The battle against cancer is a difficult one to win. With cancer incidence likely to climb dramatically globally and almost half of the cancer diagnoses coming too late, cancer care professionals must seize every opportunity. Carcinogenic exposures in the workplace are still a concern more than five decades after the World Health Organization (WHO) identified cancer as a global health issue. Many known and suspected carcinogens are still prevalent in today’s workplaces, and uncertainty over the health consequences of these hazards has slowed regulatory action and the pursuit of safer alternatives has been put on hold.
The identification of occupational carcinogens is critical for primary prevention, compensation, and monitoring of exposed workers, as well as detecting cancer causes in the broader population. Of the around 120 agents classified by the International Agency for Research on Cancer (IARC) as carcinogenic to humans, most have sufficient evidence for their carcinogenicity in humans based on epidemiological studies. Exposure to many of these carcinogens (e.g. asbestos, crystalline silica, diesel engine exhausts, cadmium, benzene, radon, wood dust, vinyl chloride, and trichloroethylene) occurs in work contexts. Screening, early diagnosis of cancer, followed by timely and appropriate therapy, are the cornerstones of cancer’s secondary prevention, which helps to stagnate, inhibit, or reverse carcinogenesis.
AI as a Tool To Drive Excellence in Cancer Patient Care
Numerous studies demonstrate the impact of artificial intelligence (AI) technologies on the delivery of healthcare. AI-related technologies have the potential to improve cancer prognosis, diagnostics, and care planning. Moreover, AI is expected to become a fundamental element of healthcare services in the near future, incorporating itself into all facets of clinical treatment. As a result, several tech entrepreneurs and government-funded initiatives have invested in the development of AI-powered clinical tools and medical applications. Patients may be among the most significant beneficiaries and their perspectives may have an impact on the broad adoption of AI-based technologies.
The use of artificial intelligence as a decision support tool in diagnostics enables the scaling up of medical knowledge and the expansion of patient access to high-quality healthcare. As a consequence, AI has the potential to advance precision medicine and have a favorable influence on the diagnosis and treatment of major diseases such as cancer.
Advanced solutions that improve patient data collection and interaction help close gaps in treatment for cancer patients and others at risk while reducing the administrative load on physicians. It is a more contemporary approach to care management and cooperation that results in earlier detection of illness development and treatment possibilities. Integrating AI-based software into specialist care coordination is a method that plugs critical data gaps, boosts efficiency, and saves lives as medical practices aim to optimize care resources to provide a better experience for clinicians and patients.
AI Outperforms Radiologists in the Early Detection of Lung Cancer
Estimates based on statistics indicate that exposure to hazardous chemicals in the workplace is responsible for between 2 percent and 8 percent of overall cancer cases. The real scale of the occupational cancer burden, however, may be greater due to the vast number of potential carcinogens (IARC Group 2B) with unclear evidence and the ongoing discovery of new potentially carcinogenic chemicals in the workplace.
Lung cancer, for example, is the most prevalent cause of cancer death in the United States, accounting for 25% of all cancer-related fatalities. The likelihood of being diagnosed with the illness is significantly greater for veterans of the United States military and certain industries. Every year, the United States Department of Veterans Affairs identifies 7,700 Veterans with lung cancer, with an estimated 900,000 Veterans still at risk due to age, smoking, and environmental exposure while serving in the military.
Cancer screening using low-dose computed tomography (LDCT), a non-invasive alternative to chest X-rays, has been shown to reduce mortality by 20%–43%. However, there is potential for improvement since screening findings aren’t always accurate – there are significant rates of false positives and false negatives because some areas on the lungs might be misdiagnosed as malignancies while others are assumed to be benign. Due to the carcinogenic potency of tobacco smoking, secondary causes of lung cancer are often downplayed in perceived relevance. However, if treated as a distinct condition, lung cancer in nonsmokers would rank seventh in terms of cancer mortality globally, surpassing cervical, pancreatic, and prostate cancers, and would rank among the top 10 causes of death in the United States.
Any technology breakthrough should constantly aim to improve upon the status quo, enabling us to do tasks more effectively, quickly, or efficiently; and that’s exactly what AI has begun to accomplish in terms of cancer detection. Scientists conducted a research study in which they taught an artificial intelligence deep learning system to detect lung cancer in CT scans with the goal of improving the accuracy of such assessments. The researchers trained the algorithm to predict the risk of lung cancer by evaluating more than 42,000 CT scans of patients, including current and historical scans.
These CT images were from individuals with confirmed diagnoses; some had lung cancer, others did not, and some had benign masses that subsequently developed malignant. The algorithm was shown to be 94 percent accurate when evaluated against 6716 instances with established diagnoses. While the tool is still in its early phases of testing, the authors highlighted that the goal is for it to assist radiologists in diagnosing patients rather than replacing them. In terms of the tool’s future, researchers will attempt to validate the accuracy of AI diagnoses in bigger cohorts.
Treatment of Aggressive Cancer Improved by AI
While early diagnosis is a top objective, AI is also supporting patients suffering from rare malignancies that need intensive therapy and specific medications. The use of an artificial immune system, for example, has allowed clinicians to diagnose malignant pleural mesothelioma with 97.74 percent accuracy, according to a recent study. According to the findings of the research, the artificial immune system surpassed the multi-layer neural network algorithm, which is a technique that has been widely utilized to identify the illness in previous studies.
This subtype of mesothelioma is responsible for 70% to 90% of mesothelioma diagnoses, and the outlook for the condition is bleak, making early discovery essential for successful treatment. The development of the illness follows a predictable route, according to a new study employing artificial intelligence to evaluate genetic information from patients. Knowing this may assist medical practitioners in selecting the most appropriate treatment and also aid in the development of novel mesothelioma therapies. This strategy is equally applicable to different types of cancer.
Artificial Intelligence Aids in the Diagnosis of Brain Tumors
Despite the fact that the etiology of the vast majority of brain tumors is still unknown and that there are only a few well-established risk factors, research is increasingly showing links between specific environmental contaminants and the incidence of brain tumors. Many experts now consider that environmental variables might increase the risk of developing a brain tumor.
For instance, a study published in the British Journal of Cancer found a correlation between parents’ occupational exposure to solvents such as benzene, toluene, and trichloroethylene and the development of brain tumors in their children after birth. Exposure to benzene vapors and jet fuel was observed during aircraft fueling and maintenance at a number of US Air Force facilities.
Thanks to the integration of a novel technology that allows brain surgeons to observe diagnostic tissue and tumor margins in near-real-time, neurosurgeons may leave the operating room with greater confidence than ever before regarding their patient’s brain tumor diagnosis. According to specialists at Michigan Medicine, accuracy and precision will continue to increase as they attempt to include deep learning and computer vision into the treatment to accelerate it.
Todd Hollon, M.D., a neurosurgeon specializing in the treatment of brain tumors and chief neurosurgery resident at Michigan Medicine, has published a study in Nature Medicine outlining a two-part method for improving intraoperative diagnostic accuracy and efficiency. Hallon et al. discuss the most current use of a method called stimulated Raman histology (SRH), which was developed at Michigan Medicine to obtain images of tumor tissue promptly at the bedside. This enables neuropathologists to evaluate the images without requiring them to be processed, stained, or interpreted in a pathology lab, so avoiding the lengthy wait time associated with standard processing, staining, and interpretation. In addition, the researchers employed an artificial intelligence system known as a deep convolutional neural network to learn the features of the ten most frequent forms of brain cancer and anticipate when the disease will manifest itself. Surgery residents and residents-in-training get a diagnostic prediction at the bedside in minutes, with accuracy equivalent to that of the traditional technique.
AI Can Make High-quality Care More Affordable
If artificial intelligence performs as predicted, it has the potential to revolutionize health care by increasing access for underserved communities while simultaneously decreasing costs. This would a boon for the United States, which ranks poorly on numerous health indicators despite an average annual health care cost of $10,966 per person.
Today’s healthcare industry is experiencing a transition in order to reform an unsustainable system. Financial constraints – mostly as a result of growing expenses and reduced revenues and reimbursements – as well as a scarcity of qualified employees, are among the primary forces driving this transformation forward. The many different uses of artificial intelligence demonstrate the capability of the technology as well as its promise in the healthcare sector. The automation of time-consuming administrative activities is one of the most apparent applications of artificial intelligence. However, it may also be used to assist in decision-making in diagnostics, remote patient services, and the development of novel diagnostics and therapeutics.
The identification of new drugs and biomarkers is another area of the health business that might benefit from AI. There is a need to progress these topics within the existing paradigm of personalized medicine. Cost increases, on the other hand, are unsustainable. The cost of developing and obtaining market authorization for a new prescription drug is estimated to be $2.6 billion. The development and commercialization costs of a novel diagnostic biomarker are estimated to surpass $100 million.
About the author:
Jonathan Sharp, CFO of Environmental Litigation Group P.C., a law firm in Birmingham, Alabama, helps individuals and families struggling with mesothelioma due to occupational asbestos exposure.,
The Editorial Team at Healthcare Business Today is made up of skilled healthcare writers and experts, led by our managing editor, Daniel Casciato, who has over 25 years of experience in healthcare writing. Since 1998, we have produced compelling and informative content for numerous publications, establishing ourselves as a trusted resource for health and wellness information. We offer readers access to fresh health, medicine, science, and technology developments and the latest in patient news, emphasizing how these developments affect our lives.
