Artificial Intelligence: How AI is Revolutionising Oncology

Artificial intelligence (AI) advancements in oncology are yielding highly promising results and playing a crucial role in enhancing drug development and refining early-stage cancer detection. In this article, we explore the strides being made by artificial intelligence and the methods being used to surmount the obstacles patients are facing for access to essential drugs.  

The progress in AI is significantly boosting the precision of cancer diagnostics, bringing in a transformative era for oncology drug development. AI and machine learning are instrumental in pinpointing early-stage cancers, precisely locating specific cancer types, recommending optimal therapeutic approaches, characterising tumours, and predicting individualised immunotherapy responses.

Moreover, these tools can help researchers in accurately assessing whether a specific drug would effectively interact with a targeted cancer-related protein, thereby significantly accelerating the drug discovery processes.

Fast-tracking the development of oncology drugs

Artificial intelligence’s ability to comprehend and analyse large amounts of imaging and non-imaging data holds immense potential to expedite the development of oncology treatments. The pharmaceutical industry is harnessing these emerging technologies to bolster traditional screening studies, identify predictive biomarkers for therapeutic response, and facilitate the selection of optimal treatments.

For instance, oncology-focused biotech firm Lantern Pharma has developed a proprietary machine-learning-based platform to analyse patient data – such as genetic makeup and health issues – to accurately organise patients for specific cancer treatments. Similarly, Massive Bio has recently launched an AI-powered platform that enables oncologists to identify more cancer treatment options for patients, including recently approved drugs and active clinical trials. 

In addition to this, the Institute of Cancer Research (ICR), in conjunction with IDIBELL and Vivan Therapeutics, is using Big Data and AI to develop novel targeted cancer treatments that can overcome drug resistance, with a special focus on KRAS, a well-known cancer-driving protein.

To determine possible targets for cancer therapy, AI systems can analyse extensive chemical and biological databases. This enables researchers and medical professionals to confirm the most promising candidates for additional testing, ultimately saving time and resources in the drug development process. In addition, AI algorithms can help sponsors design more efficient and targeted clinical trials, potentially leading to faster approvals for drugs. 

According to the GlobalData report, Artificial Intelligence in Pharma, oncology is the leading therapy area for AI-developed drugs. These treatments are expected to dominate future drug launches and sales between 2025 and 2029. GlobalData estimates that the global oncology therapeutics market will reach a value of $343.7bn by 2033, with drugs for breast, colorectal, lung, prostate, and pancreatic cancers having the largest market share. 

Using AI for cancer diagnostics

In the healthcare sector, advanced technology can substantially improve the accuracy of diagnostics. AI algorithms can analyse medical images such as CT scans and mammograms, as well as detect tumours or any abnormalities with higher accuracy than conventional methods. 

Exploiting the potential of AI models, experts can predict the risk of patients developing cancer in the future. Using information from genetic data and medical imaging, oncology teams can analyse tumour gene sequencing data to predict the primary source of a patient’s cancer. This can be particularly useful in cases where the source of the tumour cannot be determined, helping guide treatment decisions and improving outcomes.

As of January 2023, the FDA has approved approximately 520 AI and ML algorithms for medical use. And 122 approvals in radiology account for 87% of the devices authorised in 2022.

An AI tool recently developed by scientists at the Mass General Cancer Center and the Massachusetts Institute of Technology in Cambridge can project the patient’s risk of developing lung cancer. According to one study, the technology named Sybil can identify whether a person could develop lung cancer in the next year. Accuracy rates were between 86% and 94%.

In Scotland, trials at the Aberdeen Royal Infirmary are investigating how AI can assist radiologists in reviewing thousands of mammograms each year. The Gemini project at NHS Grampian used an AI software called Mia to perform further evaluations after mammography scan assessments. An early-stage patient identified in the study has since undergone surgery. 

Meanwhile, researchers at the Royal Marsden NHS Foundation Trust, Imperial College London, and the Institute of Cancer Research, London are all developing AI technology to determine whether growths detected on CT scans are malignant. A radiomics-based AI algorithm was created using CT scans of 500 patients with large lung nodules. Medical photos can be analysed by technology to extract information that the human eye is not capable of seeing. Although the Libra study has shown promising results, further testing is needed before adoption by healthcare systems.

Patients support for the clinical uses of AI is evident. A GlobalData poll of patients’ perspectives on AI in clinical practice found that more than half of the 574 respondents were comfortable with medical practitioners using AI to support patient referrals, diagnoses, and treatment.

Facilitating access to oncology drugs

Despite these strides in the early detection of cancer using AI and the development of new drugs, challenges persist in access to oncology products and these can have a serious impact on a patient’s long-term health in fighting the disease. Geographical location, regulatory issues, healthcare systems and insurance coverage can form obstacles for healthcare treatments, not to mention the cost of such treatments which can form a significant barrier.

This is the case for Keytruda, a market-leading drug many predict will be the most-sold cancer treatment in 2023. Keytruda has proven effective at slowing down progression in multiple types of cancers at different stages, including breast, melanoma, kidney, and Hodgkin’s lymphoma, offering hope to patients at varying stages of the disease. However, with a list price as high as $150,000 a year, the cost of Keytruda is an issue for many patients. 

Similarly, targeted cancer drug Bevacizumab, also known as Avastin, has proven to be successful in treating different types of cancer. Avastin can reportedly cost between $4,000-$9,000 a month, depending on a patient’s weight and the type of cancer.

Cost-effective options for cancer drugs from Oximio

Increased demand for these treatments can drive up the costs. In such a landscape, medicine access programmes can help ensure more cost-effective options and efficient access to vital drugs for patients. At Oximio, we can assist patients and physicians in accessing effective oncology treatments such as Keytruda, Avastin, and Pomalidomide.

Through access programmes, we can help patients obtain oncology drugs often at lower prices than on the market – potentially saving thousands of Euros per treatment. While for uses of these drugs in clinical trials, we can quickly provide a quote. 

With an extensive global network of depots and warehouses, we can provide a range of options such as worldwide shipping and adaptive logistics to ensure shorter supply routes and protect the contents of shipments. We can also meet specific batch requirements with expiry dates that meet the needs of the patient or trial.

With almost two decades of expertise in clinical trial services, we can assist with navigating regulatory obstacles in the client’s country to ensure patients receive vital medical treatments – often ahead of schedule. 

Further information on our comparator sourcing services and latest oncology drug prices, are available on our website.

Further Reading

Application Note: 4 Major Trends in Oncology Clinical Trials.