Neural network analysis of preoperative variables and outcome in epilepsy surgery

Journal of Neurosurgery - Tập 90 Số 6 - Trang 998-1004 - 1999
Jeffrey E. Arle1, Kenneth Perrine, Orrin Devinsky, Werner Doyle
1Department of Neurosurgery, Hospital of The University of Pennsylvania, Philadelphia 19104, USA.

Tóm tắt

Object. Because appropriate patient selection is essential for achieving successful outcomes after epilepsy surgery, the need for more robust methods of predicting postoperative seizure control has been created. Standard multivariate techniques have been only 75 to 80% accurate in this regard. Recent use of artificial intelligence techniques, including neural networks, for analyzing multivariate clinical data has been successful in predicting medical outcome.Methods. The authors applied neural network techniques to 80 consecutive patients undergoing epilepsy surgery in whom data on demographic, seizure, operative, and clinical variables to predict postoperative seizures were collected.Neural networks could be used to predict postoperative seizures in up to 98% of cases. Student's t-tests or chi-square analysis performed on individual variables revealed that only the preoperative medication index was significantly different (p = 0.02) between the two outcome groups. Six different combinations of input variables were used to train the networks. Neural network accuracies differed in their ability to predict seizures: using all data (96%); all data minus electroencephalography concordance and operative side (93%); all data except intra- or postoperative variables such as tissue pathological category (98%); all data excluding pathological category, intelligence quotient (IQ) data, and Wada results (84%); only demographics and tissue pathological category (65%); and only IQ data (63%).Conclusions. Analysis of the results reveals that several networks that are trained with the usual accepted variables characterizing the typical evaluation of epilepsy patients can predict postoperative seizures with greater than 95% accuracy.

Từ khóa


Tài liệu tham khảo

Arle, 1997, Prediction of posterior fossa tumor type in children by means of magnetic resonance image properties, spectroscopy, and neural networks., 86, 755, 10.3171/jns.1997.86.5.0755

Armon, 1996, Predictors of outcome of epilepsy surgery: multivariate analysis with validation., 37, 814, 10.1111/j.1528-1157.1996.tb00033.x

Barry, 1992, Presurgical electroencephalographic patterns and outcome from anterior temporal lobectomy., 49, 21, 10.1001/archneur.1992.00530250025010

Bengzon, 1968, Prognostic factors in the surgical treatment of temporal lobe epileptics., 18, 717, 10.1212/WNL.18.8.717

Bergen, 1984, Predictors of success in surgical treatment of intractable epilepsy., 25, 665

DiMauro, 1998, Mitochondrial DNA and diseases of the nervous system: the spectrum., 4, 53, 10.1177/107385849800400113

Dodrill, 1990, Stability of predictors of outcome of surgical treatment for epilepsy., 3, 29, 10.1016/0896-6974(90)90075-A

Dodrill, 1986, Multidisciplinary prediction of seizure relief from cortical resection surgery., 20, 2, 10.1002/ana.410200103

Elwes, 1991, Outcome following resective surgery for temporal lobe epilepsy: a prospective follow-up study of 102 consecutive cases., 54, 949, 10.1136/jnnp.54.11.949

Engel, 1987, Outcome wth respect to epileptic seizures, 553

French, 1992, Early risk factor predicts successful epilepsy surgery outcome., 33, 27

Grigsby, 1998, Predicting outcome of anterior temporal lobectomy using simulated neural networks., 39, 61, 10.1111/j.1528-1157.1998.tb01275.x

Guldvog, 1994, Predictive factors for success in surgical treatment for partial epilepsy: a multivariate analysis., 35, 566, 10.1111/j.1528-1157.1994.tb02476.x

Hölmstrom, 1992, Using additive noise in backpropagation training., 3, 24, 10.1109/72.105415

Jack, 1992, Magnetic resonance image-based hippocampal volumetry: correlation with outcome after temporal lobectomy., 31, 138, 10.1002/ana.410310204

Kaufman, 1991, Amazingly short forms of the WAIS-R., 9, 4, 10.1177/073428299100900101

Kuzniecky, 1993, Predictive value of magnetic resonance imaging in temporal lobe epilepsy surgery., 50, 65, 10.1001/archneur.1993.00540010059018

Lieb, 1981, Surface and depth EEG correlates of surgical outcome in temporal lobe epilepsy., 22, 515, 10.1111/j.1528-1157.1981.tb04124.x

Manno, 1994, Predictors of outcome after anterior temporal lobectomy: positron emission tomography., 44, 2331

McBride, 1991, Predictive value of intraoperative electrocorticograms in resective epilepsy surgery., 30, 526, 10.1002/ana.410300404

Radtke, 1993, Temporal lobe hypometabolism on PET: predictor of seizure control after temporal lobectomy., 43, 1088, 10.1212/WNL.43.6.1088

1997, FAQ for AI.

Spencer, 1996, Long-term outcome after epilepsy surgery., 37, 807, 10.1111/j.1528-1157.1996.tb00032.x

Spencer, 1993, Predictors of remission one year after resective epilepsy surgery: a multivariate analysis., 34, 27

Sperling, 1990, Auras and subclinical seizures: characteristics and prognostic significance., 28, 320, 10.1002/ana.410280304

Swartz, 1992, Neuroimaging in temporal lobe epilepsy: test sensitivity and relationships to pathology and postoperative outcome., 33, 624, 10.1111/j.1528-1157.1992.tb02338.x

Walczak, 1987, Factors predicting success in temporal lobectomy for complex partial seizures., 28, 610

Ward, 1990, Prediction of verbal, performance, and full-scale IQs from seven subtests of the WAIS-R., 46, 436, 10.1002/1097-4679(199007)46:4<436::AID-JCLP2270460411>3.0.CO;2-M

Wingkun, 1991, Natural history of recurrent seizures after resective surgery for epilepsy., 32, 851, 10.1111/j.1528-1157.1991.tb05541.x

Thông tin
Thông tin xuất bản

Journal of Neurosurgery

Tập 90 Số 6

998-1004

Thông tin tác giả