Neural Network-based Treatment Decision Support Tool in Patients With Refractory Solid Organ Malignancies (DRUID)

A Phase II Trial of Neural Network-based Treatment Decision Support Tool in Patients With Refractory Solid Organ Malignancies

DRUID is a treatment decision support tool combining predictive models and public databases related to multi-gene markers, drug response screens, gene essentiality and clinical status of drugs to provide drug recommendations personalized based on an input genomic profile. We hypothesize that DRUID analysis of patients' somatic mutational profile from NGS diagnostic platform can be used as a treatment decision support tool in patients with refractory cancer without targetable mutations.

Study Overview

• Status: Recruiting
• Conditions: Solid Organ Malignancies
• Intervention / Treatment: Other: DRUID AI Program

Detailed Description

2.1. Hypothesis We hypothesize that DRUID analysis of patients' somatic mutational profile from NGS diagnostic platform can be used as a treatment decision support tool in patients with refractory cancer without targetable mutations. Using algorithm selected treatment from a panel of 60 drugs we predict an objective response rate (ORR) of ≥ 25%.

2.2. Primary Objectives

• To prospectively determine if DRUID selected therapy based on NGS diagnostic profile input can lead to objective responses in refractory solid organ malignancies.

2.3. Secondary Objectives

• To assess clinical benefit rate (complete response, partial response and stable disease for ≥ 24 weeks)
• To assess progression-free and overall survival of patients treated with DRUID-guided therapy

• Study Type: Interventional
• Enrollment (Estimated): 37
• Phase: Phase 2

Contacts and Locations

• Study Contact: Name: Robert John Walsh; Phone Number: 69082222; Email: robert_walsh@nuhs.edu.sg
• Study Contact Backup: Name: Robert John Walsh

Study Locations

• Singapore
  • Singapore, Singapore, 119074
    • Recruiting
    • Department of Hematology-Oncology, National University Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 21 years to 99 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

Patients may be included in the study only if they meet all of the following criteria:

• Age ≥ 21 years.
• Histological or cytological diagnosis solid organ malignancy
• Available results of comprehensive NGS panel testing performed on either tumour tissue or blood-based assay. If results are from blood-based assay, test must have been performed in the metastatic setting.
• ECOG 0-2.
• At least 1 measurable tumour lesions based on RECIST 1.1 criteria
• Estimated life expectancy of at least 12 weeks.
• Has documented progressive disease from last line of therapy.
• Has received at least 2 lines of palliative systemic therapy with no available standard therapy:

• Adequate organ function including the following:

  • Bone marrow:

    • Absolute neutrophil (segmented and bands) count (ANC) ≥ 1.5 x 109/L
    • Platelets ≥ 100 x 109/L
    • Haemoglobin ≥ 8 x 109/L

  • Hepatic:

    • Bilirubin ≤ 1.5 x upper limit of normal (ULN),
    • ALT or AST ≤ 2.5x ULN, (or ≤ 5 X with liver metastases)

  • Renal:

    • Creatinine ≤ 1.5x ULN
    • Signed informed consent from patient or legal representative.
• Able to comply with study-related procedures.

Exclusion Criteria:

• Treatment within the last 30 days with any investigational drug.
• Concurrent administration of any other tumour therapy, including cytotoxic chemotherapy, hormonal therapy, and immunotherapy.
• Major surgery within 28 days of study drug administration.
• Active infection that in the opinion of the investigator would compromise the patient's ability to tolerate therapy.
• Pregnancy.
• Breast feeding.
• Serious concomitant disorders that would compromise the safety of the patient or compromise the patient's ability to complete the study, at the discretion of the investigator.
• Active bleeding disorder or bleeding site.
• Non-healing wound.
• Second primary malignancy that is clinically detectable at the time of consideration for study enrolment.
• Symptomatic brain metastasis.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: DRUID; Patients NGS profile will be analysed with DRUID system to generate recommendations based on predicted efficacy. Patients with available archival tissue will have gene expression analysis performed to optimise DRUID recommendation. Patients will subsequently receive single agent therapy based on DRUID recommendations and criteria for therapy choice.	Other: DRUID AI Program; Patients will begin single agent therapy within 4 weeks of enrolment and continue until disease progression, maximum safe cumulative dose reached (where applicable, per standard institution practice) or unacceptable toxicity as per physician's discretion.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Objective response rate (ORR)	Defined as patient exhibiting a best study response of complete or partial clinical response based on radiological imaging per RECIST 1.1 criteria.	10 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Clinical benefit	Defined as presence of best study response of complete or partial response or stable disease for at least 24 weeks (based on RECIST 1.1 criteria).	10 months
Progression free survival	Defined as the time from the date of study enrolment to the first date of documented disease progression.	From enrolment till disease progression or date of death or final follow-up visit (1 year).

Collaborators and Investigators

• Sponsor: National University Hospital, Singapore
• Collaborators: School of Computing, National University of Singapore; National University of Singapore
• Investigators: Principal Investigator: Robert John Walsh, National University Hospital, Singapore

Publications and helpful links

General Publications

• Garraway LA, Verweij J, Ballman KV. Precision oncology: an overview. J Clin Oncol. 2013 May 20;31(15):1803-5. doi: 10.1200/JCO.2013.49.4799. Epub 2013 Apr 15. No abstract available.
• Mariappan R, Jayagopal A, Sien HZ, Rajan V. Neural Collective Matrix Factorization for integrated analysis of heterogeneous biomedical data. Bioinformatics. 2022 Sep 30;38(19):4554-4561. doi: 10.1093/bioinformatics/btac543.
• Nguyen T, Nguyen GTT, Nguyen T, Le DH. Graph Convolutional Networks for Drug Response Prediction. IEEE/ACM Trans Comput Biol Bioinform. 2022 Jan-Feb;19(1):146-154. doi: 10.1109/TCBB.2021.3060430. Epub 2022 Feb 3.
• Garnett MJ, Edelman EJ, Heidorn SJ, Greenman CD, Dastur A, Lau KW, Greninger P, Thompson IR, Luo X, Soares J, Liu Q, Iorio F, Surdez D, Chen L, Milano RJ, Bignell GR, Tam AT, Davies H, Stevenson JA, Barthorpe S, Lutz SR, Kogera F, Lawrence K, McLaren-Douglas A, Mitropoulos X, Mironenko T, Thi H, Richardson L, Zhou W, Jewitt F, Zhang T, O'Brien P, Boisvert JL, Price S, Hur W, Yang W, Deng X, Butler A, Choi HG, Chang JW, Baselga J, Stamenkovic I, Engelman JA, Sharma SV, Delattre O, Saez-Rodriguez J, Gray NS, Settleman J, Futreal PA, Haber DA, Stratton MR, Ramaswamy S, McDermott U, Benes CH. Systematic identification of genomic markers of drug sensitivity in cancer cells. Nature. 2012 Mar 28;483(7391):570-5. doi: 10.1038/nature11005.
• Hickcox JP. Treatment of fractures with Hirschhorn compression plates. J Am Vet Med Assoc. 1970 Jan 15;156(2):187-96. No abstract available.
• Clerch AR, Miale JB. A comparison of the Unitest system with three other methods for determining blood glucose. Am J Clin Pathol. 1971 Feb;55(2):159-62. doi: 10.1093/ajcp/55.2.159. No abstract available.
• De Lange T, Kooter JM, Michels PA, Borst P. Telomere conversion in trypanosomes. Nucleic Acids Res. 1983 Dec 10;11(23):8149-65. doi: 10.1093/nar/11.23.8149.
• Ford TF, Grant DA, Austen BM, Hermon-Taylor J. Intramucosal activation of pepsinogens in the pathogenesis of acute gastric erosions and their prevention by the potent semisynthetic amphipathic inhibitor pepstatinyl-glycyl-lysyl-lysine. Clin Chim Acta. 1985 Jan 15;145(1):37-47. doi: 10.1016/0009-8981(85)90017-8.

Study record dates

Study Major Dates

• Study Start (Actual): August 28, 2023
• Primary Completion (Estimated): December 31, 2025
• Study Completion (Estimated): June 30, 2026

Study Registration Dates

• First Submitted: January 30, 2023
• First Submitted That Met QC Criteria: January 30, 2023
• First Posted (Actual): February 9, 2023

Study Record Updates

• Last Update Posted (Actual): July 25, 2025
• Last Update Submitted That Met QC Criteria: July 22, 2025
• Last Verified: July 1, 2025

More Information

Terms related to this study

• Keywords: Next generation sequencing; DRUID
• Additional Relevant MeSH Terms: Neoplasms
• Other Study ID Numbers: 2022/00653

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No