Dataset Information

Forecasting Seizure Likelihood With Wearable Technology.

ABSTRACT: The unpredictability of epileptic seizures exposes people with epilepsy to potential physical harm, restricts day-to-day activities, and impacts mental well-being. Accurate seizure forecasters would reduce the uncertainty associated with seizures but need to be feasible and accessible in the long-term. Wearable devices are perfect candidates to develop non-invasive, accessible forecasts but are yet to be investigated in long-term studies. We hypothesized that machine learning models could utilize heart rate as a biomarker for well-established cycles of seizures and epileptic activity, in addition to other wearable signals, to forecast high and low risk seizure periods. This feasibility study tracked participants' (n = 11) heart rates, sleep, and step counts using wearable smartwatches and seizure occurrence using smartphone seizure diaries for at least 6 months (mean = 14.6 months, SD = 3.8 months). Eligible participants had a diagnosis of refractory epilepsy and reported at least 20 seizures (mean = 135, SD = 123) during the recording period. An ensembled machine learning and neural network model estimated seizure risk either daily or hourly, with retraining occurring on a weekly basis as additional data was collected. Performance was evaluated retrospectively against a rate-matched random forecast using the area under the receiver operating curve. A pseudo-prospective evaluation was also conducted on a held-out dataset. Of the 11 participants, seizures were predicted above chance in all (100%) participants using an hourly forecast and in ten (91%) participants using a daily forecast. The average time spent in high risk (prediction time) before a seizure occurred was 37 min in the hourly forecast and 3 days in the daily forecast. Cyclic features added the most predictive value to the forecasts, particularly circadian and multiday heart rate cycles. Wearable devices can be used to produce patient-specific seizure forecasts, particularly when biomarkers of seizure and epileptic activity cycles are utilized.

SUBMITTER: Stirling RE

PROVIDER: S-EPMC8320020 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundSeizure risk forecasting could reduce injuries and even deaths in people with epilepsy. There is great interest in using non-invasive wearable devices to generate forecasts of seizure risk. Forecasts based on cycles of epileptic activity, seizure times or heart rate have provided promising forecasting results. This study validates a forecasting method using multimodal cycles recorded from wearable devices.MethodSeizure and heart rate cycles were extracted from 13 participants. The mean period of heart rate data from a smartwatch was 562 days, with a mean of 125 self-reported seizures from a smartphone app. The relationship between seizure onset time and phases of seizure and heart rate cycles was investigated. An additive regression model was used to project heart rate cycles. The results of forecasts using seizure cycles, heart rate cycles, and a combination of both were compared. Forecasting performance was evaluated in 6 of 13 participants in a prospective setting, using long-term data collected after algorithms were developed.FindingsThe results showed that the best forecasts achieved a mean area under the receiver-operating characteristic curve (AUC) of 0.73 for 9/13 participants showing performance above chance during retrospective validation. Subject-specific forecasts evaluated with prospective data showed a mean AUC of 0.77 with 4/6 participants showing performance above chance.InterpretationThe results of this study demonstrate that cycles detected from multimodal data can be combined within a single, scalable seizure risk forecasting algorithm to provide robust performance. The presented forecasting method enabled seizure risk to be estimated for an arbitrary future period and could be generalised across a range of data types. In contrast to earlier work, the current study evaluated forecasts prospectively, in subjects blinded to their seizure risk outputs, representing a critical step towards clinical applications.FundingThis study was funded by an Australian Government National Health & Medical Research Council and BioMedTech Horizons grant. The study also received support from the Epilepsy Foundation of America's 'My Seizure Gauge' grant.

Project description:SEE MORMANN AND ANDRZEJAK DOI101093/BRAIN/AWW091 FOR A SCIENTIFIC COMMENTARY ON THIS ARTICLE : Accurate forecasting of epileptic seizures has the potential to transform clinical epilepsy care. However, progress toward reliable seizure forecasting has been hampered by lack of open access to long duration recordings with an adequate number of seizures for investigators to rigorously compare algorithms and results. A seizure forecasting competition was conducted on kaggle.com using open access chronic ambulatory intracranial electroencephalography from five canines with naturally occurring epilepsy and two humans undergoing prolonged wide bandwidth intracranial electroencephalographic monitoring. Data were provided to participants as 10-min interictal and preictal clips, with approximately half of the 60 GB data bundle labelled (interictal/preictal) for algorithm training and half unlabelled for evaluation. The contestants developed custom algorithms and uploaded their classifications (interictal/preictal) for the unknown testing data, and a randomly selected 40% of data segments were scored and results broadcasted on a public leader board. The contest ran from August to November 2014, and 654 participants submitted 17 856 classifications of the unlabelled test data. The top performing entry scored 0.84 area under the classification curve. Following the contest, additional held-out unlabelled data clips were provided to the top 10 participants and they submitted classifications for the new unseen data. The resulting area under the classification curves were well above chance forecasting, but did show a mean 6.54 ± 2.45% (min, max: 0.30, 20.2) decline in performance. The kaggle.com model using open access data and algorithms generated reproducible research that advanced seizure forecasting. The overall performance from multiple contestants on unseen data was better than a random predictor, and demonstrates the feasibility of seizure forecasting in canine and human epilepsy.media-1vid110.1093/brain/aww045_video_abstractaww045_video_abstract.

Project description:BackgroundTo experience external objects in such a way that they are perceived as an integral part of one's own body is called embodiment. Wearable technology is a category of objects, which, due to its intrinsic properties (eg, close to the body, inviting frequent interaction, and access to personal information), is likely to be embodied. This phenomenon, which is referred to in this paper as wearable technology embodiment, has led to extensive conceptual considerations in various research fields. These considerations and further possibilities with regard to quantifying wearable technology embodiment are of particular value to the mobile health (mHealth) field. For example, the ability to predict the effectiveness of mHealth interventions and knowing the extent to which people embody the technology might be crucial for improving mHealth adherence. To facilitate examining wearable technology embodiment, we developed a measurement scale for this construct.ObjectiveThis study aimed to conceptualize wearable technology embodiment, create an instrument to measure it, and test the predictive validity of the scale using well-known constructs related to technology adoption. The introduced instrument has 3 dimensions and includes 9 measurement items. The items are distributed evenly between the 3 dimensions, which include body extension, cognitive extension, and self-extension.MethodsData were collected through a vignette-based survey (n=182). Each respondent was given 3 different vignettes, describing a hypothetical situation using a different type of wearable technology (a smart phone, a smart wristband, or a smart watch) with the purpose of tracking daily activities. Scale dimensions and item reliability were tested for their validity and Goodness of Fit Index (GFI).ResultsConvergent validity of the 3 dimensions and their reliability were established as confirmatory factor analysis factor loadings (>0.70), average variance extracted values (>0.50), and minimum item to total correlations (>0.40) exceeded established threshold values. The reliability of the dimensions was also confirmed as Cronbach alpha and composite reliability exceeded 0.70. GFI testing confirmed that the 3 dimensions function as intercorrelated first-order factors. Predictive validity testing showed that these dimensions significantly add to multiple constructs associated with predicting the adoption of new technologies (ie, trust, perceived usefulness, involvement, attitude, and continuous intention).ConclusionsThe wearable technology embodiment measurement instrument has shown promise as a tool to measure the extension of an individual's body, cognition, and self, as well as predict certain aspects of technology adoption. This 3-dimensional instrument can be applied to mixed method research and used by wearable technology developers to improve future versions through such things as fit, improved accuracy of biofeedback data, and customizable features or fashion to connect to the users' personal identity. Further research is recommended to apply this measurement instrument to multiple scenarios and technologies, and more diverse user groups.

Project description:ObjectiveSeizure forecasting algorithms have become increasingly accurate and may reduce the morbidity and mortality caused by seizure unpredictability. Translating these benefits into meaningful health outcomes for people with epilepsy requires effective data visualization of algorithm outputs. To date, no studies have investigated patient and physician perspectives on effective translation of algorithm outputs into data visualizations through health information technology.Materials and methodsWe developed front-end data visualizations as part of a Seizure Forecast Visualization Toolkit. We surveyed 627 people living with epilepsy and caregivers, and 28 epilepsy healthcare providers. Respondents scored each visualization in terms of international standardized software quality criteria for functionality, appropriateness, and usability.ResultsPeople with epilepsy and caregivers ranked hourly radar charts highest for protecting against errors in interpreting forecasts, reducing anxiety from seizure unpredictability, and understanding seizure patterns. Accuracy in interpreting visuals, such as a risk gauge, was dependent on seizure frequency. Visuals showing hourly/daily forecasts were more useful for patients who experienced seizure cycling than those who did not. Hourly line graphs and monthly heat maps were rated highest among clinicians for ease of understanding, anticipated integration into clinical practice, and the likelihood of clinical usage. Epilepsy providers indicated that daily heat maps, daily line graphs, and hourly line graphs were most useful for interpreting seizure diary patterns, assessing therapy impact, and counseling on seizure safety.DiscussionThe choice of data visualization impacts the effective translation of seizure forecast algorithms into meaningful health outcomes.ConclusionThis effort underlines the importance of incorporating standardized, quantitative methods for assessing the effectiveness of data visualization to translate seizure forecast algorithms into clinical practice.

Project description:BackgroundCurrent technology innovations, such as wearables, have caused surprising reactions and feelings of deep connection to devices. Some researchers are calling mobile and wearable technologies cognitive prostheses, which are intrinsically connected to individuals as if they are part of the body, similar to a physical prosthesis. Additionally, while several studies have been performed on the phenomenology of receiving and wearing a physical prosthesis, it is unknown whether similar subjective experiences arise with technology.ObjectiveIn one of the first qualitative studies to track wearables in a longitudinal investigation, we explore whether a wearable can be embodied similar to a physical prosthesis. We hoped to gain insights and compare the phases of embodiment (ie, initial adjustment to the prosthesis) and the psychological responses (ie, accept the prosthesis as part of their body) between wearables and limb prostheses. This approach allowed us to find out whether this pattern was part of a cyclical (ie, period of different usage intensity) or asymptotic (ie, abandonment of the technology) pattern.MethodsWe adapted a limb prosthesis methodological framework to be applied to wearables and conducted semistructured interviews over a span of several months to assess if, how, and to what extent individuals come to embody wearables similar to prosthetic devices. Twelve individuals wore fitness trackers for 9 months, during which time interviews were conducted in the following three phases: after 3 months, after 6 months, and at the end of the study after 9 months. A deductive thematic analysis based on Murray's work was combined with an inductive approach in which new themes were discovered.ResultsOverall, the individuals experienced technology embodiment similar to limb embodiment in terms of adjustment, wearability, awareness, and body extension. Furthermore, we discovered two additional themes of engagement/reengagement and comparison to another device or person. Interestingly, many participants experienced a rarely reported phenomenon in longitudinal studies where the feedback from the device was counterintuitive to their own beliefs. This created a blurring of self-perception and a dilemma of "whom" to believe, the machine or one's self.ConclusionsThere are many similarities between the embodiment of a limb prosthesis and a wearable. The large overlap between limb and wearable embodiment would suggest that insights from physical prostheses can be applied to wearables and vice versa. This is especially interesting as we are seeing the traditionally "dumb" body prosthesis becoming smarter and thus a natural merging of technology and body. Future longitudinal studies could focus on the dilemma people might experience of whether to believe the information of the device over their own thoughts and feelings. These studies might take into account constructs, such as technology reliance, autonomy, and levels of self-awareness.

Project description:ObjectiveTracking seizures is crucial for epilepsy monitoring and treatment evaluation. Current epilepsy care relies on caretaker seizure diaries, but clinical seizure monitoring may miss seizures. Wearable devices may be better tolerated and more suitable for long-term ambulatory monitoring. This study evaluates the seizure detection performance of custom-developed machine learning (ML) algorithms across a broad spectrum of epileptic seizures utilizing wrist- and ankle-worn multisignal biosensors.MethodsWe enrolled patients admitted to the epilepsy monitoring unit and asked them to wear a wearable sensor on either their wrists or ankles. The sensor recorded body temperature, electrodermal activity, accelerometry (ACC), and photoplethysmography, which provides blood volume pulse (BVP). We used electroencephalographic seizure onset and offset as determined by a board-certified epileptologist as a standard comparison. We trained and validated ML for two different algorithms: Algorithm 1, ML methods for developing seizure type-specific detection models for nine individual seizure types; and Algorithm 2, ML methods for building general seizure type-agnostic detection, lumping together all seizure types.ResultsWe included 94 patients (57.4% female, median age = 9.9 years) and 548 epileptic seizures (11 066 h of sensor data) for a total of 930 seizures and nine seizure types. Algorithm 1 detected eight of nine seizure types better than chance (area under the receiver operating characteristic curve [AUC-ROC] = .648-.976). Algorithm 2 detected all nine seizure types better than chance (AUC-ROC = .642-.995); a fusion of ACC and BVP modalities achieved the best AUC-ROC (.752) when combining all seizure types together.SignificanceAutomatic seizure detection using ML from multimodal wearable sensor data is feasible across a broad spectrum of epileptic seizures. Preliminary results show better than chance seizure detection. The next steps include validation of our results in larger datasets, evaluation of the detection utility tool for additional clinical seizure types, and integration of additional clinical information.

Dataset Information

Forecasting Seizure Likelihood With Wearable Technology.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets