Cancer Pain Control App Works -- Palliative Care for Everyone?

Kristin Jenkins

November 20, 2018

A smartphone application powered by artificial intelligence (AI) for monitoring and managing pain in patients with advanced cancer has the potential to provide access to palliative care for the entire aging population, say experts.

A randomized trial showed that the app, which uses clinical algorithms, was instrumental in decreasing pain by 20% and pain-related hospitalization by 69% in patients with metastatic, solid-organ cancer compared to control patients.

The study results were presented November 16 at the Palliative Care in Oncology Symposium (PCOS) 2018 in San Diego, California, by Mihir M. Kamdar, MD, associate director of the Division of Palliative Care at Massachusetts General Hospital (MGH) in Boston.

"Cancer can make life feel like it's out of control, and the underlying central theme that we saw was that most patients wanted to feel more empowered, educated, and in control of their pain," Kamdar told Medscape Medical News.

Pain affects 70% to 90% of patients with advanced malignancy and results in reduced quality of life and increased use of healthcare services, he noted. What's more, the current shortage of palliative care providers is expected to get worse as the population ages.

"Novel care delivery models are needed to optimize care for patients dealing with cancer-related pain in between clinic visits," Kamdar said in a statement from the American Society of Clinical Oncology, which organized the meeting.

"This is one of the reasons why technology solutions to help manage palliative care challenges, such as cancer pain, are so important," he added.

The smartphone app, which is called ePAL, was developed as part of a collaborative effort between Partners HealthCare Pivot Labs, the MGH Cancer Center, and the MGH Division of Palliative Care.

ePAL's functions include pain tracking, barrier identification, intervention, daily tailored AI educational coaching messages, an educational library with videos, and mind-body therapies. It can be used to request prescription refills, and it captures data for patients and clinicians.

"The vast majority of people with cancer experience pain at some point, and we need better tools to track and report it," said Joshua Adam Jones, MD, chair of the symposium's news planning 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."

Study Details

For the study, 112 patients from the MGH Palliative Care Clinic were randomly assigned to either a control group, which received usual care, or an intervention group, which received the smartphone app. There were 56 patients in each group.

The mean age of patients in the intervention group was 54.6 years; 31 were men, and 25 were women. In the control group, the mean age was 50.7 years; 30 were women, and 26 were men.

The majority of participants in both groups were white. Of these cancer patients, gastrointestinal cancer was most prevalent, followed by breast cancer and lung cancer. More than half of the participants in each group had earned a bachelor's degree or higher.

During an 8-week period, patients in the ePAL group received via their smartphones a daily coaching message aimed at improving their ability to manage pain. The messages were framed in easy-to-understand language and format. "We wanted to lower the threshold of interaction by having the app reach out to the patient, rather than vice versa," Kamdar pointed out.

Three days a week, the app prompted patients to enter their average pain score over the past 24 hours on a scale from 0 (no pain) to 10 (the worst pain imaginable). Using these data, the AI algorithm differentiated between nonurgent and urgent pain and determined whether anything more was needed to improve pain control.

If the AI decided that the patient was having severe, new, or escalating pain or that clinician input was needed to help manage a barrier to pain control, the app would send an alert directly to a secure phone carried by the on-call triage nurse at the palliative care clinic. The patient would get a return phone call within the hour.

The app would also send the nurse a secure email message containing information on the problem. This eliminated the need to have the information repeated at the time of the call-back. After office hours, the app would direct the patient to the on-call palliative care clinician.

"Patients often reported that when they are in pain, it is difficult to navigate a hospital's phone message system, and so we wanted to lower the threshold to get them help on short order," said Kamdar.

At baseline and at 4 and 8 weeks, the study participants completed the Brief Pain Inventory (BPI) interference scale, the Barriers Questionnaire II, which measures attitudes toward cancer treatment, and the seven-item Generalized Anxiety Disorder Questionnaire. The researchers then assessed how outcome measures changed over time. They controlled for baseline differences at enrollment with respect to depression score, age, and sex.

At the beginning of the study, the average pain levels for patients in both treatment groups was 4.0. For patients who received usual care, this did not change during the 8-week course of the study. Patients who used ePAL reported a 20% drop in pain severity at the end of 8 weeks, from 4.0 to 2.99.

Dealing with cancer pain can be incredibly frightening and stressful. Dr Mihir Kamdar

"Dealing with cancer pain can be incredibly frightening and stressful, and many patients wanted to have a feeling of being more connected to their clinicians," Kamdar explained. "Knowing that their care team would reach out to them if a moment of need arose put many patients' minds at ease."

On average, there were 0.57 app-triggered calls per patient during the course of the study. This amounted to one call for every two patients. Engagement with the app was well maintained by all of the patients in the intervention group.

"This suggested to us that the app was actually able to handle many of the patients' issues internally through its AI algorithm and education/empowerment features without increasing clinical burden," said Kamdar.

Impairment of pain control was often related to the effects of treatment or pain medication, such as constipation or nausea. In addition, many patients were confused about how to take their medication. This was the case regarding the use of long-acting scheduled pain medications and short-acting as-needed medications. Some patients said they were afraid to take prescribed opioids because of concern about becoming dependent, despite the fact that they had severe, cancer-related pain.

Among ePAL users, there were only four pain-related inpatient hospital admissions; among the control group, there were 20 such hospital admissions. There was a 40% reduction in total all-cause hospitalizations in ePAL users compared to control patients (15 vs 25 admissions; P = .048).

"It's significant that patients who used the app had significantly fewer hospital admissions without an associated increase in outpatient clinical burden," said Kamal Jethwani, MD, senior director of Pivot Labs at Partners Healthcare and a senior study investigator. "These findings suggest that integrating innovations like mobile technology and AI could have a real impact on patient well-being, resource utilization, and cost of care."

Similarly, BPI scores decreased significantly for patients using the app compared to control patients (P = .034), as did negative attitudes toward cancer pain treatment (P = .042).

However, anxiety scores increased for those using ePAL but decreased for those receiving usual care (6.67 to 7.68 vs 5.9 to 5.03; P = .015). Simply asking about pain may induce anxiety in some people, the researchers said.

There was no significant improvement in quality of life, as reflected in Functional Assessment of Cancer–General scores, or in global symptoms, as indicated on scores on the Edmonton Symptom Assessment Scale.

Given the growing disparity between the need for palliative care and the availability of clinicians to provide it, there is mounting evidence that patient-reported data lead to improved outcomes in oncology, Kamdar emphasized.

ePAL was designed from the patient's perspective, rather than the clinician's, making it more relevant to the patient and, ultimately, more effective, he pointed out. At the end of the study, almost half of the participants (47.6%) were still using the app more than 1 day a week.

The next step is to create a 2.0 version of ePAL. This version will have more innovative features, said Kamdar. He would like to study the new version in rural areas where there is limited access to palliative care "or really in any setting where palliative care is present but the demands overwhelm the care team's delivery capacity, which is common," he said.

Eventually, the application could be extended to the management of diseases other than cancer. "Our broader goal is to use AI and telemedicine technology to extend the reach of palliative care across a spectrum of symptoms and illnesses to those who need it most," he said.

The study was funded by the McKesson Foundation. Dr Kamdar has a financial relationship with Amorsa Therapeutics. The other investigators have disclosed no relevant financial relationships.

Palliative Care in Oncology Symposium (PCOS) 2018. Abstract 76, presented November 16, 2018.


Comments on Medscape are moderated and should be professional in tone and on topic. You must declare any conflicts of interest related to your comments and responses. Please see our Commenting Guide for further information. We reserve the right to remove posts at our sole discretion.
Post as: