The aspirin-creator has partnered with startups and other tech companies to develop software and apps to speed diagnosis and guide treatment. The company is working with hospitals, academic researchers and others to compile everything the AI software needs to "learn" before it analyzes a patient's condition. That includes information on disease causes, symptoms and progression, plus many past patients' test results, doctor reports and scanned images.
The Associated Press recently interviewed Angeli Moeller, who heads artificial intelligence projects across Bayer's pharmaceutical business. Answers have been edited for clarity and brevity. Q: Why use partners for developing AI software and apps?
A: These areas are so new and so exploratory that you just wouldn't get there on time alone. We partner with companies that have that expertise and can accelerate development. We believe we will save a couple years.
Q: How is Bayer using AI? A: We're looking at cardiovascular disease, oncology and women's health. Our focus is on diagnosis but also on digital therapeutics, where you're using the technology to recommend a patient make a change in behavior to improve their health, or you're recommending medication changes.
Q: How would Bayer and other drugmakers working on AI software get hospitals or insurers to pay for using it? A: We would show that the software does what it says. It becomes cost effective and attractive for them when we can prove the improved outcomes with our app.
Q: How are you using AI to improve design and patient testing of experimental drugs? A: When developing a new drug, we can model how it will behave in a cell in combination with other drugs the patients might be taking. We're looking at how we can identify the right patients and sites to run our clinical trials. We would be able to run shorter studies and show where the medication is the right one for those patients earlier.
Q: How might this eventually affect doctors and patients? A: Everything we're doing in our artificial intelligence program is for decision support, because we want the doctor to make the decision on treatment. In the doctor's office, you would have a computer dashboard showing recommendations, but the really high-powered computing would happen somewhere else. What's most important for patients is that they're still in control of their treatment.
Q: How long will it be before this is helping average patients? A: It's probably going to take two years before it really hits mainstream medical practice. Getting the technology to the patient is still the hard part.