Fight Chance AI

FightChanceAI is a platform that assists healthcare providers understand their patients’ medical history and recommend promising clinical trials.

Overview

In the medical field, clinical notes are an essential aspect of patient care and treatment. These notes contain critical information about a patient's medical history, symptoms, diagnoses, and treatment plans. However, the sheer volume of clinical notes can make it challenging for healthcare professionals to extract the necessary information efficiently. This is where the importance of summarization of complex clinical notes comes in.

Summarization of complex clinical notes is the process of condensing large amounts of clinical data into a concise and meaningful summary. This process can save healthcare professionals a significant amount of time and effort and can help them identify key information that is relevant to a patient's treatment.

Another crucial aspect of clinical research is finding matching patient trials. Patient trials are critical to advancing medical knowledge and improving patient outcomes. However, finding the right patient trial can be a daunting task, particularly with the vast amount of clinical data available.

To address this issue, advanced technologies such as natural language processing and machine learning algorithms can be utilized to automatically identify relevant patient trials based on patient data. This approach can save significant time and effort for healthcare professionals, allowing them to focus on providing the best possible care for their patients.

Overall, the summarization of complex clinical notes and finding matching patient trials are critical aspects of patient care and clinical research. The use of advanced technologies can help streamline these processes, saving time and effort and ultimately improving patient outcomes.

Project Impact

There are about 38k Clinical Trials each year in the US alone and a crucial challenge in these trials is recruiting patients. Over $2B is spent annually on recruiting patients and a recent study in 2019 estimated that 55% of terminated trials are due to inadequate patient recruitment. At the same time, there are 30m patients recorded having rare diseases and 4.5M patients per month looking for trials and only 0.2% of the healthcare providers actively refer patients to the trials. Our project is targeting to change this.

Data Sources

• MIMIC-III and BioNLP Summarization datasets
• Clinical Trials dataset

Final Product

Try it in action