MétaCan
Menu
← Back to cohort
Record W3110620563 · doi:10.1101/2020.11.29.20240028

Evaluation of the PREDIGT Score in Discriminating Parkinson Disease from Neurological Health

2020· preprint· en· W3110620563 on OpenAlexafffundabout
Juan Li, Tiago Mestre, Brit Mollenhauer, Mark Frasier, Julianna J. Tomlinson, Claudia Trenkwalder, Tim Ramsay, Douglas G. Manuel, Michael G. Schlossmacher

Bibliographic record

VenuemedRxiv · 2020
Typepreprint
Languageen
FieldMedicine
TopicParkinson's Disease Mechanisms and Treatments
Canadian institutionsOttawa HospitalUniversity of Ottawa
FundersParkinson CanadaOttawa Hospital FoundationDeutsche Parkinson VereinigungMichael J. Fox Foundation for Parkinson's Research
KeywordsParkinson's diseaseInternal medicineCohortMedicineDiseaseIncidence (geometry)Discriminative modelArea under the curveMachine learning

Abstract

fetched live from OpenAlex

Abstract Background We previously created the PREDIGT Score as an algorithm to predict the incidence of Parkinson disease. The model rests on a hypothesis-driven formula, [P R =(E+D+I)xGxT], that uses numerical values for five categories known to modulate Parkinson’s risk (P R ): environmental exposure (E); DNA variants (D); evidence of gene-environment interactions (I); gender (G); and time (T). Notably, the formula does not rely on motor examination results. Methods To evaluate the PREDIGT Score, we tested it in two established case-control cohorts: ‘De Novo Parkinson Study’ (DeNoPa) and ‘Parkinson’s Progression Marker Initiative’ (PPMI). Using baseline data from 589 patients and 309 controls enrolled in the DeNoPa and PPMI cohorts, we evaluated the PREDIGT Score’s discriminative performance in distinguishing Parkinson’s patients from healthy controls by area-under-the-curve (AUC) analyses. Findings When examining cohorts separately and using all available variables in each cohort to calculate the PREDIGT Score, AUCs were 0.83 (95% CI 0.77-0.89) for DeNoPa and 0.87 (95% CI 0.84-0.9) for PPMI, respectively, in distinguishing Parkinson disease patients from healthy individuals. When combining DeNoPa and PPMI data sets by using eleven variables that had been collected in both cohorts, the PREDIGT Score discriminated patients from controls with an AUC of 0.84 (95% CI 0.81-0.87). The mean score of Parkinson disease patients was significantly higher than that of control individuals at 108.48 (+52.08) and 47.33 (+34.1), respectively (p < 0.0001). Interpretation Our results demonstrate a robust performance of the original PREDIGT Score in distinguishing patients diagnosed with Parkinson disease from neurologically healthy subjects without reliance on motor examination data. In future efforts, the predictive performance of the algorithm will be studied in longitudinal cohorts of at-risk persons. Funding Parkinson Canada, Michael J. Fox Foundation, Department of Medicine (The Ottawa Hospital), Uttra & Subash Bhargava Family, Paracelsus-Elena-Klinik Kassel, Parkinson Fond Deutschland, and Deutsche Parkinson Vereinigung.

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)0.009
metaresearch head score (Gemma)0.022
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: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.009
Threshold uncertainty score0.049

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0090.022
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0040.001
Science and technology studies0.0000.001
Scholarly communication0.0020.001
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.115
GPT teacher head0.342
Teacher spread0.227 · 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
GenreEmpirical

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
Published2020
Admission routes3
Has abstractyes

Explore more

Same venuemedRxiv→Same topicParkinson's Disease Mechanisms and Treatments→French-language works237,207→