A Machine‐Learning Derived Huntington's Disease Progression Model: Insights for Clinical Trial Design

2021 ◽  
Author(s):  
Amrita Mohan ◽  
Zhaonan Sun ◽  
Soumya Ghosh ◽  
Ying Li ◽  
Swati Sathe ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Trial ◽  
Huntington's Disease ◽  
Huntington’S Disease ◽  
Disease Progression ◽  
Trial Design ◽  
Clinical Trial Design ◽  
Progression Model ◽  
Disease Progression Model

scholarly journals Short-interval observational data to inform clinical trial design in Huntington's disease

2015 ◽  
Vol 86 (12) ◽  
pp. 1291-1298 ◽  
Author(s):  
N. Z. Hobbs ◽  
R. E. Farmer ◽  
E. M. Rees ◽  
J. H. Cole ◽  
S. Haider ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Huntington's Disease ◽  
Huntington’S Disease ◽  
Observational Data ◽  
Trial Design ◽  
Short Interval ◽  
Clinical Trial Design

scholarly journals Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
E. Schwager ◽  
K. Jansson ◽  
A. Rahman ◽  
S. Schiffer ◽  
Y. Chang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Clinical Trial ◽  
Acute Respiratory Distress Syndrome ◽  
Respiratory Distress Syndrome ◽  
Respiratory Distress ◽  
Trial Design ◽  
Statistical Power ◽  
Distress Syndrome ◽  
Univariate Analysis ◽  
Clinical Trial Design

AbstractHeterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era in clinical trial design. In this study, we designed a ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing the required number of patients by increasing statistical power through cohort homogeneity. From the Philips eICU Research Institute (eRI) database, no less than 51,555 ARDS patients were extracted. We defined three subpopulations by outcome: (1) rapid death, (2) spontaneous recovery, and (3) long-stay patients. A retrospective univariate analysis identified highly predictive variables for each outcome. All 220 variables were used to determine the most accurate and generalizable model to predict long-stay patients. Multiclass gradient boosting was identified as the best-performing ML model. Whereas alterations in pH, bicarbonate or lactate proved to be strong predictors for rapid death in the univariate analysis, only the multivariate ML model was able to reliably differentiate the disease course of the long-stay outcome population (AUC of 0.77). We demonstrate the feasibility of prospective patient stratification using ML algorithms in the by far largest ARDS cohort reported to date. Our algorithm can identify patients with sufficiently long ARDS episodes to allow time for patients to respond to therapy, increasing statistical power. Further, early enrollment alerts may increase recruitment rate.

scholarly journals Predicting future regional tau accumulation in asymptomatic and early Alzheimer’s disease

2020 ◽  
Author(s):  
Joseph Giorgio ◽  
William J Jagust ◽  
Suzanne Baker ◽  
Susan M. Landau ◽  
Peter Tino ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trial ◽  
Trial Design ◽  
Clinical Trial Design ◽  
Learning Approach ◽  
Multimodal Data ◽  
Machine Learning Approach ◽  
Β Amyloid

AbstractThe earliest stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological data and predict future tau accumulation, translating predictive information from deep phenotyping cohorts at early stages of AD to cognitively normal individuals. In particular, we use machine learning to quantify interactions between key pathological markers (β-amyloid, medial temporal atrophy, tau and APOE 4) at early and asymptomatic stages of AD. We next derive a predictive index that stratifies individuals based on future pathological tau accumulation, highlighting two critical features for optimal clinical trial design. First, future tau accumulation provides a better outcome measure compared to changes in cognition. Second, stratification based on multimodal data compared to β-amyloid alone reduces the sample size required to detect a clinically meaningful change in tau accumulation. Further, we extend our machine learning approach to derive individualised trajectories of future pathological tau accumulation in early AD patients and accurately predict regional future rate of tau accumulation in an independent sample of cognitively unimpaired individuals. Our results propose a robust approach for fine scale stratification and prognostication with translation impact for clinical trial design at asymptomatic and early stages of AD.One Sentence SummaryOur machine learning approach combines baseline multimodal data to make individualised predictions of future pathological tau accumulation at prodromal and asymptomatic stages of Alzheimer’s disease with high accuracy and regional specificity.

scholarly journals Development of a Disease Progression Model for Leucine‐Rich Repeat Kinase 2 in Parkinson's Disease to Inform Clinical Trial Designs

2019 ◽  
Vol 107 (3) ◽  
pp. 553-562 ◽  
Author(s):  
Malidi Ahamadi ◽  
Daniela J Conrado ◽  
Sreeraj Macha ◽  
Vikram Sinha ◽  
Julie Stone ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Clinical Trial ◽  
Parkinson's Disease ◽  
Disease Progression ◽  
Leucine Rich Repeat ◽  
Progression Model ◽  
Disease Progression Model ◽  
Clinical Trial Designs

scholarly journals DEFORMATION BASED MORPHOMETRY STUDY OF LONGITUDINAL MRI CHANGES IN BEHAVIORAL VARIANT FRONTOTEMPORAL DEMENTIA

2019 ◽  
Author(s):  
Ana L. Manera ◽  
Mahsa Dadar ◽  
D. Louis Collins ◽  
Simon Ducharme ◽  
Keyword(s):  
Clinical Trial ◽  
Sample Size ◽  
Disease Progression ◽  
Frontotemporal Dementia ◽  
Trial Design ◽  
Clinical Trial Design ◽  
Cross Sectional ◽  
One Year ◽  
Deformation Based Morphometry

ABSTRACTObjectiveTo objectively quantify how cerebral volume loss could assist with clinical diagnosis and clinical trial design in the behavioural variant of frontotemporal dementia (bvFTD).MethodsWe applied deformation-based morphometric analyses with robust registration to precisely quantify the magnitude and pattern of atrophy in patients with bvFTD as compared to cognitively normal controls (CNCs), to assess the progression of atrophy over one year follow up and to generate clinical trial sample size estimates to detect differences for the structures most sensitive to change. This study included 203 subjects - 70 bvFTD and 133 CNCs - with a total of 482 timepoints from the Frontotemporal Lobar Degeneration Neuroimaging Initiative.ResultsDeformation based morphometry (DBM) revealed significant atrophy in the frontal lobes, insula, medial and anterior temporal regions bilaterally in bvFTD subjects compared to controls with outstanding subcortical involvement. We provide detailed information on regional changes per year. In both cross-sectional analysis and over a one-year follow-up period, ventricle expansion was the most prominent differentiator of bvFTD from controls and a sensitive marker of disease progression.ConclusionsAutomated measurement of ventricular expansion is a sensitive and reliable marker of disease progression in bvFTD to be used in clinical trials for potential disease modifying drugs, as well as possibly to implement in clinical practice. Ventricular expansion measured with DBM provides the lowest published estimated sample size for clinical trial design to detect significant differences over one and two years.

scholarly journals Defining prior therapy in myelodysplastic syndromes and criteria for relapsed and refractory disease: implications for clinical trial design and enrollment

Blood ◽  
2009 ◽  
Vol 114 (13) ◽  
pp. 2575-2580 ◽  
Author(s):  
Mikkael A. Sekeres ◽  
David P. Steensma
Keyword(s):  
Clinical Trial ◽  
Disease Progression ◽  
Myelodysplastic Syndromes ◽  
Trial Design ◽  
Clinical Trial Design ◽  
Refractory Disease ◽  
Prior Therapy ◽  
Previously Treated ◽  
New Challenges ◽  
Design Challenges

Abstract The recent approval of 3 drugs for the treatment of myelodysplastic syndromes (MDSs) has resulted in a revolution in therapeutic options that was absent a decade ago. At the same time, the changing MDS environment is raising new challenges in clinical trial design and defining new indications for MDS drugs. Many current trials still rely on IPSS-based enrollment criteria, despite the well-recognized limitations of the IPSS. Clinical trialists designing studies struggle with several important trial design challenges, including which patients constitute the “previously treated” and “relapsed/refractory” MDS populations, and how specifically to define disease “progression.” This article considers some of these issues as they relate to study design, including how to identify certain MDS populations and define disease progression.

scholarly journals A three‐dimensional neuroimaging based deep learning model to predict Alzheimer’s disease progression for clinical trial design

2021 ◽  
Vol 17 (S1) ◽  
Author(s):  
Scott Gladstein ◽  
Liuqing Yang ◽  
Dustin W Wooten ◽  
Hana Florian ◽  
Xin Huang ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trial ◽  
Deep Learning ◽  
Disease Progression ◽  
Trial Design ◽  
Three Dimensional ◽  
Clinical Trial Design ◽  
Learning Model ◽  
Deep Learning Model

scholarly journals Predicting future regional tau accumulation in asymptomatic and early Alzheimer’s disease

2020 ◽  
Author(s):  
Joseph Giorgio ◽  
William Jagust ◽  
Suzanne Baker ◽  
Susan Landau ◽  
Peter Tino ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trial ◽  
Trial Design ◽  
Clinical Trial Design ◽  
Learning Approach ◽  
Early Stages ◽  
Machine Learning Approach ◽  
Β Amyloid

Abstract The earliest stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological data and predict future tau accumulation, translating predictive information from deep phenotyping cohorts at early stages of AD to cognitively normal individuals. In particular, we use machine learning to quantify interactions between key pathological markers (β-amyloid, medial temporal atrophy, tau and APOE 4) at early and asymptomatic stages of AD. We next derive a predictive index that stratifies individuals based on future pathological tau accumulation, highlighting two critical features for optimal clinical trial design. First, future tau accumulation provides a better outcome measure compared to changes in cognition. Second, stratification based on multimodal data compared to β-amyloid alone reduces the sample size required to detect a clinically meaningful change in tau accumulation. Further, we extend our machine learning approach to derive individualised trajectories of future pathological tau accumulation in early AD patients and accurately predict regional future rate of tau accumulation in an independent sample of cognitively unimpaired individuals. Our results propose a robust approach for fine scale stratification and prognostication with translation impact for clinical trial design at asymptomatic and early stages of AD.

Sign in / Sign up

Export Citation Format

Share Document