Machine Learning In Medicine

The world of medicine is changing due to the implementation of Artificial Intelligence. Fast improvement in computer science and availability of huge amount of data in the field of medicine makes machine learning system to tackle increasingly complex learning tasks, often with unbelievable success. The increasing focus of AI in medicine has led to some experts suggesting that someday AI may even replace doctors. Machine Learning In Medicine

Aim of this blog is to provide you with context, to interpret study results and attempt to make sense of the digital health.

If medical professionals want to get ahead of the curve, they should get familiarized with the basics of Machine Learning and have an idea of what medical problems they aim to solve.

Applied Machine Learning in Healthcare

1. Google Computers Trained to Detect Breast Cancer

Google is using the power of computer-based neural network to detect breast cancer (mainly occurs in women and rarely in men) by training the tool to look for cell patterns in slides of tissue.

Pathologist always face a problem of having huge amount of data to make a final conclusion. Data is slides containing cells from tissue biopsies, thinly sliced and stained. This data must be scanned in search of any abnormal cell.

There can be many slides per patient. And each slide contains more than 10 gigapixels.

Even well trained doctors make mistakes and may arrive to different conclusions. But, Google introduce a well trained neural network system to look at specific pattern in slides containing cells.

Study finds Google system could improve breast cancer detection - Reuters. Machine Learning In Medicine

The Google team found that the system can autonomously learn what pathology looks like. The computer was educated by studying billions of images donated from Radboud University Medical Center in the Netherlands.

Fun fact – This system has achieved 89 percent accuracy, beyond the 73 percent score of a human pathologist.

2. Neural Network for Detection of Diabetic Retinopathy in Retinal Fundus Photographs

From the last few years, the number of diabetes patients has increased exponentially. As a result, diabetic retinopathy (DR) has also become a big challenge.

According to study it is seen that more than 30% of diabetic patient faces an eye issue. Diabetic Retinopathy (DR) is an eye ailment which caused by damage to the blood vessels of the light-sensitive tissue at the back of the eye (retina) that influences eighty to eighty-five percent of the patients who have diabetes from a long time.

The retinal fundus images are commonly used for detection and analysis of diabetic retinopathy disease.

Diabetic Retinopathy Long Island | Eye Exams Huntington, NY Machine Learning in Medicine

It is found that Deep Neural Networks helps to detect retinopathic eye by identifying abnormality on pupil with very high accuracy.

I suggest you to do this project personally. You can get data from Kaggle. The Kaggle platform provides a large set of high-resolution fundus images taken under a variety of imaging conditions.

3. Drug Discovery and Manufacturing

Artificial Intelligence is playing crucial role in pharma industry. Only one percent of drugs reaches the market. Because, many medicines are rejected due to their ineffectiveness or danger to human health. Which reduced the net worth of many pharmaceutical companies.

As a result more than 200 start up companies are implementing machine learning in there business model.

Cheaper versions of the most expensive drugs may be coming, but monopolies will likely remain Machine Learning in Medicine

What pharmaceutical startups are doing with the help of machine learning ?

Finding correlation and association between different diseases, targets, and drugs. Which helps them to Re-purpose drugs for new indications.

Processing raw images, drugs, and genomic data sets, Genomics is an interdisciplinary field of biology focusing on the structure, function, evolution and mapping. Which allows researchers to Integrate rapid analytics and machine learning capabilities into existing business processes to improve care and enhance discoveries.

Generating organized big data from the analysis of published scientific research papers. Which helps to extract structured biological information to enhance drug discovery applications.

Analyzing and visualizing applicable results from multiple biomedical data sources. Allows researchers to gain a deeper understanding of a topic and avoid missing key information.

4. Clinical Studies

Machine learning has several potential applications in the field of clinical studies and research. Clinical studies means doing research by the help of human volunteers. And what I read is clinical research costs a lot of time and money.

I want to be frank with my audience. I have very little knowledge about clinical research. But, I will try to learn more about this in near future and will update this blog post.

Until then, If you know anything about this topic, please share your views and knowledge in the comment section below.