MétaCan
Menu
← Back to cohort
Record W4412075616 · doi:10.2196/71955

Improving Prediction of Falls and Cognitive Impairment in Parkinson Disease: Protocol for a Decentralized Observational Study

2025· article· en· W4412075616 on OpenAlexvenueno aff
Peggy Auinger, Kathryn Murphy, Michelle Porto, Katrina Schmier, Renée Wilson, James C. Beck, Stephanie Benvengo, Kevin Biglan, E. Ray Dorsey, Alberto J. Espay, Eric A. Macklin, Mariana H.G. Monje, Dan Novak, David Oakes, Larsson Omberg, Michael A. Schwarzschild, Solveig K. Sieberts, Tanya Simuni, Caroline M. Tanner, Daniel Weintraub, Ruth B. Schneider

Bibliographic record

VenueJMIR Research Protocols · 2025
Typearticle
Languageen
FieldHealth Professions
TopicBalance, Gait, and Falls Prevention
Canadian institutionsnot available
FundersNational Institute of Neurological Disorders and Stroke
KeywordsPreprintObservational studyParkinson's diseaseCognitive impairmentProtocol (science)MedicineCognitionPsychologyDiseaseGerontologyPsychiatryComputer scienceAlternative medicineWorld Wide WebInternal medicine

Abstract

fetched live from OpenAlex

BACKGROUND: Falls and cognitive impairment are major sources of disability in Parkinson disease (PD). The ability to accurately identify individuals with PD at high risk for falls and cognitive impairment would provide an opportunity for intervention and potentially improve long-term outcomes. In a previous study, Assessing Telehealth Outcomes in Multiyear Extensions of Parkinson Disease Trials (AT-HOME PD), we remotely characterized participants with early PD who had participated in 1 of 2 PD clinical trials over 2 years of follow-up. These participants with advancing disease provide a unique opportunity to examine whether the capture of objective in-home measures via digital tools and bothersome symptoms via direct participant report improves the prediction of disease milestones. OBJECTIVE: Assessing Telehealth Outcomes in Multiyear Extensions of Parkinson Disease Trials-2 (AT-HOME PD2) aims to examine whether digital tools and remote participant reporting can improve the prediction of falls and cognitive impairment, quantify changes in physical activity over time, and explore the relationship between physical activity and clinical progression over time. METHODS: This is a decentralized observational study of up to 200 individuals with PD, with clinical and digital phenotyping for up to 3 years of follow-up. Participants are those who took part in the STEADY-PD III (NCT02168842), Study of Urate Elevation in Parkinson's Disease, Phase 3 (SURE-PD3; NCT02642393), AT-HOME PD (NCT03538262), or PD GENEration (NCT04057794) studies. All participants complete 2 video visits per year, wear 2 wrist-worn sensors (Fitbit Charge 5 and ActiGraph CentrePoint Insight Watch) for 1 week each month, complete smartphone-based motor tasks (using the mPower 2.0 app) for 10 days each quarter, and complete online surveys (within the companion Fox Insight study) each quarter. Falls are assessed via a weekly automated telephone call. A cognitive diagnosis is determined by a consensus committee that considers scores on a global cognitive measure, detailed neuropsychological tests, a cognitive-related disability measure, and clinical information. Prediction models will be constructed, and prediction accuracy will be compared across the models. RESULTS: Recruitment for the study was initiated in September 2023. Enrollment is ongoing, with 142 participants enrolled as of January 2025. Within the cohort, the average age is 69.2 (SD 8.7) years; 85 (59.9%) participants are male, 137 (96.5%) are White, and 2 (1.4%) are Hispanic or Latino; and the average disease duration is 8.9 (SD 1.3) years. CONCLUSIONS: AT-HOME PD2 is remotely clinically and digitally phenotyping participants with midstage PD to predict falls and cognitive impairment and to provide insights into long-term progression. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/71955.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.038
metaresearch head score (Gemma)0.031
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Protocol · Consensus signal: Protocol
Teacher disagreement score0.042
Threshold uncertainty score0.199

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0380.031
Meta-epidemiology (narrow)0.0040.003
Meta-epidemiology (broad)0.0060.005
Bibliometrics0.0020.003
Science and technology studies0.0050.003
Scholarly communication0.0030.002
Open science0.0030.003
Research integrity0.0050.006
Insufficient payload (model declined to judge)0.0420.010

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.311
GPT teacher head0.596
Teacher spread0.285 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreProtocol

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Research Protocols→Same topicBalance, Gait, and Falls Prevention→French-language works237,207→