Limits...
Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data.

Pagán J, De Orbe MI, Gago A, Sobrado M, Risco-Martín JL, Mora JV, Moya JM, Ayala JL - Sensors (Basel) (2015)

Bottom Line: However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain.The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches.The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives.

View Article: PubMed Central - PubMed

Affiliation: Computer Architecture and Automation Department, Complutense University of Madrid, Madrid 28040, Spain. jpagan@ucm.es.

ABSTRACT
Migraine is one of the most wide-spread neurological disorders, and its medical treatment represents a high percentage of the costs of health systems. In some patients, characteristic symptoms that precede the headache appear. However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain. To solve this problem, this paper sets up a realistic monitoring scenario where hemodynamic variables from real patients are monitored in ambulatory conditions with a wireless body sensor network (WBSN). The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches. The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives.

No MeSH data available.


Related in: MedlinePlus

Fit for 15 randomly-chosen migraines and the average after training them with the N4SID algorithm and 30 min of a future horizon.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541837&req=5

f5-sensors-15-15419: Fit for 15 randomly-chosen migraines and the average after training them with the N4SID algorithm and 30 min of a future horizon.

Mentions: As shown in Section 3.3, a symptomatic curve can be modeled as the junction of two Gaussian curves. The training of the models has been performed for Patient A with T = 15 randomly chosen symptomatic crisis, as described in Section 4.1.2. The training has been run for the four predictors (features) available: TEMP, EDA, HR and SpO2. The training has been made for a fixed prediction horizon of 30 min; this time is justified by the pharmacokinetics in Section 2.1.2. In Figure 5, the fit metric shows how some migraines behave far better than others for the fixed horizon. Some models (six models) show a fit over or equal 80%, and none show a fit lower than 70%. On average, these models with four features are able to fit a migraine event with 75.1% accuracy.


Robust and Accurate Modeling Approaches for Migraine Per-Patient Prediction from Ambulatory Data.

Pagán J, De Orbe MI, Gago A, Sobrado M, Risco-Martín JL, Mora JV, Moya JM, Ayala JL - Sensors (Basel) (2015)

Fit for 15 randomly-chosen migraines and the average after training them with the N4SID algorithm and 30 min of a future horizon.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541837&req=5

f5-sensors-15-15419: Fit for 15 randomly-chosen migraines and the average after training them with the N4SID algorithm and 30 min of a future horizon.
Mentions: As shown in Section 3.3, a symptomatic curve can be modeled as the junction of two Gaussian curves. The training of the models has been performed for Patient A with T = 15 randomly chosen symptomatic crisis, as described in Section 4.1.2. The training has been run for the four predictors (features) available: TEMP, EDA, HR and SpO2. The training has been made for a fixed prediction horizon of 30 min; this time is justified by the pharmacokinetics in Section 2.1.2. In Figure 5, the fit metric shows how some migraines behave far better than others for the fixed horizon. Some models (six models) show a fit over or equal 80%, and none show a fit lower than 70%. On average, these models with four features are able to fit a migraine event with 75.1% accuracy.

Bottom Line: However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain.The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches.The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives.

View Article: PubMed Central - PubMed

Affiliation: Computer Architecture and Automation Department, Complutense University of Madrid, Madrid 28040, Spain. jpagan@ucm.es.

ABSTRACT
Migraine is one of the most wide-spread neurological disorders, and its medical treatment represents a high percentage of the costs of health systems. In some patients, characteristic symptoms that precede the headache appear. However, they are nonspecific, and their prediction horizon is unknown and pretty variable; hence, these symptoms are almost useless for prediction, and they are not useful to advance the intake of drugs to be effective and neutralize the pain. To solve this problem, this paper sets up a realistic monitoring scenario where hemodynamic variables from real patients are monitored in ambulatory conditions with a wireless body sensor network (WBSN). The acquired data are used to evaluate the predictive capabilities and robustness against noise and failures in sensors of several modeling approaches. The obtained results encourage the development of per-patient models based on state-space models (N4SID) that are capable of providing average forecast windows of 47 min and a low rate of false positives.

No MeSH data available.


Related in: MedlinePlus