scholarly journals Towards AI-Enabled Multimodal Diagnostics and Management of COVID-19 and Comorbidities in Resource-Limited Settings

Informatics ◽  
2021 ◽  
Vol 8 (4) ◽  
pp. 63
Author(s):  
Olawande Daramola ◽  
Peter Nyasulu ◽  
Tivani Mashamba-Thompson ◽  
Thomas Moser ◽  
Sean Broomhead ◽  
...  

A conceptual artificial intelligence (AI)-enabled framework is presented in this study involving triangulation of various diagnostic methods for management of coronavirus disease 2019 (COVID-19) and its associated comorbidities in resource-limited settings (RLS). The proposed AI-enabled framework will afford capabilities to harness low-cost polymerase chain reaction (PCR)-based molecular diagnostics, radiological image-based assessments, and end-user provided information for the detection of COVID-19 cases and management of symptomatic patients. It will support self-data capture, clinical risk stratification, explanation-based intelligent recommendations for patient triage, disease diagnosis, patient treatment, contact tracing, and case management. This will enable communication with end-users in local languages through cheap and accessible means, such as WhatsApp/Telegram, social media, and SMS, with careful consideration of the need for personal data protection. The objective of the AI-enabled framework is to leverage multimodal diagnostics of COVID-19 and associated comorbidities in RLS for the diagnosis and management of COVID-19 cases and general support for pandemic recovery. We intend to test the feasibility of implementing the proposed framework through community engagement in sub-Saharan African (SSA) countries where many people are living with pre-existing comorbidities. A multimodal approach to disease diagnostics enabling access to point-of-care testing is required to reduce fragmentation of essential services across the continuum of COVID-19 care.

2019 ◽  
Vol 11 (4) ◽  
pp. 314-315
Author(s):  
James S Leathers ◽  
Maria Belen Pisano ◽  
Viviana Re ◽  
Gertine van Oord ◽  
Amir Sultan ◽  
...  

Abstract Background Treatment of HCV with direct-acting antivirals has enabled the discussion of HCV eradication worldwide. Envisioning this aim requires implementation of mass screening in resource-limited areas, usually constrained by testing costs. Methods We validated a low-cost, rapid diagnosis test (RDT) for HCV in three different continents in 141 individuals. Results The HCV RDT showed 100% specificity and sensitivity across different samples regardless of genotype or viral load (in samples with such information, 90%). Conclusions The HCV test validated in this study can allow for HCV screening in areas of need when properly used.


Biosensors ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 133
Author(s):  
Benjamin Heidt ◽  
Williane Siqueira ◽  
Kasper Eersels ◽  
Hanne Diliën ◽  
Bart van Grinsven ◽  
...  

Point of care (PoC) diagnostics are at the focus of government initiatives, NGOs and fundamental research alike. In high-income countries, the hope is to streamline the diagnostic procedure, minimize costs and make healthcare processes more efficient and faster, which, in some cases, can be more a matter of convenience than necessity. However, in resource-limited settings such as low-income countries, PoC-diagnostics might be the only viable route, when the next laboratory is hours away. Therefore, it is especially important to focus research into novel diagnostics for these countries in order to alleviate suffering due to infectious disease. In this review, the current research describing the use of PoC diagnostics in resource-limited settings and the potential bottlenecks along the value chain that prevent their widespread application is summarized. To this end, we will look at literature that investigates different parts of the value chain, such as fundamental research and market economics, as well as actual use at healthcare providers. We aim to create an integrated picture of potential PoC barriers, from the first start of research at universities to patient treatment in the field. Results from the literature will be discussed with the aim to bring all important steps and aspects together in order to illustrate how effectively PoC is being used in low-income countries. In addition, we discuss what is needed to improve the situation further, in order to use this technology to its fullest advantage and avoid “leaks in the pipeline”, when a promising device fails to take the next step of the valorization pathway and is abandoned.


Author(s):  
John P. Sibbitt ◽  
Mei He

Microfluidic lab-on-a-chip (MLOC) technology is a promising approach for point-of-care (POC) diagnosis; low reagent consumption, high sensitivity and quick analysis time are the most prominent benefits. However, microfabrication of MLOCs utilizes specialized techniques and infrastructure, making conventional fabrication time consuming and difficult. While relatively inexpensive production techniques exist for POC diagnoses, such as replication of polymer-based (e.g., PDMS) microfluidic POC devices on lithographic molds, this approach has limitations including: further hydrophilic surface modifications of PDMS, inability to change lithographic mold Z dimensions, and slow prototyping. In contrast, stereo-lithographical (SLA) printing can integrate all of the necessary fabrication resources in one instrument, allowing highly versatile microfluidic devices to be made at low cost. In this paper, we report two microfabrication approaches of microfluidics utilizing (SLA) 3D printing technology: I) Direct SLA printing of channels and structures of a monolithic microfluidic POC device; II) Indirect fabrication, utilizing SLA 3D printed molds for PDMS based microfluidic device replication. Additionally, we discuss previous work providing a proof of concept of applications in POC diagnosis, using direct 3D printing fabrication (approach I). The robustness and simplicity of these protocols allow integrating 3D design and microfabrication with smartphone-based disease diagnosis as a stand-alone system, offering strong adaptability for establishing diagnostic capacity in resource-limited areas and low-income countries.


ACS Sensors ◽  
2021 ◽  
Author(s):  
Nan Jiang ◽  
Natha Dean Tansukawat ◽  
Laura Gonzalez-Macia ◽  
H. Ceren Ates ◽  
Can Dincer ◽  
...  

PLoS ONE ◽  
2015 ◽  
Vol 10 (9) ◽  
pp. e0135869 ◽  
Author(s):  
Christopher T. Lam ◽  
Marlee S. Krieger ◽  
Jennifer E. Gallagher ◽  
Betsy Asma ◽  
Lisa C. Muasher ◽  
...  

TECHNOLOGY ◽  
2017 ◽  
Vol 05 (03) ◽  
pp. 115-128 ◽  
Author(s):  
Kurt Pianka ◽  
Alan Rothman ◽  
Anubhav Tripathi

Climate change, travel, and urbanization contribute to increasing exposure to Zika, Dengue and Chikungunya. Lab-based diagnostics are required because of overlapping clinical presentations. Here we review the current diagnostic methods, and find them poorly adapted to point of care use in resource-limited settings: generally, serologic assays are hindered by cross-reactivity while molecular assays require laboratory conditions. We conclude that a differential diagnostic device is critically needed, requiring a simpler molecular assay kit that maintains high sensitivity and specificity.


2017 ◽  
Vol 55 (8) ◽  
pp. 2313-2320 ◽  
Author(s):  
Thomas R. Kozel ◽  
Amanda R. Burnham-Marusich

ABSTRACT Point-of-care (POC) diagnostics provide rapid actionable information for patient care at the time and site of an encounter with the health care system. The usual platform has been the lateral flow immunoassay. Recently, emerging molecular diagnostics have met requirements for speed, low cost, and ease of use for POC applications. A major driver for POC development is the ability to diagnose infectious diseases at sites with a limited infrastructure. The potential use in both wealthy and resource-limited settings has fueled an intense effort to build on existing technologies and to generate new technologies for the diagnosis of a broad spectrum of infectious diseases.


2017 ◽  
Author(s):  
Sung-Jin Kim ◽  
Chuangqi Wang ◽  
Bing Zhao ◽  
Hyungsoon Im ◽  
Jouha Min ◽  
...  

ABSTRACTLens-free digital in-line holography (LDIH) is a promising microscopic tool that overcomes several drawbacks (e.g., limited field of view) of traditional lens-based microcopy. However, extensive computation is required to reconstruct object images from the complex diffraction patterns produced by LDIH, which limits LDIH utility for point-of-care applications, particularly in resource limited settings. Here, we describe a deep transfer learning (DTL) based approach to process LDIH images in the context of cellular analyses. Specifically, we captured holograms of cells labeled with molecular-specific microbeads and trained neural networks to classify these holograms without reconstruction. Using raw holograms as input, the trained networks were able to classify individual cells according to the number of cell-bound microbeads. The DTL-based approach including a VGG19 pretrained network showed robust performance even with noisy experimental data. Combined with the developed DTL approach, LDIH could be realized as a low-cost, portable tool for point-of-care diagnostics.


Sign in / Sign up

Export Citation Format

Share Document