Predict lung function decline
Imagine one day, your breathing became consistently labored and shallow. Months later you were finally diagnosed with pulmonary fibrosis, a disorder with no known cause and no known cure, created by scarring of the lungs. If that happened to you, you would want to know your prognosis. That’s where a troubling disease becomes frightening for the patient: outcomes can range from long-term stability to rapid deterioration, but doctors aren’t easily able to tell where an individual may fall on that spectrum. Your help, and data science, may be able to aid in this prediction, which would dramatically help both patients and clinicians.
Current methods make fibrotic lung diseases difficult to treat, even with access to a chest CT scan. In addition, the wide range of varied prognoses create issues organizing clinical trials. Finally, patients suffer extreme anxiety—in addition to fibrosis-related symptoms—from the disease’s opaque path of progression.
In this competition, you’ll predict a patient’s severity of decline in lung function based on a CT scan of their lungs. You’ll determine lung function based on output from a spirometer, which measures the volume of air inhaled and exhaled. The challenge is to use machine learning techniques to make a prediction with the image, metadata, and baseline FVC as input.
The aim of this competition is to predict a patient’s severity of decline in lung function based on a CT scan of their lungs. Lung function is assessed based on output from a spirometer, which measures the forced vital capacity (FVC), i.e. the volume of air exhaled.
In the dataset, you are provided with a baseline chest CT scan and associated clinical information for a set of patients. A patient has an image acquired at time Week = 0 and has numerous follow up visits over the course of approximately 1-2 years, at which time their FVC is measured.
In the training set, you are provided with an anonymized, baseline CT scan and the entire history of FVC measurements. In the test set, you are provided with a baseline CT scan and only the initial FVC measurement. You are asked to predict the final three FVC measurements for each patient, as well as a confidence value in your prediction.
This competition is evaluated on a modified version of the Laplace Log Likelihood. In medical applications, it is useful to evaluate a model's confidence in its decisions. Accordingly, the metric is designed to reflect both the accuracy and certainty of each prediction.
For each true FVC measurement, you will predict both an FVC and a confidence measure (standard deviation σ σ ). The metric is computed as:
σclipped=max(σ,70),
Δ=min(|FVCtrue−FVCpredicted|,1000),
metric=−2‾√Δσclipped−ln(2‾√σclipped).
The error is thresholded at 1000 ml to avoid large errors adversely penalizing results, while the confidence values are clipped at 70 ml to reflect the approximate measurement uncertainty in FVC. The final score is calculated by averaging the metric across all test set Patient_Weeks (three per patient). Note that metric values will be negative and higher is better.