Symptom alert by type and severity among cancer patients using electronic patient reported outcomes for remote symptom monitoring.
Bibliographic record
Abstract
340 Background: Remote symptom monitoring (RSM) by electronic patient-reported outcomes (ePRO) data can elicit actionable symptoms from patients with cancer. However, patients with different cancer diagnoses are likely to have differing symptom profiles and variability in symptom alerts. To understand potential workflow needs, this analysis was conducted to determine which types of symptoms and severity of alerts can be expected based on cancer type. Methods: Cancer patients initiating chemotherapy, immunotherapy, or targeted therapy at 2 academic cancer centers in Alabama, UAB O’Neal Comprehensive Cancer Center and USA Health Mitchell Cancer Institute (MCI), were enrolled in ePRO-based RSM. Site rollouts were differential: UAB enrolled by disease group starting May 2021, MCI by provider starting July 2021. Patients received weekly symptom surveys of selected PRO-CTCAE questions through the Carevive ePRO mobile platform (PROmpt), triggering alerts to clinical teams if reported symptoms were determined to be moderate or severe. Demographics, cancer diagnosis, and ePRO data were extracted from electronic health records and Carevive. Descriptive statistics of categorical variables were calculated by frequencies and percentages; Cramer’s V and Cohen’s d were used for associations and effect size. Results: UAB enrolled 598 patients and MCI enrolled 274 patients by April 2023, consistent with the patient volume difference of the centers. 68% of enrollees were White; MCI saw a moderately higher % of Black patients (V: 0.21). 67% of enrolled patients were female. Median age was 61 years (Interquartile range: 51-69); UAB patients were slightly younger (d: 0.15). Among 872 enrolled patients, 9765 symptom alerts were generated. There was a small effect of cancer type on the overall type of symptoms and symptom severity reported (V: 0.11 and 0.09 respectively). Of the total number of symptom alerts, 28.0% of the alerts generated were for pain, followed by nausea/vomiting (14.9%), and constipation (11.7%). When broken down by cancer type, pain was the symptom most frequently reported for each type. The next most frequently reported symptoms differed but were as expected by cancer type: coughing/dyspnea by lung cancer patients (20.6%); urinary complaints in genitourinary cancers (14.1%); and nausea/vomiting in gastrointestinal cancers (18.0%). The frequency of moderate alerts was 62.1%, varying from 34.0% in sarcoma to 66.6% in gastrointestinal cancers. 31.1% of the alerts were severe; sarcoma had the most severe alerts (56.0%) and hematologic had the least (27.1%). Conclusions: Across patients with differing cancer types, pain and gastrointestinal issues were over half the reported symptoms. However, variability by cancer diagnosis in both symptom type and severity was observed, suggesting the remote symptom management workload for providers may vary by cancer type.
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 | 0.005 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".