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

Validation applying the average model, and training for triads of features for Patient A. (a) Average model with Mbest models applied over the remaining 10 migraines; (b) Fitness comparison for N4SID and different three-features combinations in the training stage.
© Copyright Policy
Related In: Results  -  Collection

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

f6-sensors-15-15419: Validation applying the average model, and training for triads of features for Patient A. (a) Average model with Mbest models applied over the remaining 10 migraines; (b) Fitness comparison for N4SID and different three-features combinations in the training stage.

Mentions: According to the results previously mentioned, we wonder if the best model, M6, is good enough for performing the migraine prediction. As seen in Table 2, the maximum horizon is not achieved by M6, but for M11. This possibility was taken into account in the design of the experimental setup (see Section 4.1), and a ranking of the models is performed. With this purpose, the best Mbest = M/3 = 5 models (first five models in Table 2), according to the selection made in Section 4.1.5, are chosen to define an average model. This works as follows: for each migraine, each model Mbesti is applied. Five predicted symptomatic curve are achieved. The result is the average of these five validations for a given horizon. At the end, the false positives are removed with the model repair submodule. The result is shown in Figure 6a. Axis x represents the prediction horizon, meanwhile axis y represents the fit between the average prediction and the real symptomatic curve. In this process, the average, minimum and maximum horizons achieved at 70% are: 25, 18 and 28 min, respectively.


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)

Validation applying the average model, and training for triads of features for Patient A. (a) Average model with Mbest models applied over the remaining 10 migraines; (b) Fitness comparison for N4SID and different three-features combinations in the training stage.
© Copyright Policy
Related In: Results  -  Collection

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

f6-sensors-15-15419: Validation applying the average model, and training for triads of features for Patient A. (a) Average model with Mbest models applied over the remaining 10 migraines; (b) Fitness comparison for N4SID and different three-features combinations in the training stage.
Mentions: According to the results previously mentioned, we wonder if the best model, M6, is good enough for performing the migraine prediction. As seen in Table 2, the maximum horizon is not achieved by M6, but for M11. This possibility was taken into account in the design of the experimental setup (see Section 4.1), and a ranking of the models is performed. With this purpose, the best Mbest = M/3 = 5 models (first five models in Table 2), according to the selection made in Section 4.1.5, are chosen to define an average model. This works as follows: for each migraine, each model Mbesti is applied. Five predicted symptomatic curve are achieved. The result is the average of these five validations for a given horizon. At the end, the false positives are removed with the model repair submodule. The result is shown in Figure 6a. Axis x represents the prediction horizon, meanwhile axis y represents the fit between the average prediction and the real symptomatic curve. In this process, the average, minimum and maximum horizons achieved at 70% are: 25, 18 and 28 min, respectively.

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