulation technology to conduct positive neural enhancement and adjustment training on the target brain area. Based on physical therapy stimulation, neuromodulation improves core symptoms in children.
3. Statistical analysis. By integrating multiple methods such as scale evaluation, behavioral testing, and experience sampling into the tool library, digitization, and interface visualization are realized. Combined with the multi-center cloud data platform, a generalized linear probability model is created, and an early evaluation tool is established. Capturing multimodal neuroimaging features of early childhood using fNIRS; training a hierarchical machine learning scoring model using fused neural features. Based on the classic support vector machine algorithm, the detection model is trained with the post-diagnosis as the result label, and the leave-one-out cross-validation method is used for testing.
4. Ethical matters and data protection. The patients who participated in the study will sign the informed consent (obtained from the guardian). And this study was approved by the local ethics committee. The patient's name will be abbreviated and the research data will be assigned a code then to provide to the researcher. The authorization from parents on the patient's health information remains valid until the study is completed. After that, researchers will delete private information from the study record.
