Electrochemical biosensors, systems, and methods of use

A method of detecting a biomarker associated with a disease in a biological fluid sample, comprising:

• contacting the biological fluid sample with a working electrode of an electrochemical biosensor, wherein the working electrode comprises a surface coated with graphene oxide nanoparticles and a capture agent conjugated to the graphene oxide nanoparticles;
• detecting, using the electrochemical biosensor, one or more changes in an electronic property of the working electrode resulting from binding of the biomarker to the capture agent;
• determining, using a computing device, electrochemical data based at least in part on the one or more changes in the electronic property of the working electrode detected by the electrochemical biosensor;
• inputting, by the computing device, the electrochemical data into a machine-learning (ML) model trained to analyze the electrochemical data to determine a risk level associated with the disease;
• and
• determining, by the computing device, the risk level associated with the disease based at least in part on the ML model.

A disease risk prediction system, comprising:

• an electrochemical biosensor comprising at least a working electrode, wherein a capture agent is disposed on a surface of the working electrode and is configured to selectively bind to a target biomarker associated with a disease, and wherein the electrochemical biosensor is configured to detect one or more changes in an electronic property of the working electrode based at least in part on the target biomarker binding to the capture agent;
• a computing device comprising a processor and a memory;
• and
• machine-readable instructions that, when executed by the processor, cause the computing device to at least:
• determine electrochemical data based at least in part on the one or more changes in the electronic property of the working electrode detected by the electrochemical biosensor;
• input the electrochemical data into a machine-learning (ML) model trained to analyze the electrochemical data to determine a risk level associated with the disease;
• and
• determine the risk level associated with the disease based at least in part on the ML model.