Developing patient-centred strategies to optimize the management of vasomotor symptoms in breast cancer patients: a survey of health care providers

Using machine learning to predict individual patient toxicities from cancer treatments

PURPOSE

Machine learning (ML) is a powerful tool for interrogating datasets and learning relationships between multiple variables. We utilized a ML model to identify those early breast cancer (EBC) patients at highest risk of developing severe vasomotor symptoms (VMS).

METHODS

A gradient boosted decision model utilizing cross-sectional survey data from 360 EBC patients was created. Seventeen patient- and treatment-specific variables were considered in the model. The outcome variable was based on the Hot Flush Night Sweats (HFNS) Problem Rating Score, and individual scores were dichotomized around the median to indicate individuals with high and low problem scores. Model accuracy was assessed using the area under the receiver operating curve, and conditional partial dependence plots were constructed to illustrate relationships between variables and the outcome of interest.

RESULTS

The model area under the ROC curve was 0.731 (SD 0.074). The most important variables in the model were as follows: the number of hot flashes per week, age, the prescription, or use of drug interventions to manage VMS, whether patients were asked about VMS in routine follow-up visits, and the presence or absence of changes to breast cancer treatments due to VMS. A threshold of 17 hot flashes per week was identified as being more predictive of severe VMS. Patients between the ages of 49 and 63 were more likely to report severe symptoms.

CONCLUSION

Machine learning is a unique tool for predicting severe VMS. The use of ML to assess other treatment-related toxicities and their management requires further study.

Vasomotor symptoms in early breast cancer-a "real world" exploration of the patient experience

Background

Despite the frequency of vasomotor symptoms (VMS) in patients with early breast cancer (EBC), their optimal management remains unknown. A patient survey was performed to determine perspectives on this important clinical challenge.

Methods

Patients with EBC experiencing VMS participated in an anonymous survey. Patients reported on the frequency and severity of VMS using the validated Hot Flush Rating Scale (HFRS) and ranked their most bothersome symptoms. Respondents were also asked to determine endpoints that defined effective treatment of VMS and report on the effectiveness of previously tried interventions.

Results

Responses were received from 373 patients, median age 56 years (range 23–83), who experienced an average of 5.0 hot flashes per day (SD 6.57). Patients reported the most bothersome symptoms to be feeling hot/sweating (155/316, 49%) and sleeping difficulties (86/316, 27%). Fifty-five percent (201/365) of patients would consider a treatment to be effective if it reduced night-time awakenings. While 68% of respondents were interested in trying interventions from their healthcare team to manage VMS, only 18% actually did so. Of the 137 patients who had tried an intervention for VMS, pharmacological treatments, exercise, and relaxation strategies were more likely to be effective, while therapies such as melatonin and black cohosh were deemed less effective.

Conclusion

VMS are a common and bothersome problem for EBC patients, with a minority receiving interventions to manage these symptoms. Further research is needed to identify patient-centered strategies for managing these distressing symptoms.

The Rethinking Clinical Trials (REaCT) Program. A Canadian-Led Pragmatic Trials Program: Strategies for Integrating Knowledge Users into Trial Design

We reviewed patient and health care provider (HCP) surveys performed through the REaCT program. The REaCT team has performed 15 patient surveys (2298 respondents) and 13 HCP surveys (1033 respondents) that have addressed a broad range of topics in breast cancer management. Over time, the proportion of surveys distributed by paper/regular mail has fallen, with electronic distribution now the norm. For the patient surveys, the median duration of the surveys was 3 months (IQR 2.5-7 months) and the median response rate was 84% (IQR 80-91.7%). For the HCP surveys, the median survey duration was 3 months (IQR 1.75-4 months), and the median response rate, where available, was 28% (IQR 21.2-49%). The survey data have so far led to: 10 systematic reviews, 6 peer-reviewed grant applications and 19 clinical trials. Knowledge users should be an essential component of clinical research. The REaCT program has integrated surveys as a standard step of their trials process. The COVID-19 pandemic and reduced face-to-face interactions with patients in the clinic as well as the continued importance of social media highlight the need for alternative means of distributing and responding to surveys.