Automatically summarizing patients’ main problems from the daily care notes in the electronic health record can help mitigate information and cognitive overload for clinicians and provide augmented intelligence via computerized diagnostic decision support at the bedside.
The task of Problem List Summarization aims to generate a list of diagnoses and problems in a patient’s daily care plan using input from the provider’s progress notes during hospitalization. This task aims to promote NLP model development for downstream applications in diagnostic decision support systems that could improve efficiency and reduce diagnostic errors in hospitals. This task will contain 768 hospital daily progress notes and 2783 diagnoses in the training set, and a new set of 300 daily progress notes will be annotated by physicians as the test set. The annotation methods and annotation quality have previously been reported
here.
The goal of this shared task is to attract future research efforts in building NLP models for real-world decision support applications, where a system generating relevant and accurate diagnoses will assist the healthcare providers’ decision-making process and improve the quality of care for patients.
Our corpora is based on MIMIC-III and will be released through PhysioNet. Receiving the dataset requires a Data Use Agreement (DUA) with PhysioNet who owns and manages the MIMIC-III data and will ultimately release the dataset.
This process requires two steps: (1) completing Human Subject Research training through CITI; and (2) complete the PhysioNet credentialing after your CITI training is complete to get signed onto their DUA and receive the dataset. These steps can be completed in parallel to registering with our Task. Once you complete this form please go to the following website to complete Steps 1 and 2: https://physionet.org/about/citi-course/
We collaborate with PhysioNet to speed up the DUA approval process, and we will need your participation information for this process.
Please provide your email address (institutional email address is preferred). Please use the same email address for this form and PhysioNet. If you have a PhysioNet account and MIMIC DUA already, please indicate through the below option.
Once you submit this form and we obtain approval from PhysioNet, we will email you the link to the dataset.
IMPORTANT: Registration will close on March 1, 2023.
