Early detection of migraine attacks based on wearable sensors

Koskimäki, Heli; Mönttinen, Henna; Siirtola, Pekka; Huttunen, Hanna-Leena; Halonen, Raija; Röning, Juha

doi:10.1145/3123024.3124434

Cited by 25 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study strengthens earlier studies that migraine is a geneticregulated illness and it is inherited from generation to generation. Because of hormonal changes, women suffer from migraine more than men and migraine sickness is located in the 25-44 age group [4,23,1]. In this study most of the respondents were 30-49 years old, and they had been diagnosed with migraine over the years.…”

Section: Discussionmentioning

confidence: 80%

“…All of the respondents were willing to use a device that reads and syncs the information about migraine attack to migraine diary by a confirm button. Measuring human biosignals from the wrist is recognised to be useful in predicting emergence of diseases [1] and biosignals provide useful information on physiological changes which can be used to improve the availability of treatment [7,11]. The current study listed sleep quality, pulse, blood pressure, stress levels and sleep rhythms as well as energy consumption as the six most important biosignals of a device to measure.…”

Section: Discussionmentioning

confidence: 99%

“…With an intelligent device, the emergence of migraine can be predicted, and patients can be assisted in their own care monitoring. Furthermore, wearable sensors make self-monitoring more efficient and users more aware of their own health (see [1]). Wearable sensors collect information from users and provide feedback in real time using health applications.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Preferred Biosignals to Predict Migraine Attack

Huttunen

Halonen

2018

Well-Being in the Information Society. Fighting Inequalities

Self Cite

View full text Add to dashboard Cite

Abstract. Migraine is classified to two classes, with aura and without aura, and migraine seizures last usually several hours. The goal of this study was to identify the most important symptoms of migraine to be monitored by wearable sensors to predict the migraine attack. The purpose of wearable sensors is to guide patients to take the migraine medication in time, and to support their own care. Self-measurement is a growing trend worldwide and sensor technology has been used for several years in activity wristbands, smartphones, rings, mobile phones, and mobile applications. The study was conducted as an operational study, randomised for those who had been diagnosed with migraine by a doctor. The study was divided into two parts, at first a questionnaire was sent to 17 people in social media. On the basis of the questionnaire, a qualitative interview was conducted for 12 persons with migraine. Responses to the questionnaire were compared to the results of the interview, and the answers to the research questions were sought. Migraine patients considered important that device reports quality of sleep, pulse, blood pressure, stress levels, sleep apnea, and energy consumption.

show abstract

Section: Discussionmentioning

confidence: 80%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Preferred Biosignals to Predict Migraine Attack

Huttunen

Halonen

2018

Well-Being in the Information Society. Fighting Inequalities

Self Cite

View full text Add to dashboard Cite

show abstract

“…The system described in [279] proposes a multisensory approach (accelerometry, photoplethysmography (PPG), body temperature and electrodermal activity) to detect a migraine event in a previous state in order to notify patients to take their medications with enough time. In [280], another multisensory approach was used, based on acceleration and electromyogram sensors, to assess low back pain.…”

Section: Other Pain Sensors and Data Fusionmentioning

confidence: 99%

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

Naranjo-Hernández

Reina‐Tosina

Roa

2020

Sensors

View full text Add to dashboard Cite

Non-oncologic chronic pain is a common high-morbidity impairment worldwide and acknowledged as a condition with significant incidence on quality of life. Pain intensity is largely perceived as a subjective experience, what makes challenging its objective measurement. However, the physiological traces of pain make possible its correlation with vital signs, such as heart rate variability, skin conductance, electromyogram, etc., or health performance metrics derived from daily activity monitoring or facial expressions, which can be acquired with diverse sensor technologies and multisensory approaches. As the assessment and management of pain are essential issues for a wide range of clinical disorders and treatments, this paper reviews different sensor-based approaches applied to the objective evaluation of non-oncological chronic pain. The space of available technologies and resources aimed at pain assessment represent a diversified set of alternatives that can be exploited to address the multidimensional nature of pain.

show abstract

“…The IBI data file consists of two columns: a timestamp and the duration of the detected beats. The incorrect peaks caused by noise in the BVP signal were removed from the file [ 39 , 40 ]. The IBI data for the public speaking and mental math task were combined to reflect the stress class to build a binary classification model to classify the stress state of a person into two categories: stressed or non-stressed.…”

Section: Materials and Datamentioning

confidence: 99%

Stress Classification Using Photoplethysmogram-Based Spatial and Frequency Domain Images

Elzeiny

Qaraqe

2020

Sensors

View full text Add to dashboard Cite

Stress is subjective and is manifested differently from one person to another. Thus, the performance of generic classification models that classify stress status is crude. Building a person-specific model leads to a reliable classification, but it requires the collection of new data to train a new model for every individual and needs periodic upgrades because stress is dynamic. In this paper, a new binary classification (called stressed and non-stressed) approach is proposed for a subject’s stress state in which the inter-beat intervals extracted from a photoplethysomogram (PPG) were transferred to spatial images and then to frequency domain images according to the number of consecutive. Then, the convolution neural network (CNN) was used to train and validate the classification accuracy of the person’s stress state. Three types of classification models were built: person-specific models, generic classification models, and calibrated-generic classification models. The average classification accuracies achieved by person-specific models using spatial images and frequency domain images were 99.9%, 100%, and 99.8%, and 99.68%, 98.97%, and 96.4% for the training, validation, and test, respectively. By combining 20% of the samples collected from test subjects into the training data, the calibrated generic models’ accuracy was improved and outperformed the generic performance across both the spatial and frequency domain images. The average classification accuracy of 99.6%, 99.9%, and 88.1%, and 99.2%, 97.4%, and 87.6% were obtained for the training set, validation set, and test set, respectively, using the calibrated generic classification-based method for the series of inter-beat interval (IBI) spatial and frequency domain images. The main contribution of this study is the use of the frequency domain images that are generated from the spatial domain images of the IBI extracted from the PPG signal to classify the stress state of the individual by building person-specific models and calibrated generic models.

show abstract

Early detection of migraine attacks based on wearable sensors

Cited by 25 publications

References 9 publications

Preferred Biosignals to Predict Migraine Attack

Preferred Biosignals to Predict Migraine Attack

Sensor Technologies to Manage the Physiological Traits of Chronic Pain: A Review

Stress Classification Using Photoplethysmogram-Based Spatial and Frequency Domain Images

Contact Info

Product

Resources

About