Skip to Content

Empathy and AI

January 20, 2026
Pictured from left: Sampath Rapuri, Bikram Bains, and Edgar Robitaille.

In his sophomore year, Bikram Bains was determined to find a meaningful volunteer opportunity at the Johns Hopkins Hospital. His search led him to Chaplain Elizabeth Tracey in the medical intensive care unit (MICU), who created the This is My Story (TIMS) Program during the COVID-19 pandemic in 2020. Tracey needed help using AI to streamline the program’s audio editing process, making it possible for interviews to be quickly condensed while still conveying unique patient attributes to the care team.

“Our level of involvement in the program came as a surprise. While in the process of reaching out to be a volunteer, Chaplain Tracey asked if I could help with this project because of my biomedical engineering background,” Bains said.

Bains recruited his roommates Sampath Rapuri and Edgar Robitaille, who are biomedical engineering and computer science double majors, to join him. The students have been working on this project for the past two years, culminating in a recent publication in JMIR Informatics.

The TIMS Program’s goal is to improve human-centered care in the hospital. Chaplain Tracey and her team do this by interviewing patients or their loved ones (if they are unable to verbally communicate) to get to know them on a personal level. These interviews seek to capture the patient’s identity by asking preferred name, sources of joy, essential care information for the medical team, and sources of peace. The interviews are edited into audio files that are integrated into the medical records so that the entire care team can listen to them at any time.

The students developed an AI model that can automate the editing process of interviews and recognize subtle details that help a clinician and patient connect on a human level, such as shared love of dogs. They were also challenged with training the model to remove disfluencies such as “um.”

A Catalyst Award from the Hopkins Office for Undergraduate Research funded the computational resources needed to turn their concepts into working solutions. “It is not hard to get an output from an AI model, but it is hard to get the right output especially when you have such sensitive information. You must have a lot of thoughtfulness, and we had high standards on what we wanted the output to be which took a lot of experimenting,” Bains said.

By uniting empathy and AI in their work, the students were able to get their model to edit the interviews to a comparable level of a medical student trained for one hour by the chaplains. The students are also finalizing a paper analyzing the application of their model throughout the hospital.

“Having that instant feedback with a direct pipeline for applying the knowledge we are learning in class is extremely gratifying,” said Rapuri.

The students credit several BME faculty for inspiring and preparing them to take on real biomedical engineering work while keeping up with the demands of being a student. “Everyone in the BME department has been great at helping us build the skillset and have the perseverance to learn how to approach problems through an engineering mindset,” said Rapuri.

Now seniors, all three students plan to attend medical school after graduation with an interest in specializing in critical care. They also hope to stay involved even from afar and pass on the project to other students to continue.

Read the Johns Hopkins University privacy statement here.

Accept