Artificial Intelligence and Machine Learning In Healthcare

Artificial Intelligence (AI) and its connected services are on track to becoming the biggest stimulators of lifestyle changes, automation, healthcare innovation, global productivity, and the foundation of a tremendous amount of revenue. By 2030, AI’s potential contribution to the global economy will be about 15.7 trillion dollars and 45% of the total economic gains by then will be from product enhancements, provoking consumer demand. Artificial intelligence (AI) is heralded as the most disruptive technology to health services in the 21st century. This is because AI will drive increased customization, product variety, affordability and “intelligent” decision-making in global healthcare industries. The healthcare industry has already been using AI/ML in diverse situations. The impact of these tools in healthcare are bolstered due to their highly suitable applications. From AI assisted robotic surgery, to image analysis, the use of AI/ML technologies have allowed healthcare systems to apply Big Data tools for data analytics. In this post, we will discuss AI and ML examples and applications that are in use today.

‍

Diagnosing and Identifying diseases

Rare diseases are often difficult to identify and their diagnoses often depend on detecting edge cases, defined as problems or situations that occur only at an extreme (maximum or minimum) operating parameter. One of the main applications of ML is the diagnosis and identification of diseases which are otherwise nearly impossible to diagnose.

Machine Learning systems are built on vast sets of data containing raw images (and various transformations). This in turn allows for them to be far more advanced than humans in the detection of diseases such as cancers in their initial stages or other genetic diseases. An example of this is, Project InnerEye which uses 3D radiological imaging to identify tumors by aiding in precise surgery planning, navigation, and efficient tumor-contouring for radiotherapy. Moreover, IBM Watson Genomics is an example of how the combination of genetic based tumor sequencing and ML can be integrated to help make faster and more accurate diagnosis. As imaging systems such as MRI are increasingly used for early cancer diagnosis, they are being implemented with ML algorithms.
‍

Drug discovery

Ask anyone in the pharma industry and they will tell you that drug discovery is a viciously difficult process. Nowadays however, big names in the pharma industry are applying AI and ML to their strategies from metabolic diseases to cancer treatments and immuno-oncology drugs. R&D technologies such as next-generation sequencing and precision medicine can help in finding alternative paths for therapy of diseases.

According to Berg, a biotechnology company, they use their AI platform to analyze immense amounts of biological and outcomes data (lipid, metabolite, enzyme, and protein profiles) from patients to highlight key differences between diseased and healthy cells and identify novel cancer mechanisms. Project Hanover developed by Microsoft is using ML-based technologies for multiple initiatives including developing AI-based technology for cancer treatment and personalizing drug combinations for AML (Acute Myeloid Leukemia).

‍Medical Imaging Diagnosis

Artificial intelligence can support radiologists and pathologists as they use medical imaging to diagnose a wide variety of conditions. AI/ML can improve traditional medical imaging methods like Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and X-ray by offering computational capabilities that process images with greater speed and accuracy.

These days, well-trained radiologists are hard to come by and on top of that, there are many ailments such as cancers, lesions and foci, which cannot be modeled using complex equations. Because ML based algorithms take information from a multitude of different samples available on-hand and learn from these samples, it becomes easier to diagnose and find the variables. An example of one of the most popular ML applications in imaging diagnosis and analysis is the classification of lesions and cancers as normal or abnormal. But these days, machines can interpret and identify much more, for instance, suspicious spots on the skin, lesions, tumors, and brain bleeds. The usage of AI/ML tools/platforms for assisting radiologists is, therefore, primed to expand exponentially.

According to Abhimanyu S. Ahuja in her article on, the impact of artificial intelligence in medicine on the future role of the physician, AI has the potential to improve medical imaging with:

• Increased productivity: AI has better computational capabilities than humans, so it can analyze medical images faster than medical doctors.
• Higher automation: AI can automate parts of the radiology workflow.
• Standardized processes: AI can supply doctors with AI tools to compute big data and help doctors and encourage them to work smarter and more efficiently.
• More accurate diagnosis: Studies show that AI can be more efficient than doctors and experts at diagnosing many diseases like cancer from medical images. For example, scientists at Google have created an AI that diagnoses breast cancer. The AI is fed with slides of medical images and uses DL algorithms to diagnose cancerous cells. The AI recorded a 99% accuracy in cancer diagnosis based on these slides compared to 38% of some doctors in the comparison group.
• Computing quantitative data: AI has the ability to use quantitative data in ways that are beyond the limits of human cognition. For example, AI can predict if a patient will suffer from heart failure based on their medical history and rate of hospital visits.
• Assistance for doctors: AI can compute a large amount of data, map it and represent the relevant parts in a brief and efficient format that doctors can use

Furthermore, in order to standardize AI and make sure it is effective, yet safe, the American College of Radiology Data Science Institute (ACR DSI) has released a number of high-value use cases for artificial intelligence in medical imaging, which will be continuously updated as new opportunities present themselves. Chief Medical Officer at DSI, Bibb Allen Jr. states, “The ACR DSI use cases present a pathway to help AI developers solve health care problems in a comprehensive way that turns concepts for AI solutions into safe and effective tools to help radiologists provide better care for our patients.”

Outbreak Prediction

In light of the ongoing COVID-19 crisis and the rising fear of pandemics, AI/ML are being used to monitor and predict future outbreaks globally. With the technology that is available to scientists today, the data collected from social media, satellites, website information and even medical devices help assemble this information and predict diseases like malaria. These predictions are crucial to third world countries where there is a severe lack of educational and medical infrastructure in place. With COVID-19 and the fear of pandemics running higher than ever, the importance of running parallel vaccine development trials and therapeutic research projects has never been more apparent. AI techniques must be put to action for global problem-solving.

More AI/ML applications in Healthcare:

• Prevent hospital acquired infections (HAIs): Health systems can reduce HAIs, such as central-line associated bloodstream infections (CLABSIs)—40 percent of CLABSI patients die—by predicting which patients with a central line will develop a CLABSI. Clinicians can monitor high-risk patients and intervene to reduce that risk by focusing on patient-specific risk factors.
• Predict propensity-to-pay: Health systems can determine who needs reminders, who needs financial assistance, and how the likelihood of payment changes over time and after particular events.
• Predict chronic disease: Machine learning can help hospital systems identify patients with undiagnosed or misdiagnosed chronic disease, predict the likelihood that patients will develop chronic disease, and present patient-specific prevention interventions.
• Reduce readmissions: Machine learning can reduce readmissions in a targeted, efficient, and patient-centered manner. Clinicians can receive daily guidance as to which patients are most likely to be readmitted and how they might be able to reduce that risk.
• Reduce hospital Length-of-Stay (LOS): Health systems can reduce LOS and improve other outcomes like patient satisfaction by identifying patients that are likely to have an increased LOS and then ensure that best practices are followed.

Although known challenges from data privacy and legal frameworks will continue to be obstacles, there are many exciting applications of AI/ML techniques and platforms, to look forward to in the future of healthcare. One of these applications is the CypherMed Cloud, which is an integrated, highly secured, platform for collecting medical devices and patient data. CypherMed Cloud works hand-in-hand with analysis software and cloud-based AI/Machine Learning algorithms.