Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing
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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-10-01
|
| Series: | Frontiers in Digital Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fdgth.2020.567158/full |
| _version_ | 1818250083975561216 |
|---|---|
| author | Anastasia Ntracha Dimitrios Iakovakis Stelios Hadjidimitriou Vasileios S. Charisis Magda Tsolaki Leontios J. Hadjileontiadis Leontios J. Hadjileontiadis |
| author_facet | Anastasia Ntracha Dimitrios Iakovakis Stelios Hadjidimitriou Vasileios S. Charisis Magda Tsolaki Leontios J. Hadjileontiadis Leontios J. Hadjileontiadis |
| author_sort | Anastasia Ntracha |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T15:46:45Z |
| format | Article |
| id | doaj.art-9f87b1410c304157a961b28b7bd1178b |
| institution | Directory Open Access Journal |
| issn | 2673-253X |
| language | English |
| last_indexed | 2024-12-12T15:46:45Z |
| publishDate | 2020-10-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Digital Health |
| spelling | doaj.art-9f87b1410c304157a961b28b7bd1178b2022-12-22T00:19:44ZengFrontiers Media S.A.Frontiers in Digital Health2673-253X2020-10-01210.3389/fdgth.2020.567158567158Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing ProcessingAnastasia Ntracha0Dimitrios Iakovakis1Stelios Hadjidimitriou2Vasileios S. Charisis3Magda Tsolaki4Leontios J. Hadjileontiadis5Leontios J. Hadjileontiadis6Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceThird Department of Neurology, Medical School, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Aristotle University of Thessaloniki, Thessaloniki, GreeceDepartment of Electrical and Computer Engineering, Khalifa University of Science and Technology, Abu Dhabi, United Arab EmiratesMild 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.https://www.frontiersin.org/article/10.3389/fdgth.2020.567158/fullAlzheimer's diseasenatural language processingkeystroke dynamicsfine motor impairmentmachine learningremote screening |
| spellingShingle | Anastasia Ntracha Dimitrios Iakovakis Stelios Hadjidimitriou Vasileios S. Charisis Magda Tsolaki Leontios J. Hadjileontiadis Leontios J. Hadjileontiadis Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing Frontiers in Digital Health Alzheimer's disease natural language processing keystroke dynamics fine motor impairment machine learning remote screening |
| title | Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing |
| title_full | Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing |
| title_fullStr | Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing |
| title_full_unstemmed | Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing |
| title_short | Detection of Mild Cognitive Impairment Through Natural Language and Touchscreen Typing Processing |
| title_sort | detection of mild cognitive impairment through natural language and touchscreen typing processing |
| topic | Alzheimer's disease natural language processing keystroke dynamics fine motor impairment machine learning remote screening |
| url | https://www.frontiersin.org/article/10.3389/fdgth.2020.567158/full |
| work_keys_str_mv | AT anastasiantracha detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT dimitriosiakovakis detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT stelioshadjidimitriou detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT vasileiosscharisis detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT magdatsolaki detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT leontiosjhadjileontiadis detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing AT leontiosjhadjileontiadis detectionofmildcognitiveimpairmentthroughnaturallanguageandtouchscreentypingprocessing |