Leveraging EA8191 to Assess AI-Augmented EHR Abstraction

NCT06561230 | Active Not Recruiting

• 1 other identifier: 854974
• Study Type: observational
• Target: 300
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this prospective study is to assess the performance of AI (artificial intelligence) augmentation (compared against historical controls) to identify oncology patients who meet inclusion criteria for a clinical trial. The study staff will leverage a natural language processing (NLP)-based AI algorithm that rank-orders patients most likely to meet inclusion criteria for a trial. We hypothesize that this collaborative Human+AI workflow can improve the efficiency, accuracy, and diversity of trial prescreening.

Conditions

Prostate Cancer

Outcome Measures

Primary Outcomes (1)

• Efficiency

  The number of eligible patients per 10 charts prescreened

  1 year

Secondary Outcomes (2)

• Accuracy

  6 months

• Diversity

  6 months

Study Arms (1)

Human + AI

Other: Chart review

Interventions

Chart review OTHER

Patients eligible for prescreening will be identified using structured criteria (e.g., anyone with an appointment in the upcoming 2 months with a relevant provider). All individual charts will be de-identified. De-identified EHRs will then be transferred to Mendel's secure data abstraction platform, where trial eligibility criteria will be abstracted. Patients will be rank-ordered by number of eligibility criteria met, with patients meeting the most eligibility criteria at the top of the queue. The study team will then review eligibility criteria and flag eligible patients.

Human + AI

Eligibility Criteria

• Age: 18 Years+
• Sex: male
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients with a diagnosis code of prostate cancer and with an upcoming genitourinary radiation oncology or medical oncology appointments at the Perelman Center for Advanced Medicine

You may qualify if:

• Patient must be male and \>= 18 years of age.
• Patient must have had a radical prostatectomy (RP) as definitive therapy for histopathologically-proven prostatic adenocarcinoma
• Patient must have biochemical recurrence (BCR) after RP, defined as follows:
• If time to BCR, defined as time to first detectable PSA ( \> lower limit of normal for assay used) after RP, is \< 12 months, a minimum PSA level of \>= 0.2 ng/mL and a confirmatory reading of \>= 0.2 ng/mL is required, per the American Urological Association (AUA) definition (Note: patients with a persistent PSA reading of at least 0.2 ng/mL are eligible)
• If time to BCR, defined as time to first detectable PSA (\> lower limit of normal for assay used) after RP, is \>= 12 months, a minimum absolute PSA of 0.5 ng/mL is required
• If the patient has a detectable PSA (\> lower limit of normal for assay used) at any time after RP AND has an eligible baseline SOC PET (PET1) with at least one positive lesion in any location, then there is no minimum PSA requirement
• Patients must have no definite evidence for extrapelvic metastatic disease by conventional imaging modalities (CIM) (CT abdomen/pelvis or MRI abdomen/pelvis AND bone scintigraphy, or equivalent), within 26 weeks prior to Step 0 registration. If a patient only has a study-eligible PET/CT or PET/MR (i.e., PET done without prior CIM): if the PET is negative for extrapelvic lesions, then baseline CIM is NOT required. If the PET positive for extrapelvic lesions, then patient should have a baseline CT/MRI for soft tissue lesions and/or a bone scan for osseous lesions
• Study eligible = PET using FDA-approved radiotracer and performed within 16 weeks prior to study registration
• Extra-pelvic metastases is defined as any osseous metastases and/or any extrapelvic soft tissue, lymph nodes and organ metastases; extra-pelvic is defined as superior to common iliac bifurcation, outside of standard prostate bed + whole pelvis nodal RT fields. Baseline PET/CT or PET/MR scan (PET1) is eligible for this study if the SOC PET scan is completed with an FDA approved radiotracer for prostate cancer after Step 0 registration and prior to Step 1 randomization OR up to 16 weeks prior to Step 0 registration
• Patient must be a candidate for SOC post-prostatectomy radiation therapy (RT) to the prostate bed and pelvic nodes with androgen deprivation therapy (ADT)
• Patient must have the ability to understand and the willingness to sign a written informed consent document. Patients with impaired decision-making capacity (IDMC) who have a legally authorized representative (LAR) or caregiver and/or family member available will also be considered eligible
• Patient must have an Eastern Cooperative Oncology Group (ECOG) performance status 0-2
• Patient must not have started ADT for biochemical recurrence prior to baseline PET (PET1) imaging. A short course of low-dose anti-androgen such as bicalutamide, given after baseline study PET/CT but prior to study registration, is permitted as a brief temporizing measure in advance of starting protocol-approved SOC ADT.
• Patient must not be enrolled in another therapeutic clinical trial
• Patient must be able to lie flat and still for approximately 20-30 minutes or otherwise tolerate a PET scan and radiation treatment planning and delivery

Sponsors & Collaborators

• University of Pennsylvania: lead
• Mendel AI: collaborator

Study Sites (1)

University of Pennsylvania

Philadelphia, Pennsylvania, 19104, United States

Location

MeSH Terms

Conditions

Prostatic Neoplasms

Condition Hierarchy (Ancestors)

Genital Neoplasms, Male; Urogenital Neoplasms; Neoplasms by Site; Neoplasms; Genital Diseases, Male; Genital Diseases; Urogenital Diseases; Prostatic Diseases; Male Urogenital Diseases

Study Design

• Study Type: observational
• Observational Model: OTHER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 16, 2024
• First Posted: August 19, 2024
• Study Start: April 4, 2025
• Primary Completion: May 1, 2026
• Study Completion (Estimated): August 1, 2026
• Last Updated: March 12, 2026

Record last verified: 2026-03

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)