Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials
Abstract Background The ideal participants for Alzheimer's disease (AD) clinical trials would show cognitive decline in the absence of treatment (i.e., placebo arm) and would also respond to the therapeutic intervention. Objective To investigate if predictive models can be an effective tool for...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Alzheimer’s & Dementia: Translational Research & Clinical Interventions |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/trc2.12223 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850060140762365952 |
|---|---|
| author | Ali Ezzati Christos Davatzikos David A. Wolk Charles B. Hall Christian Habeck Richard B. Lipton |
| author_facet | Ali Ezzati Christos Davatzikos David A. Wolk Charles B. Hall Christian Habeck Richard B. Lipton |
| author_sort | Ali Ezzati |
| collection | DOAJ |
| description | Abstract Background The ideal participants for Alzheimer's disease (AD) clinical trials would show cognitive decline in the absence of treatment (i.e., placebo arm) and would also respond to the therapeutic intervention. Objective To investigate if predictive models can be an effective tool for identifying and excluding people unlikely to show cognitive decline as an enrichment strategy in AD trials. Method We used data from the placebo arms of two phase 3, double‐blind trials, EXPEDITION and EXPEDITION2. Patients had 18 months of follow‐up. Based on the longitudinal data from the placebo arm, we classified participants into two groups: one showed cognitive decline (any negative slope) and the other showed no cognitive decline (slope is zero or positive) on the Alzheimer's Disease Assessment Scale–Cognitive subscale (ADAS‐cog). We used baseline data for EXPEDITION to train regression‐based classifiers and machine learning classifiers to estimate probability of cognitive decline. Models were applied to EXPEDITION2 data to assess predicted performance in an independent sample. Features used in predictive models included baseline demographics, apolipoprotein E ε4 genotype, neuropsychological scores, functional scores, and volumetric magnetic resonance imaging. Result In EXPEDITION, 46.3% of placebo‐treated patients showed no cognitive decline and the proportion was similar in EXPEDITION2 (45.6%). Models had high sensitivity and modest specificity in both the training (EXPEDITION) and replication samples (EXPEDITION2) for detecting the stable group. Positive predictive value of models was higher than the base prevalence of cognitive decline, and negative predictive value of models were higher than the base rate of participants who had stable cognition. Conclusion Excluding persons with AD unlikely to decline from the active and placebo arms of clinical trials using predictive models may boost the power of AD trials through selective inclusion of participants expected to decline. |
| format | Article |
| id | doaj-art-75a33871d6df4b5ca29f977fcb0ee460 |
| institution | DOAJ |
| issn | 2352-8737 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Alzheimer’s & Dementia: Translational Research & Clinical Interventions |
| spelling | doaj-art-75a33871d6df4b5ca29f977fcb0ee4602025-08-20T02:50:40ZengWileyAlzheimer’s & Dementia: Translational Research & Clinical Interventions2352-87372022-01-0181n/an/a10.1002/trc2.12223Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trialsAli Ezzati0Christos Davatzikos1David A. Wolk2Charles B. Hall3Christian Habeck4Richard B. Lipton5Department of Neurology Albert Einstein College of Medicine and Montefiore Medical Center Bronx New York USACenter for Biomedical Image Computing and Analytics University of Pennsylvania Philadelphia Pennsylvania USADepartment of Neurology University of Pennsylvania Philadelphia Pennsylvania USADepartment of Department of Epidemiology and Population Health Albert Einstein College of Medicine Bronx New York USADepartment of Neurology Cognitive Neuroscience Division Columbia University New York New York USADepartment of Neurology Albert Einstein College of Medicine and Montefiore Medical Center Bronx New York USAAbstract Background The ideal participants for Alzheimer's disease (AD) clinical trials would show cognitive decline in the absence of treatment (i.e., placebo arm) and would also respond to the therapeutic intervention. Objective To investigate if predictive models can be an effective tool for identifying and excluding people unlikely to show cognitive decline as an enrichment strategy in AD trials. Method We used data from the placebo arms of two phase 3, double‐blind trials, EXPEDITION and EXPEDITION2. Patients had 18 months of follow‐up. Based on the longitudinal data from the placebo arm, we classified participants into two groups: one showed cognitive decline (any negative slope) and the other showed no cognitive decline (slope is zero or positive) on the Alzheimer's Disease Assessment Scale–Cognitive subscale (ADAS‐cog). We used baseline data for EXPEDITION to train regression‐based classifiers and machine learning classifiers to estimate probability of cognitive decline. Models were applied to EXPEDITION2 data to assess predicted performance in an independent sample. Features used in predictive models included baseline demographics, apolipoprotein E ε4 genotype, neuropsychological scores, functional scores, and volumetric magnetic resonance imaging. Result In EXPEDITION, 46.3% of placebo‐treated patients showed no cognitive decline and the proportion was similar in EXPEDITION2 (45.6%). Models had high sensitivity and modest specificity in both the training (EXPEDITION) and replication samples (EXPEDITION2) for detecting the stable group. Positive predictive value of models was higher than the base prevalence of cognitive decline, and negative predictive value of models were higher than the base rate of participants who had stable cognition. Conclusion Excluding persons with AD unlikely to decline from the active and placebo arms of clinical trials using predictive models may boost the power of AD trials through selective inclusion of participants expected to decline.https://doi.org/10.1002/trc2.12223Alzheimer's diseaseanti‐amyloid monoclonal antibodyclinical trialscognitive declinemachine learningpredictive analytics |
| spellingShingle | Ali Ezzati Christos Davatzikos David A. Wolk Charles B. Hall Christian Habeck Richard B. Lipton Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials Alzheimer’s & Dementia: Translational Research & Clinical Interventions Alzheimer's disease anti‐amyloid monoclonal antibody clinical trials cognitive decline machine learning predictive analytics |
| title | Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials |
| title_full | Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials |
| title_fullStr | Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials |
| title_full_unstemmed | Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials |
| title_short | Application of predictive models in boosting power of Alzheimer's disease clinical trials: A post hoc analysis of phase 3 solanezumab trials |
| title_sort | application of predictive models in boosting power of alzheimer s disease clinical trials a post hoc analysis of phase 3 solanezumab trials |
| topic | Alzheimer's disease anti‐amyloid monoclonal antibody clinical trials cognitive decline machine learning predictive analytics |
| url | https://doi.org/10.1002/trc2.12223 |
| work_keys_str_mv | AT aliezzati applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials AT christosdavatzikos applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials AT davidawolk applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials AT charlesbhall applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials AT christianhabeck applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials AT richardblipton applicationofpredictivemodelsinboostingpowerofalzheimersdiseaseclinicaltrialsaposthocanalysisofphase3solanezumabtrials |