Development of Machine Learning Algorithms Incorporating Electronic Health Record Data, Patient-Reported Outcomes, or Both to Predict Mortality for Outpatients With Cancer.
Ravi B ParikhJill S HaslerYichen ZhangManqing LiuCorey ChiversWilliam J FerrellPeter E GabrielCaryn LermanJustin E BekelmanJinbo ChenPublished in: JCO clinical cancer informatics (2022)
Routinely collected PROs contain added prognostic information not captured by an EHR-based ML mortality risk algorithm. Augmenting an EHR-based algorithm with PROs resulted in a more accurate and clinically relevant model, which can facilitate earlier and targeted supportive care for patients with cancer.
Keyphrases
- electronic health record
- machine learning
- patient reported outcomes
- deep learning
- artificial intelligence
- clinical decision support
- papillary thyroid
- big data
- healthcare
- adverse drug
- palliative care
- squamous cell
- cardiovascular events
- cancer therapy
- risk factors
- high resolution
- health information
- pain management
- lymph node metastasis
- type diabetes
- mass spectrometry
- affordable care act
- chronic pain
- social media