Big Data in Oncology Nursing Research: State of the Science.
Carolyn S Harris, Rachel A Pozzar, Yvette Conley and 5 others
PMID 37085404WHAT IT FOUND
Oncology nursing big-data examples include electronic notes, patient reports and wearable data for tracking pain, distress and end-of-life needs.
They report feasibility and ethical limits, not proven care improvements.
Key findings
01Software that reads clinician notes detected social distress, spiritual pain, severe pain, shortness of breath and nausea with high accuracy, but severe insomnia and anxiety with moderate accuracy.
02Home-based wearable monitoring has been feasible in some oncology settings, but adherence can be low; one smartwatch study reported 31% adherence.
03For nursing, missing patient-reported outcome data in EHRs limits measurement of nursing interventions such as patient education, symptom evaluation and symptom management.
STILL TO COME
How it was doneWhat they foundWhat it means for RNs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
This is a narrative review, not an original clinical study, so it does not establish that any big-data method improves patient care. The examples include feasibility, adherence and model accuracy results, not tested patient-care interventions. Adherence to wearable monitoring was variable, and one smartwatch study reported only 31% adherence. Unstructured EHR data and patient-reported outcomes may be missing, inconsistently recorded or not displayed well in clinical systems. Underrepresentation in datasets can make models less reliable for minoritized patients.
The easy way to misread this
Do not read the note-reading accuracy, home-monitoring adherence or wearable examples as proof that big-data tools improve cancer patient care. The review reports feasibility and limitations, not tested clinical outcomes.