Journal of Health Care Communications Open Access

  • ISSN: 2472-1654
  • Journal h-index: 15
  • Journal CiteScore: 6.77
  • Journal Impact Factor: 7.34
  • Average acceptance to publication time (5-7 days)
  • Average article processing time (30-45 days) Less than 5 volumes 30 days
    8 - 9 volumes 40 days
    10 and more volumes 45 days
Reach us +32 25889658


Cancer Detection Using Innovative Advanced Artificial Intelligence

David Herman*, Christy Hunter and German Alfredo Sinuco Leon

This evidence report discusses an advanced artificial intelligence technology to detect cancer early, accurately and inexpensively. Initial type is breast cancer; however this technology is not limited and can be applied to other cancers.

This technology uses scans that are image files. Scans are from a patient who may have cancer. The image files are then provided to this technology for analysis. The technology automatically generates a report indicating the probability that the patient has cancer.

The report is intended to be reviewed by a medical specialist who may perform additional tests on the patient with a high probability of having cancer. If, on the other hand, the report indicated a low probability of having cancer, scarce resources may not need to be allocated as a high priority.

As an example, mammograms are required to use two independent radiologists to review the results. This technology could be utilized without mandatory radiologists at this stage. These radiologists could be more effectively utilized at a later stage to determine how far the cancer may have spread.

Sources of image files can be mammograms, finite needle aspirations, ultrasound scan as examples. Artificial intelligence technology is first trained so it can recognize cancer reliably. Other artificial intelligence technologies typically require thousands for training. And, results are not comparably reliable. The advanced artificial intelligence technology discussed in this report trains with high reliable image files using bespoke pretraining modules that are one of many factors to keep the training samples low and accurate. After training, this technology utilizes additional bespoke advanced modules for further accuracy refinements.

Training summary:

• May be skipped entirely based on analysis of known scans.

• This relies on existing training using NCBI vetted cancer samples.

• Or, if training is required, very few training samples are needed. This is due to bespoke non AI modules.

Published Date: 2023-10-31; Received Date: 2023-10-03