Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing

TLDR

Mild cognitive impairment, a prodromal stage of Alzheimer’s disease, is frequently missed in early clinical assessments. The study investigates whether unobtrusive smartphone interaction data can serve as a screening tool for MCI and its progression. Keystroke dynamics extracted from touchscreen typing were modeled with convolutional neural networks, while linguistic features of spontaneous written speech were analyzed with natural language processing; the resulting multimodal features were fed into cascaded classifiers and evaluated via leave‑one‑subject‑out cross‑validation on 11 MCI patients and 12 healthy controls. Keystroke‑based k‑NN achieved an AUC of 0.78, NLP‑based logistic regression an AUC of 0.76, and the fused ensemble an AUC of 0.75, indicating that these digital biomarkers can provide a highly specific remote screening method for early cognitive decline.

Abstract

Mild cognitive impairment (MCI), an identified prodromal stage of Alzheimer's Disease (AD), often evades detection in the early stages of the condition, when existing diagnostic methods are employed in the clinical setting. From an alternative perspective, smartphone interaction behavioral data, unobtrusively acquired in a non-clinical setting, can assist the screening and monitoring of MCI and its symptoms' progression. In this vein, the diagnostic ability of digital biomarkers, drawn from Fine Motor Impairment (FMI)- and Spontaneous Written Speech (SWS)-related data analysis, are examined here. In particular, keystroke dynamics derived from touchscreen typing activities, using Convolutional Neural Networks, along with linguistic features of SWS through Natural Language Processing (NLP), were used to distinguish amongst MCI patients and healthy controls (HC). Analytically, three indices of FMI (rigidity, bradykinesia and alternate finger tapping) and nine NLP features, related with lexical richness, grammatical, syntactical complexity, and word deficits, formed the feature space. The proposed approach was tested on two demographically matched groups of 11 MCI patients and 12 HC, having undergone the same neuropsychological tests, producing 4,930 typing sessions and 78 short texts, within 6 months, for analysis. A cascaded-classifier scheme was realized under three different feature combinations and validated via a Leave-One-Subject-Out cross-validation scheme. The acquired results have shown: (a) keystroke features with a k-NN classifier achieved an Area Under Curve (AUC) of 0.78 [95% confidence interval (CI):0.68-0.88; specificity/sensitivity (SP/SE): 0.64/0.92], (b) NLP features with a Logistic regression classifier achieved an AUC of 0.76 (95% CI: 0.65-0.85; SP/SE: 0.80/0.71), and (c) an ensemble model with the fusion of keystroke and NLP features resulted in AUC of 0.75 (95% CI:0.63-0.86; SP/SE 0.90/0.60). The current findings indicate the potentiality of new digital biomarkers to capture early stages of cognitive decline, providing a highly specific remote screening tool in-the-wild.