Penn Medicine uses AI chatbot ‘Penny’ to improve cancer care

Over the past 25 years, the field of oncology has seen a dramatic change in cancer care delivery with the development of new therapeutics, the desire to move care from inpatient and clinic settings to the home, and the widespread implementation of electronic health records.

Problem

One area of ​​innovation has been the development of oral anti-cancer drugs, including cytotoxic chemotherapy, that patients can administer at home. It is estimated that approximately 25% of new anti-cancer agents in development are intended for oral administration. NCCN Task Force Report: Oral Chemotherapy.

Using these drugs allows patients to become more autonomous in their care and enables them to spend more time at home, said Dr. Parul Agarwal, assistant professor of clinical medicine at the University of Pennsylvania Health System, who Are on the “penny” of the organization. “The team is taking the lead in its role, particularly in gastrointestinal cancer.

“However, there are several issues to consider when administering oral chemotherapy at home,” she said. “Drug schedules can be complex, and there are concerns for compromised efficacy if patients take less than the prescribed dose, and increased risk of potentially life-threatening toxicity if more than the prescribed dose is administered.

“Recognizing these challenges, several mitigation strategies have been evaluated, including intensive, provider- and pharmacist-driven outpatient surveillance programs,” she continued. “In addition, measuring drug adherence and appropriately identifying and managing toxicities for patients on oral chemotherapy is challenging.”

Capecitabine is a particularly complex oral chemotherapy regimen that serves as the treatment backbone for many gastrointestinal malignancies. It is manufactured in two tablet sizes and is prescribed twice daily, dosed by body surface area, and the treatment regimen is cyclical, with treatment days on and off.

“Our Penny pilot using an augmented intelligence chatbot is an initiative to improve medication adherence and manage toxicity related to oral chemotherapy agents with the primary goal of improving patient outcomes and the secondary goal of improving healthcare utilization metrics. New strategy.”

Dr. Parul Agarwal, University of Pennsylvania Health System

“In addition, capecitabine is often administered concurrently with other intravenous chemotherapy, other oral chemotherapy regimens, or with radiation which can lead to further complications with administration,” Agarwal explained. “Typically, monitoring these agents to ensure safe management is provider- and resource-intensive, and the literature documents frequent errors and resulting avoidable complications.

“Our Penny pilot using an augmented intelligence chatbot aims to improve medication adherence and manage toxicity related to oral chemotherapy agents with the primary goal of improving patient outcomes and the secondary goal of improving healthcare utilization metrics,” he added. A new strategy to do.”

Proposal

To improve medication adherence and monitor and manage toxicities, with the ultimate goal of providing high-quality patient care, the algorithm-driven, augmented intelligence chatbot Penny was proposed.

Penny uses text-based, bi-directional, conversational interactions to guide patients through potentially complex regimens and minimize potential mistakes they may make through their courses of chemotherapy.

meet the challenge

Patients with gastrointestinal cancer on the oral chemotherapy capecitabine alone, or capecitabine in combination with other anti-cancer drugs or radiation, were able to participate. The Penny chatbot was bidirectional and messages could be initiated by the chatbot or the patient.

To address issues related to medication adherence and dosage, the chatbot sent twice-daily medication reminders to patients about the dose of capecitabine and when to take it. In the first phase of the pilot, participants received a message to respond “TAKEN” after each dose of capecitabine. This was later modified to a weekly survey to assess medication adherence.

To address the toxicities associated with oral anti-cancer agents, the chatbot also launched a weekly survey to solicit patient-reported symptoms. These traits were tested using a combination of algorithmic surveys and natural language processing, a form of AI.

Participants can send a message to the chatbot at any time during the entire process to report a symptom. All interactions between participants and the chatbot were monitored in real time by the study team.

Result

“The primary outcome of this study was to evaluate the feasibility of using augmented intelligence chatbots from a patient safety perspective,” Agarwal explained. “Of approximately 4,000 drug-related text messages exchanged, approximately 93% were accurately interpreted by Penny.

“A medication adherence rate of approximately 70% was measured among participants who responded ‘Taken,’ although the actual medication adherence rate was likely much higher,” she continued. “Over 500 symptom-related text messages were exchanged and approximately 98% were correctly interpreted by Penny.”

Through an iterative process, patient engagement in symptom assessment increased from 25% to nearly 70%, and most misinterpreted messages were acted upon by the research team in real time, he said.

More than 50% of participants completed a qualitative exit interview. this interview She added that Penny provided an additional layer of support, demonstrating a greater level of patient engagement with clear feedback to increase their confidence in taking medication and interacting with their care team.

advice for others

“The manner in which this intervention was implemented resulted in several improvements to Penny’s natural language processing task and resulted in a high level of patient engagement as the pilot progresses, which is critical to healthcare innovation in this area.” is,” said Aggarwal.

“This process required a high level of involvement from all parties involved – the healthcare team, the research team and the MEMORA team, with whom we partnered for a technology platform,” she continued. “Penny identified care delivery discrepancies with the schedule, dose, and monitoring of capecitabine among gastrointestinal cancer providers, leading to initiatives to reduce unnecessary variations in care.”

A patient journey dashboard was created to clearly outline schedule and dosage with the aim of facilitating high-quality care delivery.

“Going forward, this dashboard will be integrated into the EHR to become a standard tool for clinical teams to monitor their patients and adjust dosages as needed.” Aggarwal.

Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him at: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.