Validating a Patient-Reported Outcomes–Derived Algorithm for Classifying Symptom Complexity Levels Among Patients With Cancer
Bibliographic record
Abstract
BACKGROUND: The patient-reported outcomes (PROs) symptom complexity algorithm, derived from self-reported symptom scores using the Edmonton Symptom Assessment System and concerns indicated on the Canadian Problem Checklist, has not been validated extensively. METHODS: This is a retrospective chart review study using data from the Alberta Cancer Registry and electronic medical records from Alberta Health Services. The sample includes patients with cancer who visited a cancer facility in Alberta, Canada, from February 2016 through November 2017 (n=1,466). RESULTS: The effect size (d=1.2) indicates that the magnitude of difference in health status between the severe- and low-complexity groups is large. The symptom complexity algorithm effectively classified subgroups of patients with cancer with distinct health status. Using Karnofsky performance status, the algorithm shows a sensitivity of 70.3%, specificity of 84.1%, positive predictive value of 79.1%, negative predictive value of 76.7%, and accuracy of 77.7%. An area under the receiver operating characteristic of 0.824 was found for the complexity algorithm, which is generally regarded as good, This same finding was also regarded as superior to the alternative algorithm generated by 2-step cluster analysis (area under the curve, 0.721). CONCLUSIONS: The validity of the PRO-derived symptom complexity algorithm is established in this study. The algorithm demonstrated satisfactory accuracy against a clinician-driven complexity assessment and a strong correlation with the known group analysis. Furthermore, the algorithm showed a higher screening capacity compared with the algorithm generated from 2-step cluster analysis, reinforcing the importance of contextualization when classifying patients' symptoms, rather than purely relying on statistical outcomes. The algorithm carries importance in clinical settings, acting as a symptom complexity flag, helping healthcare teams identify which patients may need more timely, targeted, and individualized patient symptom management.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".