Kirsten I. Taylor
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Kirsten I. Taylor has a total of 203 co-authors. Here are the top co-authors by number of shared publications:
- Lorraine Komisarjevsky Tyler
University of Cambridge
11 shared publications Andreas U. Monsch
Memory Clinic, University Center for Medicine of Aging Basel, Felix-Platter Hospital, Basel, Switzerland
8 shared publications- Sasa L. Kivisaari
Department of Neuroscience and Biomedical Engineering, Aalto University, Aalto, Finland
7 shared publications - Andreas U. Monsch
Memory Clinic, University Center for Medicine of Aging Basel, Felix Platter Hospital, Basel, Switzerland
6 shared publications - Florian Lipsmeier
F. Hoffmann-La Roche Ltd, Basel, Switzerland
6 shared publications Manfred Berres
Department of Mathematics & Technology, RheinAhrCampus, Remagen, Germany
6 shared publications
Latest Publications
- Open Access
- 5 September 2026
- Published by Springer Nature in npj Digital Medicine
From feasibility to neuroanatomic validity of remote cognitive smartphone assessments in early Alzheimer’s disease
- 5 September 2026
- Published by Springer Nature in npj Digital Medicine
Open AccessFrom feasibility to neuroanatomic validity of remote cognitive smartphone assessments in early Alzheimer’s disease
- Open Access
- 16 June 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 1-12
Exploratory digital outcome measures of motor sign progression in Parkinson’s disease patients treated with prasinezumab
Digital health technology (DHT) tools for Parkinson’s disease (PD) e.g., smartphones and wearables were used for remote and frequent measurement of motor signs in the phase 2 PASADENA study of the anti-alpha-synuclein monoclonal antibody prasinezumab. 316 early-stage PD participants were randomized to placebo, 1500 mg, or 4500 mg prasinezumab for 52 weeks; placebo participants were re-randomized to prasinezumab for the ensuing 52 weeks. Patients performed daily smartphone motor “active tests”, and were passively monitored by smartphone/smartwatch throughout the day over 2 y. Change from baseline analyses censored data at dopaminergic treatment start. Bilateral speeded tapping variability and hand-turning, U-turn speed, passively monitored hand movement power, and summary Simple Sum scores progressed numerically less in prasinezumab-treated vs placebo at week 52. All findings except hand-turning persisted at week 104. DHT sensor-based outcome measures may contribute to quantifying disease progression in clinical research of early-stage, dopaminergic treatment-naïve PD. Clinical Trial Registry Name: ClinicalTrials.gov; Clinical Trial Registry ID: NCT03100149; registered 2017-03-29.
- 16 June 2025
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 1-12
Open AccessExploratory digital outcome measures of motor sign progression in Parkinson’s disease patients treated with prasinezumab
Digital health technology (DHT) tools for Parkinson’s disease (PD) e.g., smartphones and wearables were used for remote and frequent measurement of motor signs in the phase 2 PASADENA study of the anti-alpha-synuclein monoclonal antibody prasinezumab. 316 early-stage PD participants were randomized to placebo, 1500 mg, or 4500 mg prasinezumab for 52 weeks; placebo participants were re-randomized to prasinezumab for the ensuing 52 weeks. Patients performed daily smartphone motor “active tests”, and were passively monitored by smartphone/smartwatch throughout the day over 2 y. Change from baseline analyses censored data at dopaminergic treatment start. Bilateral speeded tapping variability and hand-turning, U-turn speed, passively monitored hand movement power, and summary Simple Sum scores progressed numerically less in prasinezumab-treated vs placebo at week 52. All findings except hand-turning persisted at week 104. DHT sensor-based outcome measures may contribute to quantifying disease progression in clinical research of early-stage, dopaminergic treatment-naïve PD. Clinical Trial Registry Name: ClinicalTrials.gov; Clinical Trial Registry ID: NCT03100149; registered 2017-03-29.
- Open Access
- 6 February 2024
- Published by Springer Nature in Research Square
Exploratory Sensor-based Outcome Measures Show Divergent Slopes of Motor Sign Progression in Parkinson’s Disease Patients Treated with Prasinezumab
Digital health technology (DHT) tools for Parkinson’s disease (PD) such as smartphones and wearable sensors enable remote and frequent measurement of motor signs which may facilitate research on novel treatments for PD. Here, we report the effect of the anti-alpha-synuclein monoclonal antibody prasinezumab on two-year motor sign progression in an early-stage PD population as measured with the Roche PD Mobile Application DHT. 316 early-stage PD participants of the phase 2 PASADENA study (NCT03100149) were randomized to treatment with placebo, 1500 mg, or 4500 mg prasinezumab for 52 weeks (Part 1); and placebo treated patients in Part 1 were re-randomized to 1500 mg or 4500 mg prasinezumab for the ensuing 52 weeks (Part 2, delayed-start group). Patients performed daily motor ‘active tests’ on provisioned study smartphones, carried the phone and wore a smartwatch throughout the day for passive monitoring, over two years. Change from baseline on 17 pre-specified individual sensor features and a summary Simple Sum score were analyzed with linear random slope and intercept models or mixed models for repeated measures, censoring patient data following the start of dopaminergic treatment. Adherence to active testing averaged 5.7 and 5.0 days/week in Parts 1 and 2, respectively. Bilateral speeded tapping variability and hand turning, U-turn speed, the power of passively monitored non-gait hand movements, and the Simple Sum score progressed less in prasinezumab-treated vs placebo at week 52. All findings except hand turning persisted at week 104. While the primary outcome for Part 1 PASADENA (MDS-UPDRS sum of Parts I, II and III) showed no significant difference from placebo, exploratory sensor-based outcome measures showed reduced motor sign progression in prasinezumab-treated individuals with early-stage PD.
- 6 February 2024
- Published by Springer Nature in Research Square
Open AccessExploratory Sensor-based Outcome Measures Show Divergent Slopes of Motor Sign Progression in Parkinson’s Disease Patients Treated with Prasinezumab
Digital health technology (DHT) tools for Parkinson’s disease (PD) such as smartphones and wearable sensors enable remote and frequent measurement of motor signs which may facilitate research on novel treatments for PD. Here, we report the effect of the anti-alpha-synuclein monoclonal antibody prasinezumab on two-year motor sign progression in an early-stage PD population as measured with the Roche PD Mobile Application DHT. 316 early-stage PD participants of the phase 2 PASADENA study (NCT03100149) were randomized to treatment with placebo, 1500 mg, or 4500 mg prasinezumab for 52 weeks (Part 1); and placebo treated patients in Part 1 were re-randomized to 1500 mg or 4500 mg prasinezumab for the ensuing 52 weeks (Part 2, delayed-start group). Patients performed daily motor ‘active tests’ on provisioned study smartphones, carried the phone and wore a smartwatch throughout the day for passive monitoring, over two years. Change from baseline on 17 pre-specified individual sensor features and a summary Simple Sum score were analyzed with linear random slope and intercept models or mixed models for repeated measures, censoring patient data following the start of dopaminergic treatment. Adherence to active testing averaged 5.7 and 5.0 days/week in Parts 1 and 2, respectively. Bilateral speeded tapping variability and hand turning, U-turn speed, the power of passively monitored non-gait hand movements, and the Simple Sum score progressed less in prasinezumab-treated vs placebo at week 52. All findings except hand turning persisted at week 104. While the primary outcome for Part 1 PASADENA (MDS-UPDRS sum of Parts I, II and III) showed no significant difference from placebo, exploratory sensor-based outcome measures showed reduced motor sign progression in prasinezumab-treated individuals with early-stage PD.
- Open Access
- 25 December 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S18)
Preliminary validation of a dual‐task gait assessment in early Alzheimer’s Disease
Background: Early stages of Alzheimer’s disease (eAD) are marked by changes in gait characteristics that may be measured using simple smartphone‐based gait tasks. Here we present an assessment of cognitive‐motor‐interference where participants walk for 30 seconds with a smartphone placed in a running belt while counting backwards, called the 30‐Second Walk Test Dual Task (30sWTDT). We report the preliminary reliability and validation of the 30sWTDT in a cohort of healthy individuals (HC), individuals with subjective cognitive decline amyloid‐PET negative and positive (SCDn and SCDp, respectively) and eAD.Method: 123 participants (32 HC, 31 SCDn, 30 SCDp and 30 eAD) were recruited as a part of a Proof‐of‐Concept study of the Alzheimer’s Disease Digital Assessment Suite (AD‐DAS) (https://www.isrctn.com/ISRCTN17035495). Participants performed 9 sessions of 30sWTDT over 28 days on provisioned smartphones. Feasibility was evaluated as the proportion of completed 30sWTDT relative to the total number of expected sessions. Two gait characteristic metrics were estimated: variability in step frequency (VSF) and the 25th percentile in step power (25SP). Intraclass correlation coefficients (ICC) tested the metrics’ reliability. Convergent validity was established as partial correlation between VSF/25SP and adjusted mean duration in Timed 25 foot Walk Test (T25WT). Clinical validity was evaluated using a proportional odds logistic regression model to differentiate between groups.Result: Among the 97.5% of participants who completed the study (i.e., n = 120), participants completed 88.9% of all assigned 30sWTDT tasks, with no group difference in adherence. VSF and 25SP metrics showed moderate (ICC = 0.74) and good (ICC = 0.79) reliability, respectively. Both metrics significantly distinguished between HC and all other study groups (odds ratio = [0.012,0.029]), and were associated with T25WT adjusted mean duration (adjusted r2 = [0.09,0.069]).Conclusion: Preliminary findings demonstrate that a smartphone‐based 30sWTDT can be successfully self‐administered by cognitively healthy participants and individuals on the eAD continuum. Participants show high adherence in an ecologically valid environment. 30sWTDT differentiated HC from all other groups with subjective or objective cognitive problems, indicating a lack of specificity of gait characteristics to differentiate between increasing levels of cognitive impairment. These findings require replication in larger independent datasets.
- 25 December 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S18)
Open AccessPreliminary validation of a dual‐task gait assessment in early Alzheimer’s Disease
Background: Early stages of Alzheimer’s disease (eAD) are marked by changes in gait characteristics that may be measured using simple smartphone‐based gait tasks. Here we present an assessment of cognitive‐motor‐interference where participants walk for 30 seconds with a smartphone placed in a running belt while counting backwards, called the 30‐Second Walk Test Dual Task (30sWTDT). We report the preliminary reliability and validation of the 30sWTDT in a cohort of healthy individuals (HC), individuals with subjective cognitive decline amyloid‐PET negative and positive (SCDn and SCDp, respectively) and eAD.Method: 123 participants (32 HC, 31 SCDn, 30 SCDp and 30 eAD) were recruited as a part of a Proof‐of‐Concept study of the Alzheimer’s Disease Digital Assessment Suite (AD‐DAS) (https://www.isrctn.com/ISRCTN17035495). Participants performed 9 sessions of 30sWTDT over 28 days on provisioned smartphones. Feasibility was evaluated as the proportion of completed 30sWTDT relative to the total number of expected sessions. Two gait characteristic metrics were estimated: variability in step frequency (VSF) and the 25th percentile in step power (25SP). Intraclass correlation coefficients (ICC) tested the metrics’ reliability. Convergent validity was established as partial correlation between VSF/25SP and adjusted mean duration in Timed 25 foot Walk Test (T25WT). Clinical validity was evaluated using a proportional odds logistic regression model to differentiate between groups.Result: Among the 97.5% of participants who completed the study (i.e., n = 120), participants completed 88.9% of all assigned 30sWTDT tasks, with no group difference in adherence. VSF and 25SP metrics showed moderate (ICC = 0.74) and good (ICC = 0.79) reliability, respectively. Both metrics significantly distinguished between HC and all other study groups (odds ratio = [0.012,0.029]), and were associated with T25WT adjusted mean duration (adjusted r2 = [0.09,0.069]).Conclusion: Preliminary findings demonstrate that a smartphone‐based 30sWTDT can be successfully self‐administered by cognitively healthy participants and individuals on the eAD continuum. Participants show high adherence in an ecologically valid environment. 30sWTDT differentiated HC from all other groups with subjective or objective cognitive problems, indicating a lack of specificity of gait characteristics to differentiate between increasing levels of cognitive impairment. These findings require replication in larger independent datasets.
- Open Access
- 25 December 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S18)
Functional neuroanatomic validity of a novel, smartphone‐based remote assessment of processing speed in early Alzheimer’s Disease
Background: The quantification of information processing speed (IPS) and its changes over time is a cornerstone of neuropsychological assessment for early Alzheimer’s disease (eAD). Additionally, clinical practice and drug development increasingly require tools enabling the remote assessment of cognition. We previously reported the feasibility, reliability and clinical validity of a novel, smartphone‐based IPS test remotely self‐administered to healthy controls (HC) and individuals with subjective cognitive decline (SCD) and eAD. The present study performed whole‐brain voxel‐based morphometry (VBM) analyses to determine whether smartphone‐based IPS performance indeed correlated with atrophy of brain regions known to support processing speed.Method: 31 HC, 31 SCDn (amyloid‐PET negative), 31 SCDp (amyloid‐PET positive) and 30 eAD individuals participated in a Alzheimer’s Digital Assessment Suite (AD‐DAS) Proof‐of‐Concept study (https://www.isrctn.com/ISRCTN17035495). Participants performed 9 IPS assessments (90s digit‐symbol matching) over 28 days on provisioned smartphones. Each response sequence and digit‐symbol pairing was novel and matched for difficulty within/across sessions.High‐resolution anatomic, T1‐weighted MRI were submitted to whole‐brain VBM analyses (Computational Anatomy Toolbox, SPM12/Matlab 2021) testing whether performance (number correct) correlated with gray matter signal intensities (covariates: age, gender, years of education, study site, total intracranial volume). The statistical parametric map was thresholded at p<0.001 uncorrected (voxel‐level) and family‐wise error corrected p<0.05 (cluster‐level). Peak voxel MNI coordinates and t‐values, cluster‐level p‐values are reported.Result: Poor smartphone‐based IPS performance correlated with atrophy in five regions centered in: (1) right insula (57, ‐14, 15; t = 5.83; p<0.0001), (2) right lingual gyrus (14, ‐64, ‐8; t = 5.21; p = 0.006), (3) left hippocampus (‐36, ‐24, ‐16; t = 4.83; p = 0.021), (4) left precuneus (‐10, ‐57, 26; t = 4.73; p = 0.017), (5) right fusiform gyrus (27, ‐38, ‐15; t = 4.69; p = 0.043), replicating previous functional MRI findings with IPS (lingual gyrus, precuneus) and known neuroanatomical correlates of working memory (insula, hippocampus).Conclusion: These findings support the functional neuroanatomic validity of a novel smartphone‐based IPS task and thus remote, clinically meaningful characterization of preclinical/early AD individuals’ IPS impairments in clinical monitoring and drug trials.
- 25 December 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S18)
Open AccessFunctional neuroanatomic validity of a novel, smartphone‐based remote assessment of processing speed in early Alzheimer’s Disease
Background: The quantification of information processing speed (IPS) and its changes over time is a cornerstone of neuropsychological assessment for early Alzheimer’s disease (eAD). Additionally, clinical practice and drug development increasingly require tools enabling the remote assessment of cognition. We previously reported the feasibility, reliability and clinical validity of a novel, smartphone‐based IPS test remotely self‐administered to healthy controls (HC) and individuals with subjective cognitive decline (SCD) and eAD. The present study performed whole‐brain voxel‐based morphometry (VBM) analyses to determine whether smartphone‐based IPS performance indeed correlated with atrophy of brain regions known to support processing speed.Method: 31 HC, 31 SCDn (amyloid‐PET negative), 31 SCDp (amyloid‐PET positive) and 30 eAD individuals participated in a Alzheimer’s Digital Assessment Suite (AD‐DAS) Proof‐of‐Concept study (https://www.isrctn.com/ISRCTN17035495). Participants performed 9 IPS assessments (90s digit‐symbol matching) over 28 days on provisioned smartphones. Each response sequence and digit‐symbol pairing was novel and matched for difficulty within/across sessions.High‐resolution anatomic, T1‐weighted MRI were submitted to whole‐brain VBM analyses (Computational Anatomy Toolbox, SPM12/Matlab 2021) testing whether performance (number correct) correlated with gray matter signal intensities (covariates: age, gender, years of education, study site, total intracranial volume). The statistical parametric map was thresholded at p<0.001 uncorrected (voxel‐level) and family‐wise error corrected p<0.05 (cluster‐level). Peak voxel MNI coordinates and t‐values, cluster‐level p‐values are reported.Result: Poor smartphone‐based IPS performance correlated with atrophy in five regions centered in: (1) right insula (57, ‐14, 15; t = 5.83; p<0.0001), (2) right lingual gyrus (14, ‐64, ‐8; t = 5.21; p = 0.006), (3) left hippocampus (‐36, ‐24, ‐16; t = 4.83; p = 0.021), (4) left precuneus (‐10, ‐57, 26; t = 4.73; p = 0.017), (5) right fusiform gyrus (27, ‐38, ‐15; t = 4.69; p = 0.043), replicating previous functional MRI findings with IPS (lingual gyrus, precuneus) and known neuroanatomical correlates of working memory (insula, hippocampus).Conclusion: These findings support the functional neuroanatomic validity of a novel smartphone‐based IPS task and thus remote, clinically meaningful characterization of preclinical/early AD individuals’ IPS impairments in clinical monitoring and drug trials.
- Open Access
- 25 November 2020
- Published by Oxford University Press (OUP) in Archives of Clinical Neuropsychology
- Vol. 36 (5) , 838-843
Cats and Apples: Semantic Fluency Performance for Living Things Identifies Patients with Very Early Alzheimer’s Disease
Objective: Reduced semantic memory performance is a known neuropsychological marker of very early Alzheimer’s disease (AD), but the task format that best predicts disease status is an open question. The present study aimed to identify the semantic fluency task and measure that best discriminates early-stage AD patients (PATs) from cognitively healthy controls. Method: Semantic fluency performance for animals, fruits, tools, and vehicles was assessed in 70 early-stage AD PATs and 67 cognitively healthy participants. Logistic regressions and receiver operating characteristics were calculated for five total score semantic fluency measures. Results: Compared with all other measures, living things (i.e., total correct animals + total correct fruits) achieved highest z-statistics, highest area under the curve and smallest difference between the upper and lower 95% confidence intervals. Conclusion: Living things total correct is a powerful tool to detect the earliest signs of incipient AD.
- 25 November 2020
- Published by Oxford University Press (OUP) in Archives of Clinical Neuropsychology
- Vol. 36 (5) , 838-843
Open AccessCats and Apples: Semantic Fluency Performance for Living Things Identifies Patients with Very Early Alzheimer’s Disease
Objective: Reduced semantic memory performance is a known neuropsychological marker of very early Alzheimer’s disease (AD), but the task format that best predicts disease status is an open question. The present study aimed to identify the semantic fluency task and measure that best discriminates early-stage AD patients (PATs) from cognitively healthy controls. Method: Semantic fluency performance for animals, fruits, tools, and vehicles was assessed in 70 early-stage AD PATs and 67 cognitively healthy participants. Logistic regressions and receiver operating characteristics were calculated for five total score semantic fluency measures. Results: Compared with all other measures, living things (i.e., total correct animals + total correct fruits) achieved highest z-statistics, highest area under the curve and smallest difference between the upper and lower 95% confidence intervals. Conclusion: Living things total correct is a powerful tool to detect the earliest signs of incipient AD.
- Open Access
- 23 July 2020
- Published by Springer Nature in npj Digital Medicine
- Vol. 3 (1) , 1-8
Outcome measures based on digital health technology sensor data: data- and patient-centric approaches
Digital health technology tools (DHTT) are technologies such as apps, smartphones, and wearables that remotely acquire health-related information from individuals. They have the potential advantages of objectivity and sensitivity of measurement, richness of high-frequency sensor data, and opportunity for passive collection of health-related data. Thus, DHTTs promise to provide patient phenotyping at an order of granularity several times greater than is possible with traditional clinical research tools. While the conceptual development of novel DHTTs is keeping pace with technological and analytical advancements, an as yet unaddressed gap is how to develop robust and meaningful outcome measures based on sensor data. Here, we describe two roadmaps which were developed to generate outcome measures based on DHTT data: one using a data-centric approach and the second a patient-centric approach. The data-centric approach to develop digital outcome measures summarizes those sensor features maximally sensitive to the concept of interest, exemplified with the quantification of disease progression. The patient-centric approach summarizes those sensor features that are optimally relevant to patients’ functioning in everyday life. Both roadmaps are exemplified for use in tracking disease progression in observational and clinical interventional studies, and with a DHTT designed to evaluate motor symptom severity and symptom experience in Parkinson’s disease. Use cases other than disease progression (e.g., case-finding) are considered summarily. DHTT research requires methods to summarize sensor data into meaningful outcome measures. It is hoped that the concepts outlined here will encourage a scientific discourse and eventual consensus on the creation of novel digital outcome measures for both basic clinical research and clinical drug development.
- 23 July 2020
- Published by Springer Nature in npj Digital Medicine
- Vol. 3 (1) , 1-8
Open AccessOutcome measures based on digital health technology sensor data: data- and patient-centric approaches
Digital health technology tools (DHTT) are technologies such as apps, smartphones, and wearables that remotely acquire health-related information from individuals. They have the potential advantages of objectivity and sensitivity of measurement, richness of high-frequency sensor data, and opportunity for passive collection of health-related data. Thus, DHTTs promise to provide patient phenotyping at an order of granularity several times greater than is possible with traditional clinical research tools. While the conceptual development of novel DHTTs is keeping pace with technological and analytical advancements, an as yet unaddressed gap is how to develop robust and meaningful outcome measures based on sensor data. Here, we describe two roadmaps which were developed to generate outcome measures based on DHTT data: one using a data-centric approach and the second a patient-centric approach. The data-centric approach to develop digital outcome measures summarizes those sensor features maximally sensitive to the concept of interest, exemplified with the quantification of disease progression. The patient-centric approach summarizes those sensor features that are optimally relevant to patients’ functioning in everyday life. Both roadmaps are exemplified for use in tracking disease progression in observational and clinical interventional studies, and with a DHTT designed to evaluate motor symptom severity and symptom experience in Parkinson’s disease. Use cases other than disease progression (e.g., case-finding) are considered summarily. DHTT research requires methods to summarize sensor data into meaningful outcome measures. It is hoped that the concepts outlined here will encourage a scientific discourse and eventual consensus on the creation of novel digital outcome measures for both basic clinical research and clinical drug development.
- 20 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 67 (12) , 3491-3500
Building a Machine-Learning Framework to Remotely Assess Parkinson's Disease Using Smartphones
Parkinson's disease (PD) is a neurodegenerative disorder that affects multiple neurological systems. Traditional PD assessment is conducted by a physician during infrequent clinic visits. Using smartphones, remote patient monitoring has the potential to obtain objective behavioral data semi-continuously, track disease fluctuations, and avoid rater dependency. Smartphones collect sensor data during various active tests and passive monitoring, including balance (postural instability), dexterity (skill in performing tasks using hands), gait (the pattern of walking), tremor (involuntary muscle contraction and relaxation), and voice. Some of the features extracted from smartphone data are potentially associated with specific PD symptoms identified by physicians. To leverage large-scale cross-modality smartphone features, we propose a machine-learning framework for performing automated disease assessment. The framework consists of a two-step feature selection procedure and a generic model based on the elastic-net regularization. Using this framework, we map the PD-specific architecture of behaviors using data obtained from both PD participants and healthy controls (HCs). Utilizing these atlases of features, the framework shows promises to (a) discriminate PD participants from HCs, and (b) estimate the disease severity of individuals with PD. Data analysis results from 437 behavioral features obtained from 72 subjects (37 PD and 35 HC) sampled from 17 separate days during a period of up to six months suggest that this framework is potentially useful for the analysis of remotely collected smartphone sensor data in individuals with PD.
- 20 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 67 (12) , 3491-3500
Building a Machine-Learning Framework to Remotely Assess Parkinson's Disease Using Smartphones
Parkinson's disease (PD) is a neurodegenerative disorder that affects multiple neurological systems. Traditional PD assessment is conducted by a physician during infrequent clinic visits. Using smartphones, remote patient monitoring has the potential to obtain objective behavioral data semi-continuously, track disease fluctuations, and avoid rater dependency. Smartphones collect sensor data during various active tests and passive monitoring, including balance (postural instability), dexterity (skill in performing tasks using hands), gait (the pattern of walking), tremor (involuntary muscle contraction and relaxation), and voice. Some of the features extracted from smartphone data are potentially associated with specific PD symptoms identified by physicians. To leverage large-scale cross-modality smartphone features, we propose a machine-learning framework for performing automated disease assessment. The framework consists of a two-step feature selection procedure and a generic model based on the elastic-net regularization. Using this framework, we map the PD-specific architecture of behaviors using data obtained from both PD participants and healthy controls (HCs). Utilizing these atlases of features, the framework shows promises to (a) discriminate PD participants from HCs, and (b) estimate the disease severity of individuals with PD. Data analysis results from 437 behavioral features obtained from 72 subjects (37 PD and 35 HC) sampled from 17 separate days during a period of up to six months suggest that this framework is potentially useful for the analysis of remotely collected smartphone sensor data in individuals with PD.
- Open Access
Gallery Game: Smartphone-based Assessment of Long-Term Memory in Adults at Risk of Alzheimer’s Disease
Gallery Game, deployed within the Mezurio smartphone app, targets the processes of episodic memory first vulnerable to neurofibrillary tau-related degeneration in Alzheimer’s Disease, prioritising both perirhinal and entorhinal cortex/hippocampal demands. Thirty-five healthy adults (aged 40-59 years), biased towards those at elevated familial risk of dementia, completed daily Gallery Game tasks for a month. Assessments consisted of cross-modal paired-associate learning, with subsequent tests of recognition and recall following delays ranging from one to 13 days. There was a non-linear decline in memory retention with increasing delays between learning and test, with significant forgetting first reported following delays of three and five days for paired-associate recall and recognition respectively, supporting the need for ecologically valid measures of longer-term memory. Gallery Game outcomes correlated as expected with established neuropsychological memory assessments, confirming the validity of this digital assessment of episodic memory. In addition, there was preliminary support for utilising the perirhinal-dependent pattern of semantic errors during object recognition as a marker of early impairment, justifying ongoing validation against traditional biomarkers of Alzheimer’s disease.
Open AccessGallery Game: Smartphone-based Assessment of Long-Term Memory in Adults at Risk of Alzheimer’s Disease
Gallery Game, deployed within the Mezurio smartphone app, targets the processes of episodic memory first vulnerable to neurofibrillary tau-related degeneration in Alzheimer’s Disease, prioritising both perirhinal and entorhinal cortex/hippocampal demands. Thirty-five healthy adults (aged 40-59 years), biased towards those at elevated familial risk of dementia, completed daily Gallery Game tasks for a month. Assessments consisted of cross-modal paired-associate learning, with subsequent tests of recognition and recall following delays ranging from one to 13 days. There was a non-linear decline in memory retention with increasing delays between learning and test, with significant forgetting first reported following delays of three and five days for paired-associate recall and recognition respectively, supporting the need for ecologically valid measures of longer-term memory. Gallery Game outcomes correlated as expected with established neuropsychological memory assessments, confirming the validity of this digital assessment of episodic memory. In addition, there was preliminary support for utilising the perirhinal-dependent pattern of semantic errors during object recognition as a marker of early impairment, justifying ongoing validation against traditional biomarkers of Alzheimer’s disease.
- 24 August 2018
- Published by Springer Nature
- p. 12-19
Large-Scale Continuous Mobility Monitoring of Parkinson’s Disease Patients Using Smartphones
- 24 August 2018
- Published by Springer Nature
- p. 12-19
Large-Scale Continuous Mobility Monitoring of Parkinson’s Disease Patients Using Smartphones