Using Artificial Intelligence in Oncology

Using Artificial Intelligence in Oncology

AI has made significant inroads in various therapeutic areas, with cancer care benefiting greatly from this powerful technology.

The FDA provides information on Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices, many of which support patient care in the oncology space.

This week’s Domain Knowledge explores how AI in oncology is positively transforming cancer diagnosis and treatment.

Cancer Impact

A cancer diagnosis brings unprecedented economic and social change to patients and their families. There’s understandable pain, fear, and confusion, as well as a need for education about treatment options and available technologies. As a healthcare community, it’s important for us to find solutions that support the best possible patient outcomes. 

Cancer treatment costs are significant, even when individuals are covered by insurance. There’s also a potential loss of income during treatment that needs to be considered. Some insurance policies may not cover all related cancer treatment costs, and patients can end up with large out-of-pocket expenses. 

Finances aside, cancer breaks the social fabric. Relationships are tested during the patient journey. A cancer diagnosis may lead to depression and feelings of defeat, along with many other stressful emotions.

Numerous studies show when cancer is diagnosed in the early stages; patients have better outcomes. It’s therefore critical for the healthcare community to do all they can to support the early diagnosis of cancer. One way to support this effort is through a second safety net read on all imaging studies – ensuring no potential or early-stage cancers are missed. 

Current Cancer Screening Processes

Presently, cancer screening and diagnosis involve a review of the patient’s medical history, physical exams, genetic tests, laboratory tests, and imaging procedures.

Imaging studies are the backbone of a cancer diagnosis, but they, too, have their limits, as seen in errors of omission resulting in missed or delayed diagnoses. Factors like staffing shortages, clinical experience level, fatigue, and limited peer review can contribute to a missed diagnosis. 

Other additional factors known to negatively impact effective cancer screening and diagnosis include communication failure between medical professionals and the lack of appropriate follow-up for needed care.

Improving Cancer Screening & Diagnosis With AI

Errors of omission can lead to missed or delayed diagnoses and have a negative impact on patient outcomes. AI, in the quality workflow, can support providers and improve patient care by acting as a safety net and achieving a second read on a large number of imaging studies vs the typical 3-5% during the peer review process.

How does this safety net work? Let’s look at lung cancer.

Lung cancer is the second most commonly diagnosed cancer globally and is one of the leading causes of death in women. Lung nodules, while often found incidentally during chest and abdominal imaging studies, can be easily missed. AI running in the background can flag these discrepancies, leading to an opportunity for early diagnosis.

Case Study

A large United States based health system implemented AI in the quality workflow to gain that second read on a large volume of their imaging studies. AI augmented the radiologist’s work, ran a second review in the background on thousands of CT scans, and had a limited impact on the radiology workflow.

After review, specific scans were flagged if a lung nodule was detected but not mentioned in the radiology report. The flagged scans were further evaluated through the health system’s quality review program to determine if the flagged nodules were actual misses. Results include:

  • The AI platform scanned 30,000 imaging studies
  • 1,137 imaging studies were flagged for undocumented findings
  • 118 studies had clinically significant lung nodules that directly impacted the course of patient care

Based on this case study and other research, the use of AI to identify undocumented lung nodules supports early lung cancer detection and improves the time to diagnosis.

Faster Imaging Classification

Imaging classification is a crucial part of diagnosing cancer. However, even with years of experience and skill, imaging classification is difficult and time intensive – because it’s subjective. 

The use of AI in oncology provides medical professionals access to data patterns that help them quickly and efficiently understand patient data, that in turn, directly impacts care. With the adoption of AI, providers can make more informed decisions, arrive at solutions faster, and assess medical images and records with more accuracy. It also helps prevent radiology fatigue which may also contribute to misdiagnosis.

Women’s Health offers an example of AI supporting imaging classification during routine breast health screening. By using artificial intelligence in oncology, medical professionals can quickly and accurately sort through breast MRIs in patients with dense breast tissue, eliminating those without cancer. AI used in this manner supports workload, and efficiency and allows radiologists to spend more time on studies that truly need their attention.

Future of AI in Cancer Diagnosis & Treatment

The goal of using AI in the oncology space is to improve cancer diagnosis and treatment as well as support radiologists and healthcare professionals providing patient care.  

When looking for a long-term partner to support your AI strategy, be sure they can provide:

  • Algorithm validation on your patient population and imaging equipment
  • Ongoing algorithm monitoring and updates
  • Top-notch data security offering on-premises, cloud, and hybrid options
  • Enterprise AI capable of running multiple AI algorithms across all of your facilities and clinics
  • User-friendly interface, regular training, and system troubleshooting support
  • AI is a technology that can improve the quality of cancer diagnosis and clinician workflow. AI should not be viewed as something that will replace clinicians; but rather as a tool to augment and support their work in providing high-quality patient care.

Key Takeaways

AI is one of the most impactful technologies in healthcare. There are numerous areas of adoption, from powering surgical robots to enabling early cancer detection.

In radiology, AI can augment the value practitioners provide their patients, thus improving healthcare outcomes.

AI can streamline workflows and lessen the radiologists’ administrative burden.

Picture of Ferrum Health

Ferrum Health

Simplifying Healthcare AI - Ferrum's AI Hubs enable clinicians to focus on their patients and the care they need, not complicated technology deployment.

Contact Us

CASE STUDY

ARA Health Specialists

Use the button below to download your free case study and learn how our approach to validation has improved the number of clinically significant findings in AI software.

CASE STUDY

Sutter Health

Use the button below to download your free case study and learn how our approach to validation has improved the number of clinically significant findings in AI software.