I'm not going to keep you too long today as I introduce the paper by DeWayne Lazenby and colleagues  and some rather interesting data on whether early language use might help predict those toddlers who are at subsequent risk of being diagnosed on the autism spectrum.
Based on the prospective analysis of over 300 infants - "some of whom were at high risk for developing ASD [autism spectrum disorder]" - authors went about analysing various aspects of language using among other things, the MacArthur-Bates Communicative Developmental Inventories (CDI). They reported a few potentially interesting details including: "lower receptive and expressive language scores in infants who later were diagnosed with ASD" based on their testing round about 12 months of age. Further: "a Rasch analysis indicated that infants who later developed ASD had a higher degree of statistically unexpected word understanding and production." They concluded that there may indeed be more to see when it comes to language use in early childhood as a potential marker of subsequent autism diagnosis. Such findings accord with other data from some of the authors .
Accepting that within the very wide and heterogeneous autism spectrum probably better defined by the plural autisms (see here) there may be lots of factors influencing first presentation including the variable of regression (see here), these are important findings. Notwithstanding the notion that autism seems not to be protective against other language-related issues being potentially comorbid  and the effect that might have on early presentation of language, the idea that speech patterns might direct a child towards preferential early screening for autism is useful in light of the emphasis on early screening  and the 'clear benefits' of early intervention .
As part of the growing interest in aspects of telemedicine and mobile health, the recent news about ResearchKit being applied to autism (see here) might well provide something of an important platform whereby information about facial expressions is further combined with assessment of speech patterns and production (including aspects such as intonation  etc). This does not mean that every single early presentation of autism will be 'picked up' by such technology, but it does perhaps offer a way that technology can ease some of the significant pressures on clinical resources pertinent to identifying autism early and accurately.
And whilst we're on the topic of language and autism, I can recommend another article by Tager-Flusberg  worth a read...
Music: PJ Harvey - C'mon Billy.
 Lazenby DC. et al. Language Differences at 12 Months in Infants Who Develop Autism Spectrum Disorder. J Autism Dev Disord. 2015 Oct 17.
 Talbott MR. et al. Diary Reports of Concerns in Mothers of Infant Siblings of Children with Autism Across the First Year of Life. J Autism Dev Disord. 2015 Jul;45(7):2187-99.
 Tager-Flusberg H. Defining language impairments in a subgroup of children with autism spectrum disorder. Sci China Life Sci. 2015 Sep 2.
 Zwaigenbaum L. et al. Early Screening of Autism Spectrum Disorder: Recommendations for Practice and Research. Pediatrics. 2015 Oct;136 Suppl 1:S41-59.
 Zwaigenbaum L. et al. Early Intervention for Children With Autism Spectrum Disorder Under 3 Years of Age: Recommendations for Practice and Research. Pediatrics. 2015 Oct;136 Suppl 1:S60-81.
 Nakai Y. et al. Speech intonation in children with autism spectrum disorder. Brain Dev. 2014 Jun;36(6):516-22.
 Tager-Flusberg H. Risk Factors Associated with Language in Autism Spectrum Disorder: Clues to Underlying Mechanisms. J Speech Lang Hear Res. 2015 Oct 20.
Lazenby DC, Sideridis GD, Huntington N, Prante M, Dale PS, Curtin S, Henkel L, Iverson JM, Carver L, Dobkins K, Akshoomoff N, Tagavi D, Nelson CA 3rd, & Tager-Flusberg H (2015). Language Differences at 12 Months in Infants Who Develop Autism Spectrum Disorder. Journal of autism and developmental disorders PMID: 26476738