XGBoost-based model for predicting PICC occlusion risk in cancer patients: Insights from SHAP analysis
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Peripherally inserted central catheters (PICC) are commonly used in cancer patients, but occlusion is a frequent complication. Early prediction of the occlusion risk can guide timely interventions and improve patient outcomes. This study develops and validates a machine-learning model to predict the PICC occlusion risk in cancer patients using clinical data from electronic medical records. In this retrospective, single-center study, data from cancer patients with PICC lines were analyzed. Three machine learning algorithms—logistic regression, random forest, and XGBoost—were used to predict the occlusion risk. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC). Key risk factors, including patient demographics, clinical conditions, and catheter maintenance practices, were incorporated. XGBoost outperformed the other models, achieving AUC values of 0.909 in the training cohort and 0.759 in the validation cohort. Key predictors of PICC occlusion included catheter duration, electrolyte disturbances, the chemotherapy drug type, and the insertion length. SHAP analysis provided transparent model interpretation. The XGBoost model effectively predicts the PICC occlusion risk and identifies key predictors. While limited by its retrospective design, the study suggests the potential for clinical integration to improve patient outcomes. Further prospective studies are needed. Developed a machine learning model to predict PICC occlusion risk in cancer patients. XGBoost model demonstrated high predictive accuracy (AUC 0.909 in training, 0.759 in validation). Identified key predictors of PICC occlusion: catheter duration, chemotherapy regimen, electrolyte disturbances. SHAP analysis provided transparent insights into feature importance, aiding clinical decision-making. Statistical validation confirmed the significance of key risk factors, supporting personalized patient 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.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| 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 it