Introduction We present a methodology to automatically evaluate the performance of patients during picture description tasks. Methods Transcriptions and audio recordings of the Cookie Theft picture description task were used. With 25 healthy elderly control (HC) samples and an information coverage measure, we automatically generated a population-specific referent. We then assessed 517 transcriptions (257 Alzheimer's disease [AD], 217 HC, and 43 mild cognitively impaired samples) according to their informativeness and pertinence against this referent. We extracted linguistic and phonetic metrics which previous literature correlated to early-stage AD. We trained two learners to distinguish HCs from cognitively impaired individuals. Results Our measures significantly ( P < .001) correlated with the severity of the cognitive impairment and the Mini–Mental State Examination score. The classification sensitivity was 81% (area under the curve of receiver operating characteristics = 0.79) and 85% (area under the curve of receiver operating characteristics = 0.76) between HCs and AD and between HCs and AD and mild cognitively impaired, respectively. Discussion An automated assessment of a picture description task could assist clinicians in the detection of early signs of cognitive impairment and AD.

Many studies have been made on the language alterations that take place over the course of Alzheimer's disease (AD). As a consequence, it is now admitted that it is possible to discriminate between healthy and ailing patients solely based on the analysis of language production. Most of these studies, however, were made on very small samples-30 participants per study, on an average-, or involved a great deal of manual work in their analysis. In this paper, we present an automatic analysis of transcripts of elderly participants describing six common objects. We used partof-speech and lexical richness as linguistic features to train an SVM classifier to automatically discriminate between healthy and AD patients in the early and moderate stages. The participants, in the corpus used for this study, were 63 Spanish adults over 55 years old (29 controls and 34 AD patients). With an accuracy of 88%, our experimental results compare favorably to those relying on the manual extraction of attributes, providing evidence that the need for manual analysis can be overcome without sacrificing in performance.

No abstract

Many studies have found that language alterations can aid in the detection of certain medical afflictions. In this work, we present an ongoing project for recollecting multilingual conversations with the elderly in Latin America. This project, so far, involves the combined efforts of psychogeriatricians, linguists, computer scientists, research nurses and geriatric caregivers from six institutions across USA, Canada, Mexico and Ecuador. The recollections are being made available to the international research community. They consist of conversations with adults aged sixty and over, with different nationalities and socioeconomic backgrounds. Conversations are recorded on video, transcribed and time-aligned. Additionally, we are in the process of receiving written texts-recent or old-authored by the participants, provided voluntarily. Each participant is recorded at least twice a year to allow longitudinal studies. Furthermore, information such as medical history, educational background, economic level, occupation, medications and treatments is being registered to aid conducting research on treatment progress and pharmacological effects. Potential studies derived from this work include speech, voice, writing, discourse, and facial and corporal expression analysis. We believe that our recollections incorporate complementary data that can aid researchers in further understanding the progression of cognitive degenerative diseases of the elderly.