Artificial Intelligence in Healthcare – Potential Use Cases

Mar 11, 2019

 

The greatest change AI will bring about in healthcare is the enabling of clinicians to make sense of the mind-boggling amount of patient data being generated every day. Establishing concrete patterns between diverse data points will empower doctors to make precise diagnoses and prescribe well-informed treatments. IBM Watson may be the pioneer when it comes to cognitive computing for healthcare, but the battleground is already getting crowded with players like Apple, Dell, HP, Hitachi Data Systems, Highspot, and Enterra — just to mention a few.

AI has already found its way into healthcare and has begun revolutionizing many fields in dire need of innovation.

Mining medical records

Extracting information from medical data is the most obvious application of AI in healthcare. Collecting, storing, normalizing, and tracing its lineage — that’s how data will work for us rather than against us. Alphabet, Google’s parent company, recently launched the DeepMind Health project. As part of it, medical records will be mined to provide better and faster health services. Google had acquired DeepMind for £400 million.

 

Assisting repetitive jobs

IBM launched an algorithm called Medical Sieve, an ambitious long-term project to build the next generation ‘cognitive assistant’ with never-before-seen capabilities. AI solutions like Medical Sieve can analyze radiology scans to detect problems faster and far more reliably — no need for radiologists to go through each case. They could focus on other tasks and step in only in the most complicated cases. Last year, Google showed that its deep-learning algorithm, trained on a large set of fundus images, can detect diabetic retinopathy with more than 90% accuracy. IBM also acquired medical imaging company Merge Healthcare for $1 billion to build on the work started by the Medical Sieve project. It’s safe to say that AI in healthcare is making groundbreaking progress.

 

Drug creation

Billions of dollars and decade-plus years are spent to bring a new drug to the market. Speeding up the process would be hailed as the Holy Grail for drug research. Atomwise uses supercomputers that spit out therapies from a database of molecular structures. Last year, Atomwise launched a virtual search for existing medicines that could be redesigned to treat the Ebola virus. They found two drugs predicted by it that may significantly reduce Ebola infectivity. This analysis was completed in less than a day, compared to the typical months or years. Atomwise has raised more than $6 million in multiple rounds of funding. Hence, AI in medicines is also making rapid progress.

 

Precision medicine

To be able to develop customized treatment for everyone has long been an elusive dream for healthcare. Deep Genomics identifies patterns in huge data sets of genetic information and medical records, looking for mutations and linkages to disease, thus precisely identifying the responsible cell. They are also inventing computational technologies that can tell doctors what will happen within a cell when its DNA is altered by genetic variation. Deep Genomics has raised more than $16 million in funding as of September 2017. The worth of worldwide precision medicine market is expected to cross $96 billion by 2024.

 

Telehealth

The telehealth market’s worth is estimated to reach $9.35 billion by 2021. Babylon, the British online medical consultation service, launched an app this year which offers medical AI consultation based on personal medical history and common medical knowledge. It can use speech recognition to check the symptoms against a database of diseases and then offer an appropriate course of action. The app will also remind patients to take their medication and follow up to find out how they’re feeling. Through such AI solutions, the waiting time in front of the doctor’s examining room would drop significantly, while the efficiency of diagnosing patients can increase by multiple times. Babylon has raised more than $85 million in funding as of April 2017.

 

For these breakthroughs to really shine and create real, affordable, and accessible value for all, the prejudices and fears regarding AI must be demolished, paving the way for the widespread understanding of how AI can be beneficial and how we can fight its possible dangers. This would mean creating ethical standards for the entire healthcare sector, getting accustomed to basic AI like Siri, more communication toward the public, and pushing companies toward offering affordable AI solutions.

 

Tags: , , ,