機械学習ベースのコンピュータ適応型テスト（ML-CAT）を用いたマッカーサー・ベイツ発達検査（MacArthur-Bates Communicative Developmental Inventory）の短縮化

Early identification of infants and toddlers at risk for developmental disorders can improve the efficiency of early intervention programs and can reduce healthcare costs. The MacArthur-Bates Communicative Development Inventory (MB-CDI) is a standardized tool for assessing children's early lexical development. However, due to its long list of words, administration is time-consuming and often limiting. In this paper we use Machine learning together with a computerized adaptive testing approach (ML-CAT), to shorten the MB-CDI by adapting the sequence of words to the subject's responses. We show that the ML-CAT can reliably predict the final score of the H-MB-CDI with as few as 10 words on average while maintaining 94% to 96% accuracy. We further show that the ML-CAT outperforms existing approaches, including fixed, non adaptive methods as well as statistical models based on Item Response Theory (IRT). Results are also given for five different languages. Most importantly, ML-CAT is shown to outperform IRT based methods when handling atypical talkers (outliers). The ML-CAT enables more efficient lexical development assessment, allowing for a wider and repeated screening in the community. Additionally, due to its shorter length, assessment is expected to be less of a burden on the subject or her caregiver and consequently more reliable.