The medical field is going through an evolution — and artificial intelligence is powering its push.
The field of artificial intelligence — which includes machine learning and deep learning — is transforming from its research-based roots into reality, driving the charge to get more personalized, integrated and accessible health care.
Clearview Diagnostics is currently working on getting FDA approval for its AI-based cancer diagnostic tool, which is aimed both at providing more accurate and less costly breast cancer diagnosis. Company co-founder Dr. Rick Mammone says that by feeding that data through Clearview’s AI platform, the tool could work as an aid to drive down radiologist workloads, allowing them to focus on spending more time with their patients and dealing with more difficult cases.
CEO and co-founder Dr. Chris Podilchuk estimates that due to modern imaging technology and workload demands, radiologists have to, on average, interpret an image every three to four seconds in an eight-hour work day. Software to assist in image interpretation could be a valuable tool in this scenario.
The company’s AI platform has been validated through a National Institutes of Health study, which showed that the software could reduce the number of unnecessary biopsies on benign conditions by 70 percent while identifying all cancers.
Another company taking advantage of this spike in health care data is AiCure, which operates a visual recognition platform using computer vision and deep learning technology to confirm patients participating in clinical trials are taking their medications.
“About 20 to 30 percent of clinical trials fail because patients aren’t following protocol,” says Adam Hanina, CEO of AiCure. “Drugs don’t get to market that should because patients aren’t taking the investigative product.”
It also reduces the workload on nurses, who spend about 25 percent of their time on medication management. By automating some of this process, Hanina says AiCure aims to alleviate the nursing shortage and refocus those resources on patients who really need care.
“We believe AI in general is going to democratize health care in a way that’s not been possible before.”
Clearview Diagnostics is also tackling the high cost of health care, which is close to $3.3 trillion in the United States, by letting doctors make better recommendations leading to fewer unnecessary procedures and avoiding overdiagnosis.
“[Health care spending] is almost one out of every five dollars spent in this country,” says Mammone. “We have to make better decisions in order to shift to value-based health care that is focused on the patient.”
As this market shifts into high gear, let’s take a look at AI-based health care companies with transformational potential in 2017.
Babylon Health combines real doctors with AI to deliver a 24/7 personalized health care experience, all through a smartphone.
CareSkore leverages Google’s TensorFlow and Hadoop to identify at-risk patients by combining clinical, behavioral, demographic and socioeconomic information.
AiCure reduces the risk of patients skipping medications they are prescribed through a HIPAA-compliant AI agent that observes the patient through a smartphone.
Atomwise is revolutionizing drug discovery through deep learning algorithms that review diseases at the molecular level and pair them up with appropriate drugs based on that structure.
Recursion Pharmaceuticals combines biological science and machine learning techniques to discover new disease treatment, with the goal of treating 100 diseases in 10 years.
Arterys uses intelligent analytics combined with MRIs to visualize and quantify blood flow through an artery. The information is processed in the cloud and a full report is generated in 10 minutes.
Clearview Diagnostics is an AI software company developing tools to assist physicians in disease diagnosis. The company’s initial focus is breast cancer.
Butterfly Network has created a portable medical imaging device integrated with a deep learning assistant that helps diagnose patients in remote areas where clinicians aren’t available or are less likely to specialize.
DeepMind Health, which was acquired by Google in 2014, is leveraging machine learning to efficiently analyze eye scans, which are typically difficult to read and take a long time to process.