Autonomous Reliability Assessment Boosts Sensitivity of Rapid Diagnostic Tests
The Californer/10348802

LOS ANGELES - Californer -- Researchers at the University of California, Los Angeles (UCLA) have developed an uncertainty quantification framework that autonomously identifies and excludes unreliable neural network predictions in computational point-of-care diagnostic platforms. As a testbed, they used a paper-based vertical flow assay for rapid diagnosis of Lyme disease—the most common tick-borne disease worldwide.

The vertical flow assay platform combines a disposable paper-based assay, a handheld smartphone-based optical reader, and a deep learning inference algorithm to deliver Lyme disease diagnostic results in under 20 minutes using only a droplet of patient serum. Unlike conventional single-analyte rapid tests that display a single test line, the vertical flow assay contains a multiplexed panel of 25 spots, each coated with proteins that specifically bind to antibodies developed in response to Lyme exposure. After activation, the assay produces a rich image-based signal pattern that is interpreted by a neural network, which delivers a binary Lyme-positive or Lyme-negative result.

More on The Californer

• Senco Home Services Expands Residential Construction Services
• Ricci's Painting & Contracting Expands Home Transformation Services
• Best Wig for First-Time Wig Wearers
• ROBAM Launches Next-Generation Under Cabinet Range Hoods Designed for High-Heat Home Cooking
• gptmelo Helps Brands Improve Visibility In AI Search And LLM Recommendations

To improve the reliability of this vertical flow assay platform, UCLA researchers developed an uncertainty quantification framework based on Monte Carlo dropout (MCDO). In this framework, each sample is processed not only by the baseline diagnostic neural network, but also by 1,000 additional models, termed MCDO models. These models share the same architecture and trained weights as the baseline model, but during inference, a random subset of their neurons is temporarily deactivated, producing a distribution of 1,000 additional predictions. By comparing this distribution with the baseline disease prediction, the researchers introduced a score termed the uncertainty figure of merit, which autonomously quantifies the reliability of each diagnostic result.

Tests with low figure-of-merit values are deemed unreliable and automatically flagged as "Do not use". Such tests are excluded from clinical decision-making. Tests with high figure-of-merit values are labeled "Trust", and their diagnostic predictions can be reported to clinicians for follow-up care and treatment.

More on The Californer

• Fall Jewellery Trends 2026: The Timeless Pieces Defining Autumn Luxury
• New Podcast 'Circles | Edges' Revives Late-Night Intimate Talk Radio Format
• Long Beach Parks, Recreation and Marine Invites Community Volunteers to Join Independence from Litter Cleanup
• California: Governor Newsom signs historic housing bond set for voters on the November ballot
• Audilus Named Sync Licensing Representative for Three Labrador Entertainment Catalogs

With this MCDO-based approach, the researchers specifically aimed to reduce false negative predictions — cases where a patient with Lyme disease is incorrectly diagnosed as Lyme-negative. In blinded testing on new patient samples, applying the uncertainty quantification pipeline improved the sensitivity of the vertical flow assay from 88.2% to 95.7%, while preserving 100% specificity.

The approach is designed to also work with any rapid diagnostic test processed by a neural network, including tests for other infectious diseases, cardiovascular conditions, and various clinical biomarker panels.

The study was supervised by Professors Aydogan Ozcan and Dino Di Carlo of UCLA. The other authors include Artem Goncharov, Rajesh Ghosh, and Hyou-Arm Joung.

Article: https://doi.org/10.1021/acsnano.6c06616