The cooperative research between Kaiku Health and Oulu University Hospital aimed to investigate whether patient-reported symptom data (Patient-Reported Outcomes) could be used as an input for machine learning-based prediction models for early detection of immune-related adverse events (irAEs). The research was published at ASCO Annual Meeting 2020 Online Publication on the 13th of May, 2020.
The results suggest that machine learning-based prediction models, using patient-reported symptom data as input for the models, can predict the presence and onset of irAEs with high accuracy. This indicates that digital symptom monitoring combined with machine learning could enable the early detection of irAEs in cancer patients treated with immune checkpoint inhibitors (ICI).
The results are encouraging as ICI therapies can lead to various and severe irAEs that require discontinuation of the therapy. Detecting adverse events early could thus lead to an improved safety profile of the treatment as well as improved quality of life for the patient.
“This is an important step forward in better understanding how patient-reported outcomes data can signal clinical outcomes in cancer treatment. It also provides us with insights to how machine learning can be used to predict development of adverse reactions and thus enhance the management of these toxicities special to the novel cancer immunotherapies. We are excited to continue working with our partners in gaining more understanding about this”, Dr. Vesa Kataja, Chief Medical Officer of Kaiku Health explains.
The data was gathered in a prospective clinical trial, where 33 patients treated with ICIs used Kaiku Health digital symptom monitoring platform to manage their symptoms during their treatment and altogether reported 16 540 symptoms. Investigator-assessed irAE data was combined with the patient-reported symptom data and two machine learning models were built and trained to detect the presence and the onset of irAEs.
Kaiku Health has been developing its machine learning algorithms and predictive analytics since early 2018. In late 2019 Kaiku Health and the Oulu University Hospital presented results on how machine learning can be used to predict the onset and continuity of patient-reported symptoms on patients receiving immune checkpoint inhibitor therapies at the ESMO Immuno-Oncology Congress 2019.
The whole abstract is accessible here.
For more information contact:
Vesa Kataja
Chief Medical Officer, Kaiku Health
vesa.kataja@kaikuhealth.com
+358 40 707 3497
About Kaiku Health
Kaiku Health is a digital health intervention platform classified as a Medical Device in cancer care. Its algorithms screen symptoms, notify the care team and provide personalised support for patients. Kaiku Health has modules for over 25 cancer types across different cancer care pathways and is currently in use in over 40 European cancer clinics and hospitals.
