array(40) {
  ["project_status"]=>
  string(7) "ongoing"
  ["project_assoc_trials"]=>
  array(1) {
    [0]=>
    object(WP_Post)#4098 (24) {
      ["ID"]=>
      int(13163)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2023-08-09 22:12:42"
      ["post_date_gmt"]=>
      string(19) "2023-08-09 22:12:42"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(258) "NCT02407236 - A Phase 3, Randomized, Double-blind, Placebo-controlled, Parallel-group, Multicenter Protocol to Evaluate the Safety and Efficacy of Ustekinumab Induction and Maintenance Therapy in Subjects With Moderately to Severely Active Ulcerative Colitis"
      ["post_excerpt"]=>
      string(0) ""
      ["post_status"]=>
      string(7) "publish"
      ["comment_status"]=>
      string(6) "closed"
      ["ping_status"]=>
      string(6) "closed"
      ["post_password"]=>
      string(0) ""
      ["post_name"]=>
      string(193) "nct02407236-a-phase-3-randomized-double-blind-placebo-controlled-parallel-group-multicenter-protocol-to-evaluate-the-safety-and-efficacy-of-ustekinumab-induction-and-maintenance-therapy-in-subj"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2025-05-15 16:28:46"
      ["post_modified_gmt"]=>
      string(19) "2025-05-15 20:28:46"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(242) "https://dev-yoda.pantheonsite.io/clinical-trial/nct02407236-a-phase-3-randomized-double-blind-placebo-controlled-parallel-group-multicenter-protocol-to-evaluate-the-safety-and-efficacy-of-ustekinumab-induction-and-maintenance-therapy-in-subj/"
      ["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_title"]=>
  string(129) "Predicting likelihood of achieving remission from baseline information including endoscopy using an artificial intelligence model"
  ["project_narrative_summary"]=>
  string(701) "Currently available pharmaceutical treatments for ulcerative colitis (UC) and Crohn’s disease (CD) are known to achieve relatively low rates of remission (30% - 40%). Despite efforts to develop treatment algorithms and predictive biomarkers, clinicians lack tools to accurately predict drug response. While the Mayo Endoscopic Score (MES) and Simple Endoscopic Score for Crohn’s disease (SES-CD) standardize disease severity scoring, they do not provide predictive capabilities. We have developed an AI model that extracts information-dense feature representations from endoscopy. This study will assess the ability to use this AI model to predictively classify drug responders vs. non-responders."
  ["project_learn_source"]=>
  string(9) "colleague"
  ["principal_investigator"]=>
  array(7) {
    ["first_name"]=>
    string(4) "Matt"
    ["last_name"]=>
    string(8) "Schwartz"
    ["degree"]=>
    string(4) "B.E."
    ["primary_affiliation"]=>
    string(36) "Virgo Surgical Video Solutions, Inc."
    ["email"]=>
    string(17) "matt@virgosvs.com"
    ["state_or_province"]=>
    string(2) "CA"
    ["country"]=>
    string(13) "United States"
  }
  ["project_key_personnel"]=>
  array(3) {
    [0]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(5) "Safia"
      ["p_pers_l_name"]=>
      string(5) "Speer"
      ["p_pers_degree"]=>
      string(23) "Master of Public Health"
      ["p_pers_pr_affil"]=>
      string(5) "Virgo"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [1]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(7) "Patrick"
      ["p_pers_l_name"]=>
      string(7) "Dermyer"
      ["p_pers_degree"]=>
      string(2) "BS"
      ["p_pers_pr_affil"]=>
      string(5) "Virgo"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [2]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(5) "Angad"
      ["p_pers_l_name"]=>
      string(5) "Singh"
      ["p_pers_degree"]=>
      string(2) "MS"
      ["p_pers_pr_affil"]=>
      string(6) "Virgo "
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
  }
  ["project_ext_grants"]=>
  array(2) {
    ["value"]=>
    string(2) "no"
    ["label"]=>
    string(68) "No external grants or funds are being used to support this research."
  }
  ["project_date_type"]=>
  string(18) "full_crs_supp_docs"
  ["property_scientific_abstract"]=>
  string(1632) "Background:

We have developed an AI model capable of extracting meaningful representational features from endoscopy videos, which can then be used to make predictions or classifications about those procedures. If this model can accurately predict endoscopic disease scoring, patient characteristics, and drug response in patients with UC, it could help advance clinical trial design and treatment algorithms. 



Objective:

We aim to study the efficacy of this AI model to take baseline information, including endoscopy imaging, as input, and output predictions of endoscopic disease score, patient characteristics, and drug response.



Study Design:

This is a retrospective analysis of endoscopy videos and images from a phase 3 trial of ustekinumab for the treatment of UC. All videos and images will be processed by our AI model to extract visual features. These features will be used to classify endoscopic disease score, patient characteristics, and drug response.



Participants:

All participants from a phase 3 trias of ustekinumab for UC with endoscopy data.



Primary Outcomes:

The area under the receiver operating characteristic (AUROC) will be reported for all classification evaluations.



Secondary Outcomes:

Sensitivity, specificity, precision, and recall will be reported as secondary evaluation metrics.



Statistical Analysis:

Full confusion matrix including AUROC, F1 score, sensitivity, specificity, precision, and recall. Random split 80/10/10 into training, validation, and test sets."
  ["project_brief_bg"]=>
  string(3009) "Currently available treatment options for UC and CD patients achieve only modest rates of clinical and endoscopic response. For example, in its phase 3 UC induction study, patients assigned to golimumab (200/100mg and 400/200mg) achieved 51.0% and 54.9% clinical response, respectively at six weeks, compared to 30.3% for placebo [1]. Furthermore, in the phase 3 UC maintenance study of golimumab (50mg and 100mg), clinical response was maintained in only 47.0% and 49.7% of patients, respectively at 54 weeks, compared to 31.2% for placebo [2]. Combined, this means we can expect only 24.0% to 27.3% of golimumab UC patients to successfully achieve and maintain clinical response over 54 weeks. Similar results are seen across a wide range of UC and CD treatment options.



Attempts to characterize UC and CD based on genetic sequencing have advanced scientific understanding of these diseases and contributing genes, but they have not yet yielded any predictive capabilities for drug response [3]. Current FDA guidelines for developing drugs to treat UC and CD define clinical remission in part based on endoscopic disease activity scoring using the MES and SES-CD, respectively [4,5]. These scoring systems (and many others) have been extensively studied as measurement tools for disease activity in UC and CD; however, they have not been fully validated or established as tools for measuring responsiveness [6].



We have developed an AI model to extract information-dense visual features from endoscopy. This model was trained in a self-supervised fashion on a curated dataset of frames sampled from a pool of over 120,000 unique endoscopic procedures, representing over 3.2 billion total frames. Because it has been trained on an extremely diverse endoscopy dataset, our model serves as a powerful backbone feature extractor for training new models with limited data.



In this study, we will leverage endoscopy data from a phase 3 trial of ustekinumab for UC who have undergone endoscopic evaluation to assess the efficacy of our AI model in predicting endoscopic disease score, patient characteristics, and drug response. For all prediction tasks, we will split the available data into random splits of 80/10/10 for training, validation, and testing. For tasks where data is limited, we will conduct k-fold cross validation.



This study will determine whether our AI model is capable of automatically replicating the MES with high efficacy. It will also help determine whether there are other visual features present in endoscopy that can predict patient characteristics such as age, sex, race and comorbidities. Finally and most importantly, this study will examine whether there are visual endoscopic features present at baseline that can help determine which patients are most likely to respond to specific drugs. If true, this could help advance future trial design and ultimately lead to significantly higher response rates for IBD treatments."
  ["project_specific_aims"]=>
  string(379) "1) To evaluate the efficacy of our AI model for predicting the centrally read MES.

2) To determine the ability for our AI model to accurately predict patient characteristics such as age, sex, race, and comorbidities.

3) To evaluate the efficacy of our AI model for predicting which trial subjects will respond to treatment based on their baseline endoscopy.

"
  ["project_study_design"]=>
  array(2) {
    ["value"]=>
    string(8) "meth_res"
    ["label"]=>
    string(23) "Methodological research"
  }
  ["project_purposes"]=>
  array(3) {
    [0]=>
    array(2) {
      ["value"]=>
      string(56) "new_research_question_to_examine_treatment_effectiveness"
      ["label"]=>
      string(114) "New research question to examine treatment effectiveness on secondary endpoints and/or within subgroup populations"
    }
    [1]=>
    array(2) {
      ["value"]=>
      string(34) "research_on_clinical_trial_methods"
      ["label"]=>
      string(34) "Research on clinical trial methods"
    }
    [2]=>
    array(2) {
      ["value"]=>
      string(50) "research_on_clinical_prediction_or_risk_prediction"
      ["label"]=>
      string(50) "Research on clinical prediction or risk prediction"
    }
  }
  ["project_research_methods"]=>
  string(174) "Only trial data made available through the YODA Project will be used.



Inclusion criteria: patients with endoscopic images/video

Exclusion criteria: none"
  ["project_main_outcome_measure"]=>
  string(876) "Primary Outcome Measures:



The area under the receiver operating curve (AUROC) for predicting:

1) Centrally read MES and scores

2) Patient characteristics such as age, sex, gender, race, comorbidities, and biomarker panel

3) Response to treatment based on baseline endoscopy



An AUROC that is statistically significantly greater than 0.5 will be classified as better than chance. An AUROC of 0.6 to 0.7 will be considered of interest and worth additional study, 0.7 to 0.8 will be considered good, 0.8 to 0.9 will be considered excellent, and >0.9 will be considered outstanding.



Secondary Outcome Measures:



For each category of classification, we will report the full confusion matrix, sensitivity, specificity, precision, and recall for training, validation, and test subsets.



"
  ["project_main_predictor_indep"]=>
  string(220) "The main independent variable will be achievement of clinical or endoscopic response or remission as defined in the phase 3 ustekinumab study. These are generally defined based on clinical and endoscopic scoring indices."
  ["project_other_variables_interest"]=>
  string(1144) "Other variables of interest will include:

-MES

-Subscores of the Mayo Score (e.g. stool frequency, rectal bleeding, and physician global assessment)

-Age and sex

-Race and ethnicity

-Other comorbidities

-Biomarker panels

-Disease duration

-Previous and concomitant treatment exposures

-Disease extent UC (left sided vs. extensive/pancolitis for UC)



The purpose of studying whether our AI model is capable of predicting patient characteristics such as age, sex, race/ethnicity, and comorbidities is to serve as a proof of concept for whether there may also be other available biomarker signals in endoscopy that are not readily apparent to human experts. To our knowledge, no prior study has been made as to whether these types of patient characteristics can be ascertained from endoscopy data. If successful, our results would help advance scientific understanding of endoscopic differences between patient demographics that are clinically relevant. Analogous work has been done in retinal imaging to predict cardiovascular risk, age, gender, and smoking status [7]."
  ["project_stat_analysis_plan"]=>
  string(791) "Study selection: phase 3 clinical trial of ustekinumab for the treatment of UC with endoscopy data.



We will apply the following statistical analyses through a full confusion matrix: AUROC, sensitivity, specificity, precision, recall, and F1 score. We will also report inference results from our AI model for select examples of true positives, false positives, true negatives, and false negatives to provide representative examples of the model working and not working.



It is important to note that the prediction of patient characteristics such as age, sex, race/ethnicity, and comorbidities will only use the already provided de-identified trial data. No attempts will be made to re-identify the de-identified data that is provided, nor would this be possible."
  ["project_software_used"]=>
  array(1) {
    [0]=>
    array(2) {
      ["value"]=>
      string(6) "python"
      ["label"]=>
      string(6) "Python"
    }
  }
  ["project_timeline"]=>
  string(376) "Project Start Date: August 1, 2024

Initial Analysis: August 15, 2024

Analysis Completion: August 30, 2024

Manuscript Drafted: September 15, 2024

Abstract Submitted to ECCO: November 15, 2024

Manuscript Submitted for Publication: November 30, 2024

Results Reported to YODA: December 15, 2024

Project Completed: December 30, 2024"
  ["project_dissemination_plan"]=>
  string(477) "We anticipate that this project will lead to a manuscript submitted in either a clinical gastroenterology or artificial intelligence journal. We intend to submit the draft manuscript to medrxiv.org (founded by Cold Spring Harbor Laboratory, Yale University, and BMJ). We also plan to share our results at relevant conferences, such as European Crohn’s and Colitis Organization, Crohn’s and Colitis Congress, Digestive Disease Week, and American College of Gastroenterology."
  ["project_bibliography"]=>
  string(2508) "

Sandborn WJ, Feagan BG, Marano C, Zhang H, Strauss R, Johanns J, Adedokun OJ, Guzzo C, Colombel JF, Reinisch W, Gibson PR, Collins J, Järnerot G, Hibi T, Rutgeerts P; PURSUIT-SC Study Group. Subcutaneous golimumab induces clinical response and remission in patients with moderate-to-severe ulcerative colitis. Gastroenterology. 2014 Jan;146(1):85-95; quiz e14-5. doi: 10.1053/j.gastro.2013.05.048. Epub 2013 Jun 2. PMID: 23735746.
Sandborn WJ, Feagan BG, Marano C, Zhang H, Strauss R, Johanns J, Adedokun OJ, Guzzo C, Colombel JF, Reinisch W, Gibson PR, Collins J, Järnerot G, Rutgeerts P; PURSUIT-Maintenance Study Group. Subcutaneous golimumab maintains clinical response in patients with moderate-to-severe ulcerative colitis. Gastroenterology. 2014 Jan;146(1):96-109.e1. doi: 10.1053/j.gastro.2013.06.010. Epub 2013 Jun 14. PMID: 23770005.
Dubinsky MC, Collins R, Abreu MT; International Organization for the Study of Inflammatory Bowel Diseases (IOIBD). Challenges and Opportunities in IBD Clinical Trial Design. Gastroenterology. 2021 Aug;161(2):400-404. doi: 10.1053/j.gastro.2021.03.065. Epub 2021 Apr 20. PMID: 33864796.
Ulcerative Colitis: Developing Drugs for Treatment Guidance for Industry. FDA Draft Guidance. 2022 April. https://www.fda.gov/media/158016/download.
Crohn’s Disease: Developing Drugs for Treatment Guidance for Industry. FDA Draft guidance. 2022 April. https://www.fda.gov/media/158001/download.
Mohammed Vashist N, Samaan M, Mosli MH, Parker CE, MacDonald JK, Nelson SA, Zou GY, Feagan BG, Khanna R, Jairath V. Endoscopic scoring indices for evaluation of disease activity in ulcerative colitis. Cochrane Database Syst Rev. 2018 Jan 16;1(1):CD011450. doi: 10.1002/14651858.CD011450.pub2. PMID: 29338066; PMCID: PMC6491285.
Poplin R, Varadarajan AV, Blumer K, Liu Y, McConnell MV, Corrado GS, Peng L, Webster DR. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng. 2018 Mar;2(3):158-164. doi: 10.1038/s41551-018-0195-0. Epub 2018 Feb 19. PMID: 31015713.

"
  ["project_suppl_material"]=>
  array(1) {
    [0]=>
    array(1) {
      ["suppl_file"]=>
      array(21) {
        ["ID"]=>
        int(15450)
        ["id"]=>
        int(15450)
        ["title"]=>
        string(69) "YODA-Project-Protocol-2024-0668-Additional-Information-Statement.docx"
        ["filename"]=>
        string(69) "YODA-Project-Protocol-2024-0668-Additional-Information-Statement.docx"
        ["filesize"]=>
        int(7734)
        ["url"]=>
        string(118) "https://yoda.yale.edu/wp-content/uploads/2024/08/YODA-Project-Protocol-2024-0668-Additional-Information-Statement.docx"
        ["link"]=>
        string(115) "https://yoda.yale.edu/data-request/2024-0668/yoda-project-protocol-2024-0668-additional-information-statement-docx/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1824"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(69) "yoda-project-protocol-2024-0668-additional-information-statement-docx"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(15250)
        ["date"]=>
        string(19) "2024-08-05 17:15:30"
        ["modified"]=>
        string(19) "2024-08-05 17:15:30"
        ["menu_order"]=>
        int(0)
        ["mime_type"]=>
        string(71) "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
        ["type"]=>
        string(11) "application"
        ["subtype"]=>
        string(59) "vnd.openxmlformats-officedocument.wordprocessingml.document"
        ["icon"]=>
        string(62) "https://yoda.yale.edu/wp/wp-includes/images/media/document.png"
      }
    }
  }
  ["project_coi"]=>
  array(4) {
    [0]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(15292)
        ["id"]=>
        int(15292)
        ["title"]=>
        string(25) "MattSchwartz-YODA-COI.pdf"
        ["filename"]=>
        string(25) "MattSchwartz-YODA-COI.pdf"
        ["filesize"]=>
        int(29617)
        ["url"]=>
        string(74) "https://yoda.yale.edu/wp-content/uploads/2024/07/MattSchwartz-YODA-COI.pdf"
        ["link"]=>
        string(71) "https://yoda.yale.edu/data-request/2024-0668/mattschwartz-yoda-coi-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1824"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(25) "mattschwartz-yoda-coi-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(15250)
        ["date"]=>
        string(19) "2024-07-03 11:42:03"
        ["modified"]=>
        string(19) "2024-07-03 11:42:05"
        ["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(16003)
        ["id"]=>
        int(16003)
        ["title"]=>
        string(6) "PD COI"
        ["filename"]=>
        string(10) "PD-COI.pdf"
        ["filesize"]=>
        int(27750)
        ["url"]=>
        string(59) "https://yoda.yale.edu/wp-content/uploads/2024/06/PD-COI.pdf"
        ["link"]=>
        string(52) "https://yoda.yale.edu/data-request/2024-0668/pd-coi/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1885"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(6) "pd-coi"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(15250)
        ["date"]=>
        string(19) "2024-11-19 16:32:46"
        ["modified"]=>
        string(19) "2024-11-19 16:32:46"
        ["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"
      }
    }
    [2]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(16004)
        ["id"]=>
        int(16004)
        ["title"]=>
        string(6) "SS COI"
        ["filename"]=>
        string(10) "SS-COI.pdf"
        ["filesize"]=>
        int(27956)
        ["url"]=>
        string(59) "https://yoda.yale.edu/wp-content/uploads/2024/06/SS-COI.pdf"
        ["link"]=>
        string(52) "https://yoda.yale.edu/data-request/2024-0668/ss-coi/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1885"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(6) "ss-coi"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(15250)
        ["date"]=>
        string(19) "2024-11-19 16:32:48"
        ["modified"]=>
        string(19) "2024-11-19 16:32:48"
        ["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"
      }
    }
    [3]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(16118)
        ["id"]=>
        int(16118)
        ["title"]=>
        string(6) "AS COI"
        ["filename"]=>
        string(10) "AS-COI.pdf"
        ["filesize"]=>
        int(27785)
        ["url"]=>
        string(59) "https://yoda.yale.edu/wp-content/uploads/2024/06/AS-COI.pdf"
        ["link"]=>
        string(52) "https://yoda.yale.edu/data-request/2024-0668/as-coi/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1885"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(6) "as-coi"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(15250)
        ["date"]=>
        string(19) "2024-12-02 15:45:31"
        ["modified"]=>
        string(19) "2024-12-02 15:45:31"
        ["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)
  ["search_order"]=>
  string(1) "0"
  ["project_send_email_updates"]=>
  bool(false)
  ["project_publ_available"]=>
  bool(true)
  ["project_year_access"]=>
  string(4) "2024"
  ["project_rep_publ"]=>
  bool(false)
  ["project_assoc_data"]=>
  array(0) {
  }
  ["project_due_dil_assessment"]=>
  array(21) {
    ["ID"]=>
    int(15896)
    ["id"]=>
    int(15896)
    ["title"]=>
    string(47) "YODA Project Due Diligence Assessment 2024-0668"
    ["filename"]=>
    string(51) "YODA-Project-Due-Diligence-Assessment-2024-0668.pdf"
    ["filesize"]=>
    int(145054)
    ["url"]=>
    string(100) "https://yoda.yale.edu/wp-content/uploads/2024/06/YODA-Project-Due-Diligence-Assessment-2024-0668.pdf"
    ["link"]=>
    string(93) "https://yoda.yale.edu/data-request/2024-0668/yoda-project-due-diligence-assessment-2024-0668/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(47) "yoda-project-due-diligence-assessment-2024-0668"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(15250)
    ["date"]=>
    string(19) "2024-11-05 17:27:06"
    ["modified"]=>
    string(19) "2024-11-05 17:27:06"
    ["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"
  }
  ["project_title_link"]=>
  array(21) {
    ["ID"]=>
    int(16119)
    ["id"]=>
    int(16119)
    ["title"]=>
    string(42) "YODA Project Protocol 2024-0668 - 24-11-27"
    ["filename"]=>
    string(44) "YODA-Project-Protocol-2024-0668-24-11-27.pdf"
    ["filesize"]=>
    int(127953)
    ["url"]=>
    string(93) "https://yoda.yale.edu/wp-content/uploads/2024/06/YODA-Project-Protocol-2024-0668-24-11-27.pdf"
    ["link"]=>
    string(86) "https://yoda.yale.edu/data-request/2024-0668/yoda-project-protocol-2024-0668-24-11-27/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(40) "yoda-project-protocol-2024-0668-24-11-27"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(15250)
    ["date"]=>
    string(19) "2024-12-02 15:50:47"
    ["modified"]=>
    string(19) "2024-12-02 15:50:47"
    ["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"
  }
  ["project_review_link"]=>
  array(21) {
    ["ID"]=>
    int(15897)
    ["id"]=>
    int(15897)
    ["title"]=>
    string(36) "YODA Project Review - 2024-0668_SITE"
    ["filename"]=>
    string(38) "YODA-Project-Review-2024-0668_SITE.pdf"
    ["filesize"]=>
    int(1838705)
    ["url"]=>
    string(87) "https://yoda.yale.edu/wp-content/uploads/2024/06/YODA-Project-Review-2024-0668_SITE.pdf"
    ["link"]=>
    string(80) "https://yoda.yale.edu/data-request/2024-0668/yoda-project-review-2024-0668_site/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(34) "yoda-project-review-2024-0668_site"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(15250)
    ["date"]=>
    string(19) "2024-11-05 17:40:52"
    ["modified"]=>
    string(19) "2024-11-05 17:40:52"
    ["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"
  }
  ["project_highlight_button"]=>
  string(0) ""
  ["request_data_partner"]=>
  string(15) "johnson-johnson"
  ["human_research_protection_training"]=>
  bool(false)
  ["request_overridden_res"]=>
  string(1) "3"
}
data partner
array(1) {
  [0]=>
  string(15) "johnson-johnson"
}


pi country
array(0) {
}


pi affil
array(0) {
}


products
array(1) {
  [0]=>
  string(7) "stelara"
}


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


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