A recessive ataxia diagnosis algorithm for the next generation sequencing era
Bibliographic record
Abstract
OBJECTIVE: Differential diagnosis of autosomal recessive cerebellar ataxias can be challenging. A ranking algorithm named RADIAL that predicts the molecular diagnosis based on the clinical phenotype of a patient has been developed to guide genetic testing and to align genetic findings with the clinical context. METHODS: An algorithm that follows clinical practice, including patient history, clinical, magnetic resonance imaging, electromyography, and biomarker features, was developed following a review of the literature on 67 autosomal recessive cerebellar ataxias and personal clinical experience. Frequency and specificity of each feature were defined for each autosomal recessive cerebellar ataxia, and corresponding prediction scores were assigned. Clinical and paraclinical features of patients are entered into the algorithm, and a patient's total score for each autosomal recessive cerebellar ataxia is calculated, producing a ranking of possible diagnoses. Sensitivity and specificity of the algorithm were assessed by blinded analysis of a multinational cohort of 834 patients with molecularly confirmed autosomal recessive cerebellar ataxia. The performance of the algorithm was assessed versus a blinded panel of autosomal recessive cerebellar ataxia experts. RESULTS: The correct diagnosis was ranked within the top 3 highest-scoring diagnoses at a sensitivity and specificity of >90% for 84% and 91% of the evaluated genes, respectively. Mean sensitivity and specificity of the top 3 highest-scoring diagnoses were 92% and 95%, respectively. The algorithm outperformed the panel of ataxia experts (p = 0.001). INTERPRETATION: Our algorithm is highly sensitive and specific, accurately predicting the underlying molecular diagnoses of autosomal recessive cerebellar ataxias, thereby guiding targeted sequencing or facilitating interpretation of next-generation sequencing data. Ann Neurol 2017;82:892-899.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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 source (direct Gemma or distilled Codex), 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".