2023 has seen a leap forward in generative AI text-based tools such as ChatGPT and artistic applications such as MidJourney and Dall-E. Many productivity and search applications have integrated new AI functions as part of their tool kit. These new functions have enormous potential, while also raising concerns about how these new AI tools will be regulated and controlled.
However, while AI may be new to many users, the use of artificial intelligence (AI) in healthcare is already well established. AI systems have the potential to improve the efficiency of healthcare systems and provide physicians with an expert assistant. For patients, the benefits are potentially life changing. AI solutions have paved the way for clinicians to gain more in-depth data and insights to detect various diseases. Like any other tool available for clinicians, these AIs are subject to rigorous regulation — but are already delivering tangible benefits that save lives.
In one example, lung cancer patients have benefited from AI software that helps detect and diagnose lung cancer much earlier in the patient care journey. Nodule clinic teams at several leading lung-cancer centers are using this system to help them distinguish benign lung nodules from malignant ones. Armed with expert analytics and insights, clinicians can make better patient care decisions and improve patient outcomes through faster diagnosis and earlier intervention.
The Reality Check of AI in Healthcare
Lung cancer is the leading cause of cancer deaths worldwide, with approximately 1.8 million people dying from this disease each year. Most patients are diagnosed after symptoms have appeared and the disease has progressed to an advanced stage (Stage III or IV), which is consistent with the current worldwide five-year survival rate of just 20 percent. In contrast, the survival rate for small lung tumors that are treated at Stage 1A is as high as 90 percent. This significant difference highlights a critical need for diagnosis and treatment of lung cancer at the earliest possible stage — and this is where AI has already made a notable impact.
AiThority News of the Week: Deepset Raises $30 Million From Balderton Capital to Help the World’s Biggest Companies Leverage LLM Promise
Fast-Track Patient Care
One of best opportunities to diagnose more small, pre-symptomatic lung cancers earlier is presented by the two million patients in the United States every year who have a lung nodule identified incidentally during chest CT scans ordered for other reasons, such as during an ER visit or after a cardiac event.
Current care guidelines mandate follow-up over one to two years to determine whether a nodule is cancerous.
However, more than 60 percent of these patients do not receive guideline-recommended follow-up, which severely limits opportunities for early intervention and treatment. Patients who do receive recommended follow-up often require multiple imaging scans and biopsies, and sometimes unnecessary invasive procedures such as surgical biopsies and lung resections, before arriving at a definite diagnosis.
By integrating AI decision-support software with CT scan data, clinicians can identify and track at-risk patients, and optimally diagnose the signs of lung cancer much earlier. This means treatment can be started sooner for patients with tumors, and invasive procedures such as biopsies on benign lesions are minimized. And, with many hospitals running short-staffed, the AI system can review hundreds of case notes and CT scans — a task that would otherwise require additional full-time employees.
Recommended AI ML Insights: Top AI Software Companies for Image Recognition
The proven potential for better outcomes with this integrated AI-assisted approach has led to its FDA approval and the granting of a medical Current Procedural Terminology (CPT) code that helps streamline reporting, process claims and develop guidelines that will accelerate the adoption of this diagnostic system across more healthcare systems.
Considerations When Applying AI in Clinical Settings
Just as with every new technology, much is learned during its initial deployments. Here are some practical considerations that are key to making the application of AI in healthcare settings successful:
- Invest in training: clinicians must learn how to apply the insights generated by the AI-based diagnostics; the role of the AI is that of a trusted advisor that can consistently identify a potential problem that may otherwise be overlooked.
- Systems integration: an integrated approach to care is needed so that insights can be gathered across multiple CT scans across the entire patient pathway and the appropriate timely action is taken across teams and healthcare settings.
- Collaboration: fostering information sharing across teams and settings is key to ensure that the AI-driven insights are responded to by clinicians who are the ultimate decision-makers.
With a combination of clinically trialed AI software that has proven results, and the right practical support in place across healthcare systems, modern medicine can utilize these new transformative technologies to continue to improve the standard of patient care.
Comments are closed.