array(42) {
  ["project_status"]=>
  string(7) "ongoing"
  ["project_assoc_trials"]=>
  array(1) {
    [0]=>
    object(WP_Post)#4157 (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(143) "External Validation of novel Endo-Histo AI fusion model for predicting histologic remission and early response to therapy in Ulcerative Colitis"
  ["project_narrative_summary"]=>
  string(837) "Accurate disease assessment is crucial for managing UC and determining treatment response in clinical trials. Endoscopic and histological scores are complex and burdened by variability. This study aims to validate our new AI model that integrates endoscopic and histological data to objectively assess activity and predict treatment response in UC. Furthermore, it aims to validate our model to detect and localise neutrophils, determining a cutoff to define histological remission and predict treatment response. Moreover, we propose to enhance the prediction of response to therapy by integrating AI outputs with clinical, laboratory, and Omics data (genomics, RNA transcriptomics, proteomics). This multidimensional approach aims to identify biological signatures associated to treatment outcomes, supporting precision medicine in UC."
  ["project_learn_source"]=>
  string(5) "other"
  ["project_learn_source_exp"]=>
  string(0) ""
  ["principal_investigator"]=>
  array(7) {
    ["first_name"]=>
    string(8) "Marietta"
    ["last_name"]=>
    string(7) "Iacucci"
    ["degree"]=>
    string(4) "Prof"
    ["primary_affiliation"]=>
    string(94) "APC Microbiome Ireland, College of Medicine and Health, University College Cork, Cork, Ireland"
    ["email"]=>
    string(17) "iacuccim@yahoo.it"
    ["state_or_province"]=>
    string(4) "Cork"
    ["country"]=>
    string(7) "Ireland"
  }
  ["project_key_personnel"]=>
  array(3) {
    [0]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(6) "Enrico"
      ["p_pers_l_name"]=>
      string(6) "Grisan"
      ["p_pers_degree"]=>
      string(4) "Prof"
      ["p_pers_pr_affil"]=>
      string(63) "School of Engineering, London South Bank University, London, UK"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [1]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(6) "Valery"
      ["p_pers_l_name"]=>
      string(7) "Naranjo"
      ["p_pers_degree"]=>
      string(4) "Prof"
      ["p_pers_pr_affil"]=>
      string(136) "Instituto Universitario de Investigacion e Innovacion en Bioingenieria, HUMAN-tech, Universitat Politecnica de Valencia, Valencia, Spain"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [2]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(5) "Pablo"
      ["p_pers_l_name"]=>
      string(14) "Meseguer Esbri"
      ["p_pers_degree"]=>
      string(3) "MSc"
      ["p_pers_pr_affil"]=>
      string(35) "Universitat Politecnica de Valencia"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
  }
  ["project_ext_grants"]=>
  array(2) {
    ["value"]=>
    string(3) "yes"
    ["label"]=>
    string(65) "External grants or funds are being used to support this research."
  }
  ["project_funding_source"]=>
  string(40) "Start up funds of Prof. Marietta Iacucci"
  ["project_date_type"]=>
  string(18) "full_crs_supp_docs"
  ["property_scientific_abstract"]=>
  string(1638) "Background: Mucosal healing is crucial in UC, making objective disease assessment paramount, particularly in clinical trial. Moreover, the integration of Omics, endoscopic, histological data is crucial to identify predictors of treatment response. We developed AI models integrating endoscopic/histological data to localize/quantify neutrophils to assess activity and predict treatment response. Models were developed and tested on phase II trial of mirikizumab in UC, showing promising results. Objective: Validate models’ performance on an external cohort (phase III trial on efficacy and safety of Ustekinumab as induction and maintenance treatment in UC). Develop predictive models by integrating AI endoscopic/histological assessment with Omics data.

Study design: retrieve endoscopy videos, WSI (W0, W8, W52), laboratory and Omics data. 

Participants: patients enrolled in this trial with endoscopic and histological data available at W0, W8 and W52.

Primary outcome: assess models' ability to determine activity through validated scores combining endoscopic-histological data or based on automated neutrophil cutoff.

Secondary outcome: assess the models’ ability to predict treatment response as histological improvement/remission through validated scores. Identify predictors of response to therapy by integrating Omics data.

Statistics: diagnostic performance will be reported as sensitivity, specificity, PPV, NPV, accuracy, F1 score.  Kappa agreement with expert will be evaluated. Predictive modelling will involve machine learning techniques, logistic regression and survival analysis. "
  ["project_brief_bg"]=>
  string(3227) "Accurately assessing endoscopic and histological activity is critical for disease management in Ulcerative Colitis (UC)(1). Precise evaluation informs clinical decision-making and ensures objective assessment of treatment response in clinical trials(2). Endoscopic and histologic scoring systems are complex and burdened by interobserver variability, highlighting the need for standardised evaluation(3,4). Clinical trials often mitigate interobserver variability through expert central readouts. While this helps achieve greater consistency, it is expensive and still subject to variability. Moreover, neutrophils are considered key cells to determine histological remission (HR)(3). Indeed, the PICaSSO Histological Remission Index (PHRI) focused only on neutrophils and showed a good ability to assess disease activity and predict outcomes(5). However, the potential role of number and localisation of neutrophils (epithelial and lamina propria) in defining disease remission is still unexplored. 

Several AI models have been developed to assess disease activity based on validated scores or evaluating specific cellular features(6). Recently, starting from data from the phase II trial on efficacy and safety of mirikizumab in UC, we developed an innovative AI model based on a foundational framework that integrates endoscopic and histological data. The new fusion model outperformed single-modality assessments to assess HR, achieving sensitivity 89.7% (95% CI 82.3–94.7), specificity 89.6% (95% CI 84.3–93.6), and accuracy 89.6% (95% CI 85.6–92.9). It demonstrated remarkable performance in assessing response to therapy, achieving sensitivity 97.9% (95% CI 89.1–99.9), specificity 86.8% (95% CI 71.9–95.5) and accuracy 93.1% (95% CI 85.5–97.4) for predicting HR at W52.  

Furthermore, we developed a novel AI-driven model to standardize the detection, localization, and quantification of neutrophils, supporting objective evaluations of histological activity and enabling prediction of early therapy response predictions in the same trial. Our new model showed remarkable ability to localize (DICE score 67.6%) and detect (F1 score 72%) neutrophils. We identified optimal neutrophil density cutoffs (cells/mm²) to indicate disease activity and response to therapy.

Validating these AI-driven algorithms in external clinical trial cohorts of UC patients could further standardize and optimize disease assessment in UC. This approach would reduce variability and improve precision of treatment allocation in clinical trials, reducing costs of expert central readout and advance disease evaluation.  Moreover, there is increasing evidence on the role of multi-omics data as crucial elements in predicting response to therapy [9]. Genetic variations and mRNA expression patterns can significantly contribute to the response to therapy. Therefore, we aim to identify biological markers predictive of treatment success or failure by integrating omics data (genomic, transcriptomic, proteomic) profiles with clinical and imaging data. 

Ultimately, this work has the potential to enhance clinical trial outcomes and support tailored, evidence-based treatment strategies for UC patients."
  ["project_specific_aims"]=>
  string(1584) "Validate in an external clinical trial UC cohort the endo-histo fusion model, and the automated neutrophil detection and localization developed on a phase II UC trial by assessing performance on data from the phase III trial on efficacy and safety of Ustekinumab as induction and maintenance treatment in UC. We plan to retrieve endoscopic videos and WSI from W0, W8 and W52. We would like to retrieve data on endoscopic activity evaluated by MES, UCEIS, and histological activity evaluated by Geboes score. We would like to retrieve demographic data (country, year of birth, age, sex, BMI, smoking status, race, year of diagnosis), clinical information (Partial Mayo score, IBDQ score [total and single items], lab data (fecal calprotectin, CRP) and treatment information (prior biologic exposure, current treatments). We aim to assess the model's performance to assess disease activity and remission according to established endoscopic scores and histological scores, such as Geboes(7) and PHRI(5). We aim to retrieve Omics data (genomic, transcriptomic, proteomic) to build predictive models of response integrating Omics, clinical, lab, and AI-derived imaging data. Specifically, we would like to evaluate serum biomarkers for proteins associated with proinflammatory/anti-inflammatory effects, as well as recruitment and proliferation of cells involved in inflammation and repair. Additionally, we aim to assess markers associated with tissue injury or repair. Furthermore, we will examine mucosal biopsy RNA for mRNA/microRNA expression patterns and conduct genetic evaluations."
  ["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(76) "confirm_or_validate previously_conducted_research_on_treatment_effectiveness"
      ["label"]=>
      string(76) "Confirm or validate previously conducted research on treatment effectiveness"
    }
    [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(1336) "Inclusion and exclusion criteria will be the ones considered by the trial. Patients enrolled in this phase III trial with available demographic data, endoscopy videos and histological WSIs at W0, W8 and W52 will be included. Namely, adults with moderate-severe UC (Mayo score 6-12 and MES >=2 at W0) with failure/intolerance to conventional treatment, regardless of prior biologic use. Excluded patients will be the ones without demographic, endoscopic and histological features at the predefined time-points, as well as the ones excluded according to trial criteria.

Endoscopic videos and histological WSI at W0, W8 and W52 will be used. Data on disease activity assessed through MES and UCEIS and histological activity assessed by Geboes will be retrieved, as well as single items of each score.

Moreover, demographic characteristics (country, year of birth, age, sex, weight, height, smoking status, race, year of UC diagnosis), clinical information (PMS, IBDQ score [total+single items - bowel symptoms;systemic symptoms;emotional function;social function]), laboratory data (FC, CRP) and treatment information (prior biologic exposure; use of steroids/mesalamine/thiopurines) will be retrieved. Where available, multi-Omics (genomic, transcriptomics, proteomics) data at the same time point will also be retrieved."
  ["project_main_outcome_measure"]=>
  string(1272) "The primary outcome is to assess the AI foundational fusion and neutrophil detection/localization algorithms’ ability in assessing disease activity trough validated score combining endoscopic and histological data. 

Endoscopic activity will be evaluated through MES and UCEIS, and endoscopic remission will be defined as MES 0 and UCEIS <=1.

Histological activity will be evaluated through Geboes score and PHRI, and histological remission will be defined as Geboes <=2B.0 and PHRI 0.

The secondary outcome is to assess their ability in detecting, localizing and quantifying neutrophils to evaluate disease activity and remission and predict response to therapy in terms of histological improvement and remission through validated histological scores (Geboes and PHRI). Histological activity will be evaluated through Geboes score and PHRI, and histological remission will be defined as Geboes <=2B.0 and PHRI 0. Histological improvement will be defined as Geboes < 3.1 and PHRI <=1. Another secondary outcome will be to evaluate lab, and multi-omics data to identify predictors of response to therapy and fuse these data with AI-enabled assessment of endoscopic and histological activity to develop a comprehensive predictive model. "
  ["project_main_predictor_indep"]=>
  string(340) "The main predictors of the study include endoscopic and histologic disease severity at baseline and W8-52. Endoscopic remission will be defined as MES 0 and UCES <= 1, while 

histological remission will be defined as Geboes <=2B.0 and PHRI 0. Histological improvement will be defined as Geboes <3.1 and PHRI <= 1.

"
  ["project_other_variables_interest"]=>
  string(703) "Other variables such as age, sex, body mass index (BMI), smoking status, disease location, disease duration, partial Mayo score, IBDQ score (total and items), fecal calprotectin, C-reactive protein, treatment allocation, prior biologic exposure, concomitant treatments (immunomodulators, steroids or mesalamine), will be used for descriptive statistics to describe the study population. Continuous variables will be represented as means/standard deviations (or medians/interquartile ranges) and categorical variables will be represented as proportions and percentages. Omics data (genomic, transcriptomic, proteomic) at baseline and follow-up will be used to identify predictors of response to therapy. "
  ["project_stat_analysis_plan"]=>
  string(1358) "The foundational model previously developed will be applied in the new cohort of data.

The diagnostic performance of the AI-enabled Endo-Histo fusion model will be reported as sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy and F1 score. The 95% confidence intervals (CIs) for each metric will be calculated.

Inter-rater agreement between the AI model and central readout in assessing histological remission and response to therapy at weeks 8 and 52 will be calculated according to Cohen’s Kappa (K). Results will be presented as K coefficient, 95% confidence interval and p-values. K values above 0.41 signify moderate agreement, K values higher than 0.61 correspond to substantial agreement, and values above 0.81 represent almost perfect agreement, according to Landis and Koch’s criteria. A p-value <0.05 will be considered statistically significant. Optimal cell density cut-offs for neutrophils will be determined by the Youden Index to assess disease activity and to predict early response to therapy at weeks 8 and 52. Data derived from the Endo-Histo fusion model will be integrated with clinical, laboratory and multi-Omics data (genomic, proteomic, transcriptomic), through machine learning techniques to better identify predictors of response to therapy at weeks 8 and 52."
  ["project_software_used"]=>
  array(1) {
    [0]=>
    array(2) {
      ["value"]=>
      string(1) "r"
      ["label"]=>
      string(1) "R"
    }
  }
  ["project_timeline"]=>
  string(398) "Project Timeline

Start date - February 2025

Analysis completion date - March 2025

Manuscript draft - April 2025

Submitted for publication - April/May 2025



Updated Project Timeline

Start date – August 2025

Analysis completion date – October 2025

Manuscript draft – November 2025

Submitted for publication – December 2025"
  ["project_dissemination_plan"]=>
  string(384) "Results arising from this study may be presented as abstracts and papers to target audiences. These may be submitted to relevant conferences such as European Crohn’s Colitis Organization (ECCO) and Digestive Disease Week. A manuscript may also be submitted for publication. The YODA Project will be acknowledged in all study products, which will be shared at the time of submission."
  ["project_bibliography"]=>
  string(2667) "

Turner D, Ricciuto A, Lewis A, et al. STRIDE-II: An Update on the Selecting Therapeutic Targets in Inflammatory Bowel Disease (STRIDE) Initiative of the International Organization for the Study of IBD (IOIBD): Determining Therapeutic Goals for Treat-to-Target strategies in IBD. Gastroenterology 2021;160:1570–1583.
Adamina M, Feakins R, Iacucci M, et al. ECCO Topical Review Optimising Reporting in Surgery, Endoscopy, and Histopathology. J Crohns Colitis 2021;15:1089–1105. Available at: https://academic.oup.com/ecco-jcc/article/15/7/1089/6081305.
Magro F, Doherty G, Peyrin-Biroulet L, et al. ECCO Position Paper: Harmonization of the Approach to Ulcerative Colitis Histopathology. J Crohns Colitis 2020;14:1503–1511.
Feakins R, Borralho Nunes P, Driessen A, et al. Definitions of Histological Abnormalities in Inflammatory Bowel Disease: an ECCO Position Paper. J Crohns Colitis 2024;18:175–191. Available at: https://academic.oup.com/ecco-jcc/article/18/2/175/7247579.
Gui X, Bazarova A, Amor R del, et al. PICaSSO Histologic Remission Index (PHRI) in ulcerative colitis: development of a novel simplified histological score for monitoring mucosal healing and predicting clinical outcomes and its applicability in an artificial intelligence system. Gut 2022;71:889–898.
Iacucci M, Santacroce G, Zammarchi I, et al. Artificial intelligence and endo-histo-omics: new dimensions of precision endoscopy and histology in inflammatory bowel disease. Lancet Gastroenterol Hepatol 2024. Available at: https://linkinghub.elsevier.com/retrieve/pii/S2468125324000530.
Iacucci M, Santacroce G, Meseguer P, et al. P0340 Endo-Histo Foundational Fusion Model: A Novel Artificial Intelligence Approach for Predicting Histologic Remission and Early Response to Therapy in a Phase 2 Ulcerative Colitis Clinical Trial. J Crohns Colitis 2025;19:i806–i807.
Iacucci M, Vadori V, Meseguer P, et al. DOP045 Novel AI-Driven Detection, Localisation and Quantification of Neutrophils for Prediction of Early Response to Therapy in a Phase 2 Ulcerative Colitis Clinical Trial. J Crohns Colitis 2025;19:i168–i169.
Wyatt NJ, Watson H, Anderson CA, et al. Defining predictors of responsiveness to advanced therapies in Crohn’s disease and ulcerative colitis: protocol for the IBD-RESPONSE and nested CD-metaRESPONSE prospective, multicentre, observational cohort study in precision medicine. BMJ Open 2024;14:e073639.
Geboes K. A reproducible grading scale for histological assessment of inflammation in ulcerative colitis. Gut 2000;47:404–409.

 
 
"
  ["project_suppl_material"]=>
  bool(false)
  ["project_coi"]=>
  array(4) {
    [0]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(16300)
        ["id"]=>
        int(16300)
        ["title"]=>
        string(17) "COI-Iacucci-3.pdf"
        ["filename"]=>
        string(17) "COI-Iacucci-3.pdf"
        ["filesize"]=>
        int(20138)
        ["url"]=>
        string(66) "https://yoda.yale.edu/wp-content/uploads/2024/12/COI-Iacucci-3.pdf"
        ["link"]=>
        string(63) "https://yoda.yale.edu/data-request/2024-1060/coi-iacucci-3-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1981"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(17) "coi-iacucci-3-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16292)
        ["date"]=>
        string(19) "2024-12-27 18:59:31"
        ["modified"]=>
        string(19) "2024-12-27 18:59:37"
        ["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(16302)
        ["id"]=>
        int(16302)
        ["title"]=>
        string(16) "COI-Grisan-3.pdf"
        ["filename"]=>
        string(16) "COI-Grisan-3.pdf"
        ["filesize"]=>
        int(20187)
        ["url"]=>
        string(65) "https://yoda.yale.edu/wp-content/uploads/2024/12/COI-Grisan-3.pdf"
        ["link"]=>
        string(62) "https://yoda.yale.edu/data-request/2024-1060/coi-grisan-3-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1981"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(16) "coi-grisan-3-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16292)
        ["date"]=>
        string(19) "2024-12-27 18:59:33"
        ["modified"]=>
        string(19) "2024-12-27 18:59:37"
        ["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(16304)
        ["id"]=>
        int(16304)
        ["title"]=>
        string(17) "COI-Naranjo-3.pdf"
        ["filename"]=>
        string(17) "COI-Naranjo-3.pdf"
        ["filesize"]=>
        int(19786)
        ["url"]=>
        string(66) "https://yoda.yale.edu/wp-content/uploads/2024/12/COI-Naranjo-3.pdf"
        ["link"]=>
        string(63) "https://yoda.yale.edu/data-request/2024-1060/coi-naranjo-3-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1981"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(17) "coi-naranjo-3-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16292)
        ["date"]=>
        string(19) "2024-12-27 18:59:35"
        ["modified"]=>
        string(19) "2024-12-27 18:59:37"
        ["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(18238)
        ["id"]=>
        int(18238)
        ["title"]=>
        string(11) "COI_FORM_PM"
        ["filename"]=>
        string(15) "COI_FORM_PM.pdf"
        ["filesize"]=>
        int(18152)
        ["url"]=>
        string(64) "https://yoda.yale.edu/wp-content/uploads/2024/12/COI_FORM_PM.pdf"
        ["link"]=>
        string(59) "https://yoda.yale.edu/data-request/2024-1060/coi_form_pm-2/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1885"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(13) "coi_form_pm-2"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16292)
        ["date"]=>
        string(19) "2025-10-31 15:02:10"
        ["modified"]=>
        string(19) "2025-10-31 15:02:10"
        ["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)
  ["human_research_protection_training"]=>
  bool(true)
  ["certification"]=>
  bool(true)
  ["request_data_partner"]=>
  string(15) "johnson-johnson"
  ["search_order"]=>
  string(1) "0"
  ["project_send_email_updates"]=>
  bool(false)
  ["project_publ_available"]=>
  bool(true)
  ["project_year_access"]=>
  string(4) "2025"
  ["project_rep_publ"]=>
  bool(false)
  ["project_assoc_data"]=>
  array(0) {
  }
  ["project_due_dil_assessment"]=>
  array(21) {
    ["ID"]=>
    int(16912)
    ["id"]=>
    int(16912)
    ["title"]=>
    string(47) "YODA Project Due Diligence Assessment 2024-1060"
    ["filename"]=>
    string(51) "YODA-Project-Due-Diligence-Assessment-2024-1060.pdf"
    ["filesize"]=>
    int(143923)
    ["url"]=>
    string(100) "https://yoda.yale.edu/wp-content/uploads/2024/12/YODA-Project-Due-Diligence-Assessment-2024-1060.pdf"
    ["link"]=>
    string(93) "https://yoda.yale.edu/data-request/2024-1060/yoda-project-due-diligence-assessment-2024-1060/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(47) "yoda-project-due-diligence-assessment-2024-1060"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16292)
    ["date"]=>
    string(19) "2025-03-19 15:03:35"
    ["modified"]=>
    string(19) "2025-03-19 15:03:35"
    ["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(18239)
    ["id"]=>
    int(18239)
    ["title"]=>
    string(42) "YODA Project Protocol 2024-1060 - 25-10-31"
    ["filename"]=>
    string(44) "YODA-Project-Protocol-2024-1060-25-10-31.pdf"
    ["filesize"]=>
    int(129213)
    ["url"]=>
    string(93) "https://yoda.yale.edu/wp-content/uploads/2024/12/YODA-Project-Protocol-2024-1060-25-10-31.pdf"
    ["link"]=>
    string(86) "https://yoda.yale.edu/data-request/2024-1060/yoda-project-protocol-2024-1060-25-10-31/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(40) "yoda-project-protocol-2024-1060-25-10-31"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16292)
    ["date"]=>
    string(19) "2025-10-31 15:12:55"
    ["modified"]=>
    string(19) "2025-10-31 15:12:55"
    ["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(16914)
    ["id"]=>
    int(16914)
    ["title"]=>
    string(36) "YODA Project Review - 2024-1060_site"
    ["filename"]=>
    string(38) "YODA-Project-Review-2024-1060_site.pdf"
    ["filesize"]=>
    int(1315702)
    ["url"]=>
    string(87) "https://yoda.yale.edu/wp-content/uploads/2024/12/YODA-Project-Review-2024-1060_site.pdf"
    ["link"]=>
    string(80) "https://yoda.yale.edu/data-request/2024-1060/yoda-project-review-2024-1060_site/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(34) "yoda-project-review-2024-1060_site"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16292)
    ["date"]=>
    string(19) "2025-03-19 15:04:42"
    ["modified"]=>
    string(19) "2025-03-19 15:04:42"
    ["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_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"
}