Distilling Features of Importance into Clinically Meaningful Patterns
Bibliographic record
Abstract
This Excel file contains important features extracted from interviews with six clinical professionals—neurologists (n = 5) and a neuropsychologist (n = 1)—as they reviewed two documents (one Montreal Cognitive Assessment and one neuropsychological report) for nine patients with Parkinson's disease. In the Interviews tab, the important features are organized into columns titled according to sections on the Montreal Cognitive Assessment and in a neuropsychological report. The rows are organized by patient number and then by the clinical professional who reviewed the documents. “G1–G3” indicates which of the three groups the nine patients were assigned to, with a total of three patients per group. Columns AO–AQ provide a more condensed summary of the columns on the left, placing all the noted important features into one box from the observations on the Montreal Cognitive Assessment and the neuropsychological report. Column AR provides the known diagnosis of the nine patients reviewed. The Patterns tab contains the process of distilling—based on consensus—three clinically meaningful patterns composed of the features of importance from the interviews. This process was conducted by A. Journey Eubank, Dr. Fred W. Prior, and Dr. Abhilash Thatikala. The columns are organized according to the professional interviewed, the pattern from each interviewee, the patient number (1–9 excluding patient 6), and the pattern when all patterns from each interviewee were combined. The features are organized based on the column they came from in the Interviews tab, with the “Additional” header marking the start of important features from the neuropsychological report. The red text indicates features that interview coder Dr. Thatikala felt needed to be included, based on the interviews, but that neither A. Journey Eubank nor Dr. Prior included during their feature extraction processes. Column E, titled “Can these be combined more,” refers to the question of whether any patterns in column D could be further combined. Columns F–H contain each individual interview coder's answer to the question in column E. Based on multiple consensus meetings, column J, titled “Final consensus (A/B/C),” was created, resulting in the final patterns.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".