Wearable Activity Tracking for Cancer Patients
This observational study aims to understand if data from wearable devices like Fitbit or Apple HealthKit can help predict when cancer patients might need emergency room visits or hospitalization. The study is for adults aged 18 and older who have been diagnosed with cancer (hematopoietic neoplasm, malignant solid neoplasm, or lymphatic system neoplasm) and are able to follow study procedures. Researchers will collect health data generated by your personal device to see if it can accurately forecast the risk of needing acute care before, during, and after radiation therapy. The main goal is to validate existing models that use step counts to predict these events. This study plans to enroll 260 participants, but its current status is unclear.
- Study design
- This is an observational study with 260 planned participants. You would be assigned to one of two groups, either receiving a Fitbit device or using your own Apple HealthKit-based device.
- What's involved
- You would wear a Fitbit device or your own Apple HealthKit-based device and share data with the study team. You would also undergo standard of care radiation therapy.
- Compensation
- Not stated in the trial record.
- Follow-up
- The primary endpoints for this study are measured for up to 3 years.
AI-generated from the public study record. Only the study team can confirm whether you're eligible — confirm details with them before making decisions.
Wearable Activity Tracking to Curb Hospitalizations
At a glance
Conditions
Where it's being run
1 sites across 1 statesStudy leadership
- Julian Hong, MD, MS · PRINCIPAL_INVESTIGATOR · University of California, San Francisco
Who to contact
Opens a ready-to-send draft in your own email app — review before sending.
Do you actually qualify for this trial?
Add a private profile and we'll compare every criterion below against your situation — and tell you which ones are met, uncertain, or excluding.
Inclusion
Exclusion
What this trial measures
- Area under the receiver operating characteristic curve (AUC-ROC) of the step count modelUp to 3 years
The AUC-ROC of the step count model will measure the performance of a classification model by plotting the rate of true positives against false positives, and the score ranges from 0 - 1. The higher the AUC, the better the model's performance at distinguishing between the positive and negative classes. The AUC-ROC will be reported including both estimates and confidence intervals. All models will be reported per up-to-date guidelines, such as Minimum Information about Clinical Artificial Intelligence Modeling (MI-CLAIM) and Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD). The performance metrics will only be calculated with respect to first acute care event.
- Calculation of a Brier ScoreUp to 3 years
The Brier Score is a strictly proper score function or strictly proper scoring rule that measures the accuracy of probabilistic predictions. A Brier Score can take on any value between 0 and 1, with 0 being the best score achievable and 1 being the worst score achievable. The lower the Brier Score, the more accurate the prediction(s). The score will be reported including both estimates and confidence intervals. All models will be reported per up-to-date guidelines, such as MI-CLAIM and TRIPOD. The performance metrics will only be calculated with respect to first acute care event.
- Calculation of Log-Loss ScoreUp to 3 years
Logarithmic loss indicates how close a prediction probability comes to the actual/corresponding true value. The Log-Loss Score can take on any value between 0 and 1. The more the predicted probability diverges from the actual value, the higher is the log-loss value. The log-loss value will be reported including both estimates and confidence intervals. All models will be reported per up-to-date guidelines, such as MI-CLAIM and TRIPOD. The performance metrics will only be calculated with respect to first acute care event.
- Area Under the Precision-Recall Curves (AUCPR)Up to 3 years
The area under the precision-recall curve (AUCPR) is a single number summary of the information in the precision-recall (PR) curve. It represents the tradeoff between precision and recall for different thresholds, where high AUCPR indicates both high recall and high precision. The AUCPR will be reported including both estimates and confidence intervals. All models will be reported per up-to-date guidelines, such as MI-CLAIM and TRIPOD. The performance metrics will only be calculated with respect to first acute care event.