Screening for Multiple Gastrointestinal Cancers With CanDELA
Rishabh Ranjan and Gopalaniruddh Tadinada · Louisville, Kentucky
H. Robert Horvitz Prize for Fundamental Research ($10,000) · Regeneron International Science and Engineering Fair · 2023
An automated system combining robotics and machine learning to analyse blood samples and distinguish healthy patients from those with pancreatic, colorectal or hepatic cancer, built for settings without a diagnostic laboratory.
Reported results in approximately three hours at an estimated cost of about $300 per run.
Time and cost are reported alongside the classification, and for a screening tool those two numbers are the entire deployment argument. Detecting three cancers with one assay is what makes the cost defensible.
- Automated blood sample handling
- Machine-learning classification
- Discrimination between three cancer types
- Turnaround time and cost analysis
- For a diagnostic, turnaround time and cost per test are findings, not logistics
- Automating the workflow is what makes a benchtop assay into something a clinic could run
Archive entries are summaries compiled for study. Read them for how a project was structured, argued, and defended — not as a template to reproduce. Copying someone else's project is the one thing that will end yours.
Compiled by ResearchForge from the Society for Science public award announcement linked on this record. Names, hometowns, project titles and reported results are as published. The "why it worked" and "what to take from this" notes are ResearchForge's editorial reading of that public record — they are not statements by the students and not the judges' rationale. All rights to the original projects remain with their authors; no project materials are rehosted here.