Oncogeriatric Screening and Evaluation Program
ConditionSolid Tumor Cancer
Trial statusNot yet recruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age65+
SponsorLatin American Cooperative Oncology Group
About this trial
This study aims to develop, train, and validate a machine learning-based prediction model (PROTEGER) to provide treatment decision recommendations for older adults diagnosed with solid tumor cancers. The study has a two-phase observational design: a retrospective cohort using anonymized data from an oncogeriatric telecommittee to train the predictive model, followed by a prospective multicenter cohort across Chile, Peru, and Brazil. Information from Comprehensive Geriatric Assessments (CGA), treatment decisions, and 3- and 6-month clinical outcomes will be collected to evaluate and validate the decision-support platform's performance in assisting oncology teams.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 65 years or older.
Diagnosis of solid tumor cancer.
Must have been evaluated and followed up by a local oncology team.
Signed Informed Consent Form (ICF) applied in accordance with the local ethics committee.
Disqualifiers
None
Trial population
The study population consists of older adults (aged 65 years and older) diagnosed with solid tumor cancers who receive care in public and private health institutions in South America (Chile, Brazil, and Peru). The retrospective cohort includes anonymized historical data from patients evaluated by the Oncogeriatric Tele-Committee of the Chilean Ministry of Health. The prospective cohort comprises consecutive patients seen in routine oncological care who undergo a Comprehensive Geriatric Assessment (CGA) and are managed by local oncogeriatric teams.
Trial design
Design model
Cohort
Time perspective
Other
Treatments tested in this trial
Not listed
Trial groups
412 Participants
are grouped into 2 trial groupsGroup A: Retrospective Training Cohort (Chile)
Group B: Prospective Validation Cohort (Chile, Brasil, Peru)
Trial outcomes
Primary outcomes
1
Predictive Accuracy of the PROTEGER Machine Learning Model
Discrimination performance of the machine learning predictive model in recommending oncogeriatric treatment decisions (standard treatment, dose-adjusted treatment, or supportive care/no treatment) based on Comprehensive Geriatric Assessment (CGA) data, measured by the Area Under the Receiver Operating Characteristic Curve (AUC-ROC), with scores ranging from 0.5 (no discrimination/chance) to 1.0 (perfect discrimination).
Time frame
Up to 6 months post-enrollment.Secondary outcomes
1
Incidence of High-Grade Chemotherapy-Related Adverse Events
Percentage of participants experiencing Grade 3 or higher toxicities/adverse reactions evaluated using the Common Terminology Criteria for Adverse Events (CTCAE) version 5.0.
Time frame
At 3 and 6 months post-enrollment.2
General Quality of Life Score (EORTC QLQ-C30)
Global health status and quality of life assessed using the European Organisation for Research and Treatment of Cancer Quality of Life Questionnaire (EORTC QLQ-C30). Scores range from 0 to 100, where higher scores represent a better overall quality of life and higher functioning.
Time frame
Baseline, 3 months, and 6 months post-enrollment.3
Elderly-Specific Quality of Life Score (EORTC QLQ-ELD14)
Elderly-specific quality of life issues assessed using the EORTC QLQ-ELD14 module. Scores range from 0 to 100. For symptom scales, higher scores represent worse outcomes (higher level of symptoms/problems); for functional scales, higher scores represent better outcomes.
Time frame
Baseline, 3 months, and 6 months post-enrollment.4
Incidence of Hospitalizations
Number of patients requiring unplanned hospital admissions during the treatment course
Time frame
At 3 and 6 months post-enrollment.Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Latin American Cooperative Oncology Group
Lead sponsor
ONCOGER SpA
Collaborator
Source ClinicalTrials.gov
This trial is not recruiting at the moment. You can still explore other options: