array(41) {
  ["project_title"]=>
  string(83) "Machine Learning Approaches to Predicting Treatment Outcomes in Alzheimer's Disease"
  ["project_narrative_summary"]=>
  string(680) "Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development. This research project will compare datasets on Alzheimer's Disease as a way to develop new ML methods for predicting outcomes for Alzheimer's treatment. The results for different datasets will be compared for validation."
  ["project_learn_source"]=>
  string(6) "pubmed"
  ["project_learn_source_exp"]=>
  string(0) ""
  ["project_key_personnel"]=>
  array(2) {
    [0]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(5) "Felix"
      ["p_pers_l_name"]=>
      string(7) "Beacher"
      ["p_pers_degree"]=>
      string(3) "PhD"
      ["p_pers_pr_affil"]=>
      string(20) "Kings College London"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(0) ""
    }
    [1]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(8) "Lilianne"
      ["p_pers_l_name"]=>
      string(13) "Mujica-Parodi"
      ["p_pers_degree"]=>
      string(3) "PhD"
      ["p_pers_pr_affil"]=>
      string(7) "LCNeuro"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(0) ""
    }
  }
  ["project_ext_grants"]=>
  array(2) {
    ["value"]=>
    string(68) "No external grants or funds are being used to support this research."
    ["label"]=>
    string(68) "No external grants or funds are being used to support this research."
  }
  ["project_funding_source"]=>
  string(0) ""
  ["project_assoc_trials"]=>
  array(9) {
    [0]=>
    object(WP_Post)#4695 (24) {
      ["ID"]=>
      int(1345)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2015-02-11 08:46:00"
      ["post_date_gmt"]=>
      string(19) "2015-02-11 08:46:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(84) "Long Term Safety and Efficacy of Galantamine in the treatment of Alzheimer's Disease"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(85) "long-term-safety-and-efficacy-of-galantamine-in-the-treatment-of-alzheimers-disease-2"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:17:36"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:17:36"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(134) "https://dev-yoda.pantheonsite.io/clinical-trial/long-term-safety-and-efficacy-of-galantamine-in-the-treatment-of-alzheimers-disease-2/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [1]=>
    object(WP_Post)#4694 (24) {
      ["ID"]=>
      int(1518)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2016-06-08 16:30:00"
      ["post_date_gmt"]=>
      string(19) "2016-06-08 16:30:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(102) "NCT00253188 - Efficacy, Tolerability and Safety of Galantamine in the Treatment of Alzheimer's Disease"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(98) "nct00253188-efficacy-tolerability-and-safety-of-galantamine-in-the-treatment-of-alzheimers-disease"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:22:07"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:22:07"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(147) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00253188-efficacy-tolerability-and-safety-of-galantamine-in-the-treatment-of-alzheimers-disease/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [2]=>
    object(WP_Post)#4693 (24) {
      ["ID"]=>
      int(1521)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2016-06-08 16:31:00"
      ["post_date_gmt"]=>
      string(19) "2016-06-08 16:31:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(155) "NCT00253214 - Placebo-Controlled Evaluation of Galantamine in the Treatment of Alzheimer's Disease: Safety and Efficacy of a Controlled-Release Formulation"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(151) "nct00253214-placebo-controlled-evaluation-of-galantamine-in-the-treatment-of-alzheimers-disease-safety-and-efficacy-of-a-controlled-release-formulation"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:22:10"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:22:10"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(200) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00253214-placebo-controlled-evaluation-of-galantamine-in-the-treatment-of-alzheimers-disease-safety-and-efficacy-of-a-controlled-release-formulation/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [3]=>
    object(WP_Post)#4692 (24) {
      ["ID"]=>
      int(1523)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2016-06-08 16:33:00"
      ["post_date_gmt"]=>
      string(19) "2016-06-08 16:33:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(242) "NCT00236574 - A Randomized Double Blind Placebo-Controlled Trial to Evaluate the Efficacy and Safety of Galantamine in Patients With Mild Cognitive Impairment (MCI) Clinically at Risk for Development of Clinically Probable Alzheimer's Disease"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(195) "nct00236574-a-randomized-double-blind-placebo-controlled-trial-to-evaluate-the-efficacy-and-safety-of-galantamine-in-patients-with-mild-cognitive-impairment-mci-clinically-at-risk-for-development"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:22:14"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:22:14"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(244) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00236574-a-randomized-double-blind-placebo-controlled-trial-to-evaluate-the-efficacy-and-safety-of-galantamine-in-patients-with-mild-cognitive-impairment-mci-clinically-at-risk-for-development/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [4]=>
    object(WP_Post)#4691 (24) {
      ["ID"]=>
      int(1552)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2016-08-03 14:04:00"
      ["post_date_gmt"]=>
      string(19) "2016-08-03 14:04:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(162) "NCT00679627 - A Randomized, Double-Blind, Placebo-controlled Trial of Long-term (2-year) Treatment of Galantamine in Mild to Moderately-Severe Alzheimer's Disease"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(155) "nct00679627-a-randomized-double-blind-placebo-controlled-trial-of-long-term-2-year-treatment-of-galantamine-in-mild-to-moderately-severe-alzheimers-disease"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:22:53"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:22:53"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(204) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00679627-a-randomized-double-blind-placebo-controlled-trial-of-long-term-2-year-treatment-of-galantamine-in-mild-to-moderately-severe-alzheimers-disease/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [5]=>
    object(WP_Post)#4690 (24) {
      ["ID"]=>
      int(1591)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2017-03-30 16:26:00"
      ["post_date_gmt"]=>
      string(19) "2017-03-30 16:26:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(241) "NCT00216593 - Treatment of Severe Alzheimer's Disease in a Residential Home, Nursing Home, or Geriatric Residential Setting: Evaluation of Efficacy and Safety of Galantamine Hydrobromide in a Randomised, Doubleblind, Placebo-Controlled Study"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(194) "nct00216593-treatment-of-severe-alzheimers-disease-in-a-residential-home-nursing-home-or-geriatric-residential-setting-evaluation-of-efficacy-and-safety-of-galantamine-hydrobromide-in-a-randomis"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:23:48"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:23:48"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(243) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00216593-treatment-of-severe-alzheimers-disease-in-a-residential-home-nursing-home-or-geriatric-residential-setting-evaluation-of-efficacy-and-safety-of-galantamine-hydrobromide-in-a-randomis/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [6]=>
    object(WP_Post)#4689 (24) {
      ["ID"]=>
      int(1657)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2018-01-10 16:02:00"
      ["post_date_gmt"]=>
      string(19) "2018-01-10 16:02:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(152) "Placebo-controlled evaluation of galantamine in the treatment of Alzheimer’s disease: Evaluation of safety and efficacy under a slow titration regimen"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(148) "placebo-controlled-evaluation-of-galantamine-in-the-treatment-of-alzheimers-disease-evaluation-of-safety-and-efficacy-under-a-slow-titration-regimen"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:25:08"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:25:08"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(197) "https://dev-yoda.pantheonsite.io/clinical-trial/placebo-controlled-evaluation-of-galantamine-in-the-treatment-of-alzheimers-disease-evaluation-of-safety-and-efficacy-under-a-slow-titration-regimen/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [7]=>
    object(WP_Post)#4688 (24) {
      ["ID"]=>
      int(1847)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2019-12-12 12:58:00"
      ["post_date_gmt"]=>
      string(19) "2019-12-12 12:58:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(251) "NCT00575055 - A Phase 3, Multicenter, Randomized, Double-Blind, Placebo-Controlled, Parallel-Group, Efficacy and Safety Trial of Bapineuzumab (AAB-001, ELN115727) In Patients With Mild to Moderate Alzheimer's Disease Who Are Apolipoprotein E4 Carriers"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(189) "nct00575055-a-phase-3-multicenter-randomized-double-blind-placebo-controlled-parallel-group-efficacy-and-safety-trial-of-bapineuzumab-aab-001-eln115727-in-patients-with-mild-to-moderate-alz"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:28:23"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:28:23"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(238) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00575055-a-phase-3-multicenter-randomized-double-blind-placebo-controlled-parallel-group-efficacy-and-safety-trial-of-bapineuzumab-aab-001-eln115727-in-patients-with-mild-to-moderate-alz/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
    [8]=>
    object(WP_Post)#4687 (24) {
      ["ID"]=>
      int(1848)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2019-12-12 13:04:00"
      ["post_date_gmt"]=>
      string(19) "2019-12-12 13:04:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(256) "NCT00574132 - A Phase 3, Multicenter, Randomized, Double-Blind, Placebo-Controlled, Parallel-Group, Efficacy and Safety Trial of Bapineuzumab (AAB-001, ELN115727) In Patients With Mild to Moderate Alzheimer's Disease Who Are Apolipoprotein E4 Non- Carriers"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(4) "open"
      ["ping_status"]=>
      string(4) "open"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(189) "nct00574132-a-phase-3-multicenter-randomized-double-blind-placebo-controlled-parallel-group-efficacy-and-safety-trial-of-bapineuzumab-aab-001-eln115727-in-patients-with-mild-to-moderate-alz"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2023-02-06 13:28:23"
      ["post_modified_gmt"]=>
      string(19) "2023-02-06 13:28:23"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(238) "https://dev-yoda.pantheonsite.io/clinical-trial/nct00574132-a-phase-3-multicenter-randomized-double-blind-placebo-controlled-parallel-group-efficacy-and-safety-trial-of-bapineuzumab-aab-001-eln115727-in-patients-with-mild-to-moderate-alz/"
      ["menu_order"]=>
      int(0)
      ["post_type"]=>
      string(14) "clinical_trial"
      ["post_mime_type"]=>
      string(0) ""
      ["comment_count"]=>
      string(1) "0"
      ["filter"]=>
      string(3) "raw"
    }
  }
  ["project_date_type"]=>
  string(91) "Individual Participant-Level Data, which includes Full CSR and all supporting documentation"
  ["property_scientific_abstract"]=>
  string(1122) "Background
Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development.
Objective
This research project will compare the effectiveness of a variety of ML methods to predict outcomes for Alzheimer's disease treatment. The results for different datasets will be compared for validation.
Study Design
Exploratory methods development.
Participants
Clinical trial participants
Main Outcome Measures
Treatment success (e.g. length of survival post-treatment)
Statistical Analysis
A range of ML algorithms (neural networks, random forest, KNN etc ) will be applied to the data in order to predict outcomes. The success of the different algorithms will be compared." ["project_brief_bg"]=> string(2287) "Background on Alzheimer?s disease
Alzheimer?s disease is a brain disorder that slowly destroys memory and thinking skills, and, eventually, the ability to carry out simple tasks. Symptoms usually first appear in the mid-60s. An estimated 6 million Americans have Alzheimer?s disease. Alzheimer?s disease is currently ranked as the sixth leading cause of death in the United States.
Background on the Treatment of Alzheimer?s disease
Alzheimer?s is complex, and it is therefore unlikely that any one drug or other intervention will successfully treat it in all people living with the disease. Many new treatments are being explored, however, current treatments are generally considered not to be very effective.
Several medications have been approved by the FDA to treat symptoms of Alzheimer?s. Donepezil, rivastigmine, and galantamine are used to treat the symptoms of mild to moderate Alzheimer?s. Donepezil, memantine, the rivastigmine patch, and a combination medication of memantine and donepezil are used to treat moderate to severe Alzheimer?s symptoms. These drugs work by regulating a neurotransmitter acetylcholine but do not change the underlying disease process.
Recently Aducanumab became the first disease-modifying therapy approved by the FDA for Alzheimer?s disease. This medication is claimed to reduce amyloid deposits in the brain and may help slow the progression of Alzheimer?s, although this has yet to be clearly established. Thus Alzheimer's remains difficult to treat. Also, a breakthrough in treatment is likely to require a significant amount of time to emerge: follow-up trials on Aducanumab are underway but results will likely not be available before 2030.
These considerations indicate that treatment for Alzheimer's is an important area for research. Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas
where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development." ["project_specific_aims"]=> string(572) "This research project will compare the effectiveness of a variety of ML methods to predict outcomes for Alzheimer?s treatment. The results for different datasets will be compared for validation. This is an exploratory project and does not have specific hypotheses. The objective is to explore the development of new ML methods for predicting outcomes. The potential benefits of this research are the development of methods for identifying subpopulations of patients in whom treatment would be more successful. This could enhance the development of 'personalized medicine'." ["project_study_design"]=> string(0) "" ["project_study_design_exp"]=> string(0) "" ["project_purposes"]=> array(2) { [0]=> array(2) { ["value"]=> string(37) "Develop or refine statistical methods" ["label"]=> string(37) "Develop or refine statistical methods" } [1]=> array(2) { ["value"]=> string(34) "Research on clinical trial methods" ["label"]=> string(34) "Research on clinical trial methods" } } ["project_purposes_exp"]=> string(0) "" ["project_software_used"]=> array(2) { ["value"]=> string(6) "Python" ["label"]=> string(6) "Python" } ["project_software_used_exp"]=> string(0) "" ["project_research_methods"]=> string(137) "All patients in the treatment arms of the trials will be included. Inclusion/Exclusion Criteria have already been defined by the studies." ["project_main_outcome_measure"]=> string(64) "Time to death, if available. Otherwise, time to severe symptoms." ["project_main_predictor_indep"]=> string(250) "Not applicable - the aim is to perform analyses within the treatment arm only, therefore there is no Independent Variable. However, the concept we will attempt to predict is 'good response', a composite of adverse events and efficacy (good outcomes)." ["project_other_variables_interest"]=> string(1232) "NCT00236574 - CR003145 // GAL-INT-11 ?.
Standard predictors
- Sex
- Age
- Race
- Concomitant Medications
- Blood biochemistry
- Medical examination
Additional
- dosing regimen (16 or 24 mg/day)
- controlled-release (CR) or immediate-release (IR)
mild to moderate Alzheimer?s disease
NCT00679627 - GALALZ3005
Standard predictors, as above
Additional
- tobacco use
NCT00216593 - GAL-ALZ-302
Standard predictors, as above
Additional
- ECG
- Neurological exam
- Well being schedule
Brain MRI findings
NCT00236574 - CR003145 // GAL-INT-11
Standard predictors, as above
Additional
- ECG
- Neurological exam
Brain MRI findings
NCT00679627 - GALALZ3005 -
Standard predictors, as above
Additional
- tobacco use
NCT00216593 - GAL-ALZ-302 (PMID # 19042161-CR003940)
Standard predictors, as above
Additional
- ECG
GAL-USA-10
Standard predictors, as above
Additional
tobacco use
NCT00575055 - ELN115727-302 and NCT00574132 - ELN115727-301
Data Specification and Annotated CRF not yet available" ["project_stat_analysis_plan"]=> string(826) "Descriptive analyses on basic clinical features will be presented graphically, e.g. age distribution, number of participants in each arm and clinical outcomes (e.g. survival). T tests will be used to compare treatment groups (drug vs placebo) on factor which could present biases (e.g. age and demographics). Machine learning analyses are not typically done using conventional significance testing. It is more typical to report % accuracy, since this is usually so far above chance level that conventional measures of significance are uninformative. The best ML approach will be identified by using a range of well established algorithm types suitable for use with tabular data, including Logistic Regression, K-Nearest Neighbors (KNN), CatBoost, XGBoost and a Voting Classifier. This follows our previously published method." ["project_timeline"]=> string(198) "Anticipated project start date, Sept 2021
Analysis completion date, Feb 2022
Date manuscript submitted for publication, May 2022
Results reported back to the YODA Project, May 2022" ["project_dissemination_plan"]=> string(213) "Target audience is other researchers in this field of methods development for neurodegeneration.
The papers could be submitted to the journal Algorithms or Computational and Structural Biotechnology Journal." ["project_bibliography"]=> string(341) "

The key reference is Beacher, F.D.; Mujica-Parodi, L.R.; Gupta, S.; Ancora, L.A. Machine Learning Predicts Outcomes of Phase III Clinical Trials for Prostate Cancer. Algorithms 2021, 14, 147. https://doi.org/10.3390/a14050147. This paper contains a description of proposed methods and a proof of concept that this research is viable.

" ["project_suppl_material"]=> bool(false) ["project_coi"]=> array(2) { [0]=> array(1) { ["file_coi"]=> array(21) { ["ID"]=> int(11364) ["id"]=> int(11364) ["title"]=> string(46) "yoda_project_coi_form_for_data_requestors_2019" ["filename"]=> string(50) "yoda_project_coi_form_for_data_requestors_2019.pdf" ["filesize"]=> int(436930) ["url"]=> string(99) "https://yoda.yale.edu/wp-content/uploads/2023/08/yoda_project_coi_form_for_data_requestors_2019.pdf" ["link"]=> string(92) "https://yoda.yale.edu/data-request/2021-4836/yoda_project_coi_form_for_data_requestors_2019/" ["alt"]=> string(0) "" ["author"]=> string(4) "1363" ["description"]=> string(0) "" ["caption"]=> string(0) "" ["name"]=> string(46) "yoda_project_coi_form_for_data_requestors_2019" ["status"]=> string(7) "inherit" ["uploaded_to"]=> int(5727) ["date"]=> string(19) "2023-08-09 17:38:15" ["modified"]=> string(19) "2023-08-09 19:13:44" ["menu_order"]=> int(0) ["mime_type"]=> string(15) "application/pdf" ["type"]=> string(11) "application" ["subtype"]=> string(3) "pdf" ["icon"]=> string(62) "https://yoda.yale.edu/wp/wp-includes/images/media/document.png" } } [1]=> array(1) { ["file_coi"]=> array(21) { ["ID"]=> int(9489) ["id"]=> int(9489) ["title"]=> string(36) "sv_6m4tghhxg7w7uxe-r_2eluuokwnngtsyq" ["filename"]=> string(40) "sv_6m4tghhxg7w7uxe-r_2eluuokwnngtsyq.pdf" ["filesize"]=> int(28770) ["url"]=> string(89) "https://yoda.yale.edu/wp-content/uploads/2017/01/sv_6m4tghhxg7w7uxe-r_2eluuokwnngtsyq.pdf" ["link"]=> string(82) "https://yoda.yale.edu/data-request/2021-4743/sv_6m4tghhxg7w7uxe-r_2eluuokwnngtsyq/" ["alt"]=> string(0) "" ["author"]=> string(4) "1363" ["description"]=> string(0) "" ["caption"]=> string(0) "" ["name"]=> string(36) "sv_6m4tghhxg7w7uxe-r_2eluuokwnngtsyq" ["status"]=> string(7) "inherit" ["uploaded_to"]=> int(5649) ["date"]=> string(19) "2023-07-31 15:44:53" ["modified"]=> string(19) "2023-08-01 01:00:41" ["menu_order"]=> int(0) ["mime_type"]=> string(15) "application/pdf" ["type"]=> string(11) "application" ["subtype"]=> string(3) "pdf" ["icon"]=> string(62) "https://yoda.yale.edu/wp/wp-includes/images/media/document.png" } } } ["data_use_agreement_training"]=> bool(true) ["certification"]=> bool(true) ["project_send_email_updates"]=> bool(true) ["project_status"]=> string(16) "withdrawn_closed" ["project_publ_available"]=> bool(true) ["project_year_access"]=> string(0) "" ["project_rep_publ"]=> array(1) { [0]=> array(1) { ["publication_link"]=> array(3) { ["title"]=> string(55) "*Request originally approved but subsequently withdrawn" ["url"]=> string(55) "*Request originally approved but subsequently withdrawn" ["target"]=> string(6) "_blank" } } } ["project_assoc_data"]=> array(0) { } ["project_due_dil_assessment"]=> bool(false) ["project_title_link"]=> bool(false) ["project_review_link"]=> bool(false) ["project_highlight_button"]=> string(0) "" ["search_order"]=> string(5) "-7750" } data partner
array(1) { [0]=> string(15) "johnson-johnson" }

pi country
array(1) { [0]=> string(14) "United Kingdom" }

pi affil
array(1) { [0]=> string(5) "Other" }

products
array(1) { [0]=> string(8) "razadyne" }

num of trials
array(1) { [0]=> string(1) "9" }

res
array(1) { [0]=> string(1) "3" }

2021-4743

General Information

How did you learn about the YODA Project?: PubMed

Conflict of Interest

Request Clinical Trials

Associated Trial(s):
  1. Long Term Safety and Efficacy of Galantamine in the treatment of Alzheimer's Disease
  2. NCT00253188 - Efficacy, Tolerability and Safety of Galantamine in the Treatment of Alzheimer's Disease
  3. NCT00253214 - Placebo-Controlled Evaluation of Galantamine in the Treatment of Alzheimer's Disease: Safety and Efficacy of a Controlled-Release Formulation
  4. NCT00236574 - A Randomized Double Blind Placebo-Controlled Trial to Evaluate the Efficacy and Safety of Galantamine in Patients With Mild Cognitive Impairment (MCI) Clinically at Risk for Development of Clinically Probable Alzheimer's Disease
  5. NCT00679627 - A Randomized, Double-Blind, Placebo-controlled Trial of Long-term (2-year) Treatment of Galantamine in Mild to Moderately-Severe Alzheimer's Disease
  6. NCT00216593 - Treatment of Severe Alzheimer's Disease in a Residential Home, Nursing Home, or Geriatric Residential Setting: Evaluation of Efficacy and Safety of Galantamine Hydrobromide in a Randomised, Doubleblind, Placebo-Controlled Study
  7. Placebo-controlled evaluation of galantamine in the treatment of Alzheimer’s disease: Evaluation of safety and efficacy under a slow titration regimen
  8. NCT00575055 - A Phase 3, Multicenter, Randomized, Double-Blind, Placebo-Controlled, Parallel-Group, Efficacy and Safety Trial of Bapineuzumab (AAB-001, ELN115727) In Patients With Mild to Moderate Alzheimer's Disease Who Are Apolipoprotein E4 Carriers
  9. NCT00574132 - A Phase 3, Multicenter, Randomized, Double-Blind, Placebo-Controlled, Parallel-Group, Efficacy and Safety Trial of Bapineuzumab (AAB-001, ELN115727) In Patients With Mild to Moderate Alzheimer's Disease Who Are Apolipoprotein E4 Non- Carriers
What type of data are you looking for?:

Request Clinical Trials

Data Request Status

Status: Withdrawn/Closed

Research Proposal

Project Title: Machine Learning Approaches to Predicting Treatment Outcomes in Alzheimer's Disease

Scientific Abstract: Background
Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development.
Objective
This research project will compare the effectiveness of a variety of ML methods to predict outcomes for Alzheimer's disease treatment. The results for different datasets will be compared for validation.
Study Design
Exploratory methods development.
Participants
Clinical trial participants
Main Outcome Measures
Treatment success (e.g. length of survival post-treatment)
Statistical Analysis
A range of ML algorithms (neural networks, random forest, KNN etc ) will be applied to the data in order to predict outcomes. The success of the different algorithms will be compared.

Brief Project Background and Statement of Project Significance: Background on Alzheimer?s disease
Alzheimer?s disease is a brain disorder that slowly destroys memory and thinking skills, and, eventually, the ability to carry out simple tasks. Symptoms usually first appear in the mid-60s. An estimated 6 million Americans have Alzheimer?s disease. Alzheimer?s disease is currently ranked as the sixth leading cause of death in the United States.
Background on the Treatment of Alzheimer?s disease
Alzheimer?s is complex, and it is therefore unlikely that any one drug or other intervention will successfully treat it in all people living with the disease. Many new treatments are being explored, however, current treatments are generally considered not to be very effective.
Several medications have been approved by the FDA to treat symptoms of Alzheimer?s. Donepezil, rivastigmine, and galantamine are used to treat the symptoms of mild to moderate Alzheimer?s. Donepezil, memantine, the rivastigmine patch, and a combination medication of memantine and donepezil are used to treat moderate to severe Alzheimer?s symptoms. These drugs work by regulating a neurotransmitter acetylcholine but do not change the underlying disease process.
Recently Aducanumab became the first disease-modifying therapy approved by the FDA for Alzheimer?s disease. This medication is claimed to reduce amyloid deposits in the brain and may help slow the progression of Alzheimer?s, although this has yet to be clearly established. Thus Alzheimer's remains difficult to treat. Also, a breakthrough in treatment is likely to require a significant amount of time to emerge: follow-up trials on Aducanumab are underway but results will likely not be available before 2030.
These considerations indicate that treatment for Alzheimer's is an important area for research. Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas
where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development.

Specific Aims of the Project: This research project will compare the effectiveness of a variety of ML methods to predict outcomes for Alzheimer?s treatment. The results for different datasets will be compared for validation. This is an exploratory project and does not have specific hypotheses. The objective is to explore the development of new ML methods for predicting outcomes. The potential benefits of this research are the development of methods for identifying subpopulations of patients in whom treatment would be more successful. This could enhance the development of 'personalized medicine'.

Study Design:

What is the purpose of the analysis being proposed? Please select all that apply.: Develop or refine statistical methods Research on clinical trial methods

Software Used: Python

Data Source and Inclusion/Exclusion Criteria to be used to define the patient sample for your study: All patients in the treatment arms of the trials will be included. Inclusion/Exclusion Criteria have already been defined by the studies.

Primary and Secondary Outcome Measure(s) and how they will be categorized/defined for your study: Time to death, if available. Otherwise, time to severe symptoms.

Main Predictor/Independent Variable and how it will be categorized/defined for your study: Not applicable - the aim is to perform analyses within the treatment arm only, therefore there is no Independent Variable. However, the concept we will attempt to predict is 'good response', a composite of adverse events and efficacy (good outcomes).

Other Variables of Interest that will be used in your analysis and how they will be categorized/defined for your study: NCT00236574 - CR003145 // GAL-INT-11 ?.
Standard predictors
- Sex
- Age
- Race
- Concomitant Medications
- Blood biochemistry
- Medical examination
Additional
- dosing regimen (16 or 24 mg/day)
- controlled-release (CR) or immediate-release (IR)
mild to moderate Alzheimer?s disease
NCT00679627 - GALALZ3005
Standard predictors, as above
Additional
- tobacco use
NCT00216593 - GAL-ALZ-302
Standard predictors, as above
Additional
- ECG
- Neurological exam
- Well being schedule
Brain MRI findings
NCT00236574 - CR003145 // GAL-INT-11
Standard predictors, as above
Additional
- ECG
- Neurological exam
Brain MRI findings
NCT00679627 - GALALZ3005 -
Standard predictors, as above
Additional
- tobacco use
NCT00216593 - GAL-ALZ-302 (PMID # 19042161-CR003940)
Standard predictors, as above
Additional
- ECG
GAL-USA-10
Standard predictors, as above
Additional
tobacco use
NCT00575055 - ELN115727-302 and NCT00574132 - ELN115727-301
Data Specification and Annotated CRF not yet available

Statistical Analysis Plan: Descriptive analyses on basic clinical features will be presented graphically, e.g. age distribution, number of participants in each arm and clinical outcomes (e.g. survival). T tests will be used to compare treatment groups (drug vs placebo) on factor which could present biases (e.g. age and demographics). Machine learning analyses are not typically done using conventional significance testing. It is more typical to report % accuracy, since this is usually so far above chance level that conventional measures of significance are uninformative. The best ML approach will be identified by using a range of well established algorithm types suitable for use with tabular data, including Logistic Regression, K-Nearest Neighbors (KNN), CatBoost, XGBoost and a Voting Classifier. This follows our previously published method.

Narrative Summary: Machine learning (ML) involves computer algorithms that can be 'trained' on data. ML algorithms build complex mathematical models, based on relatively simple rules, to make predictions. ML can be successful in many areas where conventional programming is ineffective due to the complexity of the problem. The application of ML has been touted as a coming revolution in many areas of medicine. However, this is a new area and methods still require development. This research project will compare datasets on Alzheimer's Disease as a way to develop new ML methods for predicting outcomes for Alzheimer's treatment. The results for different datasets will be compared for validation.

Project Timeline: Anticipated project start date, Sept 2021
Analysis completion date, Feb 2022
Date manuscript submitted for publication, May 2022
Results reported back to the YODA Project, May 2022

Dissemination Plan: Target audience is other researchers in this field of methods development for neurodegeneration.
The papers could be submitted to the journal Algorithms or Computational and Structural Biotechnology Journal.

Bibliography:

The key reference is Beacher, F.D.; Mujica-Parodi, L.R.; Gupta, S.; Ancora, L.A. Machine Learning Predicts Outcomes of Phase III Clinical Trials for Prostate Cancer. Algorithms 2021, 14, 147. https://doi.org/10.3390/a14050147. This paper contains a description of proposed methods and a proof of concept that this research is viable.