In healthcare, the ability to diagnose early can be the difference between life and death or lifelong ill-health and costly medical care. Many times, ailments such as non-communicable diseases (NCDs), especially cancers, can be better treated if they were detected early. Cancer is still among the top-10 causes of mortality in Jamaica and several NCDs fill out the rest of that list. Early diagnosis is key in many instances to prevent death or disability.
Cancer, which is the general term for a group of various types of malignant tumors, is the leading cause of death worldwide, according to the World Health Organization (WHO). In 2020, cancer was responsible for nearly 10 million deaths globally.
Jamaica’s situation is much the same as the global picture, as cancer is also among the top-10 leading causes of death and is responsible for about 20 per cent of total deaths annually. In 2018, according to data from the Ministry of Health and Wellness and the WHO International Agency for Cancer Research, we should have seen over seven thousand new cases of cancer and the numbers continue to rise.
As health development progresses, technology has been adopted more and more to help in diagnosing diseases in general and specifically various types of cancers. Artificial intelligence (AI) as well as computer, machine and deep learning feature prominently as the best methods to achieve this purpose.
Just a few years ago, a revolutionary cancer diagnostic tool was developed showing how efficient and exact artificial intelligence can be in cancer diagnosis. The system first developed by neuropathologist Matija Snuderl of New York University’s Langone’s Perlmutter Cancer Center, “received state approval to use its AI classifier as a diagnostic test in October 2019, and researchers around the world are developing similar systems to help pathologists diagnose cancer more accurately” https://www.nature.com.
The AI has the ability to recognize patterns and detect elements that are too subtle for the human eye. This makes it a better option to detect cancer from its earliest stages. It can specifically capture cancer by type and subtype so that treatment can be streamlined and specific for better outcomes for the patient.
In recent years, many organisations started developing AI tools to better enable doctors to detect various types of cancers early. Colorectal cancer, for example was the second-ranked worldwide type of cancer during 2020 and has a high mortality rate. (https://www.ncbi.nlm.nih.gov/). For this reason, much effort has been put into research to try to reduce its incidence and resulting deaths.
ALGORITHMS AND AI
Machine learning algorithms and AI are able to better detect colorectal cancer and even the chance of the development of that type of cancer, than colonoscopy. Although, colonoscopy has a high detection and accuracy rate, “artificial intelligence has provided tools and algorithms capable of achieving high performance in terms of accuracy, sensitivity, and specificity to face tasks related to feature extraction, classification, detection, and region segmentation.” Viscaino, et al.
The National Institute of Dental and Craniofacial Research supported an international research team to study the extent to which artificial intelligence and deep learning could detect molecular and genetic alterations in images of tumors of 14 types of cancers. Co-leader of the study, researcher, Alexander Pearson and his team concluded that “the deep learning program successfully predicted a range of genetic and molecular changes across all fourteen cancer types tested. For example, the algorithm detected with high accuracy a mutated form of a gene, thought to be a main driver of head and neck cancer. It also accurately predicted the presence of standard molecular markers such as hormone receptors in breast cancer. Hormone receptor status is an important factor in guiding treatment options for patients with breast cancer.”
The use of technology in healthcare diagnosis is becoming more mainstream. AI has become a useful tool to achieve more specific diagnosis that would have been impossible without it. It is also used to capture people at risk of developing certain types of cancers to catch the disease sooner or take steps to prevent its development.
The overall objective is for technology to improve patient care by being able to have targeted treatment, as well as preventive care for better health outcomes.
Doug Halsall is the chairman and CEO of Advanced Integrated Systems. Email feedback to [email protected] and [email protected].