Selecting anti-epileptic drugs: a pediatric epileptologist's view, a computer's view

A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support

BACKGROUND

Probabilistic assessments of clinical care are essential for quality care. Yet, machine learning, which supports this care process has been limited to categorical results. To maximize its usefulness, it is important to find novel approaches that calibrate the ML output with a likelihood scale. Current state-of-the-art calibration methods are generally accurate and applicable to many ML models, but improved granularity and accuracy of such methods would increase the information available for clinical decision making. This novel non-parametric Bayesian approach is demonstrated on a variety of data sets, including simulated classifier outputs, biomedical data sets from the University of California, Irvine (UCI) Machine Learning Repository, and a clinical data set built to determine suicide risk from the language of emergency department patients.

RESULTS

The method is first demonstrated on support-vector machine (SVM) models, which generally produce well-behaved, well understood scores. The method produces calibrations that are comparable to the state-of-the-art Bayesian Binning in Quantiles (BBQ) method when the SVM models are able to effectively separate cases and controls. However, as the SVM models' ability to discriminate classes decreases, our approach yields more granular and dynamic calibrated probabilities comparing to the BBQ method. Improvements in granularity and range are even more dramatic when the discrimination between the classes is artificially degraded by replacing the SVM model with an ad hoc k-means classifier.

CONCLUSIONS

The method allows both clinicians and patients to have a more nuanced view of the output of an ML model, allowing better decision making. The method is demonstrated on simulated data, various biomedical data sets and a clinical data set, to which diverse ML methods are applied. Trivially extending the method to (non-ML) clinical scores is also discussed.

Epilepsy Treatment: A Futurist View

Advances in epilepsy treatment are occurring at a rapid pace, and it is challenging for us to keep up with the latest in our field. As we struggle to keep up with the literature and concentrate on our own research and clinical work, we often fail to exercise our imagination and envision what our field will be like in future decades. This was the assignment to the speakers for the Presidential Symposium at the 2016 American Epilepsy Society Annual Meeting. I challenged the experts to step outside the frame of their usual daily work to imagine what epilepsy treatment would and should look like for the next generation of epilepsy specialists and their patients. As you will read in the following sections, the speakers truly stepped up to the challenge to look into the crystal ball. The following are summaries of each lecture that describe the current state, existing cutting edge ideas, and some surprising predictions for the future. I am grateful for the tremendous effort these experts put into this challenge and hope they stimulate your imagination so you will work to bring these advances to our patients.

Changing the approach to treatment choice in epilepsy using big data

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.

Diagnosis and management of childhood epilepsy

Epilepsy is a relatively common neurologic disorder in children that has important implications for development, parents, and society. Making the correct diagnosis starts with an accurate and complete history that consequently leads to a directed diagnostic workup. This article outlines a diagnostic and management approach to pediatric seizures and epilepsy syndromes. Making the correct diagnosis of epilepsy or nonepileptic imitators allows the practitioner to prescribe appropriate therapy. Initial management for typical epileptic syndromes and seizures and potential adverse effects are discussed. Alternative treatment options for pharmacologically resistant patients such as ketogenic diet, vagal nerve stimulation, and surgery are also discussed. While most children favorably respond to antiepileptic medications, early identification of medication failure is important to ensure optimal neurodevelopment.