array(41) {
  ["project_status"]=>
  string(7) "ongoing"
  ["project_assoc_trials"]=>
  array(2) {
    [0]=>
    object(WP_Post)#5131 (24) {
      ["ID"]=>
      int(1845)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2019-12-12 12:23:00"
      ["post_date_gmt"]=>
      string(19) "2019-12-12 12:23:00"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(257) "NCT01715285 - A Randomized, Double-blind, Comparative Study of Abiraterone Acetate Plus Low-Dose Prednisone Plus Androgen Deprivation Therapy (ADT) Versus ADT Alone in Newly Diagnosed Subjects With High-Risk, Metastatic Hormone-naive Prostate Cancer (mHNPC)"
      ["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) "nct01715285-a-randomized-double-blind-comparative-study-of-abiraterone-acetate-plus-low-dose-prednisone-plus-androgen-deprivation-therapy-adt-versus-adt-alone-in-newly-diagnosed-subjects-with-h"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2025-04-30 16:02:44"
      ["post_modified_gmt"]=>
      string(19) "2025-04-30 20:02:44"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(242) "https://dev-yoda.pantheonsite.io/clinical-trial/nct01715285-a-randomized-double-blind-comparative-study-of-abiraterone-acetate-plus-low-dose-prednisone-plus-androgen-deprivation-therapy-adt-versus-adt-alone-in-newly-diagnosed-subjects-with-h/"
      ["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)#5130 (24) {
      ["ID"]=>
      int(8008)
      ["post_author"]=>
      string(4) "1363"
      ["post_date"]=>
      string(19) "2023-08-05 04:44:39"
      ["post_date_gmt"]=>
      string(19) "2023-08-05 04:44:39"
      ["post_content"]=>
      string(0) ""
      ["post_title"]=>
      string(210) "NCT02489318 - A Phase 3 Randomized, Placebo-controlled, Double-blind Study of Apalutamide Plus Androgen Deprivation Therapy (ADT) Versus ADT in Subjects With Metastatic Hormone-sensitive Prostate Cancer (mHSPC)"
      ["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(194) "nct02489318-a-phase-3-randomized-placebo-controlled-double-blind-study-of-apalutamide-plus-androgen-deprivation-therapy-adt-versus-adt-in-subjects-with-metastatic-hormone-sensitive-prostate-canc"
      ["to_ping"]=>
      string(0) ""
      ["pinged"]=>
      string(0) ""
      ["post_modified"]=>
      string(19) "2025-04-30 16:20:21"
      ["post_modified_gmt"]=>
      string(19) "2025-04-30 20:20:21"
      ["post_content_filtered"]=>
      string(0) ""
      ["post_parent"]=>
      int(0)
      ["guid"]=>
      string(243) "https://dev-yoda.pantheonsite.io/clinical-trial/nct02489318-a-phase-3-randomized-placebo-controlled-double-blind-study-of-apalutamide-plus-androgen-deprivation-therapy-adt-versus-adt-in-subjects-with-metastatic-hormone-sensitive-prostate-canc/"
      ["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(123) "Leveraging Data Science Methods to Deliver Individualized Treatment Effects in Metastatic Hormone-Sensitive Prostate Cancer"
  ["project_narrative_summary"]=>
  string(697) "Abiraterone and apalutamide are indicated in combination with androgen deprivation therapy (ADT) for men with metastatic hormone sensitive prostate cancer (mHSPC) based on the results of  the pivotal randomized clinical trials, LATITUDE and TITAN. However, these trials report average treatment effects and there may be heterogeneity in survival benefit comparing these combination protocols over ADT alone. This study will use statistical methods to derive predicted individualized treatment effects to contextualize trial findings  and assess how trial results change when re-weighted to characteristics of real world populations. This will help inform individualized care in the mHSPC setting. "
  ["project_learn_source"]=>
  string(10) "web_search"
  ["principal_investigator"]=>
  array(7) {
    ["first_name"]=>
    string(7) "Charles"
    ["last_name"]=>
    string(5) "Gaber"
    ["degree"]=>
    string(8) "PhD, MPH"
    ["primary_affiliation"]=>
    string(30) "University of Illinois Chicago"
    ["email"]=>
    string(14) "gaber1@uic.edu"
    ["state_or_province"]=>
    string(2) "IL"
    ["country"]=>
    string(13) "United States"
  }
  ["project_key_personnel"]=>
  array(5) {
    [0]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(7) "Natalie"
      ["p_pers_l_name"]=>
      string(7) "Reizine"
      ["p_pers_degree"]=>
      string(2) "MD"
      ["p_pers_pr_affil"]=>
      string(30) "University of Illinois Chicago"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(2) "no"
    }
    [1]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(4) "Todd"
      ["p_pers_l_name"]=>
      string(3) "Lee"
      ["p_pers_degree"]=>
      string(11) "PhD, PharmD"
      ["p_pers_pr_affil"]=>
      string(30) "University of Illinois Chicago"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(2) "no"
    }
    [2]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(5) "Lucia"
      ["p_pers_l_name"]=>
      string(6) "Petito"
      ["p_pers_degree"]=>
      string(3) "PhD"
      ["p_pers_pr_affil"]=>
      string(23) "Northwestern University"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [3]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(7) "Jessica"
      ["p_pers_l_name"]=>
      string(5) "Islam"
      ["p_pers_degree"]=>
      string(9) "PhD, MSPH"
      ["p_pers_pr_affil"]=>
      string(21) "Moffitt Cancer Cancer"
      ["p_pers_scop_id"]=>
      string(0) ""
      ["requires_data_access"]=>
      string(3) "yes"
    }
    [4]=>
    array(6) {
      ["p_pers_f_name"]=>
      string(17) "Hao-Hsin (Taylor)"
      ["p_pers_l_name"]=>
      string(5) "Huang"
      ["p_pers_degree"]=>
      string(3) "MSc"
      ["p_pers_pr_affil"]=>
      string(30) "University of Illinois Chicago"
      ["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(130) "Department of Defense - Congressionally Directed Medical Research Programs - Prostate Cancer Research Program - Data Science Award"
  ["project_date_type"]=>
  string(18) "full_crs_supp_docs"
  ["property_scientific_abstract"]=>
  string(1599) "Background:  For men with metastatic hormone sensitive prostate cancer (mHSPC),  improved overall survival from androgen deprivation therapy (ADT) combination with androgen receptor pathway inhibitors (ARPIs) abiraterone acetate and apalutamide was established in the LATITUDE and TITAN randomized trials. While the average treatment effects reported in these practice-changing trials were promising, it remains difficult to contextualize the results for individual-level clinical decision-making due to heterogenous treatment effects. Second, the primary results of LATITUDE and TITAN may not generalize to the real-world populations that have different distributions of effect modifiers such as age.



Objective: In the first aim, predicted individualized treatments effects will be derived from the LATITUDE and TITAN trials to characterize treatment effect heterogeneity. In the second aim, the results of the LATITUDE and TITAN trials will be re-calibrated, or "transported", to a real-world population from an EHR-derived oncology database.



Study Design: Secondary analysis of the LATITUDE and TITAN trials using statistical modeling methods.

Participants: All participants from the LATITUDE and TITAN trials, without further inclusion or exclusion criteria from the original trials.



Primary and Secondary Outcome Measure(s): Overall survival; progression-free survival



Statistical Analysis: Causal forests will be used in Aim I and transportability analysis using inverse-odds of sampling weights will be used in Aim II

"
  ["project_brief_bg"]=>
  string(2926) "Prostate cancer is the second leading cause of cancer-related mortality amongst men in the United States (U.S), with 35,250 deaths occurring in 2024.(1) The five-year survival rate for metastatic tumors is 31%, and no large gains in survival have been achieved over the past 20 years.(2,3) Prostate cancer is dependent on androgens to grow; thus, androgen deprivation therapy (ADT) is the cornerstone treatment for metastatic disease.(4,5) Nearly 90% of patients with metastatic hormone sensitive prostate cancer (mHSPC) will display an initial response to ADT.(6,7) However, the majority of mHSPC patients initiating ADT will develop resistance to hormone therapy in 2-3 years, experiencing disease progression despite castration levels (<50 ng/dL) of testosterone.(8–10) At this point, the cancer is said to have transitioned to metastatic castration-resistant prostate cancer (mCRPC). The high mortality of mCRPC has spurred the generation of therapeutic approaches to delay the onset of resistance and improve survival in mHSPC, including androgen receptor pathway inhibitors abiraterone and apalutamide (among others).



Despite the promising average treatment effects of these agents in the LATITUDE (abiraterone) and TITAN (apalutamide) trials, it is difficult to apply their results to clinical decision making at the individual-level. Trials are conducted amongst study populations and inherently generate evidence at the population-level, particularly when they report a global effect estimate such as one overall hazard ratio.(11) The difficulty in applying trial average treatment effects to individuals arises from the existence of heterogeneous treatment effects within the study populations of trials. The first aim will deliver increased personalization of the LATITUDE and TITAN main results, which for example, could aid shared decision making by enriching patient-provider conversations. By providing refined, individual-level statistical expectations for the effect of abiraterone and apalutamide on survival, patients and providers will have richer context for the trial results. 



While randomized trials function as the gold-standard study design for establishing efficacy, a frequently cited limitation of trials is their lack of generalizability to real world populations.(12,13) If the distribution of effect- modifying variables (e.g. history of myocardial infarction) varies between the trial and real-world populations, then the trial average treatment effect will not represent the effect in the real world.(14–16) Thus, it remains critical to evaluate the effectiveness of treatments using real-world data such as oncology electronic health records. In Aim II, the analysis of real-world data using hybrid designs can provide a bridge from efficacy to effectiveness, providing a crucial assessment of the effect of therapies in routine care populations.

"
  ["project_specific_aims"]=>
  string(1278) "Aim I. Develop and evaluate the impact of personalized treatment strategies from the LATITUDE and TITAN randomized controlled trials

Objective I-A: Derive personalized treatment strategies from LATITUDE and TITAN based on demographic, clinical, and tumor characteristics using supervised machine learning algorithms

Objective I-B: Develop a web-based application that yields personalized results of the LATITUDE and TITAN trials when users input their demographic, clinical, and tumor characteristics

Objective I-C: Evaluate the clinical utility of the personalized tool using counterfactual decision curve analysis



Aim II.  Use a hybrid epidemiologic design to transport the results of the TITAN and LATITUDE trials to the cohort of real-world patients who meet trial eligibility criteria.



Hypotheses tested: In Aim I, we hypothesize that clinically meaningful treatment effect heterogeneity exists within the LATITUDE and TITAN trials, with some covariate combinations predicting a larger than average benefit and some predicting a smaller effect. In Aim II, we hypothesize that the treatment effect estimate will be different when re-weighted to the effect modifier distribution of a real-world oncology populations.

"
  ["project_study_design"]=>
  array(2) {
    ["value"]=>
    string(14) "indiv_trial_an"
    ["label"]=>
    string(25) "Individual trial analysis"
  }
  ["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(37) "develop_or_refine_statistical_methods"
      ["label"]=>
      string(37) "Develop or refine statistical 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(553) "Inclusion/Exclusion criteria to be used to define patient sample: none (for either trial requested).



In Aim II, a hybrid epidemiologic design will be used that involves concatenating ("stacking", NOT merging) the trial populations and real-world populations in order to re-weight the trial data to the distribution of effect modifiers in the real-world data. For the real-world data we will be using curated oncology electronic health records data from Flatiron health, and IPD analysis will need to be performed on the Flatiron platform."
  ["project_main_outcome_measure"]=>
  string(627) "Using the LATITUDE data, the primary outcomes are overall survival and radiographic progression-free survival, while the secondary outcomes are time to initiation of chemotherapy, time to pain progression, time to symptomatic skeletal event, time to prostate-specific antigen pression, and time to subsequent prostate cancer therapy. Using the TITAN data, the primary outcomes are overall survival and radiographic progression-free survival, while the secondary outcomes are  Secondary end points were the time to cytotoxic chemotherapy, time to pain progression, time to chronic opioid use, and time to skeletal-related event."
  ["project_main_predictor_indep"]=>
  string(332) "In all analyses using LATITUDE data, the main predictor is randomized treatment group: abiraterone acetate with prednisone and androgen deprivation therapy (ADT) versus ADT alone. In all analyses using TITAN data, the main predictor is randomized treatment group: apalutamide and androgen deprivation therapy (ADT) versus ADT alone."
  ["project_other_variables_interest"]=>
  string(1041) "This project will rely on data reported in baseline characteristics tables of the trials, along with variables reported in subgroup analyses.



For analyses using LATITUDE data, the other variables of interest are: age, gleason score at initial diagnosis, bone metastases at screen, extent of bone disease, baseline pain score per Brief Pain Inventory,  previous prostate cancer therapy, ECOG performance status, visceral disease, count of bone lesions, prostate-specific antigen (PSA), and lactate dehydrogenase, and region.



For analyses using TITAN data, the other variables of interest are: age, ECOG performance status, Gleason score at initial diagnosis, metastatic stage at initial diagnosis, disease volume, previous treatment with docetaxel, previous therapy for localized cancer, PSA, and mean BPI-Short Form pain score, bone metastases only at baseline (yes/no), visceral disease and bone metastasis at baseline (yes/no),  previous docetazel use(yes/no), lactate dehydrogenase, and alkaline phosphatase."
  ["project_stat_analysis_plan"]=>
  string(3927) "Aim I will derive predicted individualized treatment effects (PITEs) from LATITUDE and TITAN using emerging machine learning methods for causal inference.(17–23) Specifically, we will estimate PITEs for each trial using causal survival forests, a supervised machine learning algorithm that detects and quantifies distinct individualized treatment effects without needing to pre-specify complex statistical interactions.(24) In our study, we will directly replicate the methodology of a recently published analysis of the TOPCAT trial that elegantly quantified heterogenous treatment effects of spironolactone amongst patients with heart failure.(25) For each trial, we will begin by sampling a proportion of the original trial population. Second, we will split this subset into training and estimation samples. Third, in the training sample we will perform a tree-building routine that recursively partitions that data based on splits of the variables (e.g., age<65) and forms terminal nodes (“leaves”) with distinct treatment effects. The variables considered for splitting during tree-building will constitute all variables reported in subgroup analyses of the main trial findings; these variables represent candidate effect modifiers. The tree-building routine will then be repeated 10,000 times, constituting the causal forest. The final PITE for an individual will be calculated as the average PITE in causal trees that included a given individual in the corresponding estimation sample. Visually, a histogram of the distribution of the survival difference will be produced for each trial population, displaying the degree of heterogeneity in benefit (or harm) of ADT combination therapy. Quartiles of anticipated benefit (or harm) will be reported. A variable importance plot will also be generated, depicting the relative frequency with which a variable was selected to be in the first split of a tree; a variable frequently chosen as the first split suggests it is highly important in driving treatment effect heterogeneity.(26) To prevent overfitting of the model we will be implementing bootstrapping to tune hyperparameters and will specify that at least 10 events occur in leaves of each causal tree. Internal validation of the causal survival forest model will be performed. Specifically, discrimination and calibration will be calculated using modified observed benefit. Briefly, because the actual effect is unobservable for an individual (it can only be predicted), dyads of treated and untreated patients are formed that have the same PITE within a caliper (e.g., 0.10 standard deviations). Then, the observed survival differences of these pairs are used to calculate a c-statistic-for-benefit(27) (discrimination) and to compare how the PITEs compare to the modified observed effect (calibration). 



Aim II will evaluate the therapeutic comparisons of LATITUDE and TITAN in routine care populations using the trial data and Flatiron Health oncology EHR data. A hybrid epidemiologic design using both sources will be used to transport the results of the TITAN and LATITUDE trials to the cohort of real-world patients who would have been trial eligible (Objective III-A). This will involve concatenating the trial and real-world datasets and using inverse-odds-of-sampling weights (IOWS) to re-weight the trial population to the distribution of potential effect modifiers in the real-world population.(14–16) IOSW will be calculated using logistic regression. Then, the IOSW used to re-weight the trial population according to the distribution of effect modifiers observed in the real-world data. In the re-weighting process, age, performance status, PSA, Gleason score, and available lab values will be considered as effect modifiers—along with any other candidate effect modifiers presented in the main trial publications’ forest plots that show subgroup analyses.



"
  ["project_software_used"]=>
  array(1) {
    [0]=>
    array(2) {
      ["value"]=>
      string(7) "rstudio"
      ["label"]=>
      string(7) "RStudio"
    }
  }
  ["project_timeline"]=>
  string(429) "Timelines are provided separately for Aim I and Aim II for several items.



Anticipated Project Start Date: August 15th, 2025.

Analysis Completion Date: August 15th, 2026 for Aim I and August 15th, 2027 for Aim II.

Date Manuscript Drafted and First Submitted for Publication: September 1st, 2026.

Date Results Reported back to the YODA Project: December 2026 for Aim I. December 2027 for Aim II."
  ["project_dissemination_plan"]=>
  string(657) "There are four anticipated products of this work: 1) Predicted individualized treatment effects from the LATITUDE trial, 2) Predicted individualized treatment effects from the TITAN trial, 3) Re-weighted estimates of the LATITUDE trial results to distribution of effect modifiers in a real-world oncology population, 4) Re-weighted estimates of the TITAN trial results to distribution of effect modifiers in a real-world oncology population. We anticipate each will result in a study manuscript. Potentially suitable journals include JAMA Oncology, Journal of the National Cancer Institute, Prostate Cancer and Prostatic Diseases, and Cancer, to name a few."
  ["project_bibliography"]=>
  string(5640) "
 

Siegel RL, Giaquinto AN, Jemal A. Cancer statistics, 2024. CA A Cancer J Clinicians. 2024;74(1):12–49.
Miller KD, Nogueira L, Devasia T, et al. Cancer treatment and survivorship statistics, 2022. CA A Cancer J Clinicians. 2022;72(5):409–436.
Wu JN, Fish KM, Evans CP, et al. No improvement noted in overall or cause-specific survival for men presenting with metastatic prostate cancer over a 20-year period: Survival in Metastatic Prostate Cancer. Cancer. 2014;120(6):818–823.
Choi E, Buie JD, Camacho J, et al. Evolution of Androgen Deprivation Therapy (ADT) and Its New Emerging Modalities in Prostate Cancer: An Update for Practicing Urologists, Clinicians and Medical Providers. RRU. 2022;Volume 14:87–108.
Massie CE, Lynch A, Ramos-Montoya A, et al. The androgen receptor fuels prostate cancer by regulating central metabolism and biosynthesis: AR coordinates anabolic program in prostate cancer. The EMBO Journal. 2011;30(13):2719–2733.
Hahn AW, Higano CS, Taplin M-E, et al. Metastatic Castration-Sensitive Prostate Cancer: Optimizing Patient Selection and Treatment. American Society of Clinical Oncology Educational Book. 2018;(38):363–371.
Harris WP, Mostaghel EA, Nelson PS, et al. Androgen deprivation therapy: progress in understanding mechanisms of resistance and optimizing androgen depletion. Nat Rev Urol. 2009;6(2):76–85.
Chandrasekar T, Yang JC, Gao AC, et al. Mechanisms of resistance in castration-resistant prostate cancer. Translational Andrology and Urology. 2015;4(3).
Wade C, Kyprianou N. Profiling Prostate Cancer Therapeutic Resistance. IJMS. 2018;19(3):904.
Vellky JE, Ricke WA. Development and prevalence of castration-resistant prostate cancer subtypes. Neoplasia. 2020;22(11):566–575.
Armstrong KA, Metlay JP. Annals Clinical Decision Making: Translating Population Evidence to Individual Patients. Annals of Internal Medicine. 2020;172(9):610–616.
Stuart EA, Bradshaw CP, Leaf PJ. Assessing the Generalizability of Randomized Trial Results to Target Populations. Prev Sci. 2015;16(3):475–485.
Westreich D, Edwards JK, Lesko CR, et al. Target Validity and the Hierarchy of Study Designs. American Journal of Epidemiology. 2019;188(2):438–443.
Lund JL, Webster‐Clark MA, Hinton SP, et al. Effectiveness of adjuvant FOLFOX vs 5FU / LV in adults over age 65 with stage II and III colon cancer using a novel hybrid approach. Pharmacoepidemiology and Drug. 2020;29(12):1579–1587.
Webster-Clark M, Lund JL, Stürmer T, et al. Reweighting Oranges to Apples: Transported RE-LY Trial Versus Nonexperimental Effect Estimates of Anticoagulation in Atrial Fibrillation. Epidemiology. 2020;31(5):605–613.
Westreich D, Edwards JK, Lesko CR, et al. Transportability of Trial Results Using Inverse Odds of Sampling Weights. American Journal of Epidemiology. 2017;186(8):1010–1014.
Bica I, Alaa AM, Lambert C, et al. From Real‐World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges. Clin Pharma and Therapeutics. 2021;109(1):87–100.
Blackstone EH. Precision Medicine Versus Evidence-Based Medicine: Individual Treatment Effect Versus Average Treatment Effect. Circulation. 2019;140(15):1236–1238.
Chang C, Jaki T, Sadiq MS, et al. A permutation test for assessing the presence of individual differences in treatment effects. Stat Methods Med Res. 2021;30(11):2369–2381.
Lamont A, Lyons MD, Jaki T, et al. Identification of predicted individual treatment effects in randomized clinical trials. Stat Methods Med Res. 2018;27(1):142–157.
Nguyen T-L, Collins GS, Landais P, et al. Counterfactual clinical prediction models could help to infer individualized treatment effects in randomized controlled trials—An illustration with the International Stroke Trial. Journal of Clinical Epidemiology. 2020;125:47–56.
Ballarini NM, Rosenkranz GK, Jaki T, et al. Subgroup identification in clinical trials via the predicted individual treatment effect. PLoS ONE. 2018;13(10):e0205971.
Hoogland J, IntHout J, Belias M, et al. A tutorial on individualized treatment effect prediction from randomized trials with a binary endpoint. Statistics in Medicine. 2021;40(26):5961–5981.
Cui Y, Kosorok MR, Sverdrup E, et al. Estimating heterogeneous treatment effects with right-censored data via causal survival forests. Journal of the Royal Statistical Society Series B: Statistical Methodology. 2023;85(2):179–211.
Desai RJ, Glynn RJ, Solomon SD, et al. Individualized Treatment Effect Prediction with Machine Learning — Salient Considerations. NEJM Evidence [electronic article]. 2024;3(4). (https://evidence.nejm.org/doi/10.1056/EVIDoa2300041). (Accessed June 28, 2024)
Seitz KP, Spicer AB, Casey JD, et al. Individualized Treatment Effects of Bougie versus Stylet for Tracheal Intubation in Critical Illness. Am J Respir Crit Care Med. 2023;207(12):1602–1611.
Van Klaveren D, Steyerberg EW, Serruys PW, et al. The proposed ‘concordance-statistic for benefit’ provided a useful metric when modeling heterogeneous treatment effects. Journal of Clinical Epidemiology. 2018;94:59–68.

"
  ["project_suppl_material"]=>
  bool(false)
  ["project_coi"]=>
  array(6) {
    [0]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(16951)
        ["id"]=>
        int(16951)
        ["title"]=>
        string(23) "Gaber-COIs-for-YODA.pdf"
        ["filename"]=>
        string(23) "Gaber-COIs-for-YODA.pdf"
        ["filesize"]=>
        int(29256)
        ["url"]=>
        string(72) "https://yoda.yale.edu/wp-content/uploads/2025/03/Gaber-COIs-for-YODA.pdf"
        ["link"]=>
        string(69) "https://yoda.yale.edu/data-request/2025-0172/gaber-cois-for-yoda-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "2033"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(23) "gaber-cois-for-yoda-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-03-25 01:35:56"
        ["modified"]=>
        string(19) "2025-03-25 01:36:03"
        ["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(16952)
        ["id"]=>
        int(16952)
        ["title"]=>
        string(16) "NR-YODA-2025.pdf"
        ["filename"]=>
        string(16) "NR-YODA-2025.pdf"
        ["filesize"]=>
        int(20866)
        ["url"]=>
        string(65) "https://yoda.yale.edu/wp-content/uploads/2025/03/NR-YODA-2025.pdf"
        ["link"]=>
        string(62) "https://yoda.yale.edu/data-request/2025-0172/nr-yoda-2025-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "2033"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(16) "nr-yoda-2025-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-03-25 01:35:57"
        ["modified"]=>
        string(19) "2025-03-25 01:36:03"
        ["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(16953)
        ["id"]=>
        int(16953)
        ["title"]=>
        string(16) "Lee_COI_YODA.pdf"
        ["filename"]=>
        string(16) "Lee_COI_YODA.pdf"
        ["filesize"]=>
        int(19891)
        ["url"]=>
        string(65) "https://yoda.yale.edu/wp-content/uploads/2025/03/Lee_COI_YODA.pdf"
        ["link"]=>
        string(62) "https://yoda.yale.edu/data-request/2025-0172/lee_coi_yoda-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "2033"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(16) "lee_coi_yoda-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-03-25 01:35:59"
        ["modified"]=>
        string(19) "2025-03-25 01:36:03"
        ["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(16954)
        ["id"]=>
        int(16954)
        ["title"]=>
        string(19) "Petito_COI_YODA.pdf"
        ["filename"]=>
        string(19) "Petito_COI_YODA.pdf"
        ["filesize"]=>
        int(28919)
        ["url"]=>
        string(68) "https://yoda.yale.edu/wp-content/uploads/2025/03/Petito_COI_YODA.pdf"
        ["link"]=>
        string(65) "https://yoda.yale.edu/data-request/2025-0172/petito_coi_yoda-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "2033"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(19) "petito_coi_yoda-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-03-25 01:36:00"
        ["modified"]=>
        string(19) "2025-03-25 01:36:03"
        ["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"
      }
    }
    [4]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(16955)
        ["id"]=>
        int(16955)
        ["title"]=>
        string(23) "Islam-COIs-for-YODA.pdf"
        ["filename"]=>
        string(23) "Islam-COIs-for-YODA.pdf"
        ["filesize"]=>
        int(20533)
        ["url"]=>
        string(72) "https://yoda.yale.edu/wp-content/uploads/2025/03/Islam-COIs-for-YODA.pdf"
        ["link"]=>
        string(69) "https://yoda.yale.edu/data-request/2025-0172/islam-cois-for-yoda-pdf/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "2033"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(23) "islam-cois-for-yoda-pdf"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-03-25 01:36:02"
        ["modified"]=>
        string(19) "2025-03-25 01:36:03"
        ["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"
      }
    }
    [5]=>
    array(1) {
      ["file_coi"]=>
      array(21) {
        ["ID"]=>
        int(17948)
        ["id"]=>
        int(17948)
        ["title"]=>
        string(11) "COI FORM TH"
        ["filename"]=>
        string(15) "COI-FORM-TH.pdf"
        ["filesize"]=>
        int(20240)
        ["url"]=>
        string(64) "https://yoda.yale.edu/wp-content/uploads/2025/03/COI-FORM-TH.pdf"
        ["link"]=>
        string(57) "https://yoda.yale.edu/data-request/2025-0172/coi-form-th/"
        ["alt"]=>
        string(0) ""
        ["author"]=>
        string(4) "1885"
        ["description"]=>
        string(0) ""
        ["caption"]=>
        string(0) ""
        ["name"]=>
        string(11) "coi-form-th"
        ["status"]=>
        string(7) "inherit"
        ["uploaded_to"]=>
        int(16844)
        ["date"]=>
        string(19) "2025-09-18 20:36:06"
        ["modified"]=>
        string(19) "2025-09-18 20:36:06"
        ["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"
      }
    }
  }
  ["data_use_agreement_training"]=>
  bool(true)
  ["human_research_protection_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) "2025"
  ["project_rep_publ"]=>
  bool(false)
  ["project_assoc_data"]=>
  array(0) {
  }
  ["project_due_dil_assessment"]=>
  array(21) {
    ["ID"]=>
    int(17676)
    ["id"]=>
    int(17676)
    ["title"]=>
    string(47) "YODA Project Due Diligence Assessment 2025-0172"
    ["filename"]=>
    string(51) "YODA-Project-Due-Diligence-Assessment-2025-0172.pdf"
    ["filesize"]=>
    int(127225)
    ["url"]=>
    string(100) "https://yoda.yale.edu/wp-content/uploads/2025/03/YODA-Project-Due-Diligence-Assessment-2025-0172.pdf"
    ["link"]=>
    string(93) "https://yoda.yale.edu/data-request/2025-0172/yoda-project-due-diligence-assessment-2025-0172/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(47) "yoda-project-due-diligence-assessment-2025-0172"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16844)
    ["date"]=>
    string(19) "2025-07-22 14:50:47"
    ["modified"]=>
    string(19) "2025-07-22 14:50:47"
    ["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_title_link"]=>
  array(21) {
    ["ID"]=>
    int(17949)
    ["id"]=>
    int(17949)
    ["title"]=>
    string(44) "YODA Project Protocol 2025-0172 - 2025-09-18"
    ["filename"]=>
    string(46) "YODA-Project-Protocol-2025-0172-2025-09-18.pdf"
    ["filesize"]=>
    int(185589)
    ["url"]=>
    string(95) "https://yoda.yale.edu/wp-content/uploads/2025/03/YODA-Project-Protocol-2025-0172-2025-09-18.pdf"
    ["link"]=>
    string(88) "https://yoda.yale.edu/data-request/2025-0172/yoda-project-protocol-2025-0172-2025-09-18/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(42) "yoda-project-protocol-2025-0172-2025-09-18"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16844)
    ["date"]=>
    string(19) "2025-09-18 20:49:34"
    ["modified"]=>
    string(19) "2025-09-18 20:49:34"
    ["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(17677)
    ["id"]=>
    int(17677)
    ["title"]=>
    string(36) "YODA Project Review - 2025-0172_SITE"
    ["filename"]=>
    string(38) "YODA-Project-Review-2025-0172_SITE.pdf"
    ["filesize"]=>
    int(1315487)
    ["url"]=>
    string(87) "https://yoda.yale.edu/wp-content/uploads/2025/03/YODA-Project-Review-2025-0172_SITE.pdf"
    ["link"]=>
    string(80) "https://yoda.yale.edu/data-request/2025-0172/yoda-project-review-2025-0172_site/"
    ["alt"]=>
    string(0) ""
    ["author"]=>
    string(4) "1885"
    ["description"]=>
    string(0) ""
    ["caption"]=>
    string(0) ""
    ["name"]=>
    string(34) "yoda-project-review-2025-0172_site"
    ["status"]=>
    string(7) "inherit"
    ["uploaded_to"]=>
    int(16844)
    ["date"]=>
    string(19) "2025-07-22 14:51:08"
    ["modified"]=>
    string(19) "2025-07-22 14:51:08"
    ["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"
  ["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(2) {
  [0]=>
  string(6) "zytiga"
  [1]=>
  string(7) "erleada"
}


num of trials
array(1) {
  [0]=>
  string(1) "2"
}


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