Point-of-care testing (POCT) has got more and more attention because of the characteristics of low-cost materials, compact designs, and user-friendly operation. However, when compared to traditional laboratory tests and assays, POCT is often less accurate. By quantifying the signals, Artificial Intelligence (AI)-based algorithms have the potential to significantly improve the performance of point-of-care (POC) sensors. As an industry-leading CRO company, Creative Biolabs has never stopped making progress and closely focuses on frontier science including AI application in medicine. With years of experience accumulated from practice, we are confident in providing high-quality AI-based POCT development services.

Application of AI in POCT

POCT provides a clinically relevant output promptly that allows a healthcare worker to make a clinical decision at the site of testing. Their development has been encouraged by the World Health Organization (WHO) and other agencies for use in developing nations that lack proper medical infrastructure. Ideally, these devices should be portable, rapid, cost-effective, and not require the use of laboratory staff and facilities. Nowadays, increasing demand and new technological developments are rapidly changing the health care industry. Due to the increasing availability of healthcare data and rapid development of big data analytic methods, the Artificial Intelligence (AI)/Machine Learning (ML)-based technologies at POCT have open their new avenues.

Typical steps in the developmental pathway for engineering mobile point-of-care diagnostics.Fig.1 Typical steps in the developmental pathway for engineering mobile point-of-care diagnostics. (Malekjahani, 2019)

Examples of AI Applied in POCT

  • Skin

Given the visibility of skin disease, dermatology has remained an active area for AI-based POCT research in medicine. There are FDA-approved systems for the assessment of skin lesions. For example, VisualDx DermExpert is a kind of mobile device deployable AI tool that automatically classifies skin morphologies from neoplasms to rashes offers a streamlined, point-of-care option.

  • Lyme disease (LD)

LD is the most common vector-borne infectious disease in both North America and Europe, causing 300, 000 infections annually in the United States. Paper-based computational multiantigen multiplexed vertical flow assay (xVFA) platform capable of diagnosing early-stage LD at the POC has been reported in recent research. The xVFA has a material cost of $0.42 per test and can be performed in 15 min by an individual with minimal training. A low-cost and hand-held optical reader enables automated analysis to quantify colorimetric signals generated on a nitrocellulose membrane, followed by analysis with a neural network for inferring a diagnosis from the multiantigen sensing information.

Overview of POC Lyme disease diagnostic testing using xVFA and machine learning.Fig.2 Overview of POC Lyme disease diagnostic testing using xVFA and machine learning. (Joung, 2020)

Services at Creative Biolabs

Focusing on the AI application over years, Creative Biolabs has thrown a lot of manpower, material, and financial resources into the research of AI-based medicine. With unremitting efforts, we have equipped our technology platform with advanced facilities, the latest technologies, and excellent scientific staff. Every step we paid during the practice gives us the confidence to provide high-level AI-based POCT development services to global customers.

With advantages in various aspects, Creative Biolabs aspires to bring every client top-rated customer experience and we are trying our best to do so. If you are interested in AI-based POCT development services or any other in vitro diagnostic (IVD) development services, please don't hesitate to contact us for more information.


  1. Malekjahani, A.; et al. Engineering steps for mobile point-of-care diagnostic devices. Acc Chem Res. 2019, 52(9): 2406-2414.
  2. Joung, H. A.; et al. Point-of-care serodiagnostic test for early-stage Lyme disease using a multiplexed paper-based immunoassay and machine learning. ACS Nano. 2020, 14(1): 229-240.

For Research Use Only.

Online Inquiry

*E-mail Address:
*Service & Products Interested:
Project Description:

Contact Us




Follow us on:
Copyright © 2021 Creative Biolabs.
Inquiry Basket