Orrin Devinsky1, Cynthia Dilley2, Michal Ozery-Flato3, Ranit Aharonov4, Ya'ara Goldschmidt5, Michal Rosen-Zvi6, Chris Clark7, Patty Fritz8. 1. Comprehensive Epilepsy Center, New York University Medical Center, 223 E. 34th Street, New York, NY 10016, USA. Electronic address: od4@nyu.edu. 2. UCB Pharma, 1950 Lake Park Dr., Smyrna, GA 30080, USA. Electronic address: Cynthia.Dilley@ucb.com. 3. IBM Research, University of Haifa Campus, Mount Carmel, Haifa 3498825, Israel. Electronic address: OZERY@il.ibm.com. 4. IBM Research, University of Haifa Campus, Mount Carmel, Haifa 3498825, Israel. Electronic address: ranitah1@gmail.com. 5. IBM Research, University of Haifa Campus, Mount Carmel, Haifa 3498825, Israel. Electronic address: YAARAG@il.ibm.com. 6. IBM Research, University of Haifa Campus, Mount Carmel, Haifa 3498825, Israel. Electronic address: ROSEN@il.ibm.com. 7. UCB Pharma, 1950 Lake Park Dr., Smyrna, GA 30080, USA. Electronic address: Chris.Clark@ucb.com. 8. UCB Pharma, 1950 Lake Park Dr., Smyrna, GA 30080, USA. Electronic address: Patty.Fritz@ucb.com.
Abstract
PURPOSE: A UCB-IBM collaboration explored the application of machine learning to large claims databases to construct an algorithm for antiepileptic drug (AED) choice for individual patients. METHODS: Claims data were collected between January 2006 and September 2011 for patients with epilepsy > 16 years of age. A subset of patient claims with a valid index date of AED treatment change (new, add, or switch) were used to train the AED prediction model by retrospectively evaluating an index date treatment for subsequent treatment change. Based on the trained model, a model-predicted AED regimen with the lowest likelihood of treatment change was assigned to each patient in the group of test claims, and outcomes were evaluated to test model validity. RESULTS: The model had 72% area under receiver operator characteristic curve, indicating good predictive power. Patients who were given the model-predicted AED regimen had significantly longer survival rates (time until a treatment change event) and lower expected health resource utilization on average than those who received another treatment. The actual prescribed AED regimen at the index date matched the model-predicted AED regimen in only 13% of cases; there were large discrepancies in the frequency of use of certain AEDs/combinations between model-predicted AED regimens and those actually prescribed. CONCLUSIONS: Chances of treatment success were improved if patients received the model-predicted treatment. Using the model's prediction system may enable personalized, evidence-based epilepsy care, accelerating the match between patients and their ideal therapy, thereby delivering significantly better health outcomes for patients and providing health-care savings by applying resources more efficiently. Our goal will be to strengthen the predictive power of the model by integrating diverse data sets and potentially moving to prospective data collection. Crown
PURPOSE: A UCB-IBM collaboration explored the application of machine learning to large claims databases to construct an algorithm for antiepileptic drug (AED) choice for individual patients. METHODS: Claims data were collected between January 2006 and September 2011 for patients with epilepsy > 16 years of age. A subset of patient claims with a valid index date of AED treatment change (new, add, or switch) were used to train the AED prediction model by retrospectively evaluating an index date treatment for subsequent treatment change. Based on the trained model, a model-predicted AED regimen with the lowest likelihood of treatment change was assigned to each patient in the group of test claims, and outcomes were evaluated to test model validity. RESULTS: The model had 72% area under receiver operator characteristic curve, indicating good predictive power. Patients who were given the model-predicted AED regimen had significantly longer survival rates (time until a treatment change event) and lower expected health resource utilization on average than those who received another treatment. The actual prescribed AED regimen at the index date matched the model-predicted AED regimen in only 13% of cases; there were large discrepancies in the frequency of use of certain AEDs/combinations between model-predicted AED regimens and those actually prescribed. CONCLUSIONS: Chances of treatment success were improved if patients received the model-predicted treatment. Using the model's prediction system may enable personalized, evidence-based epilepsy care, accelerating the match between patients and their ideal therapy, thereby delivering significantly better health outcomes for patients and providing health-care savings by applying resources more efficiently. Our goal will be to strengthen the predictive power of the model by integrating diverse data sets and potentially moving to prospective data collection. Crown
Authors: Victor Ferastraoaru; Daniel M Goldenholz; Sharon Chiang; Robert Moss; William H Theodore; Sheryl R Haut Journal: Epilepsia Open Date: 2018-07-04
Authors: Lieneke van den Heuvel; Ray R Dorsey; Barbara Prainsack; Bart Post; Anne M Stiggelbout; Marjan J Meinders; Bastiaan R Bloem Journal: J Parkinsons Dis Date: 2020 Impact factor: 5.568
Authors: Johann de Jong; Ioana Cutcutache; Matthew Page; Sami Elmoufti; Cynthia Dilley; Holger Fröhlich; Martin Armstrong Journal: Brain Date: 2021-07-28 Impact factor: 13.501