Individualized Prediction of Migraine Attacks Using a Mobile Phone App and Fitbit (Migraine Alert)
|The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been evaluated by the U.S. Federal Government. Read our disclaimer for details.|
|ClinicalTrials.gov Identifier: NCT02910921|
Recruitment Status : Completed
First Posted : September 22, 2016
Last Update Posted : August 6, 2018
This trial is collaboration between Mayo Clinic, Second Opinion Health (Simon Bloch, firstname.lastname@example.org 408-981-3814) and Allergan. Mayo Clinic investigators are conducting the clinical trial, Second Opinion Health is providing the software for use in the trial (Migraine Alert app for data collection, analysis and machine learning algorithms), and Allergan is providing funding.
The investigators hypothesize that the use of a mobile phone app and Fitbit wearable to collect daily headache diary data, exposure/trigger data and physiologic data will predict the occurrence of migraine attacks with high accuracy. The objective of the trial is to assess the ability to use daily exposure/trigger and symptom data, as well as physiologic data (collected by Fitbit) to create individual predictive migraine models to accurately predict migraine attacks in individual patients via a mobile phone app.
|Condition or disease|
|Migraine Disorders Headache Disorders, Primary Headache Disorders Brain Diseases Central Nervous System Diseases Nervous System Diseases|
Eliminating migraine attacks before they start is of an enormous importance to migraine sufferers. But figuring out the onset of an attack before it actually starts remains a major challenge for the medical community.
The widespread use of mobile smartphones, the availability of wearable devices that measure health information, and advances in multivariate pattern analysis via machine learning algorithms allow for development of individual predictive models that can determine the likelihood of an individual patient developing a migraine on a given day. Such models are based upon objectively measured biometric parameters (e.g. activity, sleep), objectively measured environmental conditions (e.g. weather parameters), exposures to possible migraine triggers, and patient reported symptoms. Using machine-learning algorithms to explore this large dataset that is collected for each patient, the optimal combination of factors that most accurately predict the likelihood of a migraine attack is determined.
Prediction of individual migraine attacks would have substantial positive impacts for patients with migraine. Accurate prediction of a migraine attack would give the migraineur a greater sense of control over their condition, a sense of control that is often lacking in patients with migraine. Most importantly, if individual migraine attacks could be predicted with high accuracy, treatment of that inevitable migraine attack before development of symptoms could prevent the attack altogether.
Eligible subjects will enter a baseline phase during which subjects will wear a Fitbit device and record data into the daily headache diary using the mobile phone app. This phase will be of variable duration for each subject to a maximum of 75 days. It is during the baseline phase that the individualized predictive model for a migraine attack is developed and optimized.
During the second phase (75 days), the accuracy of the predictive model will be tested. The probability of developing a migraine will be calculated and the accuracy of the prediction will be tested against the patient reported incidence of migraine attacks within the mobile phone app. Subjects will be blinded to the app's migraine attack predictions to avoid expectancy bias.
Migraine prediction suffers from 'the curse of dimensionality' (machine learning parlance). Too many factors affect outcomes, but the outcomes (positive migraine attacks) are few and far in between. To develop an accurate machine learning model using traditional approaches requires a long and impractical time duration. Migraine Alert has effectively addressed these using proprietary algorithms and techniques that generate individual models using fewer migraines. Covariate analysis is performed for each individual using features derived from the raw data. Individual models may differ from one other in the specific feature they use and/or the importance attached to them in the model. Proprietary techniques are used to create these individual models and to monitor their pre-validation and post-validation accuracy and recall. Concept drift as evidenced by any degradation in accuracy or recall is monitored in the prediction phase and model is retrained as necessary.
|Study Type :||Observational|
|Actual Enrollment :||19 participants|
|Official Title:||Individualized Prediction of Migraine Attacks Using a Mobile Phone App|
|Actual Study Start Date :||November 2016|
|Actual Primary Completion Date :||July 2018|
|Actual Study Completion Date :||July 31, 2018|
- AUC of individual prediction models using cross validation data on environmental and physiological variables. [ Time Frame: 10 weeks ]The study will develop a separate predictive model for each participant that will forecast probability of experiencing a migraine attack during a particular interval. The outcome measures performance of this model using the Area Under the Curve (AUC) metric. AUC measures how often the algorithm predicts a higher probability for a migraine over non-migraine. This measure is attractive because it is independent of the quantization threshold, which is required for other metrices such as precision/recall. In the baseline phase, 30% of the data will be randomly selected for cross validation and will not used for training the model. Once the model is trained, the AUC of the model is measured on the cross validation data as the outcome of this phase. The data will include various measurements of weather such as temperature, pressure, humidity, wind and physiological measurements such as sleep duration and quality and activity level measured through a wearable Fitbit device.
- AUC of individual prediction models using post prediction data on environmental and physiological variables. [ Time Frame: 10 weeks ]The metric and the type of the data is the same as in Outcome 1. The only difference is that the data is obtained from the user after the model is trained. The user is not shown the prediction to avoid expectancy bias.
To learn more about this study, you or your doctor may contact the study research staff using the contact information provided by the sponsor.
Please refer to this study by its ClinicalTrials.gov identifier (NCT number): NCT02910921
|United States, Arizona|
|Mayo Clinic Arizona|
|Scottsdale, Arizona, United States, 852589|
|United States, California|
|University of Southern California|
|Los Angeles, California, United States, 90033|
|Principal Investigator:||Rashmi Halker Singh, MD||Mayo Clinic|
|Principal Investigator:||Soma Sahai-Srivastava, MD||University of Southern California|