Software

dynamicLM (penLM)

dynamicLM is an R package for dynamic risk prediction in survival data. It enables continuous updates to a patient's risk profile based on changing conditions and treatments. The package has advanced features for data preparation, predictive modeling, and model evaluation. It can handle high-dimensional data analysis with penalization. The methodology showed high predictive accuracy in lung cancer mortality studies by integrating diverse risk factors from multiple data sources.

SPLC-RAT

Second Primary Lung Cancer Risk Assessment Tool (SPLC-RAT) is a web-based risk prediction tool for second primary lung cancer (SPLC) among patients with initial primary lung cancer (IPLC) who ever smoked before lung cancer diagnosis. By simply entering patients’ demographic data, tumor characteristics, and smoking history, the estimates for 5-year and 10-year risks of developing SPLC after initial diagnosis of lung cancer can be provided.

RAMBO

Brain metastasis is common in lung cancer, and treatment of brain metastasis can lead to significant morbidity. Although early detection of brain metastasis may improve outcomes, there is no current clinical consensus on how to identify high-risk patients for brain magnetic resonance imaging (MRI) surveillance. Our model, Risk Assessment for Metastasis to Brain Outcome (RAMBO), utilizes clinical and tumor genomic characteristics at the time of diagnosis to predict risk of future brain metastasis development.

DistinCT

DistinCT is an R package designed for automatic abstraction of CT imaging indications using natural language processing and structured electronic health records. It enables efficient prediction of whether CT scans are performed for surveillance or for other clinical reasons (e.g., symptom evaluation) without the need for manual review of radiology reports. The package integrates key-phrase extraction, parts-of-speech tagging, and structured clinical features to build an interpretable statistical model. DistinCT model was developed and validated in long-term lung cancer survivors, and it demonstrated high discrimination for CT indication prediction, facilitating robust real-world analysis of imaging surveillance patterns and associated clinical outcomes.