Search

Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Synthetic patient data generated by the CRBM accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure in the components of ADAS-Cog, and identifies sub-components associated with word recall as predictive of progression.

Introduction As drug development research efforts move toward studying patients earlier in the course of Alzheimer's disease (AD), it is important to incorporate the patient's perspective into measurement of outcomes. Methods This article summarizes the qualitative work of the Patient-Reported Outcome Consortium's Cognition Working Group in the development of a new self-reported outcome measure in persons with mild cognitive impairment (MCI) due to suspected AD, herein referred to as MCI. Results The draft measure captures the patient's voice for two functional domains, complex activities of daily living and interpersonal functioning. Discussion This work represents a series of initial steps in the development of this rating scale. The next steps are to conduct psychometric analysis and evaluate the role of insight. [ABSTRACT FROM AUTHOR]

Preclinical Research Biomarkers hold tremendous promise to improve the drug development and evaluation process, advance patient care, and reduce health ‐ care costs. However, understanding the characteristics of novel biomarkers and developing the robust evidentiary packages to support incorporating them into drug development and clinical practice is an enormous undertaking requiring significant resources and commitment from a wide range of stakeholders, including regulators, the biopharmaceutical industry, academia, governmental agencies, patients, and payors. The Predictive Safety Testing Consortium (PSTC) is a unique public – private partnership formed by Critical Path Institute (C ‐ Path) in collaboration with the United States Food and Drug Administration (FDA) to identify new and improved drug safety testing methods and submit them for formal regulatory qualification by the FDA, the European Medicines Agency, and the Japanese Pharmaceuticals and Medical Devices Agency. In 2008, the PSTC obtained the first regulatory qualification of seven urinary renal preclinical safety biomarkers for use in rodent studies and on a case ‐ by ‐ case basis for inclusion into clinical development programs. These qualified biomarkers are now successfully informing drug discovery and development decisions. PSTC has expanded their qualification efforts into dogs, nonhuman primates, and humans and focuses on six areas of organ toxicity. The collaborative effort of multiple stakeholders through PSTC has resulted in significant cost savings and more rapid scientific consensus, leading to greater acceptance of these biomarkers by health authorities and pharmaceutical companies. Regulatory qualification of a biomarker for a defined context of use provides scientifically robust assurances to sponsors and regulators that should accelerate appropriate adoption of biomarkers into drug development and, ultimately, clinical practice. [ABSTRACT FROM AUTHOR]

Introduction: As drug development research efforts move toward studying patients earlier in the course of Alzheimer's disease (AD), it is important to incorporate the patient's perspective into measurement of outcomes., Methods: This article summarizes the qualitative work of the Patient-Reported Outcome Consortium's Cognition Working Group in the development of a new self-reported outcome measure in persons with mild cognitive impairment (MCI) due to suspected AD, herein referred to as MCI., Results: The draft measure captures the patient's voice for two functional domains, complex activities of daily living and interpersonal functioning., Discussion: This work represents a series of initial steps in the development of this rating scale. The next steps are to conduct psychometric analysis and evaluate the role of insight., (Copyright © 2016 The Alzheimer's Association. Published by Elsevier Inc. All rights reserved.)