1. Samson, Kurt

Article Content

SAN DIEGO-A novel smartphone app that uses artificial intelligence (AI)-based algorithms significantly reduced pain and pain-related hospital admissions in a group of patients with various metastatic, solid-organ cancers, according to results from a randomized clinical trial reported at the 2018 Palliative and Supportive Care in Oncology Symposium sponsored by ASCO (Abstract 76).

palliative care; can... - Click to enlarge in new windowpalliative care; cancer. palliative care; cancer

The ePAL is a smartphone app that regularly monitors pain and uses AI to differentiate urgent from non-urgent issues in real time. It also collects and assesses patient-reported pain severity three times each day while providing daily tips on pain-reduction strategies. It is one of the first apps to utilize both patient-reported outcomes and AI clinical algorithms, according to the researchers.


The app was developed and tested in 56 pain patients and a matched group of 56 control patients who received regular pain management care by investigators at the Massachusetts General Hospital (MGH) Cancer Center, the hospital's Division of Palliative Care, and Partners HealthCare Pivot Labs, which is a new center of excellence that focuses on human-centered preventive care and chronic pain management. The new initiative was announced in mid-October.


Lead investigator Mihir M. Kamdar, MD, Associate Director of the MGH Division of Palliative Care, noted there is a critical shortage of palliative care providers to handle the number of cancer cases in the U.S.


"This will only worsen in the future as our population ages," he said. "This is one of the reasons why technology solutions to help manage palliative care challenges, such as cancer pain, are so important."


Kamdar, an interventional pain physician at the hospital, said users showed a 20 percent reduction in pain over an 8-week test period compared to a matched set of subjects who did not have access to the ePAL app. They also had almost 70 percent fewer hospital admissions because of pain.


In addition, there were far fewer pain-related inpatient hospital admissions for ePAL users compared to patients not using the app (4 vs. 20). Per patient, this resulted in a 40 percent reduction in admissions.


"We could not be more excited about the results. This study was started about 4 years ago, and this is one of the first products that Pivot Labs is going to implement and scale clinically," Kamal Jethwani, MD, Director of Pivot Labs told Oncology Times. "Because ePAL falls within the area of augmented intelligence and will not require any prescriptions or clinical decisions, it will not require FDA approval. It is more of a triage tool, and as such exempt from FDA approval."



Patients seen for pain at the MGH Palliative Care Clinic were recruited for the trial, half of whom received standard care while the other 56 individuals used the ePAL app in addition to receiving usual care.


The ePAL app assessed pain three times per week, and each patient completed questionnaires about their pain, their attitudes towards cancer treatment, and general anxiety at the outset and again at 1 and 2 months. The investigators then examined changes in outcome measures over the study period, controlling for baseline and periodic differences, as well as depression scores, age, and gender.


Patients using ePAL received alerts on their smartphones with daily pain management tips and were prompted to submit their pain levels 3 days a week. The AI in ePAL was able to distinguish urgent from non-urgent pain and provide appropriate patient-facing education in real time. If cancer pain was severe or worsening, the app connected patients to their clinicians for care.


All of the enrolled patients had similar pain scores at the study's outset. Pain was reported on a scale of 0-10, where 10 is the worst pain imaginable, and the research team considered a 1-point reduction significant. The average pain level of about 4 remained unchanged throughout the study for people receiving usual care, but for patients using the app pain levels decreased by 20 percent to 2.99 at the end of 8 weeks.


If the pain level was severe, the app alerted a nurse who responded within an hour. If the pain was moderate, the app asked the patient about their pain and then electronically gave the patient tailored educational feedback, such as information on how to better manage bothersome medication side effects.


Questionnaires were given to all participants at the start, midpoint, and end of the 8-week trial to assess attitudes about each patient's overall treatment and their general anxiety.


Using the ePAL app appeared to increase some patients' anxiety; however, Kamdar noted that simply asking about pain may increase anxiety for some individuals. And not all patients experienced an increase in anxiety. Those who reported pain more than twice a week while using the ePAL app more than twice each week did not report any increase, either at the beginning, during, or end of the study.


With regards to the cost of the app for patients and insurers, Kamdar said that he thinks there could be various strategies to fund future iterations of the app that would ideally minimize any direct costs to patients.


"That would be our mission," Kamdar told Oncology Times. "For example, given the reduction in admissions, our hope is that health care institutions and insurance payers will be interested in ePAL from a cost-saving, risk-based standpoint.


"The national landscape is shifting, and Medicare is covering costs of apps the have continuous glucose monitoring features. Our hope is that this broadens to other illnesses such as oncology where apps like ePAL have now demonstrated significant clinical trial benefits," he added.



"The vast majority of people with cancer experience pain at some point, and we need better tools to track and report it," commented Joshua Adam Jones, MD, Assistant Professor of Clinical Radiation Oncology at the University of Pennsylvania's Perelman Center for Advanced Medicine in Philadelphia, who was not part of the study team. "My hope is that these findings will pave the way for more widespread use of apps among patients who are experiencing pain, so that they can get the support they need."


Joseph Rotella, MD, Chief Medical Officer at the American Academy of Hospice and Palliative Medicine, also commented on the findings.


"Good things happen when patients are empowered to take an active role in their own care," he told Oncology Times. "I think we'll see a lot more innovation in devices like this that can connect patients and clinicians in real time to address problems before they become a crisis. Applications like this may work on a number of levels, by engaging patients in their own care, providing them with helpful feedback and coaching, and alerting their health care teams to emerging problems."


Kurt Samson is a contributing writer.