Maria Shepherd, President and Founder, Medi-Vantage06.06.23
Artificial intelligence (AI) has become an essential tool in the medtech market, where it is being used to improve patient outcomes, reduce costs, and enhance efficiency. AI has the potential to transform healthcare by enabling clinicians to make more informed decisions based on data-driven insights. In this article, we will explore three examples of AI strategies in the medical device market that are changing healthcare.
One example is the use of machine learning (ML) algorithms to detect breast cancer. Mammography is the gold standard for screenings, but it is not perfect. False negatives and positives can occur, leading to missed diagnoses or unnecessary biopsies. Researchers are now using ML algorithms to improve the accuracy of mammography. These algorithms can analyze thousands of mammograms and learn to recognize patterns associated with breast cancer, allowing them to identify potential tumors that may have been missed by human reviewers.
Studies have been conducted to evaluate the performance of AI algorithms for breast cancer detection and diagnosis. Following are some key statistics on breast cancer imaging using AI.
In 2020, a study published in Nature Reviews revealed an AI system developed by Google Health outperformed radiologists in detecting breast cancer on mammograms. The AI system achieved a higher level of accuracy and sensitivity.1
A 2019 study published in the Journal of the National Cancer Institute found an AI system was able to accurately identify breast cancer on mammograms with high sensitivity and specificity (Table 1).2
Another 2019 study published in Radiology found an AI system was able to accurately detect breast cancer on mammograms with an AUC (area under the curve) of 0.94 (a high level of accuracy).3
Overall, these studies suggest AI has the potential to improve breast cancer imaging and diagnosis, and may ultimately lead to better patient outcomes. However, further research is needed to validate the effectiveness of AI systems in clinical settings and to address potential challenges.
Compare this to a study published in the New England Journal of Medicine in 2007, where the accuracy of mammography in detecting breast cancer varied depending on a number of factors, including the patient age, breast density, and radiologist experience.4
It's worth noting the 2007 statistics in Table 1 reflect the performance of radiologists without the assistance of AI technology, which has since been shown to improve the accuracy of detection.
One example of AI in wearables is the use of ML algorithms to monitor sleep. Wearables such as smartwatches and fitness trackers (Table 2) can monitor sleep patterns, but they are not always accurate. ML algorithms can analyze data from these devices and learn to recognize patterns associated with different sleep stages. This can provide users with more accurate information about these patterns and help them to make changes to improve sleep quality.
Another example is the use of predictive analytics to enable ongoing monitoring of diabetes. Wearables such as continuous glucose monitors (CGM) can provide patients with real-time data about their blood sugar levels, but managing diabetes can be challenging. Predictive analytics can analyze data from CGMs and other wearables to identify patterns associated with high or low sugar levels, helping patients make more informed decisions and facilitate more personalized treatment plans.
Today, approximately 5 billion people in the world don’t have suitable access to surgical treatment (Table 3).6 When combined with advanced robotics, AI-based systems have the possibility to close the gap and ensure patients globally will receive the surgical care they deserve.
AI also ensures doctors have access to learning opportunities from the best proctors and can support a larger number of clinicians performing surgery. Regardless of location, surgeons can study and utilize AI-based surgical robotics to reach a broader patient population. Surgeons who perform one type of procedure today can increase their impact by mastering a new tool to adopt a wider variety of procedures.
References
Maria Shepherd has more than 20 years of experience in marketing in small startups and top-tier companies. She founded Medi-Vantage, which provides marketing and business strategy for the medical device industry. She can be reached at mshepherd@medi-vantage.com. Visit her website at www.medi-vantage.com.
Why This Is Important
AI is an important component in medical devices for several reasons.- Increased accuracy: AI processes vast amounts of data and is able to identify patterns not obvious to a human caregiver. This can help doctors and other medical professionals make more accurate diagnoses and determine better treatment plans.
- Improved patient outcomes: AI can enable medical devices to adapt to a patient's individual needs and preferences.
- Faster processing times: AI can process data much faster than humans, which can be critical in time-sensitive situations such as during an ER visit.
- Cost savings: By improving accuracy and efficiency, AI can help reduce costs associated with medical care.
AI in Medical Imaging
Medical imaging is one of the most critical areas in healthcare, providing clinicians with the information they need to diagnose and treat a wide range of conditions. However, interpreting medical images can be time-consuming, tedious, and complex, requiring a high level of expertise. AI is changing this by automating the process, reducing clinicians’ workload and improving accuracy.One example is the use of machine learning (ML) algorithms to detect breast cancer. Mammography is the gold standard for screenings, but it is not perfect. False negatives and positives can occur, leading to missed diagnoses or unnecessary biopsies. Researchers are now using ML algorithms to improve the accuracy of mammography. These algorithms can analyze thousands of mammograms and learn to recognize patterns associated with breast cancer, allowing them to identify potential tumors that may have been missed by human reviewers.
Studies have been conducted to evaluate the performance of AI algorithms for breast cancer detection and diagnosis. Following are some key statistics on breast cancer imaging using AI.
In 2020, a study published in Nature Reviews revealed an AI system developed by Google Health outperformed radiologists in detecting breast cancer on mammograms. The AI system achieved a higher level of accuracy and sensitivity.1
A 2019 study published in the Journal of the National Cancer Institute found an AI system was able to accurately identify breast cancer on mammograms with high sensitivity and specificity (Table 1).2
Another 2019 study published in Radiology found an AI system was able to accurately detect breast cancer on mammograms with an AUC (area under the curve) of 0.94 (a high level of accuracy).3
Overall, these studies suggest AI has the potential to improve breast cancer imaging and diagnosis, and may ultimately lead to better patient outcomes. However, further research is needed to validate the effectiveness of AI systems in clinical settings and to address potential challenges.
Compare this to a study published in the New England Journal of Medicine in 2007, where the accuracy of mammography in detecting breast cancer varied depending on a number of factors, including the patient age, breast density, and radiologist experience.4
It's worth noting the 2007 statistics in Table 1 reflect the performance of radiologists without the assistance of AI technology, which has since been shown to improve the accuracy of detection.
AI in Wearables
Wearable devices are becoming increasingly popular in healthcare, providing patients a way to monitor their health and track progress over time. AI is enabling them to provide more personalized and accurate information to users.One example of AI in wearables is the use of ML algorithms to monitor sleep. Wearables such as smartwatches and fitness trackers (Table 2) can monitor sleep patterns, but they are not always accurate. ML algorithms can analyze data from these devices and learn to recognize patterns associated with different sleep stages. This can provide users with more accurate information about these patterns and help them to make changes to improve sleep quality.
Another example is the use of predictive analytics to enable ongoing monitoring of diabetes. Wearables such as continuous glucose monitors (CGM) can provide patients with real-time data about their blood sugar levels, but managing diabetes can be challenging. Predictive analytics can analyze data from CGMs and other wearables to identify patterns associated with high or low sugar levels, helping patients make more informed decisions and facilitate more personalized treatment plans.
AI in Surgical Robotics
Robotic surgical systems allow surgeons to perform procedures with greater precision and control, potentially reducing the risk of complications and improving patient outcomes. AI is playing a crucial role in them, enabling these systems to learn from data and improve their performance over time.Today, approximately 5 billion people in the world don’t have suitable access to surgical treatment (Table 3).6 When combined with advanced robotics, AI-based systems have the possibility to close the gap and ensure patients globally will receive the surgical care they deserve.
AI also ensures doctors have access to learning opportunities from the best proctors and can support a larger number of clinicians performing surgery. Regardless of location, surgeons can study and utilize AI-based surgical robotics to reach a broader patient population. Surgeons who perform one type of procedure today can increase their impact by mastering a new tool to adopt a wider variety of procedures.
The Medi-Vantage Perspective
AI is a golden opportunity when combined with robotic surgery, imaging, wearables, and many other applications. Integrating AI-based systems into medtech is crucial to improve the surgeon and patient experience. What is your AI strategy?References
- go.nature.com/43dhEo5
- bit.ly/mpo230602
- bit.ly/mpo230603
- bit.ly/mpo230604
- bit.ly/mpo230605
- bbc.in/3ofIr4e
Maria Shepherd has more than 20 years of experience in marketing in small startups and top-tier companies. She founded Medi-Vantage, which provides marketing and business strategy for the medical device industry. She can be reached at mshepherd@medi-vantage.com. Visit her website at www.medi-vantage.com.