Development and Validation of Automated <scp>Magnetic Resonance</scp> Parkinsonism Index 2.0 to Distinguish <scp>Progressive Supranuclear Palsy‐Parkinsonism</scp> From <scp>Parkinson's Disease</scp>
Bibliographic record
Abstract
BACKGROUND: Differentiating progressive supranuclear palsy-parkinsonism (PSP-P) from Parkinson's disease (PD) is clinically challenging. OBJECTIVE: This study aimed to develop an automated Magnetic Resonance Parkinsonism Index 2.0 (MRPI 2.0) algorithm to distinguish PSP-P from PD and to validate its diagnostic performance in two large independent cohorts. METHODS: We enrolled 676 participants: a training cohort (n = 346; 43 PSP-P, 194 PD, and 109 control subjects) from our center and an independent testing cohort (n = 330; 62 PSP-P, 171 PD, and 97 control subjects) from an international research group. We developed a new in-house algorithm for MRPI 2.0 calculation and assessed its performance in distinguishing PSP-P from PD and control subjects in both cohorts using receiver operating characteristic curves. RESULTS: The automated MRPI 2.0 showed excellent performance in differentiating patients with PSP-P from patients with PD and control subjects both in the training cohort (area under the receiver operating characteristic curve [AUC] = 0.93 [95% confidence interval, 0.89-0.98] and AUC = 0.97 [0.93-1.00], respectively) and in the international testing cohort (PSP-P versus PD, AUC = 0.92 [0.87-0.97]; PSP-P versus controls, AUC = 0.94 [0.90-0.98]), suggesting the generalizability of the results. The automated MRPI 2.0 also accurately distinguished between PSP-P and PD in the early stage of the diseases (AUC = 0.91 [0.84-0.97]). A strong correlation (r = 0.91, P < 0.001) was found between automated and manual MRPI 2.0 values. CONCLUSIONS: Our study provides an automated, validated, and generalizable magnetic resonance biomarker to distinguish PSP-P from PD. The use of the automated MRPI 2.0 algorithm rather than manual measurements could be important to standardize measures in patients with PSP-P across centers, with a positive impact on multicenter studies and clinical trials involving patients from different geographic regions. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".